Evaluation code for paper 1

25 files changed, 2220 insertions, 0 deletions

diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_1.json
new file mode 100644
index 0000000..1e25ced
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_1.json
@@ -0,0 +1,120 @@
+{
+  "question": [
+    "What are the main genetic factors that influence aging?",
+    "How do genes affect the aging process in humans?",
+    "What lifestyle choices can help slow down genetic aging?",
+    "How do scientists study the genetics of aging in animals?",
+    "Are there specific genes that have been linked to longer lifespans?"
+  ],
+  "answer": [
+    "The main genetic factors that influence aging include genes such as APOE, FOXO3A, HLA-DQA1/DRB1, LPA, CHRNA3/5, CDKN2A/B, SH2B3, and MTP. These genes are associated with various biological processes such as metabolism, insulin signaling, and DNA damage and repair. Polymorphisms in these genes have been associated with longevity and healthy aging.",
+    "Genes influence the aging process in humans by governing levels of physiological capacity, repair, and turnover. They indirectly determine potential longevity. Genetic factors can explain about 20-25% of the variability of human survival to the mid-eighties. Certain genes, such as APOE and FOXOA3, have been associated with long life. However, aging is a complex process that involves the interactions of multiple genes with each other and the environment. It's also important to note that aging is likely a highly polygenic trait, meaning it's probably influenced by many genes.",
+    "Lifestyle choices that can help slow down genetic aging include mindful changes in behavior, reducing environmental exposure, healthy food and supplement use, weight loss, and regular exercise. A Mediterranean diet containing fruits, whole grains, fiber, antioxidants, soy protein, and healthy fats is also suggested. Additionally, giving up smoking and increasing educational attainment can positively correlate with lifespan.",
+    "Scientists study the genetics of aging in animals by using various animal models, including yeast, worms, flies, and mice. These models are genetically manipulated to investigate lifespan and age-related diseases. Techniques such as genotyping, genetic analysis, and forward genetic approaches are used to identify specific genes and molecular pathways related to aging. In some cases, cross-breeding of different strains is performed to identify aging-relevant genetic determinants. Additionally, in vivo studies are conducted to test the effect of certain manipulations or treatments on the whole organism.",
+    "Yes, specific genes have been linked to longer lifespans. These include the apolipoprotein E gene (APOE), the forkhead box O3A (FOXO3A) gene, and the AKT1 locus. Other genes associated with longevity include HLA-DQA1/DRB1 and LPA. However, these genes account for only a small portion of the genetic contribution to longevity."
+  ],
+  "contexts": [
+    [
+      "\t\n\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.",
+      "\t\n\nRecent developments on the genetics of aging can be seen as several streams of effort.In general, humans show a relatively modest (<50%) heritability of life spans (results obtained from twin studies discussed below).The apoE polymorphisms are remarkable for their influence on both cardiovascular disease and Alzheimer disease.In contrast, rare mutant genes with high penetrance cause these same diseases but with early onset and a major shortening of the life span.Shortlived laboratory models (fruit flies, nematodes, mice) are yielding rapid advances, with the discovery of mutants that increase life spans in association with altered metabolism, which leads to questions on the physiological organization of aging processes.Although these early findings do not show that a conserved genetic program actually controls aging processes across animal phylogeny, it is striking how frequently findings of metabolic rate, insulin signaling, and free radicals have emerged from very different approaches to aging in nematodes and mammals, for example.These findings hint that the genetic control of life span was already developed in the common ancestor of modern animals so that subsequent evolution of life spans was mediated by quantitative changes in the control of metabolism through insulin and the production of free radicals.",
+      "\tIntroduction\n\nWith the development of human genomics research, a large number of studies of the genetics of longevity have been conducted.Scientists from various countries have proposed many different theories concerning the mechanisms of aging from different perspectives, involving oxidative stress, energy metabolism, signal transduction pathways, immune response, etc. [1,2].These mechanisms interact with each other and are influenced by heredity to some degree [2,3].The identification of longevity-related biological markers is critical to an indepth understanding of the mechanisms of carrier protection against common disease and/or of the retardation of the process of aging.",
+      "\tINTRODUCTION\n\nHuman aging is affected by genes, life style, and environmental factors.The genetic contribution to average human aging can be modest with genes explaining 20-25% of the variability of human survival to the mid-eighties (Herskind et al., 1996;Fraser and Shavlik, 2001).By contrast, genetic factors may have greater impact on survival to the ninth through eleventh decades (Tan et al., 2008).Notably, exceptional longevity is rare and may involve biological mechanisms that differ from those implicated in usual human aging.",
+      "\t\n\nBefore the advent of NGS technologies, several scientists were interested in the study of allele variants associated with aging, but they were limited by the lack of aging rate biomarkers.Now with NGS technologies, these biomarkers have been emerged such as the epigenetic clock that is described in the DNA methylation sequencing section of this chapter.In this post-genomic era, different strategies have been developed in order to understand the genetic factors involved in aging [17].One strategy used is the study of aging in extreme longevity groups of people, called centenarians.Centenarians are a group that can reach an age above 100 years and has an incidence of 1 every 10,000 people [18].In a pioneering study using extreme longevity people (308 individuals belonging to 137 sibships showing extreme longevity), genome-wide scan analysis identified a region on chromosome 4 associated with extreme longevity [19] that corresponds to the microsomal transfer protein (MTP) [20], which is associated with abetalipoproteinemia and hypobeta lipoproteinemia in humans [21,22].Another approach to study the genetic factors involved in longevity consists in assessing allele frequencies from people of different ages, looking for those polymorphisms (SNPs) with enhanced allele frequencies in high-longevity individuals.Those alleles with diminished frequencies in aged individuals may be associated with age-related diseases.Using this approximation, an SNP that shifts isoleucine to valine was identified in the PKA-anchoring protein (AKAP2) gene.This polymorphism is associated with reduced longevity and cardiac disease [23].Genome-wide association studies (GWAS) have confirmed only three loci that affect longevity: FOXO3A, APOE, and an intergenic locus on chromosome 5q33.3[24][25][26].\tIndividual Genotype\n\nIndividual differences in biological ageing may be due in part to the specific variations of the genotype but also genome-environment interactions [21,37].The maintenance of genomic stability and integrity is considered an essential factor required for cell viability and the overall longevity of an organism.The accumulation of physical damage is one of the leading causes of the ageing process.When considering oxidative damage as one of the causes of the damage of genetic material, these changes alter vital processes, such as replication, transcription, and translation, leading to genomic instability and personalized processes of ageing [38,39].\tInfluence of Genetic Factors in Ageing and Lifespan\n\nAgeing is defined as the decline of physiological functions in several tissues and organs inducing an increasing probability of death [17].The understanding of genetic factors involved in ageing has been limited due to the complexity of this process and the heterogeneity among individuals and even among tissues [18][19][20].Tissue cells adopt a senescent phenotype as a consequence of multiple intrinsic, extrinsic, and stochastic factors [21].The combination of these genetic factors is related to longevity and healthy ageing [22].Although this decline is somewhat predictable, some individuals show a much slower decline and get to live past the age of 100.Studies in these individuals showed polymorphisms in some genes which are associated with long life, such as APOE and FOXO3.However, these associations have not been consistent across different populations, suggesting that ageing is rather polygenic [23].",
+      "\t\n\nInvolvement of genes in a wide range of fundamental biological processes suggests also a broad role of these genes in regulating the aging-related phenotypes.",
+      "\t\n\nM OST genetic studies involved with aging have focused on identifying genes contributing to particular diseases.More recently, it has been recognized that it is also valuable to examine genetic factors related to diseasefree or healthy aging (1,2).Utilizing twins from the National Academy of Sciences-National Research Council (NAS-NRC) twin panel, we have demonstrated that healthy physical aging is under a significant degree of genetic influence, with a heritability over 50% (3).Our definition of healthy aging focused principally on freedom from cardiovascular disease, and has received considerable support in the more recent literature.Brand and colleagues (4) reported that parental age at death was a significant predictor of coronary heart disease death in the Framingham offspring study and concluded that familial similarities for age at death may be mediated through shared coronary heart disease risk factors.Frederiksen and colleagues (5) reported that increased parental life was associated with a reduction in odds ratio for their children to have diabetes, ischemic heart disease, heart failure, stroke, and hypertension.We have found that better midlife lipid levels and blood pressures were associated with increased parental longevity in the National Heart, Lung, and Blood Institute twin study (6).Centenarian siblings and offspring, besides having increased longevity, have been shown to have better health and better cardiovascular risk factor profiles (7)(8)(9)(10).",
+      "\t\n\nIn 2021, Science published a special issue entitled \"125 Questions: Exploration and Discovery.\" One of these 125 questions was \"Can we stop ourselves from aging? \"The U.S. National Institute on Aging (NIA) at the National Institutes of Health (NIH) states that \"aging is associated with changes in dynamic biological, physiological, environmental, psychological, behavioral, and social processes.\" Although geneticists and epidemiologists have long debated the relative importance of the role played by genotype or the environment in the development of age-related diseases, it is apparent that both can play substantial roles in this process [6,7].However, most etiological studies have concentrated on the role of genotype and have considered the environment to play a secondary role.Nevertheless, an analysis of GBD data showed that nearly 50% of deaths worldwide are attributable to environmental exposure, primarily exposure to airborne particulates (including household air pollution and occupational exposure; 14% of all deaths), smoking and secondhand smoke (13%), plasma sodium concentrations (6%), and alcohol consumption (5%) [8].In contrast, a recent analysis of 28 chronic diseases in identical twins showed that the genetic-related risks of developing one of five age-related diseases were 33.3%, 10.6%, 36.3%, 19.5%, and 33.9% for AD, PD, CAD, COPD, and T2DM, respectively, with a mean of only 26% [9].The results of over 400 genome-wide association studies (GWASs) have also elucidated that the heritability of degenerative diseases is only approximately 10% [10,11].Consequently, nongenetic drivers, such as environmental factors, are now recognized as major risk factors for age-related diseases.The contributions of environmental factors to the development of age-related diseases can be revealed by analyses of all of the factors to which individuals are exposed in their life and the relationships between these exposures and age-related diseases [12,13].",
+      "\tTranslational\n\nA LTHOUGH there is much debate about the processes driving human aging, there is little doubt that genetic influences play a significant role (1).Humans clearly live very much longer than the currently favored laboratory models of aging, and such interspecies differences in reproductively 'fit' life span must have an inherited genetic foundation.Within human populations, environmental and behavioral exposures are important but at least a quarter of life expectancy variation in twin or family studies is attributable to inherited genetic or epigenetic factors (2).Age-related conditions such as type 2 diabetes, myocardial infarction, common cancers, and Alzheimer's disease (AD) typically have onsets after the fourth decade of life; \"successful\" agers delay these onsets until relatively late in life (3).Many aging traits and diseases show moderate heritability, including cardiovascular disease (CVD) (4) and impaired physical functioning (5), independent of known environmental risk factors.",
+      "\t\n\nMany factors contribute to aging, including genes.This is the first article in a 10-part series that highlight some of what is known about the influence of genes on aging and emerging treatment options that may slow down or potentially reverse the aging process.The series will address \\genes, adducts, and telomeres, decreased immune defenses, oxidation and inefficient mitochondria, toxins and radiation, glycosylation, caloric intake and sirtuin production, neurotransmitter imbalance, hormone mechanisms, reduced nitric oxide, and stem cell slowdown.Underpinning these factors are wear and tear on cells and aging as a result of inability to repair or replace these affected cells.These topics have been addressed in research, health magazines, and even by talk show hosts.There is even a LongevityMap website addressing significant and nonsignificant genetic association studies in aging across the human genome (http://genomics.senescence.info/longevity/).The series will address a scientific and clinical approach to genome-related aging topics.",
+      "\t\n\nThe genetic basis of human longevity has so far been primarily investigated by association studies.Most results from these experiments have been difficult to confirm in independent samples, probably owing to the modest heritability, multifactorial nature, and heterogeneity of the phenotype (Christensen et al., 2006).To date, variation in only two genes has been identified, which has an effect on longevity in various populations: (i) the apolipoprotein E gene (APOE) (Scha chter et al., 1994;Christensen et al., 2006) and (ii) the forkhead box O3A (FOXO3A) gene in the insulin-IGF1 signaling (IIS) pathway (Willcox et al., 2008;Flachsbart et al., 2009).Given the apparent lack of susceptibility candidates, it is conceivable that other genetic factors influence the function or expression of genes relevant for human longevity.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\tIntroduction\n\nApproximately 25-30% of the variation in adult lifespan is attributable to genetic factors that become more important with increasing age and exert their strongest effects in nonagenarians and centenarians (Go gele et al., 2010;Hjelmborg et al., 2006).As yet, however, only a few genetic variants have been found consistently to influence longevity.The first to be discovered was the e4 allele of the apolipoprotein E (APOE) gene, a mortality factor that predisposes to both Alzheimer's and cardiovascular diseases (Corder et al., 1993; Panza et al., 2004).APOE e4 is the only variant with a reportedly large adverse effect upon survival at advanced age (Scha chter et al., 1994), and this association has been replicated in several populations (Christensen et al., 2006).Variation in the human forkhead box O3A gene (FOXO3A), in contrast, has been found to be associated with the ability to live long, an effect corroborated by studies in Japanese, German, Italian, US-American, Jewish, Chinese and Danish populations (Anselmi et al., 2009;Flachsbart et al., 2009;Li et al., 2009;Pawlikowska et al., 2009;Soerensen et al., 2010;Willcox et al., 2008).More recently, we have identified exonuclease 1 (EXO1) as a potential novel longevity gene (Nebel et al., 2009).All three genes were detected through candidate-gene approaches.",
+      "\tThe mechanisms that underlie healthy agingparticularly, the cognitive as-\n\npectsremain poorly understood. Research suggests that genetics play a significant role in determining an individuals\nsusceptibility or resilience to cognitive decline and dementia\n(Harris and Deary 2011; Ridge et al. , 2013). Identification of precise genetic factors involved would provide insight into\n\nCell Reports 32, 108091, September 1, 2020  2020 The Author(s). 1\nThis is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). ll\nOPEN ACCESS\n\nReport\n\nFigure 1.",
+      "\tGenAge: the aging gene database Philosophy and overview of resources\n\nIt is undisputed that genetic factors influence aging.In a remarkable series of recent breakthroughs, a number of genes capable of altering the aging process as a whole -or at least to a large degree -have been identified in animal models and even a few in humans (Finch & Ruvkun, 2001;de Magalhes, 2005;Kenyon, 2005).Furthermore, multiple alleles have been examined for their association with human exceptional longevity (Vijg & Suh, 2005).This is a fascinating and important area of research, yet there are now so many genes being associated with aging and longevity that keeping track of them all is becoming increasingly more difficult.Moreover, it is necessary now to study not only individual genes but their interactions with each other and with the environment, and how together genes give rise to a given phenotype: the so-called systems biology approach.To help researchers address these issues we created GenAge, a database of genes related to longevity and/or aging.",
+      "\t\n\nI NCREASES in longevity of the general population world- wide are an unprecedented phenomenon with significant health and social impact.Although environmental factors have led to an increase in life span, there is ample evidence that genetic factors are involved in extreme longevity both in humans (1-7) and in other organisms (8).The protective genetic factors that lead to longevity are likely to involve fundamental processes of aging that may be different from those associated with early mortality or premature onset of age-related diseases in younger individuals.The mechanisms of aging in humans are far from understood, but available evidence suggests that several pathways-inflammation, oxidative stress and stress responses, cellular senescence, DNA damage and repair, and the growth hormone or insulinlike growth factor and insulin (GH, IGF, INS) axis-may play key roles (9)(10)(11)(12).Model organisms suggest that inhibiting the GH, IGF, or INS axis, which is involved in regulating cell proliferation, cell death, wound repair, and metabolism, may promote longevity by reducing oxidative stress and slowing the rate of cell replication and the accumulation of somatic-cell DNA mutations (13).There is also evidence for other important pathways such as the heatshock proteins and heat-shock factors that are highly conserved across species and play a role in prolongevity transcription pathways.Clinical and epidemiological investigations, including candidate gene studies, have suggested that inflammation pathways may affect life span and risk of age-related conditions such as cardiovascular disease (CVD) and its risk factors (14)(15)(16)(17)(18)(19).A combination of multiple genetic variants may be required for an individual to achieve exceptional longevity, which may account in part for its rarity.",
+      "\t\n\nHuman lifespan variation is mainly determined by environmental factors, whereas the genetic contribution is 25-30% and expected to be polygenic.Two complementary fields go hand in hand in order to unravel the mechanisms of biological aging: genomic and biomarker research.Explorative and candidate gene studies of the human genome by genetic, transcriptomic, and epigenomic approaches have resulted in the identification of a limited number of interesting positive linkage regions, genes, and pathways that contribute to lifespan variation.The possibilities to further exploit these findings are rapidly increasing through the use of novel technologies, such as next-generation sequencing.Genomic research is progressively being integrated with biomarker studies on aging, including the application of (noninvasive) deep phenotyping and omics data -generated using novel technologies -in a wealth of studies in human populations.Hence, these studies may assist in obtaining a more holistic perspective on the role of the genome in aging and lifespan regulation.\t\nHuman lifespan variation is mainly determined by environmental factors, whereas the genetic contribution is 25-30% and expected to be polygenic.Two complementary fields go hand in hand in order to unravel the mechanisms of biological aging: genomic and biomarker research.Explorative and candidate gene studies of the human genome by genetic, transcriptomic, and epigenomic approaches have resulted in the identification of a limited number of interesting positive linkage regions, genes, and pathways that contribute to lifespan variation.The possibilities to further exploit these findings are rapidly increasing through the use of novel technologies, such as next-generation sequencing.Genomic research is progressively being integrated with biomarker studies on aging, including the application of (noninvasive) deep phenotyping and omics data -generated using novel technologies -in a wealth of studies in human populations.Hence, these studies may assist in obtaining a more holistic perspective on the role of the genome in aging and lifespan regulation."
+    ],
+    [
+      "\t\n\nRecent developments on the genetics of aging can be seen as several streams of effort.In general, humans show a relatively modest (<50%) heritability of life spans (results obtained from twin studies discussed below).The apoE polymorphisms are remarkable for their influence on both cardiovascular disease and Alzheimer disease.In contrast, rare mutant genes with high penetrance cause these same diseases but with early onset and a major shortening of the life span.Shortlived laboratory models (fruit flies, nematodes, mice) are yielding rapid advances, with the discovery of mutants that increase life spans in association with altered metabolism, which leads to questions on the physiological organization of aging processes.Although these early findings do not show that a conserved genetic program actually controls aging processes across animal phylogeny, it is striking how frequently findings of metabolic rate, insulin signaling, and free radicals have emerged from very different approaches to aging in nematodes and mammals, for example.These findings hint that the genetic control of life span was already developed in the common ancestor of modern animals so that subsequent evolution of life spans was mediated by quantitative changes in the control of metabolism through insulin and the production of free radicals.",
+      "\t\nAging is a complex process affecting different species and individuals in different ways.Comparing genetic variation across species with their aging phenotypes will help understanding the molecular basis of aging and longevity.Although most studies on aging have so far focused on short-lived model organisms, recent comparisons of genomic, transcriptomic, and metabolomic data across lineages with different lifespans are unveiling molecular signatures associated with longevity.Here, we examine the relationship between genomic variation and maximum lifespan across primate species.We used two different approaches.First, we searched for parallel amino-acid mutations that co-occur with increases in longevity across the primate linage.Twenty-five such amino-acid variants were identified, several of which have been previously reported by studies with different experimental setups and in different model organisms.The genes harboring these mutations are mainly enriched in functional categories such as wound healing, blood coagulation, and cardiovascular disorders.We demonstrate that these pathways are highly enriched for pleiotropic effects, as predicted by the antagonistic pleiotropy theory of aging.A second approach was focused on changes in rates of protein evolution across the primate phylogeny.Using the phylogenetic generalized least squares, we show that some genes exhibit strong correlations between their evolutionary rates and longevity-associated traits.These include genes in the Sphingosine 1-phosphate pathway, PI3K signaling, and the Thrombin/protease-activated receptor pathway, among other cardiovascular processes.Together, these results shed light into human senescence patterns and underscore the power of comparative genomics to identify pathways related to aging and longevity.\t\n\nAging is a complex process affecting different species and individuals in different ways.Comparing genetic variation across species with their aging phenotypes will help understanding the molecular basis of aging and longevity.Although most studies on aging have so far focused on short-lived model organisms, recent comparisons of genomic, transcriptomic, and metabolomic data across lineages with different lifespans are unveiling molecular signatures associated with longevity.Here, we examine the relationship between genomic variation and maximum lifespan across primate species.We used two different approaches.First, we searched for parallel amino-acid mutations that co-occur with increases in longevity across the primate linage.Twenty-five such amino-acid variants were identified, several of which have been previously reported by studies with different experimental setups and in different model organisms.The genes harboring these mutations are mainly enriched in functional categories such as wound healing, blood coagulation, and cardiovascular disorders.We demonstrate that these pathways are highly enriched for pleiotropic effects, as predicted by the antagonistic pleiotropy theory of aging.A second approach was focused on changes in rates of protein evolution across the primate phylogeny.Using the phylogenetic generalized least squares, we show that some genes exhibit strong correlations between their evolutionary rates and longevity-associated traits.These include genes in the Sphingosine 1-phosphate pathway, PI3K signaling, and the Thrombin/protease-activated receptor pathway, among other cardiovascular processes.Together, these results shed light into human senescence patterns and underscore the power of comparative genomics to identify pathways related to aging and longevity.",
+      "\tINTRODUCTION\n\nHuman aging is affected by genes, life style, and environmental factors.The genetic contribution to average human aging can be modest with genes explaining 20-25% of the variability of human survival to the mid-eighties (Herskind et al., 1996;Fraser and Shavlik, 2001).By contrast, genetic factors may have greater impact on survival to the ninth through eleventh decades (Tan et al., 2008).Notably, exceptional longevity is rare and may involve biological mechanisms that differ from those implicated in usual human aging.",
+      "\t\n\nAdditional association studies with these families and replication of these results with an independent data set should facilitate the positional cloning of a gene that influences the ability to age well and achieve exceptional longevity.Identification of the genes in humans that allow certain individuals to live to extreme old age should lead to insights on cellular pathways that are important to the aging process.",
+      "\t\n\nInvolvement of genes in a wide range of fundamental biological processes suggests also a broad role of these genes in regulating the aging-related phenotypes.\t\n\nAging is an extremely complex process associated with interplay of genetic, biochemical, and metabolic factors in an organism in a given environment.Although genetic studies of various animal models suggest that even a single-gene mutation can remarkably extend lifespan (Kenyon 2005;Johnson 2006) and, thus, modulate aging, no such genes are revealed in humans so far.Given that a human organism is a much more complex system than a model organism (Christensen et al. 2006), it is evident that genetic effects on the aging process should be mediated via coordinate action of a large number of inter-related processes (Kirkwood 2011).Coordinated function is rather relevant to complex biological (Soltow et al. 2010;Slagboom et al. 2011) and genetic (Bloss et al. 2011) networks than to individual genes.\t\n\nEven more disappointing result is that some genes predisposing to geriatric diseases discovered by GWAS appear to be not correlated with human longevity (Beekman et al. 2010;Deelen et al. 2011).This result questions whether findings obtained from GWAS may provide insights into the bio-genetic mechanisms underlying a healthy lifespan.In fact, this finding is very surprising because (1) genetic studies of non-human species have discovered numerous genes predisposing to aging-related processes (Cutler and Mattson 2006;Vijg and Suh 2005;Kenyon 2005;Johnson 2006;Greer and Brunet 2008), (2) nongenetic association studies show that the long-living individuals are typically in better health compared to the short-living individuals (Barzilai et al. 2003;Willcox et al. 2008b;Willcox et al. 2008a;Evert et al. 2003), and (3) candidate-gene studies (but not GWAS) document that the same genes can affect diseases and lifespan (Koropatnick et al. 2008;Kulminski et al. 2011).This is an apparent paradox which has to be carefully examined.A prominent geneticist and evolutionary biologist T. G. Dobzhansky asserts that \"nothing in biology makes sense except in the light of evolution. \"Evolution primarily maximizes fitness of individuals of reproductive age.The classical evolutionary biological theory of aging claims that aging occurs because of decline in the force of natural selection with age (Kirkwood and Austad 2000).Then, according to that theory, aging-related (senescent) phenotypes with post-reproductive manifestation are non-adaptive and subject to stochastic variation.Therefore, at a first glance evolution should not be relevant to senescent phenotypes (apart so-called grandmother hypothesis; Hawkes et al. 1998).Such phenotypes, however, can be caused by reproductive-age-related risk factors making, thus, evolution to be relevant to them (Vijg and Suh 2005;Di Rienzo and Hudson 2005;Drenos and Kirkwood 2010).",
+      "\t\n\nGenes do not drive the aging process but by governing the levels of excess physiological capacity, repair, and turnover they indirectly determine potential longevity.There are no genes that specifically drive longevity but there are genes that govern biological processes that increase the likelihood of survival to reproductive maturity.The variations in excess physiological capacity, repair, and turnover accounts for the variations found in longevity both within and between species.\t\n\nThe studies in lower animals made in recent years that have led to the view that genes are involved in aging have not revealed a reversal or arrest of the inexorable expression of molecular disorder that is the hallmark of aging.These studies are more accurately interpreted to have impact on our understanding of longevity determination because all of the experimental results have altered biological variables before the aging process begins.None of these studies in invertebrates has demonstrated that the manipulation of genes has slowed, stopped, or reversed recognized biomarkers of the aging process.",
+      "\t\n\nAgeing in humans is typified by the decline of physiological functions in various organs and tissues leading to an increased probability of death.Some individuals delay, escape or survive much of this age-related decline and live past age 100.Studies comparing centenarians to average-aged individuals have found polymorphisms in genes that are associated with long life, including APOE and FOXOA3, which have been replicated many times.However, the associations found in humans account for small percentages of the variance in lifespan and many other gene associations have not been replicated in additional populations.Therefore, ageing is probably a highly polygenic trait.In humans, it is important to also consider differences in age-related decline that occur within and among tissues.Longitudinal data of age-related traits can be used in association studies to test for polymorphisms that predict how an individual will change over time.Transcriptional and genetic association studies of different tissues have revealed common and unique pathways involved in human ageing.Genomic convergence is a method that combines multiple types of functional genomic information such as transcriptional profiling, expression quantitative trait mapping and gene association.The genomic convergence approach has been used to implicate the gene MMP20 in human kidney ageing.New human genetics technologies are continually in development and may lead to additional breakthroughs in human ageing in the near future.\t\nAgeing in humans is typified by the decline of physiological functions in various organs and tissues leading to an increased probability of death.Some individuals delay, escape or survive much of this age-related decline and live past age 100.Studies comparing centenarians to average-aged individuals have found polymorphisms in genes that are associated with long life, including APOE and FOXOA3, which have been replicated many times.However, the associations found in humans account for small percentages of the variance in lifespan and many other gene associations have not been replicated in additional populations.Therefore, ageing is probably a highly polygenic trait.In humans, it is important to also consider differences in age-related decline that occur within and among tissues.Longitudinal data of age-related traits can be used in association studies to test for polymorphisms that predict how an individual will change over time.Transcriptional and genetic association studies of different tissues have revealed common and unique pathways involved in human ageing.Genomic convergence is a method that combines multiple types of functional genomic information such as transcriptional profiling, expression quantitative trait mapping and gene association.The genomic convergence approach has been used to implicate the gene MMP20 in human kidney ageing.New human genetics technologies are continually in development and may lead to additional breakthroughs in human ageing in the near future.",
+      "\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\t\n\nThe remarkable discoveries of the past 2 decades showing that single genes can regulate aging in model organisms demonstrate that aging can be genetically manipulated (Finch and Ruvkun, 2001;Kenyon, 2010).Hundreds of genes that modulate longevity have now been identified in model organisms (de Magalha es et al., 2009a).In some cases (e.g., in worms), mutations in single genes can extend lifespan by almost 10-fold (Ayyadevara et al., 2008).Nonetheless, aging is a complex process that derives not from single genes but from the interactions of multiple genes with each other and with the environment.Evidence from animal systems shows a major impact of the environment on aging, yet environmental manipulations of aging act through genes and proteins, usually by triggering signaling pathways and modulating gene expression.In fact, some genes have been shown in model organisms to have varying effects on lifespan depending on diet (Heikkinen et al., 2009).Genes that can regulate aging in model organisms cannot be directly applied to humans through genetic manipulations for numerous legal, ethical, and technical reasons.If we could understand how the environment modulates these aging-related genes, we might be able to create antiaging therapies applicable to humans, potentially through diet, lifestyle, and even pharmacological interventions.Therefore, understanding genome-environment interactions in the context of aging can be a powerful approach to identify attractive targets for drug design.",
+      "\tTranslational\n\nA LTHOUGH there is much debate about the processes driving human aging, there is little doubt that genetic influences play a significant role (1).Humans clearly live very much longer than the currently favored laboratory models of aging, and such interspecies differences in reproductively 'fit' life span must have an inherited genetic foundation.Within human populations, environmental and behavioral exposures are important but at least a quarter of life expectancy variation in twin or family studies is attributable to inherited genetic or epigenetic factors (2).Age-related conditions such as type 2 diabetes, myocardial infarction, common cancers, and Alzheimer's disease (AD) typically have onsets after the fourth decade of life; \"successful\" agers delay these onsets until relatively late in life (3).Many aging traits and diseases show moderate heritability, including cardiovascular disease (CVD) (4) and impaired physical functioning (5), independent of known environmental risk factors.",
+      "\t\n\nMany factors contribute to aging, including genes.This is the first article in a 10-part series that highlight some of what is known about the influence of genes on aging and emerging treatment options that may slow down or potentially reverse the aging process.The series will address \\genes, adducts, and telomeres, decreased immune defenses, oxidation and inefficient mitochondria, toxins and radiation, glycosylation, caloric intake and sirtuin production, neurotransmitter imbalance, hormone mechanisms, reduced nitric oxide, and stem cell slowdown.Underpinning these factors are wear and tear on cells and aging as a result of inability to repair or replace these affected cells.These topics have been addressed in research, health magazines, and even by talk show hosts.There is even a LongevityMap website addressing significant and nonsignificant genetic association studies in aging across the human genome (http://genomics.senescence.info/longevity/).The series will address a scientific and clinical approach to genome-related aging topics.",
+      "\tGenAge: the aging gene database Philosophy and overview of resources\n\nIt is undisputed that genetic factors influence aging.In a remarkable series of recent breakthroughs, a number of genes capable of altering the aging process as a whole -or at least to a large degree -have been identified in animal models and even a few in humans (Finch & Ruvkun, 2001;de Magalhes, 2005;Kenyon, 2005).Furthermore, multiple alleles have been examined for their association with human exceptional longevity (Vijg & Suh, 2005).This is a fascinating and important area of research, yet there are now so many genes being associated with aging and longevity that keeping track of them all is becoming increasingly more difficult.Moreover, it is necessary now to study not only individual genes but their interactions with each other and with the environment, and how together genes give rise to a given phenotype: the so-called systems biology approach.To help researchers address these issues we created GenAge, a database of genes related to longevity and/or aging.\t\n\nAlthough the models data set comprises all genes (to our knowledge) shown by the time of the latest update to statistically increase longevity or alter the aging process in a noticeable way, in the human data set we try to evaluate whether a given intervention is affecting the aging process itself or not.For example, many mutations may increase longevity by decreasing the incidence of specific diseases, rather than by altering the basic process of aging (de Magalhes et al ., 2005a(de Magalhes et al ., , 2005b)).Therefore, the human data set is not merely an extension of the work conducted in model organisms and of its bibliography, but a manually selected list of the most pertinent human aging candidate genes, each presented with a higher annotation level.We cite studies on whether the functions of aging-associated genes in model organisms are conserved in their human orthologues.Likewise, we cite flaws in previous studies based on new published observations, although we have a neutral stance on conflicting findings from different research groups.Our policy is to cite all conflicting reports and let visitors make their own decisions on how to interpret them.By contrast, each entry in GenAge model organisms has only one reference: the first publication reporting an association of the gene with longevity or aging.Moreover, one of the latest enhancements in the human data set was the inclusion of Gene Ontology annotation.Gene Ontology terms and annotation files were obtained from the Gene Ontology Consortium website (http://www.geneontology.org/ ) and provide an additional layer of description for the gene products in a cellular context (Ashburner et al ., 2000).",
+      "\t\n\nAgeing in humans is typified by the decline of physiological functions in various organs and tissues leading to an increased probability of death.Some individuals delay, escape or survive much of this age-related decline and live past age 100.Studies comparing centenarians to average-aged individuals have found polymorphisms in genes that are associated with long life, including APOE and FOXOA3, which have been replicated many times.However, the associations found in humans account for small percentages of the variance in lifespan and many other gene associations have not been replicated in additional populations.Therefore, ageing is probably a highly polygenic trait.In humans, it is important to also consider differences in age-related decline that occur within and among tissues.Longitudinal data of age-related traits can be used in association studies to test for polymorphisms that predict how an individual will change over time.Transcriptional and genetic association studies of different tissues have revealed common and unique pathways involved in human ageing.Genomic convergence is a method that combines multiple types of functional genomic information such as transcriptional profiling, expression quantitative trait mapping and gene association.The genomic convergence approach has been used to implicate the gene MMP20 in human kidney ageing.New human genetics technologies are continually in development and may lead to additional breakthroughs in human ageing in the near future.\t\nAgeing in humans is typified by the decline of physiological functions in various organs and tissues leading to an increased probability of death.Some individuals delay, escape or survive much of this age-related decline and live past age 100.Studies comparing centenarians to average-aged individuals have found polymorphisms in genes that are associated with long life, including APOE and FOXOA3, which have been replicated many times.However, the associations found in humans account for small percentages of the variance in lifespan and many other gene associations have not been replicated in additional populations.Therefore, ageing is probably a highly polygenic trait.In humans, it is important to also consider differences in age-related decline that occur within and among tissues.Longitudinal data of age-related traits can be used in association studies to test for polymorphisms that predict how an individual will change over time.Transcriptional and genetic association studies of different tissues have revealed common and unique pathways involved in human ageing.Genomic convergence is a method that combines multiple types of functional genomic information such as transcriptional profiling, expression quantitative trait mapping and gene association.The genomic convergence approach has been used to implicate the gene MMP20 in human kidney ageing.New human genetics technologies are continually in development and may lead to additional breakthroughs in human ageing in the near future."
+    ],
+    [
+      "\t\n\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.\t\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.",
+      "\t\n\nRecent developments on the genetics of aging can be seen as several streams of effort.In general, humans show a relatively modest (<50%) heritability of life spans (results obtained from twin studies discussed below).The apoE polymorphisms are remarkable for their influence on both cardiovascular disease and Alzheimer disease.In contrast, rare mutant genes with high penetrance cause these same diseases but with early onset and a major shortening of the life span.Shortlived laboratory models (fruit flies, nematodes, mice) are yielding rapid advances, with the discovery of mutants that increase life spans in association with altered metabolism, which leads to questions on the physiological organization of aging processes.Although these early findings do not show that a conserved genetic program actually controls aging processes across animal phylogeny, it is striking how frequently findings of metabolic rate, insulin signaling, and free radicals have emerged from very different approaches to aging in nematodes and mammals, for example.These findings hint that the genetic control of life span was already developed in the common ancestor of modern animals so that subsequent evolution of life spans was mediated by quantitative changes in the control of metabolism through insulin and the production of free radicals.",
+      "\tIntroduction\n\nWith the development of human genomics research, a large number of studies of the genetics of longevity have been conducted.Scientists from various countries have proposed many different theories concerning the mechanisms of aging from different perspectives, involving oxidative stress, energy metabolism, signal transduction pathways, immune response, etc. [1,2].These mechanisms interact with each other and are influenced by heredity to some degree [2,3].The identification of longevity-related biological markers is critical to an indepth understanding of the mechanisms of carrier protection against common disease and/or of the retardation of the process of aging.",
+      "\t\n\nSomatic mutations with the inherited gene variations of each individual cumulatively or synergistically influence the health span and life span [11].Very few genetic variants have been associated with human longevity, but those found include the transcription factor FOXO3 gene, the APOE/TOMM40 and the CDKN2B/ ANRIL loci, which are associated with Alzheimer's disease and cellular senescence [12][13][14].In fact, the heritability for human longevity has been estimated to be approximately 20-30%, according to studies of twins, suggesting that external factors such as diet, environment, physical activity and microbiomes are important factors that influence the health span [14][15][16].The increase in the rate of retrotranscription reflects genome deregulation, creating additional mutations, DNA damage, and other forms of genome instability.For instance, the expression of several families of retrotransposable elements increases with age, as observed in mouse skeletal muscle and human fibroblasts, particularly the long interspersed nuclear element-1 (L1 LINE) [17,18].\tConclusions and Perspectives\n\nThe advent of new technologies has allowed the identification of conserved pathways involved in the aging process, as well as the association of genomic variants with human longevity.Nevertheless, heritability of human longevity has been estimated from 20% to 30%, reinforcing the fact that external factors such as diet, environment, and physical activity play a critical role in the human life span.",
+      "\t\n\nM OST genetic studies involved with aging have focused on identifying genes contributing to particular diseases.More recently, it has been recognized that it is also valuable to examine genetic factors related to diseasefree or healthy aging (1,2).Utilizing twins from the National Academy of Sciences-National Research Council (NAS-NRC) twin panel, we have demonstrated that healthy physical aging is under a significant degree of genetic influence, with a heritability over 50% (3).Our definition of healthy aging focused principally on freedom from cardiovascular disease, and has received considerable support in the more recent literature.Brand and colleagues (4) reported that parental age at death was a significant predictor of coronary heart disease death in the Framingham offspring study and concluded that familial similarities for age at death may be mediated through shared coronary heart disease risk factors.Frederiksen and colleagues (5) reported that increased parental life was associated with a reduction in odds ratio for their children to have diabetes, ischemic heart disease, heart failure, stroke, and hypertension.We have found that better midlife lipid levels and blood pressures were associated with increased parental longevity in the National Heart, Lung, and Blood Institute twin study (6).Centenarian siblings and offspring, besides having increased longevity, have been shown to have better health and better cardiovascular risk factor profiles (7)(8)(9)(10).\t\nLiving to a late age without suffering any major health problems is a genetically influenced trait.To identify the genes contributing to this important phenotype, a 10 cM genome screen was performed in 95 pairs of male fraternal twins concordant for healthy aging.Individuals meeting these criteria were defined as those attaining the age of 70 free of cardiovascular disease (coronary surgery, diabetes, heart attack, and stroke) and prostate cancer.Six chromosomal regions were identified with logarithm of odds (LOD) scores greater than 1.2 ( p , .01).A region on chromosome 4 at marker D4S1564 produced a LOD score of 1.67; this was the same marker previously linked to extreme longevity segregating as an autosomal dominant trait in centenarian families.Our results provide independent evidence that a locus on the long arm of chromosome 4 is associated with better physical aging and/or longevity.",
+      "\t\n\nMany factors beside genetics influence how long a person will live and our lifespan cannot be read from our DNA alone.Nevertheless, Timmers et al. had hoped to narrow down their search and discover specific genes that directly influence how quickly people age, beyond diseases.If such genes exist, their effects were too small to be detected in this study.The next step will be to expand the study to include more participants, which will hopefully pinpoint further genomic regions and help disentangle the biology of ageing and disease.",
+      "\tIntroduction\n\nThe recent, remarkable extension of life expectancy is largely attributed to the postponement of mortality at old age (Vaupel, 1997(Vaupel, , 2010)).The years of life gained in the older population residing in developed nations are a success story of public health measures and improved health care.In addition to such external factors, longevity and healthy aging consistently show a modest heritability between 20% and 50% and aging-associated genetic research may provide further insights into the mechanisms of aging (Herskind et al., 1996;McGue et al., 1993;Reed and Dick, 2003).It has been postulated that genes involved in pathways associated with aging identified in animal models, such as insulin-like growth factor (IGF)-insulin signaling, regulation of lipoprotein metabolism, the mTOR pathway, and the oxidative stress response may also influence survival to old or even exceptionally old age in humans (Christensen et al., 2006;Kenyon, 2010;Vellai et al., 2003).However, in humans, common variants within genes involved in these pathways have not been consistently associated with lifespan (Chris-tensen et al., 2006;Kenyon, 2010;Kuningas et al., 2008;Vijg and Suh, 2005).",
+      "\t\n\nIn 2021, Science published a special issue entitled \"125 Questions: Exploration and Discovery.\" One of these 125 questions was \"Can we stop ourselves from aging? \"The U.S. National Institute on Aging (NIA) at the National Institutes of Health (NIH) states that \"aging is associated with changes in dynamic biological, physiological, environmental, psychological, behavioral, and social processes.\" Although geneticists and epidemiologists have long debated the relative importance of the role played by genotype or the environment in the development of age-related diseases, it is apparent that both can play substantial roles in this process [6,7].However, most etiological studies have concentrated on the role of genotype and have considered the environment to play a secondary role.Nevertheless, an analysis of GBD data showed that nearly 50% of deaths worldwide are attributable to environmental exposure, primarily exposure to airborne particulates (including household air pollution and occupational exposure; 14% of all deaths), smoking and secondhand smoke (13%), plasma sodium concentrations (6%), and alcohol consumption (5%) [8].In contrast, a recent analysis of 28 chronic diseases in identical twins showed that the genetic-related risks of developing one of five age-related diseases were 33.3%, 10.6%, 36.3%, 19.5%, and 33.9% for AD, PD, CAD, COPD, and T2DM, respectively, with a mean of only 26% [9].The results of over 400 genome-wide association studies (GWASs) have also elucidated that the heritability of degenerative diseases is only approximately 10% [10,11].Consequently, nongenetic drivers, such as environmental factors, are now recognized as major risk factors for age-related diseases.The contributions of environmental factors to the development of age-related diseases can be revealed by analyses of all of the factors to which individuals are exposed in their life and the relationships between these exposures and age-related diseases [12,13].",
+      "\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\t\n\nWith an aging population, there is a great and urgent need to develop approaches and therapies targeting the aging process and age-related diseases (Butler et al., 2008).Delaying the process of aging, even slightly, would have profound social, medical and economic benefits (Olshansky et al., 2006;Butler et al., 2008).For example, slowing aging by a mere 7 years would cut mortality of age-related diseases by half at every age.Therefore, the potential benefits from research on the basic biology and genetics of aging are unparalleled in terms of improving quality of life and health.Although much debate remains regarding the molecular causes of aging, findings from model organisms show that aging is surprisingly plastic and can be manipulated by both genetic and environmental factors (Finch and Ruvkun, 2001;Kenyon, 2010).In principle, therefore, it is possible to manipulate human aging.Unlocking this capacity to manipulate aging in people would result in unprecedented human health benefits, and it opens new opportunities for industry.",
+      "\t\n\nA better understanding of pathways that contribute at middle age to the divergence of healthy and unhealthy ageing humans may be substantiated by in depth studies of the cells and tissues of longevity family members in the context of their genomic background.",
+      "\tRelevance to nurse practitioner practice\n\nCurrently, there is no cure for genetic variants associated with rapid aging, but novel agents that may slow down the aging process are being tested.The authors of this article advocate individual participation in association studies of aging and pharmacologic risk mitigation or reversal of symptoms for those with known genetic disease risk.Direct to consumer epigenetic biological aging tests and telomere length tests are available; but they are not approved by the Food and Drug Administration.Health care providers may want to consider the simple but key clinical and personal changes, suggested above, to enhance DNA health, wellness, and longevity.Simple mindful changes in behavior, environmental exposure, food/supplement use, weight loss, and regular exercise can reduce adduct exposure damage and impact telomere length, potentially increasing longevity.A Mediterranean diet containing fruits and whole grains along with fiber, antioxidants, soy protein, and healthy fats (from avocados, fish, flax, and walnuts) is suggested to reduce DNA adducts and protect telomeres.In light of our current pandemic, focus on population health, and restrictions to health care access, especially in rural communities, health care providers could incorporate these lifestyle and dietary principles in telehealth visits with patients to reduce disease risk and optimize healthy aging.\t\n\nMany factors contribute to aging, including genes.This is the first article in a 10-part series that highlight some of what is known about the influence of genes on aging and emerging treatment options that may slow down or potentially reverse the aging process.The series will address \\genes, adducts, and telomeres, decreased immune defenses, oxidation and inefficient mitochondria, toxins and radiation, glycosylation, caloric intake and sirtuin production, neurotransmitter imbalance, hormone mechanisms, reduced nitric oxide, and stem cell slowdown.Underpinning these factors are wear and tear on cells and aging as a result of inability to repair or replace these affected cells.These topics have been addressed in research, health magazines, and even by talk show hosts.There is even a LongevityMap website addressing significant and nonsignificant genetic association studies in aging across the human genome (http://genomics.senescence.info/longevity/).The series will address a scientific and clinical approach to genome-related aging topics.",
+      "\t[PubMed: 18208581]\n3. de Magalhes JP, Wuttke D, Wood SH, Plank M & Vora C Genome-environment interactions that\nmodulate aging: Powerful targets for drug discovery. Pharmacol. Rev. 64, 88101 (2012). [PubMed:\n22090473]\n4. McDaid AFet al.Bayesian association scan reveals loci associated with human lifespan and linked\nbiomarkers. Nat. Commun. 8, 15842 (2017). [PubMed: 28748955]\n5. Fontana L & Partridge L Promoting health and longevity through diet: From model organisms to\nhumans. Cell 161, 106118 (2015). [PubMed: 25815989]\n6.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\tThe mechanisms that underlie healthy agingparticularly, the cognitive as-\n\npectsremain poorly understood. Research suggests that genetics play a significant role in determining an individuals\nsusceptibility or resilience to cognitive decline and dementia\n(Harris and Deary 2011; Ridge et al. , 2013). Identification of precise genetic factors involved would provide insight into\n\nCell Reports 32, 108091, September 1, 2020  2020 The Author(s). 1\nThis is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). ll\nOPEN ACCESS\n\nReport\n\nFigure 1.",
+      "\t\n\nWith modern genomic technologies and largescale data analysis methods, it is possible to sift through the genes of populations to find the loci that act to postpone aging. [3]There are uncertainties with the comparison of populations with different rates of aging.However, it is superior to experimental designs that only consider age-dependence or dietary-response, without determining causal mechanisms."
+    ],
+    [
+      "\t\n\nWhen considering the advantages and disadvantages of dogs as a model for geroscience research, it is useful to note that the vast majority of mammalian studies on the basic biology of aging are performed in a relatively small number of inbred mouse strains.Typical average lifespan for most of these mouse strains is approximately 2-3 years, and animals are generally kept in highly controlled, pathogen-free facilities and fed one of a small number of standard, refined mouse chow diets.A majority of laboratory-aged mice die from cancers, many of which are not commonly occurring in human populations.Although there have been recent efforts to define comprehensive measures of frailty and healthspan in aging mice (Parks et al. 2012;Richardson et al. 2016), consensus is still lacking, and functional measures of key organ systems are rarely utilized by the broader field.For example, changes in cardiac and cognitive/behavioral function are rarely assessed in studies of aging mice, but are obviously important components of human aging.As we discuss below, the challenges of the mouse as an aging model underscore the value of studying aging in companion dogs.In the following paragraphs, we expand on some of the additional features of companion dogs that make them uniquely well suited for geroscience research.",
+      "\t\n\nStudies on the aging of mammals are rather limited by the long life span of the commonly used model organisms.Thus, both nonvertebrate and invertebrate organisms, with their shorter life span and ease of genetic and environmental manipulations, gained popularity among researchers in the aging field as experimental models for aging studies.Among them, budding yeast or Saccharomyces cerevisiae is a highly informative organismal model for aging studies with its genetic tools, short life span, and fully sequenced genome (20,21).Despite being unicellular, yeast has been an excellent model to identify and characterize conserved basic biological processes, including aging.Yeast has been extensively used to identify genes and interventions responsible for life span extension and to gain insights into the aging processes of all eukaryotic organisms.In parallel, over the years, studies on invertebrate organisms, such as Drosophila melanogaster (flies) and Caenorhabditis elegans (worms), and certain vertebrate models, such as mice, zebrafish, naked mole rats, and, most recently, African turquoise killifish, have also provided invaluable information to help us understand the complexity of the process of aging and the influence of overlapping pathways on the outcome (22,23).",
+      "\tAfter specific tissues (brain regions and hind\nlimbs) were dissected immediately upon sacrifice,\nAging Clin Exp Res\n\ncarcasses were preserved in buffered formalin until comprehensive pathological examinations were completed. Genotyping and genetic analyses\nMice that began the phenotyping procedure in each of the 3\nage groups were genotyped at 96 microsatellite markers\n[1317]. Distortions in the frequency of alleles with aging\nwere detected by Chi-squared tests conducted for each\nlocus.",
+      "\tExperimental Goals and Significance\nThe experimental goal of the work performed in this dissertation was to identify\nspecific gene(s) and molecular pathways underlying HSC aging in two commonly used\nstrains of inbred mice using a forward genetic approach.",
+      "\t\n\nCross-breeding of N. furzeri strains with different life spans is currently being performed in our laboratory and should enable the identification of quantitative trait loci and facilitate cloning of aging-relevant genetic determinants.The present study illustrates the challenges that will have to be addressed in an N. furzeri genome project that we would like to establish in order to make maximal use of this fish species as a vertebrate model for aging research.",
+      "\t\n\nMost studies in this area have been performed in the classical animal models of aging, such as C. elegans, yeast, and rodents (mice and rats); however, in this chapter we have attempted to include only representative studies in humans, which were performed in samples of skeletal muscle, heart, and brain obtained from elderly individuals.\tAnimal Models for HGPS\n\nIn recent years, animal models have been at the forefront of aging research, making important contributions to a better understanding of this process at the organismal level.Some animals have been preferred in aging research, ranging from invertebrate (Caenorhabditis elegans and Drosophila melanogaster) to mammal species (murine and primate species).Nonetheless, scientists preferably chose mouse models for the study of age-related diseases for various reasons: (a) mice are closely related to humans, with nearly 99% of human orthologous in mice; (b) their relatively short lifespan and small size allow surveillance of the aging process within a pertinent time frame and make their housing less expensive; (c) the feasibility of performing genetic manipulations facilitates the engineering of transgenic strains (gain-and loss-of function mice) that model premature aging disorders.In this section, we describe the major HGPS mouse models previously developed (see Table 10.1 for details).",
+      "\tJournal of Theoretical Biology 12:1245. Hughes, K. A., and B. Charlesworth. 1994. A genetic analysis of senescence in Drosophila. Nature 367:6466. Hutchinson, E. W., and M. R. Rose. 1990. Quantitative genetic analysis of Drosophila stocks\nwith postponed aging. Pages 6687 in D. E. Harrison, ed. Genetic Effects on Aging II. Caldwell, NJ: Telford. Kannisto, V., J. Lauristen, and J. W. Vaupel. 1994. Reduction in mortality at advanced ages: Several decades of evidence from 27 countries. Population Development Review 20:793810. 580\n\n\n\nA P P L I C AT I O N S\nKennedy, B. K., and L. Guarente. 1996.\tGenetic analysis of aging in Saccharomyces cerevisiae. Trends in Genetics 12:355359. Khazaeli, A. A., S. D. Pletcher, and J. W. Curtsinger. 1998. The fractionation experiment:\nReducing heterogeneity to investigate age-specific mortality in Drosophila. Mechanics of\nAgeing and Development 16:301317. Khazaeli, A. A., W. Van Voorhies, and J. W. Curtsinger. 2005. The relationship between life\nspan and adult body size is highly strain-specific in Drosophila melanogaster. Experimental\nGerontology 40:37785. Kim, S. K. 2007. Common aging pathways in worms, flies, mice and humans. Journal of\nExperimental Biology 210:16071612. Kirkwood, T. B. L. 1977. Evolution of aging. Nature 270:301304.",
+      "\tIn Vivo\n\nIn vivo studies can further test the effect of a manipulation or treatment, either targeted or scattered, on the whole organism.Most of these biological models offer many advantages over humans, for instance, their basic biology and genomes are well documented and are easier to manipulate genetically.Furthermore, they have much shorter life spans than humans, enabling longitudinal studies, while ethical issues, long natural life span, environmental influences, genetic heterogeneity, and various other limiting factors complicate the use of human subjects in aging research.Regardless of the advantages listed earlier and the eminent contribution to our understanding of the aging process, the use of animal models in aging studies has its own limitations.Aging is not a simple process, and there is no genuine agreement about what it is and how to define it (14,15), despite the agreement on being a multifactorial and complex phenomenon.Additionally, there is conflicting evidence about aging as a process that is similar across all organisms or particular to each species (15,16).Therefore, it is important to draw attention to the fact that animal models are usually chosen for convenience rather than for specific features applicable to human aging.Hence, choosing the suitable animal model to answer the specific question we aim to understand is of high importance in these types of studies.Among the most prevalent aging model organisms are Saccharomyces cerevisiae, Caenorhabditis elegans, Drosophila melanogaster, and Mus musculus.As a single-celled organism, S. cerevisiae is easily grown, manipulated, and observed; together with a well-characterized genome that bares much resemblance to bigger and more complex organisms, this model organism among others is a convenient platform for the study of the aging phenotype.Another important model system for studying a range of biological processes, including aging, is the nematode C. elegans.C. elegans has a short adult life span of ~2 weeks and a well-documented anatomy which is visible using a microscope.This enables easy observations of aging-related changes in the whole organism, in specific tissues and organs, and even on molecular and cellular levels (17)(18)(19)(20)(21).The classic genetic model organism, D. melanogaster, is also used FiGURe 1 | Key elements in the DNA damage response (DDR) pathway.In case of double-strand breaks (DSB), the DNA damage sensor MRN complex recruits the protein kinase ATM which activates H2AX at the damaged site.H2AX connects to MDC1, and this complex amplifies the activity of the MRN complex which, in a positive feedback, amplifies the ATM activity and the dispersal of H2AX along the chromosome.MDC1 and 53BP1 further mediates the activation of CHK2 which carries the signal to distant locations on the genome.For single-strand breaks (SSB), the protein kinase ATR is activated and amplified by the 9-1-1 complex and TOPBP1, which also mediates the activation of CHK1.The signaling pathway cascades toward the key factors p53 and CDC25.When the lesion is repaired, the DDR complexes are dismantled (2,4,9). in the study of aging.Studies conducted in these flies have identified single gene mutations that influence their life span.One of the strengths of Drosophila as a model organism is the capability to illustrate how genes that have an established role in regulating organismal life span particularly influence cellular and tissue function, how they work together, and how their tissue-specific functions might be linked (22)(23)(24)(25).That said, Drosophila is far from being a good model for human aging as they share only 60% of the human genome.A better similarity is achieved with M. musculus, the mouse.It is the most commonly used model in biological research for various reasons.Mice are small, have a short generation time, and an accelerated life span which means they are not expensive and require only little space and time, compared to larger animal models.Another important reason is the fact that the mouse genome is well documented and can be easily manipulated.In addition, they are biologically similar to humans, exhibiting many of the same diseases and conditions.Nevertheless, mice do not develop several important age-related diseases naturally (e.g., atherosclerosis and diabetes), a fact that limits their potential as an aging model.All the organisms described earlier are short-lived, which is one of their desired traits as model organisms.However, that may not be appropriate for the study of human aging.Thus, in recent years there have been more studies conducted on non-model long-living organisms such as the naked mole rats and bats, which may be more appropriate models in understanding healthy human aging.The naked mole rat (Heterocephalus glaber) is a very important non-model organism in cancer and aging studies.This subterranean, mouse-sized, eusocial rodent is known as the longest-living rodent, living 4-17 years in the wild and with captive individuals demonstrating exceptional longevity that exceeds 30 years (26)-almost an order of magnitude longer than mice.Moreover, until a few years ago no cancer cases were reported in NMRs, and researchers failed to induce tumorigenesis, placing this rodent as a novel model for cancer studies.Bats are the second most speciose mammalian order after rodents.Little brown bats (Myotis) are the smallest bats (3-30 g) with the highest longevity records (Myotis myotis live for 37.1 years and M. brandti live for 41 years).Nevertheless, longevity is generally high in all bat lineages, which makes them an interesting model in biogerontology.One of the most interesting non-model organisms adopted for aging research is the Bowhead whale (Balaena mysticetus), which is estimated to be the longest-living mammal, reaching the age of ~200 years and also one of the biggest species, with length and weight of 20 m and 100 tons (6,27).Bowhead whales live in arctic environment and are well adapted to these harsh surroundings.They are considered to be resistance to cancer and age-related diseases, and thus, though research is very technically complicated, the study of Bowhead whale in the context of longevity could improve our understanding of molecular mechanisms of healthy aging (27).",
+      "\t\n\nOur own work has taken a different tack: we have attempted to determine whether mutations with differential effects on aging may be present within the many available populations of laboratory-adopted inbred mice.The goal is not so much to clone these genes-if indeed they existbecause positional cloning strategies of this kind require many thousands of animals and would be extremely expensive using an assay, age at death, that is itself so costly.Instead, the goal has been to use gene mapping methods to test hypotheses about aging and to develop new animal models that will be useful for testing well-specified hypotheses about the molecular basis for age-dependent changes.In the absence of a validated battery of biomarkers of aging, we (like most others) have reluctantly decided to use mouse life span as a crude surrogate for aging itself, reasoning that genetic alleles that extend life span well beyond the median for the tested population may be operating via an influence on aging itself.Work conducted using recombinant inbred mouse stocks (Gelman et al., 1988;de Haan and Van Zant, 1999) has suggested that life-span differences between pairs of inbred mouse lines might reflect the influence of as few as 4-7 polymorphic loci, providing some basis for hope that some of these would have an effect large enough to be detected by a genome scan experiment involving 300-1,200 mice.",
+      "\t\n\nThe present study offers certain alternatives relative to studies using clinical samples by employing inbred mouse strains.The use of inbred mice achieves several advantages such as isogenicity and genomewide homozygosity among individuals within a strain, which significantly reduces gene expression variability between individuals.This variability was confounding in the aging human study (18).Aging mouse models have been used, for example, to evaluate global gene expression changes in skeletal muscle (35).One of the primary findings with aged skeletal muscle suggested that stress-response genes, including heat shock-response and oxidative stress-inducible genes, were upregulated.A similar study focusing on retinal tissue also found an upregulation in stressresponse genes with age (25).While both of these previous studies used C57BL/6J (B6) mice, there was a common agedependent upregulation of stress-response genes across different tissues.",
+      "\tJournal of Theoretical Biology 12:1245. Hughes, K. A., and B. Charlesworth. 1994. A genetic analysis of senescence in Drosophila. Nature 367:6466. Hutchinson, E. W., and M. R. Rose. 1990. Quantitative genetic analysis of Drosophila stocks\nwith postponed aging. Pages 6687 in D. E. Harrison, ed. Genetic Effects on Aging II. Caldwell, NJ: Telford. Kannisto, V., J. Lauristen, and J. W. Vaupel. 1994. Reduction in mortality at advanced ages: Several decades of evidence from 27 countries. Population Development Review 20:793810. 580\n\n\n\nA P P L I C AT I O N S\nKennedy, B. K., and L. Guarente. 1996.\tGenetic analysis of aging in Saccharomyces cerevisiae. Trends in Genetics 12:355359. Khazaeli, A. A., S. D. Pletcher, and J. W. Curtsinger. 1998. The fractionation experiment:\nReducing heterogeneity to investigate age-specific mortality in Drosophila. Mechanics of\nAgeing and Development 16:301317. Khazaeli, A. A., W. Van Voorhies, and J. W. Curtsinger. 2005. The relationship between life\nspan and adult body size is highly strain-specific in Drosophila melanogaster. Experimental\nGerontology 40:37785. Kim, S. K. 2007. Common aging pathways in worms, flies, mice and humans. Journal of\nExperimental Biology 210:16071612. Kirkwood, T. B. L. 1977. Evolution of aging. Nature 270:301304.",
+      "\t\n\n(ii) Uncertainties exist as to the most suitable model systems for molecular biological studies on aging.Although material from humans should be employed where possible, for practical reasons animal model systems like rats and mice are indispensible.There is evidence that, provided their health status and husbandry is optimal, rodents age much in the same way as humans do (Burek 1978).For studying certain fundamental processes, such as the occurrence of various types of DNA rearrangement, lower organisms and cell lines can also be employed.Various aspects of mammalian development and differentiation have been revealed in such model systems, which could facilitate the interpretation of observed phenomena and their relevance to the aging process.However, in these cases results obtained cannot be extrapolated directly to the human situation with respect to physiological consequences.",
+      "\tTo identify genes and molecular\npathways regulating memory capabilities during aging, here we\nperform a forward systems genetic analysis on an aged cohort of\nstrains from the BXD GRP. 2. Methods\n2.1. Animals\nMale and female mice were group housed (2e5 per cage) and\nmaintained in colony housing (12-hour light/dark cycle) with ad\nlibitum access to food and water.",
+      "\t\n\nTaking advantage of the long-range contiguity of the N. furzeri reference sequence, we set out to study whether aging-related genes show positional gene enrichment (PGE) in sgrs.To this end, we identified aging-related DEGs in three tissues (brain, liver, and skin) by applying two different approaches: (1) we compared young versus old MZM-0410 (5 weeks versus 39 weeks, corresponding to 10% versus 75% of maximum lifespan), and (2) we compared GRZ versus MZM-0410 at 12 weeks.As aging rates differ between these strains (Terzibasi et al., 2008), the same chronological age in the second approach corresponds to 50% of the maximum lifespan in GRZ and 24% in MZM-0410 (Data S4A-S4G).",
+      "\tFor example, investigators funded by\nNIH National Institute on Aging have been working assiduously for years using a complex 4-way\nmouse F2 intercross to understand how a multitude of interventions affect longevity\n\nAccepted Article\n\n(www.nia.nih.gov/research/dab/interventions-testing-program-itp). Scientists at three sites have\nsystematically phenotyped ~15,000 animals using a range of diets, pharmaceuticals, and\nsupplements. Fortunately, they had the foresight to save tails, and the genetic component is now\nbeing bolted on at a cost of about $20/animala bargain given the cost of obtaining longevity data.",
+      "\t\n\nVarious animal models have been critical for uncovering key pathways related to aging.Genetically tractable models such as yeast have been used to investigate both replicative lifespan, measured by the maximum number of mitotic divisions a cell can undergo, and chronological lifespan, measured by the length of time a cell can survive in a post-mitotic state (Kaeberlein et al., 2007).Other studies have taken advantage of the short lifespans of worms and flies (Brandt and Vilcinskas, 2013;Tissenbaum, 2012).Studies in these models have contributed greatly to the field but cannot fully recapitulate the complex nature of human aging, particularly with respect to age-related diseases and the decline of healthspan.Therefore, vertebrate models such as mice have been utilized, taking advantage of genetic proximity to humans and the availability of gene knockout and premature aging models (Quarrie and Riabowol, 2004).Unfortunately, mouse lifespan is too long for efficient laboratory studies of normal aging, creating the need for alternative short-lived vertebrate models such as the African turquoise killifish (Nothobranchius furzeri) (Harel et al., 2015) which lives for 4-6 months and recapitulates many of the age-related pathological changes found in humans.",
+      "\t\n\nInstead, we recommend the use of organisms that have had their aging slowed or postponed, but that do not merely have life \"stretching\", unlike cooled poikilotherms.That is, we propose that aging studies normally be based on the comparison of normal healthy animals with an experimental group that lives even longer, with increased total biological activity, from reproduction to locomotion to metabolic work.Such organisms exist among Drosophila stocks, including some of the mutants with increased lifespan and the selectively bred populations."
+    ],
+    [
+      "\t\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.\t\n\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.",
+      "\t\n\nStudies revealed from 300 to 750 genes related to longevity that are critically involved in a variety of life activities, such as growth and development, energy metabolism, oxidative stress, genomic stability maintenance, and neurocognition [4].These candidate genes include mainly APOE, a gene involved in lipoprotein metabolism [5,6].Others are those involved in cell cycle regulation, cell growth and signal transduction, the maintenance of genome stability, and the endocrine-related pathway [7][8][9].In addition, the candidates for longevity encompass genes related to drug metabolism, the ones involved in protein folding, stabilization, and degradation, as well those related to coagulation and regulation of circulation [10], etc.In most cases, these genes or their polymorphic sites were examined in multiple population replication studies, which discovered certain longevity-associated genes or pathways [4][5][6][7][8][9][10].",
+      "\t\n\nSomatic mutations with the inherited gene variations of each individual cumulatively or synergistically influence the health span and life span [11].Very few genetic variants have been associated with human longevity, but those found include the transcription factor FOXO3 gene, the APOE/TOMM40 and the CDKN2B/ ANRIL loci, which are associated with Alzheimer's disease and cellular senescence [12][13][14].In fact, the heritability for human longevity has been estimated to be approximately 20-30%, according to studies of twins, suggesting that external factors such as diet, environment, physical activity and microbiomes are important factors that influence the health span [14][15][16].The increase in the rate of retrotranscription reflects genome deregulation, creating additional mutations, DNA damage, and other forms of genome instability.For instance, the expression of several families of retrotransposable elements increases with age, as observed in mouse skeletal muscle and human fibroblasts, particularly the long interspersed nuclear element-1 (L1 LINE) [17,18].",
+      "\t\n\nsmall number of genes or interventions are known to increase life span in different model organisms.A selection of these are shown here.\t\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.\t\n\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.",
+      "\t\n\nThe only two genes associated with human longevity that have been replicated in multiple populations are FOXO3A and APOE [11,12,15,26,28 -31].The effect sizes of these two genes for longevity are small with odds ratios of 1.26 and 1.45 for survival to age 100 in replicate studies for FOXO3A and APOE, respectively [10,29].These genes account for only a small portion of the genetic contribution to longevity measured through family heritability studies [4,5].Therefore, much of the heritability of lifespan remains to be explained.",
+      "\t\n\nIn most experimentally modified animal model systems, single-gene mutations in many different genes have major life extension effects (Fontana et al., 2010;Kenyon, 2010).However, natural human and animal longevity is presumed to be a complex trait (Finch & Tanzi, 1997).In humans, both candidate gene and genome-wide genetic association approaches have been applied in an attempt to identify longevity loci.The frequency of genetic variants has been typically compared between nonagenarian cases and young controls, revealing loci at which genetic variants may contribute to a higher or lower probability of survival into old age.The initial candidate gene studies aimed at finding human longevity genes were dominated by contradictory results (Christensen et al., 2006).The more consistent evidence obtained by repeated observation in independent cohort studies for association with longevity has so far only been observed for three loci, the apolipoprotein E (APOE) locus (Schachter et al., 1994;Christensen et al., 2006), the FOXO3A locus (Willcox et al., 2008;Flachsbart et al., 2009;Pawlikowska et al., 2009;Soerensen et al., 2010), and the AKT1 locus (Pawlikowska et al., 2009).Thus, despite the expectation that longevity would be influenced by many genetic variants with small effect sizes, the effect of variants has consistently been shown in only three genes.",
+      "\t\nClear evidence exists for heritability of human longevity, and much interest is focused on identifying genes associated with longer lives.To identify such longevity alleles, we performed the largest genomewide linkage scan thus far reported.Linkage analyses included 2118 nonagenarian Caucasian sibling pairs that have been enrolled in fifteen study centers of eleven European countries as part of the Genetics of Healthy Ageing (GEHA) project.In the joint linkage analyses we observed four regions that\t\n\nClear evidence exists for heritability of human longevity, and much interest is focused on identifying genes associated with longer lives.To identify such longevity alleles, we performed the largest genomewide linkage scan thus far reported.Linkage analyses included 2118 nonagenarian Caucasian sibling pairs that have been enrolled in fifteen study centers of eleven European countries as part of the Genetics of Healthy Ageing (GEHA) project.In the joint linkage analyses we observed four regions that",
+      "\t\nLiving to a late age without suffering any major health problems is a genetically influenced trait.To identify the genes contributing to this important phenotype, a 10 cM genome screen was performed in 95 pairs of male fraternal twins concordant for healthy aging.Individuals meeting these criteria were defined as those attaining the age of 70 free of cardiovascular disease (coronary surgery, diabetes, heart attack, and stroke) and prostate cancer.Six chromosomal regions were identified with logarithm of odds (LOD) scores greater than 1.2 ( p , .01).A region on chromosome 4 at marker D4S1564 produced a LOD score of 1.67; this was the same marker previously linked to extreme longevity segregating as an autosomal dominant trait in centenarian families.Our results provide independent evidence that a locus on the long arm of chromosome 4 is associated with better physical aging and/or longevity.",
+      "\tIntroduction\n\nThe recent, remarkable extension of life expectancy is largely attributed to the postponement of mortality at old age (Vaupel, 1997(Vaupel, , 2010)).The years of life gained in the older population residing in developed nations are a success story of public health measures and improved health care.In addition to such external factors, longevity and healthy aging consistently show a modest heritability between 20% and 50% and aging-associated genetic research may provide further insights into the mechanisms of aging (Herskind et al., 1996;McGue et al., 1993;Reed and Dick, 2003).It has been postulated that genes involved in pathways associated with aging identified in animal models, such as insulin-like growth factor (IGF)-insulin signaling, regulation of lipoprotein metabolism, the mTOR pathway, and the oxidative stress response may also influence survival to old or even exceptionally old age in humans (Christensen et al., 2006;Kenyon, 2010;Vellai et al., 2003).However, in humans, common variants within genes involved in these pathways have not been consistently associated with lifespan (Chris-tensen et al., 2006;Kenyon, 2010;Kuningas et al., 2008;Vijg and Suh, 2005).",
+      "\t\nIn animal models, single-gene mutations in genes involved in insulin/IGF and target of rapamycin signalling pathways extend lifespan to a considerable extent.The genetic, genomic and epigenetic influences on human longevity are expected to be much more complex.Strikingly however, beneficial metabolic and cellular features of long-lived families resemble those in animals for whom the lifespan is extended by applying genetic manipulation and, especially, dietary restriction.Candidate gene studies in humans support the notion that human orthologues from longevity genes identified in lower species do contribute to longevity but that the influence of the genetic variants involved is small.Here we discuss how an integration of novel study designs, labour-intensive biobanking, deep phenotyping and genomic research may provide insights into the mechanisms that drive human longevity and healthy ageing, beyond the associations usually provided by molecular and genetic epidemiology.Although prospective studies of humans from the cradle to the grave have never been performed, it is feasible to extract life histories from different cohorts jointly covering the molecular changes that occur with age from early development all the way up to the age at death.By the integration of research in different study cohorts, and with research in animal models, biological research into human longevity is thus making considerable progress.\t\n\nIn animal models, single-gene mutations in genes involved in insulin/IGF and target of rapamycin signalling pathways extend lifespan to a considerable extent.The genetic, genomic and epigenetic influences on human longevity are expected to be much more complex.Strikingly however, beneficial metabolic and cellular features of long-lived families resemble those in animals for whom the lifespan is extended by applying genetic manipulation and, especially, dietary restriction.Candidate gene studies in humans support the notion that human orthologues from longevity genes identified in lower species do contribute to longevity but that the influence of the genetic variants involved is small.Here we discuss how an integration of novel study designs, labour-intensive biobanking, deep phenotyping and genomic research may provide insights into the mechanisms that drive human longevity and healthy ageing, beyond the associations usually provided by molecular and genetic epidemiology.Although prospective studies of humans from the cradle to the grave have never been performed, it is feasible to extract life histories from different cohorts jointly covering the molecular changes that occur with age from early development all the way up to the age at death.By the integration of research in different study cohorts, and with research in animal models, biological research into human longevity is thus making considerable progress.\tGENETIC STUDIES OF HUMAN LONGEVITY\n\nGenetic and genomic studies into longevity have been performed based on a hypothesis, referred to as a candidate gene approach.Alternatively, explorative genome-wide analyses have been applied in which genetic variation and gene transcription across the complete genome are being studied for associations with longevity and related traits.Genetic studies into human disease and longevity include candidate gene approaches, genome-wide association studies (GWASs) and genome-wide linkage studies.",
+      "\t\n\nThe genetic basis of human longevity has so far been primarily investigated by association studies.Most results from these experiments have been difficult to confirm in independent samples, probably owing to the modest heritability, multifactorial nature, and heterogeneity of the phenotype (Christensen et al., 2006).To date, variation in only two genes has been identified, which has an effect on longevity in various populations: (i) the apolipoprotein E gene (APOE) (Scha chter et al., 1994;Christensen et al., 2006) and (ii) the forkhead box O3A (FOXO3A) gene in the insulin-IGF1 signaling (IIS) pathway (Willcox et al., 2008;Flachsbart et al., 2009).Given the apparent lack of susceptibility candidates, it is conceivable that other genetic factors influence the function or expression of genes relevant for human longevity.",
+      "\tIntroduction\n\nApproximately 25-30% of the variation in adult lifespan is attributable to genetic factors that become more important with increasing age and exert their strongest effects in nonagenarians and centenarians (Go gele et al., 2010;Hjelmborg et al., 2006).As yet, however, only a few genetic variants have been found consistently to influence longevity.The first to be discovered was the e4 allele of the apolipoprotein E (APOE) gene, a mortality factor that predisposes to both Alzheimer's and cardiovascular diseases (Corder et al., 1993; Panza et al., 2004).APOE e4 is the only variant with a reportedly large adverse effect upon survival at advanced age (Scha chter et al., 1994), and this association has been replicated in several populations (Christensen et al., 2006).Variation in the human forkhead box O3A gene (FOXO3A), in contrast, has been found to be associated with the ability to live long, an effect corroborated by studies in Japanese, German, Italian, US-American, Jewish, Chinese and Danish populations (Anselmi et al., 2009;Flachsbart et al., 2009;Li et al., 2009;Pawlikowska et al., 2009;Soerensen et al., 2010;Willcox et al., 2008).More recently, we have identified exonuclease 1 (EXO1) as a potential novel longevity gene (Nebel et al., 2009).All three genes were detected through candidate-gene approaches.",
+      "\t\n\nThe only two genes associated with human longevity that have been replicated in multiple populations are FOXO3A and APOE [11,12,15,26,28 -31].The effect sizes of these two genes for longevity are small with odds ratios of 1.26 and 1.45 for survival to age 100 in replicate studies for FOXO3A and APOE, respectively [10,29].These genes account for only a small portion of the genetic contribution to longevity measured through family heritability studies [4,5].Therefore, much of the heritability of lifespan remains to be explained.",
+      "\t\n\nMost of the human candidate gene studies were performed in cross-sectional designs (Box 1 and Fig. 1), comparing allele frequencies of potential longevity loci between highly aged individuals and young controls.The candidate gene studies based on single genes have pointed a role for genes involved in, e.g., GH/insulin/IGF-1 signaling, immune regulation, and lipoprotein metabolism (Supporting Information Table S1), although most of these results have not (yet) been confirmed in sufficient independent studies.The most convincing human longevity loci today are APOE and FOXO3A which have frequently been associated with longevity in cross-sectional studies (see for a review [26]) and survival in prospective studies [27][28][29] (Fig. 3).APOE encodes the protein apolipoprotein E which seems to play a role in e.g., lipoprotein metabolism, cognitive function, and immune regulation [30].FOXO3A encodes the protein forkhead box O3 which acts as a transcription factor for many different genes involved in processes like apoptosis and oxidative stress [31]."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "45610E53D08C987ADFE70F7C8144A035"
+    },
+    {
+      "task_id": "0104C29CA7CB011AB547E22520E72DDF"
+    },
+    {
+      "task_id": "8D7229969C792686F7C492F793386B06"
+    },
+    {
+      "task_id": "00E6DDA8461F4DDAE6AC1EBF19B51359"
+    },
+    {
+      "task_id": "2AF034316EF15DE09CCA38F533D32DB7"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_2.json
new file mode 100644
index 0000000..7eb37df
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_2.json
@@ -0,0 +1,91 @@
+{
+  "question": [
+    "How do telomeres affect the aging process?",
+    "What role does DNA repair play in aging?",
+    "Can genetic research lead to treatments that slow down aging?",
+    "How does mitochondrial DNA influence aging?",
+    "Are there any known genetic mutations that cause premature aging?"
+  ],
+  "answer": [
+    "Telomeres play a central role in aging by adjusting the cellular response to stress and DNA damage. As cells divide, telomeres shorten, and when they become critically short, they can trigger cell cycle arrest, genomic instability, and cell death, a process known as senescence. This telomere shortening is considered a major cause of replicative senescence, which is linked to aging. Additionally, telomere dysfunction can lead to mitochondrial dysfunction, contributing to aging. However, the relationship between telomere length and aging is complex and not straightforward.",
+    "DNA repair plays a significant role in aging. Evidence suggests that the rate of DNA repair declines with age, leading to an accumulation of DNA damage. This damage can cause changes in gene expression, cellular functions, and can lead to age-related diseases. Some studies also suggest that defects in DNA repair pathways can lead to premature aging. Furthermore, the balance between DNA damage and its repair is considered a major determinant of longevity and cell viability. Therefore, DNA repair mechanisms are crucial in maintaining genomic stability and cellular health, influencing the aging process.",
+    "Yes, genetic research can potentially lead to treatments that slow down aging. Discoveries about the biological determinants of aging, such as gerontogenes, could lead to therapies that slow the aging process. Additionally, understanding how the environment modulates aging-related genes could lead to the creation of anti-aging therapies applicable to humans, potentially through diet, lifestyle, and pharmacological interventions.",
+    "Mitochondrial DNA (mtDNA) influences aging through the accumulation of mutations and the reduction of mtDNA copy number over time. These changes disrupt mitochondrial energetics, which may contribute to aging and age-associated phenotypes. The accumulation of mtDNA mutations can compromise cellular energy metabolism and increase intracellular oxidative stress, leading to degenerative changes in tissues. Additionally, certain mtDNA polymorphisms have been associated with longevity and age-related diseases.",
+    "Yes, there are several known genetic mutations that cause premature aging. These include mutations in genes involved in DNA metabolism or regulation, such as those seen in Werner syndrome (WS), Bloom syndrome (BLM), Cockayne syndrome (CS), ataxia-telangiectasia (AT), Hutchinson-Gilford progeria syndrome (HGPS), and restrictive dermopathy (RD). Other examples include mutations in the LMNA gene causing Hutchinson-Gilford progeria syndrome, and mutations in RecQ genes causing Werner syndrome, Bloom syndrome, and Rothmund-Thomson syndrome."
+  ],
+  "contexts": [
+    [
+      "\t\n\nIntegration of oxidative stress and cell senescence (and, by extension, telomere shortening and in vitro senescence in general) is thus very well established in vitro.The only question remaining is whether this relationship (and the underling phenomenon) is also true, and biologically significant, in vivo.Certain correlative data would point in that direction.Short telomeres have been identified as markers in human disease in which oxidative stress is also thought to be involved (for example, [311], reviewed in Ref. [312]).Even more interesting is the finding that telomere length is a statistical predictor of survival in humans over 60 [313] and mortality and morbidity in several age-related diseases [314].It is tempting to speculate that this may be the result of an underlying oxidative stress, though further work will be needed to prove this point.",
+      "\t\n\nTelomeres play a central role in cell fate and aging by adjusting the cellular response to stress and growth stimulation on the basis of previous cell divisions and DNA damage.At least a few hundred nucleotides of telomere repeats must \"cap\" each chromosome end to avoid activation of DNA repair pathways.Repair of critically short or \"uncapped\" telomeres by telomerase or recombination is limited in most somatic cells and apoptosis or cellular senescence is triggered when too many \"uncapped\" telomeres accumulate.The chance of the latter increases as the average telomere length decreases.The average telomere length is set and maintained in cells of the germline which typically express high levels of telomerase.In somatic cells, telomere length is very heterogeneous but typically declines with age, posing a barrier to tumor growth but also contributing to loss of cells with age.Loss of (stem) cells via telomere attrition provides strong selection for abnormal and malignant cells, a process facilitated by the genome instability and aneuploidy triggered by dysfunctional telomeres.The crucial role of telomeres in cell turnover and aging is highlighted by patients with 50% of normal telomerase levels resulting from a mutation in one of the telomerase genes.Short telomeres in such patients are implicated in a variety of disorders including dyskeratosis congenita, aplastic anemia, pulmonary fibrosis, and cancer.Here the role of telomeres and telomerase in human aging and agingassociated diseases is reviewed.\t\nTelomeres play a central role in cell fate and aging by adjusting the cellular response to stress and growth stimulation on the basis of previous cell divisions and DNA damage.At least a few hundred nucleotides of telomere repeats must \"cap\" each chromosome end to avoid activation of DNA repair pathways.Repair of critically short or \"uncapped\" telomeres by telomerase or recombination is limited in most somatic cells and apoptosis or cellular senescence is triggered when too many \"uncapped\" telomeres accumulate.The chance of the latter increases as the average telomere length decreases.The average telomere length is set and maintained in cells of the germline which typically express high levels of telomerase.In somatic cells, telomere length is very heterogeneous but typically declines with age, posing a barrier to tumor growth but also contributing to loss of cells with age.Loss of (stem) cells via telomere attrition provides strong selection for abnormal and malignant cells, a process facilitated by the genome instability and aneuploidy triggered by dysfunctional telomeres.The crucial role of telomeres in cell turnover and aging is highlighted by patients with 50% of normal telomerase levels resulting from a mutation in one of the telomerase genes.Short telomeres in such patients are implicated in a variety of disorders including dyskeratosis congenita, aplastic anemia, pulmonary fibrosis, and cancer.Here the role of telomeres and telomerase in human aging and agingassociated diseases is reviewed.In the future attention undoubtedly will be centered on the genome, and with greater appreciation of its significance as a highly sensitive organ of the cell, monitoring genomic activities and correcting common errors, sensing the unusual and unexpected events, and responding to them, often by restructuring the genome.\t\n\nHigher \"background\" levels of activated p53 could decrease the threshold for activation of senescence or apoptosis in \"old\" cells, in line with the increased sensitivity to stress and more fragile nature of cells and tissues from the elderly.The role of telomeres in cellular aging relative to other proposed molecular mechanisms of aging including oxidative stress resulting from mitochondrial dysfunction or loss of ribosomal function remains to be precisely FIG. 4. Diagram of factors affecting the telomere length in primary somatic cells from human tissues.According to the model shown, telomeres in \"young\" somatic cells have long tracts of telomere repeats that favor folding into a \"closed\" structure that is invisible to the DNA damage response pathways and telomerase.As the telomere length at individual chromosome ends decreases, the likelihood that telomeres remain \"closed\" also decreases (see also Fig. 3).At one point telomeres become too short and indistinguishable from broken ends.Such ends will be processed by enzymes in the DNA repair compartment (proposed to occupy a different nuclear domain than long telomeres).Depending on the cell type and the genes that are expressed in the cell, a limited number of short ends can be elongated by limiting levels of telomerase or recombination.However, with continued cell division and telomere loss, eventually too many short ends accumulate for the limited capacity of these \"telomere salvage pathways. \"At this point, defective telomeres will trigger levels of DNA damage signals such as p53 to which cells respond by either apoptosis or senescence.Rare (mutant) cells that do not upregulate functional DNA damage responses (e.g., by loss of functional p53) continue cell divisions in the presence of dysfunctional telomeres causing genome instability via chromosome fusions, chromosome breaks, and repetitive break-fusion bridge cycles.delineated.The development of an integrated view of the various molecular mechanisms of aging that have been proposed remains as formidable a challenge.However, it has become clear that telomeres are directly responsible for sustained DNA damage signals in senescent cells (54,203), and DNA damage foci originating from telomeres in senescent cells can readily be detected in vivo (104).\tIII. LOSS OF TELOMERIC DNA WITH AGE: OVERVIEW\n\nLoss of telomeric DNA at the cellular level is well established and was shown to be related to replicative history and life span in somatic cells (see sect.II and Figs. 2 and 4).However, at the level of tissues or of the entire organism, what is the impact of telomere shortening?Does aging cause telomere shortening, or does telomere shortening cause aging (98)?The issue of organismal aging as a consequence of short telomeres was raised as a concern when Dolly, \"cloned\" by transfer of an adult mammary gland nucleus into an enucleated egg, was shown to have short telomeres (189).In contrast, nuclear transfer experiments using nuclei from senescent bovine fibroblasts yielded offspring with longer than expected telomeres and a \"youthful\" phenotype (117).Differences in donor nucleus cell type, nuclear transfer methodology, or species could explain these discrepant results (1,103,112).However, the \"immortal\" growth properties of embryonic stem cell lines derived from preimplantation embryos of many species suggest that telomere length can be maintained or telomere loss attenuated in early development.The loss of telomere repeats in human cells with age varies greatly between cells and tissues, and the amount of information for different tissues is often very limited.It has been proposed that the number of cell divisions in stem cells is 100 divisions over a human lifetime and that this efficiency is achieved by a strict hierarchy at the level of stem cells with the most primitive cells dividing the least and having the longest telomeres (115).A diagram representation of this model is shown in Figure 7.\t\n\nThe correlation between telomere length and replicative potential became a mechanistic link when it was demonstrated that the replicative potential of primary human fibroblasts can be extended indefinitely by artificially elongating telomeres.The latter was achieved in primary human fibroblasts by overexpression of the telomerase reverse transcriptase (hTERT) gene (25,211).These experiments established that progressive telomere loss is indeed the major cause of replicative senescence as had been proposed earlier (3,84).\tA. Telomeres From Cytogenetics to Replicative\n\nSenescence: Historic Background That chromosome ends play an important role in ensuring chromosome stability was first proposed in the 1930s by Barbara McClintock working with maize (142) and Hermann Muller working with fruitflies (155).Both investigators proposed that chromosome ends have special structures required for chromosome stability.Muller coined the term telomere, from the Greek for \"end\" (telos) and \"part\" (meros).McClintock noted that without these special end structures, chromosomes would fuse and often break upon mitosis, and she observed that the resulting chromosome instability was detrimental to cells.These pioneering studies established that functional \"telomeres\" are required to protect chromosome ends, to provide chromosome stability, and to ensure faithful segregation of genetic material into daughter cells upon cell division.These conclusions have stood the test of time, and since this work was published, an enormous amount of data on telomeres and their function have been produced.Some of the most striking contributions are reviewed here.However, despite this progress, it is also clear that many mysteries around telomeres and their function remain.The increasing amount of detail about individual molecules and pathways involved in telomere biology and DNA damage responses has not at all diminished the challenge of understanding how telomeres are integrated and involved in DNA damage responses, cellular fitness, and human aging.While it has become clear that telomeres play a central role in the cellular response to stress and DNA damage, neither the relative importance to other factors nor all the connections between proteins and signaling pathways that directly or indirectly involve telomeres are fully understood.The future of telomere research is bright!In the early 1960s, Leonard Hayflick observed that human cells placed in tissue culture stop dividing after a limited number of cell divisions by a process now known as replicative senescence (90,92;reviewed in Ref. 89).He proposed that the cell culture phenomenon could be used as a model to study human aging at a molecular and cellular level.However, the role of replicative senescence in human aging and the relevance of the in vitro studies remained subject to much debate.Cells presumably divide either to balance normal cell loss or in response to injury.Many cells in the human body can divide many more times than needed during a normal lifetime.A mitotic \"reserve capacity\" was used as an argument against the idea that replicative senescence has any relevance to human aging.However, one would not expect all (stem) cells in the body to have a similar replicative history (or potential), and cells that no longer exist (or can no longer divide) are easily overlooked.It has furthermore been difficult to estimate the actual turnover of the stem cells in tissues such as the intestine and hematopoietic stem cells over a normal lifetime with any degree of accuracy.Estimates range from more than 1,000 times for intestinal epithelial cells in rodents (170) to less than 100 times for hematopoietic stem cells in humans (115).Recent studies of the levels of 14 C remaining in tissues from nuclear weapons test during the Cold War have shown that the turnover of blood cells far exceeds that of the cells in the gut (197), and these data seem incompatible with thousands of cell divisions.Uncertainties about actual turnover and the fact that model organisms such as worms and flies clearly \"age\" without cell renewal being a major factor have been used to question the role of cell turnover and replicative senescence in human aging.However, as will be discussed, the tight association of telomeres to overall cellular fitness does not exclude a role for telomeres even in the aging of tissues that contain mostly long-lived postmitotic cells such as the brain, heart, or kidney.For example, it is possible that damage to telomeric DNA by reactive oxygen species (ROS) produced by either dysfunctional mitochondria (85,220) or by signaling pathways (e.g., overexpression of oncogenes such as Ras, Refs.152,239) contributes or predisposes cells to apoptosis and senescence.Thus DNA damage signals originating from telomeres could be replication independent, and the sensitivity of cells to DNA damage could increase as the overall telomere length declines.More information is needed on the role of telomeres in the cellular response to various types of insults (177).",
+      "\tImpact on aging\n\nThere is no straightforward relationship between telomere length or stringency of control of telomerase expression and organismal life span (Campisi, 2001).On the other hand, two human syndromes with features of premature aging -Werner syndrome (WS) and dyskeratosis congenita (DKC) -have been linked directly (DKC) or indirectly (WRN) to telomere length and presumably telomere structure (Chang et al., 2004;Mitchell, Wood, & Collins, 1999).Thus, functional telomeres may directly increase longevity by maintaining genomic stability and suppressing cancer while also indirectly postponing aging phenotypes by preventing apoptosis and/or senescence (Blasco, 2003;Campisi, 2003aCampisi, , 2003b)).Whatever the case, the cellular responses to telomere dysfunction -apoptosis and senescence -have been proposed to contribute to aging phenotypes (Campisi, 2003a).",
+      "\t\n\nRegarding cancer and aging, Serrano and Blasco (2007) suggested that an equilibrium between mechanisms diminishing cellular damage and mechanisms preventing excessive cellular proliferation is required between both processes [43].The authors argue that the p53 pathway may be seen as an anti-aging mechanism as it is a key defense mechanism against cellular damage protecting from both aging and cancer.One effect of aging at the cellular level is reduced telomerase activity and progressive shorter telomeres in somatic cells [45].Shortened telomeres are highly recombinogenic, leading to a genome-susceptible cancer development [46,47].Genomic instability driven by dysfunctional telomeres is also associated with the transition from benign to malignant tumors [48].Conversely, telomere dysfunction also acts to induce the p53 gene to suppress tumor development by initiating cell-cycle arrest, cellular senescence or, apoptosis.Our analysis has identified several genes involved in the regulation and activity of the p53 pathway as being affected by age.In skin, the telomerase reverse transcriptase (TERT) showed an age-related expression in association with a genetic variant (rs10866530).In addition p21, a gene directly regulated by p53 and also involved in telomere-driven aging, was shown to be differentially expressed with age [49].In brain, theZBTB16, CA9,and HEY2, genes associated to the p53 pathway directly or via SIRT1, all showed age-related expression.The activity of p53 has been shown to enhance the transcription of inhibitors of the insulin receptor pathway, preventing cell growth and division after stress signaling [50,51] and many genes from the insulin signaling pathway have been extensively associated with longevity in multiple studies and organisms.Our results suggest that the link between aging and cancer is evident in multiple tissues through differential expression of genes with age.",
+      "\tevidence From In Vitro Studies\n\nIn most organisms, telomere elongation is controlled by the enzyme telomerase under tight regulation to ensure sufficient number of replications, yet when this number is reached, telomere elongation is seized (2,83).Once telomeres reach the critical length, the cells undergo senescence and stop proliferating (84).This process is believed to be the trigger for the aging process, according to the telomere theory (11,85,86).It is further supported by Bodnar et al. who proved that telomere elongation caused by ectopic expression of telomerase avoids the senescence phenotype (87).His work relied on one of the earliest studies linking telomere shortening to aging which was performed by Harley et al. on human fibroblast cells (88).In their paper, they describe the shortening of telomeres in aging fibroblasts alongside chromosomal abnormalities, specifically the fusion of two chromosomes at the telomeric region and chromosomal rearrangement, while hinting at a biological significance to the shortening process.Since this early study, numerous studies have emerged strengthening this association and aiming to elucidate the exact underlying mechanism of telomere shortening.Murillo-Ortiz et al. ( 89) studied telomere alterations using T, B, and NK cells from 20 to 25-year-old and 60 to 65-year-old donors.Treatment with concanavalin A (a mitogen of T cells) caused increase in telomere length and number of replications in the samples from the young donors, but did not improve the samples from the older donors, which exhibited loss of telomere parts, decrease in telomere length, and decreased proliferation potential (89).Age-related changes in telomere length were also established in bone marrow hMSC in a long-term in vitro study (90).COMET assay revealed higher levels of damage in cells from older donors (91).Similar results were obtained in the study of CD34  and CD34 + cells isolated from healthy donors of different ages.However, some of the cells exhibited telomere shortening that was not correlated with age.It seems that CD34 + cells from older donor suffer from increased non-telomeric DNA damage, but the variation among the cultures hints for multiple factors contributing to DNA damage (92).\t\n\nThe Question of Telomere-Related Senescence in S. cerevisiae For S. cerevisiae, various studies were performed on the effect of missing/broken telomere and mutated telomerase on the physiology of the organism.Genetic manipulations of S. cerevisiae cells caused decreased growth, irregular shape, and eventually, cellular senescence (69).Several genes, such as EST1 (telomere elongation protein), EST2 (telomere reverse transcriptase), EST3 (telomere replication protein), TLC1 (template RNA component), RAD9, RAP1 (DNA binding protein), CDC13 (cell division control protein 13), TEL1 (serine/threonine protein kinase), MEC1 (serine/ threonine protein kinase), and MRC1 (macrophage mannose receptor 1 precursor) were studied in connection to telomererelated senescence; however, despite the extensive experimental work put into using mutated cells, the role of eroded telomeres in \"natural\" cellular senescence in yeast remained questionable (93).For example, EST1-4 (ever short telomere) mutants began to lose viability after 60 doublings, but late knockout cultures continued to maintain proliferation potential (94).Cells with mutated telomerase exhibited irregular morphology and short telomeres, but these changes did not cause deadly damage and determinate senescence (95).One hypothesis connects aging to telomere erosion through the transcription of subtelomeric genes.Genes located in subtelomeric regions are affected by transcriptional silencing which was found to change in an age-related manner.Kim et al. (96) found that silencing of genes in subtelomeric regions declined during the cell's senescence, hinting at a connection between the transcription of subtelomeric regions and cellular senescence in yeast (96).The work of Austriaco and Guarente (97) reinforced this model, as they found that mutated telomerase extended life span (relatively to the wild type), probably by hanging the silencing procedure in the subtelomeric locations (97).\tCONCLUSiON\n\nHealthy aging and cellular senescence are complex processes of great interest to researchers.The multigenic nature of both of them complicates studies and necessitates creative and novel approaches in the path for understanding those phenomena.The three spear-headed strategies implemented for this purpose have brought forth much information and knowledge, yet there is still much to learn in these fields.The doubting and contradicting results in in vivo studies are influenced both by physiological and genetic differences between the model organisms and humans and the differences in the possible research methodologies between in vitro and in vivo studies.In many cases, the age-related phenotypes searched for and studied in vitro are not visible in vivo or not relevant for the model organism (Table 1. ).Molecular processes such as DNA damage repair, telomere shortening, and epigenetic alterations discussed earlier are the driving forces of the aging process in human, but their significance is varied in other organisms.Many evidence for age-related accumulation of DNA damage were found in in vitro studies, both in human and mice cell cultures.The connection between DNA damage and aging is emphasized by the secretion of senescenceassociated proteins during cellular senescence, a phenotype which is activated by DNA damage and is common for both human and mice.Human progeroid diseases also show the connection between early aging and faulty DNA repair.In yeast, flies and mice, however, although some evidence for age-related damage and faulty DNA repair mechanisms were found, contradicting and debating results highlight the complexity of the use of these model organisms in this aging research.The study of telomeres in relation to aging demonstrates the questions derived from both physiological differences between organisms and differences in research approaches.The connection between telomere attrition and aging is very present in human aging (both in in vitro studies and as telomeropathies such as DKC, Werner syndrome, and Hutchinson-Gilford progeria) but not relevant in model organisms.In C. elegans, the evidence are contradicting.In drosophila, maybe because of the unique telomere structure, there are no evidence connecting telomere attrition to aging.In yeast and mice, genetic manipulations enabled the study of telomere-aging relations, but such relations were not seen in wild-type subjects.The study of telomere-related aging in mice especially feature the difficulties of comparing human and model organisms, since the telomeres of most laboratory mice are 5-10 times longer than in humans, but their life span is much shorter.",
+      "\t\n\nAnother attractive model of ageing is formulated by the ''telomere shortening theory'' [11].The activity of the telomerase enzyme complex responsible for maintaining the structure of the chromosome ends (telomeres) at each round of cell division likewise affects lifespan in a number of model organisms [11,12].Still, the ageing process of postmitotic cells (like neurons) contradicts the theory.Furthermore, the somatic cells of adult C. elegans do not divide, meaning that the shortening of telomeric regions is not an issue even in the case of a complete absence of telomerase activity [13].Regardless, the adult nematode ages and dies in about 2 weeks.Thus, the effect of telomere length on ageing appears to be rather complex.",
+      "\t\n\nIn aging research there has been a great deal of interest in the idea that telomere shortening is a critical feature that leads to senescence.By contrast, the mitochondrial theory of aging posits that mitochondrial dysfunction is the cause of aging [56].Telomere processing and mitochondrial bioenergetics have so far been separate fields, with very limited interaction.The emerging evidence for some crosstalk between these fields of study is very exciting.Recently it has been shown that telomere dysfunction can lead to mitochondrial dysfunction [46] and vice versa [57].It is therefore of great interest that specific proteins, such as RECQL4, have now been identified that operate in both compartments.",
+      "\t\n\nTelomere shortening is considered as the major cause of replicative senescence [82,83].It has been reported that the rate of telomere shortening is directly related to the cellular level of oxidative stress [84].Telomere shortening is significantly increased under mild oxidative stress as compared to that observed under normal conditions, whereas overexpression of the extracellular SOD in human fibroblasts decreases the peroxide content and the rate of telomere shortening [79].ROS can affect telomere maintenance at multiple levels.The presence of 8-oxoguanine (8-oxoG), an oxidative derivative of guanine, in telomeric repeat-containing DNA oligonucleotides has been shown to impair the formation of intramolecular G quadruplexes and reduces the affinity of telomeric DNA for telomerase, thereby interfering with telomerase-mediated extension of single-stranded telomeric DNA [85].ROS also affect telomeres indirectly through their interaction with the catalytic subunit of telomerase, telomerase reverse transcriptase (TERT).Increased intracellular ROS lead to loss of TERT activity, whereas ROS scavengers such as N-acetylcysteine (NAC) block ROSmediated reduction of TERT activity and delay the onset of cellular senescence [86].Furthermore, the presence of 8-oxoG in the telomeric sequence reduces the binding affinity of TRF1 and TRF2 to telomeres [87].TRF1 and TRF2 are components of the telomere-capping shelterin complex that protects the integrity of telomeres [88].In addition, ROS-induced DNA damage elicits a DNA damage response, leading to the activation of p53 [89], a critical regulator of senescence.It has been shown that p53 transactivates E3 ubiquitin ligase Siah1, which in turn mediates ubiquitination and degradation of TRF2.Consequently, knockdown of Siah1 expression stabilizes TRF2 and delays the onset of replicative senescence [90].The p53-Siah1-TRF2 regulatory axis places p53 both downstream and upstream of DNA damage signaling initiated by telomere dysfunction.By regulating telomere maintenance or integrity directly or indirectly, ROS plays a critical role in senescence.",
+      "\tThe cell-autonomous theory on the\nother hand posits that individual cells are the targets of the aging process, via a timedependent increase in homeostatic dysfunction. The potential mechanisms include\nincreases in the production of reactive oxygen species, telomere shortening and, not\nsurprisingly, genomic instability. An implication of this theory is that long-lived cells in\nthe organism, such as neurons, muscle, and importantly stem cells, would be the\npredominant substrates of aging, while those cells that undergo rapid and continuous\nturnover would be removed before they could exert an effect on tissue function.",
+      "\tTelomere Theory of Aging: Mitotic Clocks and Cancer\n\nTelomere stability has been implicated in the control of replicative senescence in human cells (Harley, 1995).The average telomere length of human germ cells is longer than that of differentiated somatic cells.As somatic cells age in vivo or in vitro, telomere arrays shorten in a progressive manner (Harley et al., 1990); telomere shortening in humans correlates with the developmental regulation of telomerase activity.Somatic cells have low or undetectable telomerase activity (Counter et al., 1992), and thus upon successive replication cycles, telomere sequences shorten as a result of incomplete replication of the 5 end of the daughter strand (Harley, 1995;Forsyth et al., 2002).Telomere shortening is proposed as the predominant \"mitotic clock\" that measures and controls the replicative life span of somatic cells.The telomere clock theory of aging states that erosion of the chromosome end triggers significant genome instability inducing cell senescence (Olovnikov, 1973;Hayflick, 1997).Numerous studies provide support for the telomere clock theory of cell aging (Harley et al., 1990;Harley, 1991;Harley, 1995;Forsyth et al., 2002).Telomere shortening is correlated with increased frequency of chromosome rearrangements (Counter et al., 1992) and p53-induced apoptosis (Karlseder et al., 1999).Of significant interest was the finding that telomerase activity resumes in the majority of immortalized cell lines and human tumors (Shay and Bacchetti, 1997) and that telomere array length stabilizes, and in some cases lengthens, in cancerous cells (Counter et al., 1992;Kim et al., 1994).Thus, telomere stabilization and abrogation of the normal telomere clock via abnormal telomerase activity (or an alternate pathway, see below) in cancerous cells may contribute to the immortalization capacity of metastatic cells (Harley et al., 1994; for a recent review, see Shay et al., 2001).Interestingly, transfection of TERT into human epithelial or fibroblast cells (Bodnar et al., 1998) has produced cell lines that are immortalized without being transformed.",
+      "\tTelomeres and Reproductive Aging\n\n7][8] Telomeres are repetitive sequences and associated proteins, which cap and protect chromosome ends. 94][15] When telomeres become critically short, the uncapped, blunt chromosome end triggers cell cycle arrest, genomic instability, and cell death, a cellular process called senescence. 8,16elomere attrition plays a central role in oocyte aging. 5,17,18elomere length in most mouse strains is 5 to 10 times longer than that of humans, and intriguingly, most mouse strains do not exhibit appreciable oocyte aging.Rather, age-related changes in the uterus and/or hypothalamus precede oocyte aging. 19,20However, pharmacologic or genetic shortening of telomeres phenocopies the reproductive aging observed in women.As telomeres shorten in telomerase-null mice, their oocytes develop abnormal meiotic spindles, 21 arrested and fragmented embryos, 22 decreased chiasmata and synapsis, 23 and infertility. 24Observational studies in women have associated leukocyte telomere DNA attrition with earlier menopause, 25 recurrent miscarriage, 26 and Down syndrome. 27,28ocyte telomere length has been associated with failed in vitro fertilization (IVF) cycles, 29 embryo fragmentation, 22 and aneuploidy 30 in fertility treatment cycles.\t\n\nImplantation rate decreases and miscarriage rate increases with advancing maternal age.The oocyte must be the locus of reproductive aging because donation of oocytes from younger to older women abrogates the effects of aging on fecundity.Nuclear transfer experiments in a mouse model of reproductive aging show that the reproductive aging phenotype segregates with the nucleus rather than the cytoplasm.A number of factors within the nucleus have been hypothesized to mediate reproductive aging, including disruption of cohesions, reduced chiasma, aneuploidy, disrupted meiotic spindles, and DNA damage caused by chronic exposure to reactive oxygen species.We have proposed telomere attrition as a parsimonious way to explain these diverse effects of aging on oocyte function.Telomeres are repetitive sequences of DNA and associated proteins, which form a loop (t loop) at chromosome ends.Telomeres prevent the blunt end of DNA from triggering a DNA damage response.Previously, we showed that experimental telomere shortening phenocopies reproductive aging in mice.Telomere shortening causes reduced synapsis and chiasma, chromosome fusions, embryo arrest and fragmentation, and abnormal meiotic spindles.Telomere length of polar bodies predicts the fragmentation of human embryos.Telomerase, the reverse transcriptase capable of reconstituting shortened telomeres, is only minimally active in oocytes and preimplantation embryos.Intriguingly, during the first cell cycles following activation, telomeres robustly elongate via a DNA double-strand break mechanism called alternative lengthening of telomeres (ALTs).Alternative lengthening of telomere takes place even in telomerase-null mice.This mechanism of telomere elongation previously had been found only in cancer cells lacking telomerase activity.We propose that ALT elongates telomeres across generations but does so at the cost of extensive genomic instability in preimplantation embryos.",
+      "\t\n\nWe examined the ant genomes and transcriptomes for signatures related to aging.Telomere shortening is a hallmark of cellular senescence in multicellular eukaryotes, and the enzyme telomerase (TERT), which counteracts telomere shortening, prolongs life span upon overexpression (8).TERT RNA levels were highest in eggs and lower in adults in both C. floridanus and H. saltator, but they were up-regulated in H. saltator gamergates (Fig. 3A).This may be explained by the gamergates acquiring many physiological characteristics of queens, including longer life span (9).Aging has also been linked to the sirtuin lysine deacetylases enzymes SIRT1 and SIRT6, homologous to the Saccharomyces cerevisiae Sir2p implicated in replicative senescence (10).In H. saltator gamergates, both of these genes are expressed at higher levels compared to workers (Fig. 3B).These results suggest that the regulation of life span in gamergates may share common mechanisms with other organisms."
+    ],
+    [
+      "\t\nThe biology of aging is an area of intense research, and many questions remain about how and why cell and organismal functions decline over time.In mammalian cells, genomic instability and mitochondrial dysfunction are thought to be among the primary drivers of cellular aging.This review focuses on the interrelationship between genomic instability and mitochondrial dysfunction in mammalian cells and its relevance to age-related functional decline at the molecular and cellular level.The importance of oxidative stress and key DNA damage response (DDR) pathways in cellular aging is discussed, with a special focus on poly (ADP-ribose) polymerase 1, whose persistent activation depletes cellular energy reserves, leading to mitochondrial dysfunction, loss of energy homeostasis, and altered cellular metabolism.Elucidation of the relationship between genomic instability, mitochondrial dysfunction, and the signaling pathways that connect these pathways/processes are key to the future of research on human aging.An important component of mitochondrial health preservation is mitophagy, and this and other areas that are particularly ripe for future investigation will be discussed\nAccepted ArticleThis article is protected by copyright.All rights reserved.defects in DNA repair, and improved understanding of the signaling pathways that connect these processes are important for future research on human aging. DNA damage response pathwaysAll cells are continuously exposed to endogenous agents that cause DNA damage, including reactive oxygen species (ROS), reactive nitrogen species (RNS) and environmental sources of DNA damaging agents, such as radiation, chemical mutagens and carcinogens.It is estimated that approximately 10 5 DNA lesions accumulate in the human genome per cell per day [4].Figure 1 summarizes the classes of DNA damage and the primary cellular mechanism responsible for repairing each class of DNA damage [5].In mammalian cells, nucleotide excision repair (NER) is the primary pathway for repair of bulky DNA lesions, including those generated by ultraviolet light, environmental and chemical mutagens [6].Base excision repair (BER) removes damaged bases caused by oxidation, alkylation, deamination, and spontaneous hydrolysis of the glycosidic bond [7].Single-strand DNA breaks (SSBs) and double-strand DNA breaks (DSBs) are among the most genotoxic DNA lesions.DSBs can lead to chromosomal rearrangements and genomic instability that can trigger cell death and/or senescence [8].Mammalian cells express four distinct DSB repair (DSBR) pathways: homologous recombination (HR), non-homologous end joining (NHEJ), alternative end joining (Alt-EJ) and single strand annealing (SSA).Since NHEJ ligates free ends it is a mutagenic process whereas HR is thought to be error free.Notably, NHEJ is less mutagenic than Alt-EJ, and SSA pathways, which are highly error-prone and promote chromosomal rearrangements and genomic instability [9,10].The mechanisms and factors that determine which pathway repairs a specific DSB in a specific cell include cell cycle phase, efficiency of DNA end-resection, and status of RecQ helicase expression, and post-translational modification [9][10][11].When a cell's capacity to repair DNA lesions is compromised or exceeded, persistent DNA lesions can accumulate and block DNA replication forks and inhibit cell cycle progression in proliferating cells.Replication fork blockage can, in some cases, be overcome by activating secondary origins of replication or by enabling lesion bypass by an error-prone translesion DNA polymerases [12].Cells that harbor a defect in one or more DNA repair pathways, accumulate persistent DNA damage and typically exhibit an elevated mutation rate [2,13].Many theories have been advanced to explain why and how organisms age, and one of the prevalent ones proposes that time-dependent accumulation of DNA damage and genetic mutations plays a major causal role in aging.Consistent with this hypothesis, several heritable human disorders characterized by accelerated aging are caused by mutant alleles in DNA repair genes which impairs DNA repair capacity [14].Thus, human premature aging disorders are strongly associated with defects in DSBR,",
+      "\t\n\nThe lacI/lacZ reporter gene mouse models have taught us that different tissues exhibit different mutation rates with age.Specific DNA repair pathways have been shown to decline with age, depending on the tissues.Except for the BER pathway, few studies have shown decline of other DNA repair pathways or repair enzymes in the mouse aging liver.As several DNA repair enzymes are posttranslationally modified upon DNA damage (thus altering their activities), appropriate experiments are warranted to follow such posttranslational changes at the protein levels in the liver of aging mice.Noteworthy, the genetic background of the mice under study and the husbandry conditions (including diet) will also impact on the phenotypes.Thus, depending on the stress imposed on mice, the severity of the phenotype will vary.Nevertheless, the control of ROS levels, structural changes at the telomere, DNA damage and mutation rate, mitochondrial dysfunction will ultimately impact on health, and such processes underline the complexity of aging.\t\n\nIt remains unclear why only certain DNA repair mutants show phenotypes related to premature aging.It is interesting to note that the DNA repair-deficient mouse models that exhibit reduced health and/or life span in addition to early appearance of age-related phenotypes also display major changes in the expression of liver genes involved in stress response, cell proliferation and apoptosis, glucose and/or lipid metabolism, and inflammatory response.This suggests that NEIL1 (associated with BER), CSB, ERCC1, XPA, XPD (associated with NER), DNA-PKcs/Ku complex (associated with NHEJ), and WRN (associated with NHEJ, HR, or BER) are also implicated (directly or indirectly) with the transcription of a subset of genes (or pathways) important for the aging phenotypes at least in the liver.Such data imply the possibility of targeting specific biochemical pathways (in addition to ROS levels, telomere structural changes, mitochondrial dysfunction) to control or slow down the progression of age-related diseases.The impact of calorie restriction, dietary restriction mimetics, or antioxidants is already under scrutiny in different mouse models of aging [129,130,137,138].",
+      "\tDiscussion\n\nAlthough great attention has been paid to the potential relationship between aging and DNA DSB repair, the major descriptive and mechanistic studies were performed in rodent models. 3,4,6,11,17,23Relevant research in humans was mainly focused on age-related change in the recruitment kinetics of essential DNA damage response factors, assayed by immune-staining; 26 age-related change of genomic instability, measured by comet assay; 7 age-related change of expression profile of important DNA repair factors, analyzed by RNA array and proteomic tools. 27,28Although the previous work greatly advanced our understanding of age-associated changes of DNA DSB repair, due to a lack of proper tools for the analysis of NHEJ and HR efficiency and fidelity separately, and the hardship of acquiring a sufficient number of human samples, whether NHEJ efficiency and fidelity, and HR efficiency change with age in humans and the consequences of any such change, and its underlying molecular mechanism are not well understood.Here, we established 50 eyelids fibroblast cell lines derived from donors who are evenly distributed by age.With these cell lines, using our well-characterized reporters for the analysis of NHEJ and HR capacities, for the first time, we conclusively demonstrate that both DNA repair pathways decline with age.The impaired recruitment of Rad51 to DNA damage sites during aging hampers the ability of aged cells to choose the precise HR pathway, forcing cells to utilize the error-prone NHEJ pathway.Simultaneously, because of decreased expression of XRCC4, DNA Lig4 and DNA Lig3 during aging, NHEJ becomes more inefficient and inaccurate with age, leaving more damage sites repaired with a loss of more genetic information.The declined DNA DSB repair by both pathways then leads to accumulation of DNA mutations, posing more damages to both NHEJ and HR repair machineries, eventually exacerbating the age-related rise of genomic instability (Figure 8).Our previous reports indicate that the efficiency of DNA DSB repair by NHEJ and HR declines, and NHEJ becomes more error-prone with replicative cellular senescence. 21,29In presenescent cells, HR efficiency declines by 38-fold, whereas NHEJ changes by only ~two to threefold.Consistent with the above results, our current aging study also shows a sharp decline of HR efficiency during aging, with the biggest difference of an ~30-fold change, whereas the change of NHEJ with age is relatively mild, albeit statistically significant.However, contradictorily, knocking out major NHEJ factors, such as DNA-PKcs, Ku70, Ku80 or Artemis in mice leads to a phenotype of progeria, 4 whereas knocking out HR factors usually leads to a phenotype of embryonic lethality, 4,30,31 suggesting that NHEJ is more likely to be involved in aging.Considering an organism's life history is likely critical for reconciling these observations.During embryogenesis cells are rapidly dividing and therefore undergoing replication stress; complete loss of HR, which is a dominant pathway for relieving replication stress, 32 may cause cells to enter apoptosis by activating P53, leading to embryonic lethality.However, the embryonic lethality could mask the roles of HR in aging.Indeed, partial loss of HR might also lead to agingassociated phenotypes.For instance, BRCA1 heterozygous mice are short lived and have a premature aging phenotype in the ovaries. 33,34Intriguingly, once an organism has developed into adulthood, a gradual suppression of the HR pathway with age is needed to counteract the potential tumorigenesis as uncontrolled or overactive single-strand annealing (SSA), which shares almost identical repair machinery with the HR pathway, 35 may cause loss of large genomic fragments due to the prevalence of repetitive sequences in human genomes.",
+      "\tPARP1 in DNA Repair. As discussed above, a substantial body of evidence demonstrates a causative role of DNA repair and genome maintenance mechanisms in mammalian longevity.",
+      "\t\n\nA similar duality is emerging in mammals, where defective DNA repair is often associated with premature aging (Lombard et al., 2005), yet the lack of a DNA damage response can be beneficial in situations of chronic DNA damage due to telomere dysfunction (Choudhury et al., 2007;Schaetzlein et al., 2007).Furthermore, exposure to genotoxic stress early in life seems to accelerate changes in gene expression that have been associated with age-related diseases such as amyloidogenesis (Wu et al., 2008).Interestingly, we found that constitutive overexpression of a set of age-deregulated SIRT1 target genes promotes apoptosis in primary neurons (Figure S11); however more work is needed to determine the physiological relevance of this observation.\t\n\nThere is some evidence that related processes occur in mammals.First, cells damaged by oxidative stress in vitro undergo stochastic transcriptional changes that parallel those in aged heart tissue (Bahar et al., 2006).Second, a deficiency in the DNA repair factor ERCC1 accelerates aging phenotypes and generates gene expression profiles reminiscent of aged animals (Niedernhofer et al., 2006).Third, cells that senesce because of replicative aging in vitro or in aged tissues in vivo exhibit alterations in heterochromatin (Herbig et al., 2006;Narita et al., 2006) and secrete growth factors that can drive tumorigenesis (Campisi, 2005).Finally, oxidative DNA damage at promoters correlates with gene repression in the aging human brain (Lu et al., 2004) and has been linked to both transcriptional and epigenetic changes that may contribute to Alzheimer's disease (Wu et al., 2008).",
+      "\t\n\nThe paradigm of the DNA damage theory of stem cell aging states that aging-associated changes in the DNA repair system in HSCs, together with changes in cell-cycle regulation due to increased DNA damage with age (Pietras et al., 2011;Rossi et al., 2007a), are thought to result in elevated DNA mutations, which then causally contribute to the decrease in HSC function with age.The paradigm is in part based on the finding that mice lacking a distinct set of DNA damage repair proteins display reduced function of HSCs, including an impaired repopulating potential and an overall depletion of the HSC pool (Ito et al., 2004;Navarro et al., 2006;Nijnik et al., 2007;Parmar et al., 2010;Prasher et al., 2005;Reese et al., 2003;Rossi et al., 2007a;Ruzankina et al., 2007;Zhang et al., 2010;Geiger et al., 2013), although in naturally aged mice, there is actually an expansion of the number of phenotypic stem cells instead of a depletion of the HSC pool.HSC aging also correlates with an increase in DNA double-strand breaks (DSBs).Both human and mouse HSCs present upon aging with a 2-to 3-fold elevated number of gH2AX foci, a bona fide surrogate marker for unresolved DSBs (Rossi et al., 2007a;R ube et al., 2011).Unresolved DSBs accumulated in quiescent, but not cycling, HSCs upon aging (Beerman et al., 2014).gH2AX foci though were very recently shown to co-localize in HSCs with proteins associated with replication and ribosomal biogenesis stress (Flach et al., 2014), rendering gH2AX foci as a general marker for persistent DNA DSBs in HSCs questionable.",
+      "\tAging\n\nThe oxidative stress theory of aging proposes that accumulation of oxidative DNA damage over the life span of an organism leads to gradual decline of cellular functions and eventual death (Bohr, 2002).This model is supported by several circumstantial evidences including the observation that lower free radical production and/or antioxidant treatment protects against agerelated deterioration, and cognitive decline (Lemon et al., 2003).Further, deficit or decrease in the repair of oxidative DNA damage appears to correlate with premature aging and age-related diseases (Bohr et al., 2007).It appears likely that overall genome repair, specifically the balance between DNA damage and its repair is a major determinant of the longevity and cell viability.A specific defect in processing 5 0 dRP residue at the strand break in Sir2 (SIRT6 homolog)-deficient mice displayed age-related degenerative phenotype (Mostoslavsky et al., 2006).The activities of DGs OGG1, NTH1 and uracil DNA glycosylase (UNG) in brain mitochondria decrease significantly with age (Gredilla et al., 2010).",
+      "\t\n\nPrevious evidence for an age-related decline in DNA repair was obtained largely from cell culture systems.For example, decreased repair has been observed in some but not all cases in mammalian cells undergoing senescence in culture [58,59], as well as cultures of primary cells taken from older versus younger individuals [26,[60][61][62][63][64].Additionally, there is a general correlation between mammalian lifespan and DNA repair (for review [65]).Further support for a relationship between DNA repair and aging comes from the existence of several human diseases caused by DNA repair defects that result in shortened lifespan in affected humans as well as rodent models, despite the much shorter normal rodent lifespan [24,25,66,67].Finally, a recent study reported that the in vivo repair of CPDs is decreased in the skin of old compared with that of young men, suggesting that the previous cell culture results are reflective of in vivo biology [27].\t\n\nWe also asked whether repair of UVC damage is less efficient in the nuclei of aging than in those of young adult C. elegans.There is evidence that nuclear genome integrity may be related to the aging process in mammals [24,25] and that repair rates decline in mammalian cells in culture [25,26].However, very few in vivo, whole organism data have been reported that address this hypothesis [27].Furthermore, there is little evidence to support the hypothesis that DNA repair capacity is related to age in C. elegans, despite the extensive use of this organism as a model for aging [5,6].In this study, we observed a 30% to 50% decrease in DNA repair in aging C. elegans (assayed at 6 days after L4 molt, corresponding to 60% of the population's mean adult lifespan), and then performed gene expression profiling in young and aging adults to generate hypotheses to explain the mechanism of that decline.\tRepair in nuclear genes is decreased in aging nematodes\n\nPrevious studies conducted in cells in culture have suggested that DNA repair declines with age in mammals [24,25].We found that repair in all ten nuclear targets was lower in aging (6 days after L4) adults than repair of those same targets in young (1 day after L4) glp-1 adults (P < 0.0001; Table 1).This difference was greatest in low and medium expression genes (about 50% decrease) but was also robust in high expression genes (about 33% decrease).We chose day 6 to represent the aging adult population because at this age more than 98% of the population is still alive, but the population as a whole has reached 60% of its mean adult lifespan (10 days; Figure 6) and 43% of its maximum adult lifespan (14 days; Figure 6).One-day-old adults have reached 10% of the mean adult lifespan, and 7% of the maximum adult lifespan.glp-1 adults raised at 25C exhibit signs of old age at 6 days, including constipation, cuticular blisters, and reduced mobility and feeding, but they have not yet begun to die in significant numbers (Figure 6 and Additional data file 2).It is therefore unlikely that repair rates are significantly confounded by DNA degradation occurring in dead animals.Initial lesion frequencies were not significantly different between young and aging adults (Table 1).",
+      "\t\n\nAlthough these age-related diseases are strongly influenced by DNA damage, there is still much debate about the extent to which DNA damage contributes to ageing.On the one hand, there is a clear link between oxidative stress and lifespan in invertebrates.In mammals, calorie restriction -a dietary intervention known to extend lifespanreduces ROS production and increases the expression of enzymes that metabolize ROS, such as superoxide dismutases (SODs) and catalase (reviewed in Ref. 80) (see figure).Decreased DNA damage and increased lifespan have also been observed in mice that overexpress catalase in mitochondria 81 .Similarly, mice with mutations in DNA-repair enzymes that are involved in transcription-coupled repair or base-excision repair show signs of premature ageing 60,82 .In humans, several defective DNA-repair pathways can cause accelerated ageing (progeroid) syndromes.On the other hand, certain mouse strains with defective DNA-repair systems accumulate high levels of DNA damage and yet have a normal lifespan (reviewed in Ref. 83).Similarly, a reduction in SOD levels in mice leads to increased oxidative DNA damage but does not affect the ageing process 84 .",
+      "\t\n\nThe role of faulty DNA repair machinery in age-related genomic instability was also found in S. cerevisiae and Drosophila.Mutations in the sgs1 and srs2 genes [encoding for RecQ helicase, homologous to the human WRN (43)] shortened S. cerevisiae life span through two distinct pathways: sgs1-and srs2-mutated cells stopped dividing randomly in an age-independent manner that required the RAD9 (cell cycle checkpoint control protein) DNA damage checkpoint, but late-generation sgs1-and srs2-mutated cells exhibited premature aging.The double sgs1/srs2-mutated yeast cells showed a high rate of terminal G2/M arrest.This arrest was suppressed by knockouts of RAD51 (DNA repair protein RAD51 homolog 1), RAD52 (DNA repair protein), and RAD57 (DNA repair protein), hinting for malfunctioning HR.In a similar study, knockout of DNA2, encoding RecQ helicase-like protein, caused premature aging phenotypes including longer cell cycle time, transcriptional silencing, genomic alterations, and eventually shorter life span (44).Shaposhnikov et al. (45) used D. melanogaster to evaluate the effect of overexpression of DNA repair genes in several locations in the body and several time points during the life period on the Drosophila life span.Beneficial effects on life span were observed with overexpression of Hus1 (checkpoint clamp component), mnk (MAPK interacting protein kinases), mei-9 (meiotic 9, D. melanogaster), mus210 (Xeroderma pigmentosum, complementation group C, D. melanogaster), spn-B (spindle B, D. melanogaster), and WRNexo (WRN exonuclease, D. melanogaster), which control the processes of DNA damage recognition and repair (45).Myc, a key regulator protein of cell growth and proliferation, was shown to act as a pro-aging factor, probably by its ability to increase genomic instability.Overexpression of Myc in Drosophila increased the frequency of large genome rearrangements associated with faulty repair of DNA DSBs and decreased adult life span.Myc knockdowns demonstrated reduced mutation rate and extended life span (46).In aged mice, increased levels of DNA breaks or unrepaired DNA damage as illustrated by the formation of H2AX (phosphorylated variant histone H2A) foci were observed (47)(48)(49).A positive effect on longevity was observed with overexpression of the human enzyme hMTH1 (MutT Human Homolog 1), which eliminates oxidized purine18 and deacetylase Sirt6 (50).Overexpression of SIRT6 promotes DSB repair by the activation of PARP1 [Poly (ADP-ribose) polymerase 1] and facilitating the recruitment of Rad51 (51) and NBS1 (Nijmegen Breakage Syndrome 1) (52) to DNA lesions.",
+      "\t\n\n40.Goukassian D, Gad F, Yaar M, Eller MS, Nehal US, Gilchrest BA. 2000.Mechanisms and implications of the age-associated decrease in DNA repair capacity.FASEB J. 14:1325-34",
+      "\tHow does the rate of DNA damage accumulation influence ovarian ageing? Detailed analysis of full genome expression profiles of multiple organs in a variety of DNA repair-deficient, progeroid mouse models has disclosed that these mutants strongly resemble genome-wide expression profiles of normal ageing, capturing a tremendous amount of underlying biological processes, which are shared between accelerated and natural ageing [31,39,40].This is consistent with the numerous parallels at the pathological, histological, physiological and functional levels, supporting the notion that the accelerated ageing to a large extent resembles the normal ageing process.The expression profile analysis also revealed that repair-deficient, premature ageing mouse mutants systemically suppress key somato-, lacto-and thyrotrophic hormonal axes, including the GH/IGF1 pathway, explaining why all progeroid repair mice -and the corresponding human patients-show dramatic early cessation of growth.Attenuation of the GH/IGF1 axis is also found with normal ageing [41].Energy appears to be redirected from growth to maintenance and defence mechanisms, such as the NRF2-controlled anti-oxidant system and stress resistance.This so-called 'survival' response resembles the response triggered by dietary restriction, which is for long known to retard the process of ageing and promote longevity in a very wide variety of organisms, ranging from yeast to mammals, including in one study non-human primates [42].Persistent DNA damage even triggers this response at the level of individual cells in culture, indicating its universal, highly conserved nature [43].The most plausible interpretation of this response is that organisms facing accelerated ageing due to rapid accumulation of DNA damage, caused by an inborn DNA repair deficiency, attempt in this way to delay ageing in order to extend their short lifespan and live as long as possible.This finding provided a link between high DNA damage loads and the insulin/IGF1 signal transduction pathway, which controls, metabolism, growth and lifespan and influences the ageing process.",
+      "\t\n\nIt is well known that a link between DNA damage and mammalian ageing exists (Sedelnikova et al., 2004;Karanjawala and Lieber, 2004;Lans and Hoeijmakers, 2006).Recent studies have shown that double-strand breaks (DSBs) typically accumulate in HGPS and RD cells and that the resultant genome instability might contribute to premature aging (Liu et al., 2005;Manju et al., 2006).DNA repair pathway defects were observed in HGPS and in a RD mouse model (Zmpste24/).Prelamin A accumulation was also associated with impairing of DNA repair factors recruitment at damage sites (Liu et al., 2005).A second study identified the overexpression of many essential p53 targets in the Zmpste24/ mouse model, which caused at least part of their Progeria-like phenotype (Bergo et al., 2002;Penda s et al., 2002;Varela et al., 2005).Indeed, double knock-out Zmpste24/, p53/ mice showed a partially rescued phenotype (Varela et al., 2005).It is known indeed that p53 activation is triggered by DNA damage (Burma et al., 1999;d'Adda di Fagagna et al., 2003), and that, to some extent, p53 activation can have deleterious effects on bone development, as observed in Progeria (Zambetti et al., 2006).Further proofs of the links existing between altered bone development, DNA repair, accelerated aging, and reduced cancer are the phenotypes of several DNA repair mouse models, as XPD mutant mice (de Boer et al., 2002), Ku80 defective mice (Difilippantonio et al., 2000) and p53 truncation mutants (Tyner et al., 2002).Furthermore, Manju et al. demonstrated that several Lamin mutants causing Progeria and muscle-specific disorders induce defects in ATR signaling pathways such as reduced phosphorylation of g-H2AX and inadequate recruitment of 53BP1 to repair sites in response to DNA damage in cultured cells (Manju et al., 2006).More recently, it has been shown that whereas DSBs repair proteins Rad51 and Rad50 were absent at Laminopathy-related DNA damage sites in patients' cells, xeroderma pigmentosum group A (XPA) protein, a unique nucleotide excisionrepair protein, colocalizes with DSB sites (Liu et al., 2007), maybe pointing to ''unifying'' pathophysiologic clues between different disorders characterized by features of premature ageing.",
+      "\t\n\nOther modulators of the DNA damage response appear to impact aging.For example, inhibition of PARP1 leads to lifespan extension in certain model organisms [21].Concomitant with the age-associated activation of PARP1 is the observation that persistent DNA damage foci containing the proteins 53BP1, gH2AX, and FOXO4 accumulate in aging cells [4,60].Notably, signaling from these foci may contribute to the senescence-associated secretory phenotype [47].Another approach to tackle this signaling cascade is therefore to break up these foci.Treatment with a FOXO4mimicking peptide leads to the removal of p53-and FOXO4-containing foci, thus facilitating apoptosis of senescent cells, regrowth of lost hair, and lifespan extension in models of severe premature aging [60].",
+      "\tCONCLUSION\n\nAccumulation of DNA lesions during aging is likely a major driver of aging and age-related diseases.Known prolongevity interventions and pathways could reduce DNA damage load.Dissecting these mechanisms might facilitate the development of novel age-related intervention strategies.Conversely, elucidating the downstream molecular and cellular mechanisms by which DNA damage drives aging and age-related diseases might also lead to novel antiaging therapies.The use of mouse models that mimic progeroid syndromes can dramatically accelerate aging research, not only by shedding light on the molecular mechanisms underlying the aging process, but also by screening for novel interventions.For instance, premature aging Ercc1 / mice with a life span of 0.5 year have the broadest spectrum of age-related pathologies recorded, which also includes the progressive frailty that is frequently observed in natural human aging.Ercc1 / mice could be used to systematically screen interventions for their ability to reduce age-related pathology much faster than in wild-type mice.\t\n\nrepair capacity and thereby reduce DNA damage load and its consequences could be promising.DNA repair, however, is comprised of multiple, complex pathways for which capacity-limiting proteins have not been identified; this hampers the development of interventions that enhance repair.If DNA damage is a main driver of aging, then known life span-extending pathways and interventions might promote longevity by reducing DNA damage load.Several lines of evidence support this hypothesis.Dietary restriction (DR), reduced calorie intake without malnutrition, is the only robust universal intervention with widespread documented longevity-and health-promoting effects in numerous species (117).DR reduces mutation accumulation (118), which suggests improved DNA repair or reduced generation of endogenous genotoxic metabolic (by-)products by direct DR-mediated alterations in metabolism.Suppression of insulin and IGF1 signaling are among the best-documented prolongevity pathways in model organisms ranging from worms and flies to mammals (119).These pathways also directly impinge on energy metabolism; hence, generation of genotoxic metabolic (by-)products could be reduced.Additionally, insulin/IGF1 longevity pathways can also impinge on DNA repair to provide a complementary protective mechanism against aging.Insulin/IGF1 signaling is reduced by DR in long-lived mouse mutants with defects in these signaling pathways (120), which leads to reduced AKT activity.AKT activity needs both T308 and S473 phosphorylation (121); insulin/IGF1 signaling induces T308 phosphorylation (121).The proteins responsible for S473 phosphorylation are less clear, but DSB-induced checkpoint kinases DNA-PK and ATM can phosphorylate AKT at S473 (122)(123)(124)(125)(126). Thus, DNA damage repair and signaling might be integrated with nutrient status.Indeed, active AKT negatively modulates DNA repair (127) by inhibiting p53 activity (128).Also, the FoxO transcription factors, repressed by AKT (129), have also been implicated in promoting DNA repair (130,131).This provides yet another mechanism by which repair might be affected by DR.Furthermore, AKT has been shown to phosphorylate and inhibit several key DDR factors including Chk1 and TopBP1 (127).Thus, DR could improve DNA repair or signaling via altered insulin/IGF1 signal transduction pathways.This could provide opportunities to improve DNA repair via existing prolongevity mechanisms."
+    ],
+    [
+      "\t\n\nBackground: Genetic research on longevity has provided important insights into the mechanism of aging and aging-related diseases.Pinpointing import genetic variants associated with aging could provide insights for aging research.\t\nBackground: Genetic research on longevity has provided important insights into the mechanism of aging and aging-related diseases.Pinpointing import genetic variants associated with aging could provide insights for aging research.Methods: We performed a whole-genome sequencing in 19 centenarians to establish the genetic basis of human longevity.Results: Using SKAT analysis, we found 41 significantly correlated genes in centenarians as compared to control genomes.Pathway enrichment analysis of these genes showed that immune-related pathways were enriched, suggesting that immune pathways might be critically involved in aging.HLA typing was next performed based on the whole-genome sequencing data obtained.We discovered that several HLA subtypes were significantly overrepresented.Conclusions: Our study indicated a new mechanism of longevity, suggesting potential genetic variants for further study.\tIntroduction\n\nWith the development of human genomics research, a large number of studies of the genetics of longevity have been conducted.Scientists from various countries have proposed many different theories concerning the mechanisms of aging from different perspectives, involving oxidative stress, energy metabolism, signal transduction pathways, immune response, etc. [1,2].These mechanisms interact with each other and are influenced by heredity to some degree [2,3].The identification of longevity-related biological markers is critical to an indepth understanding of the mechanisms of carrier protection against common disease and/or of the retardation of the process of aging.",
+      "\tConclusions\n\nIn the absence of a consensus phenotype for aging, genetic research is impeded (Melzer et al. 2007).At present, it is difficult to determine whether preventative and therapeutic strategies (such as calorie restriction) have beneficial effects in humans because there are no validated biomarkers that can serve as surrogate markers of aging (Matkovic et al. 1990).To have the \"phenome of aging\" (Xue et al. 2007) much better defined, we propose using the musculoskeletal aging phenotypes as an example and starting point.",
+      "\t\nStudies of the basic biology of aging have identified several genetic and pharmacological interventions that appear to modulate the rate of aging in laboratory model organisms, but a barrier to further progress has been the challenge of moving beyond these laboratory discoveries to impact health and quality of life for people.The domestic dog, Canis familiaris, offers a unique opportunity for surmounting this barrier in the near future.In particular, companion dogs share our environment and play an important role in improving the quality of life for millions of people.Here, we present a rationale for increasing the role of companion dogs as an animal model for both basic and clinical geroscience and describe complementary approaches and ongoing projects aimed at achieving this goal.",
+      "\t\n\nOn the other hand, the same evolutionary-motivated strategy suggesting to focus on more heterogeneous phenotypes (as opposite to more homogenous) can be highly beneficial for unraveling genetic predisposition to fundamental mechanisms of intrinsic biological aging and, consequently, to geriatric diseases.Indeed, aging is associated with systemic remodeling of an organism's functioning which increases chances of virtually all geriatric disorders (Franco et al. 2009;Franceschi et al. 2000;Martin et al. 2007;Cutler and Mattson 2006).Experiments with laboratory animals (Johnson 2006) and heritability estimates in humans (Christensen et al. 2006;Iachine et al. 1998) show that aging can be genetically regulated (Finch and Tanzi 1997;Martin et al. 2007;Vaupel 2010).Accordingly, yielding insights in genetic predisposition to aging-related processes in an organism could be a major breakthrough in preventing and/or ameliorating not one geriatric trait, but perhaps a major subset of such traits (Martin et al. 2007) that can greatly advance progress in solving the problem of extending healthy lifespan in humans.",
+      "\t\n\nThe studies in lower animals made in recent years that have led to the view that genes are involved in aging have not revealed a reversal or arrest of the inexorable expression of molecular disorder that is the hallmark of aging.These studies are more accurately interpreted to have impact on our understanding of longevity determination because all of the experimental results have altered biological variables before the aging process begins.None of these studies in invertebrates has demonstrated that the manipulation of genes has slowed, stopped, or reversed recognized biomarkers of the aging process.",
+      "\t\n\nAny discovery about the biological determinants of the rate of aging raises the possibility of therapies to slow aging.Therefore the discovery of a gerontogene with even very rare mutations that increased longevity would cause speculation about future trends in mortality.However, the discovery of such a gene would be relevant only to long-term (and, therefore, very speculative) projections.\tGENETIC ANALYSIS OF LONGEVITY, OF AGING, AND OF AGE-SENSITIVE TRAITS IN MICE\n\nBiogerontology has just begun to benefit from the attention and skills of professional geneticists.Geneticists can attack problems of aging from several related but fundamentally distinct directions.Studies of rare mutations at individual loci, such as the Werner's syndrome locus WRN, whose mutant form produces, in middle-aged people, several of the diseases typically not seen until old age, can give attractive points of entry into the pathophysiology of age-related diseases.In mice there are now four reports of mutations-two naturally occurring and two artificially produced-that lead to impressive increases in mean and maximal longevity (Miskin and Masos, 1997;Brown-Borg et al., 1996;Miller, 1999;Migliaccio et al., 1999), and thus provide extremely valuable models for testing mechanistic ideas and the control of aging.Some of these, such as the dw/dw and df/df dwarfing mutations that affect levels of growth hormone and thyroid hormone, provide clues to endocrine-dependent pathways that could regulate age effects in multiple cells and tissues.The recent report (Migliaccio et al., 1999) that mouse life span can be extended by an induced mutation that diminishes cell susceptibility to apoptotic death after injury should stimulate new inquiries into the effects of altered cell turnover on age-dependent changes.Each of these mutations, however, is exceptionally rare in natural populations; despite their effect on longevity, perhaps mediated by a direct effect on aging, each of the mutations is likely to have, overall, a negative effect on reproductive success and thus fail to become fixed in natural mouse populations.",
+      "\t\n\nIn 2021, Science published a special issue entitled \"125 Questions: Exploration and Discovery.\" One of these 125 questions was \"Can we stop ourselves from aging? \"The U.S. National Institute on Aging (NIA) at the National Institutes of Health (NIH) states that \"aging is associated with changes in dynamic biological, physiological, environmental, psychological, behavioral, and social processes.\" Although geneticists and epidemiologists have long debated the relative importance of the role played by genotype or the environment in the development of age-related diseases, it is apparent that both can play substantial roles in this process [6,7].However, most etiological studies have concentrated on the role of genotype and have considered the environment to play a secondary role.Nevertheless, an analysis of GBD data showed that nearly 50% of deaths worldwide are attributable to environmental exposure, primarily exposure to airborne particulates (including household air pollution and occupational exposure; 14% of all deaths), smoking and secondhand smoke (13%), plasma sodium concentrations (6%), and alcohol consumption (5%) [8].In contrast, a recent analysis of 28 chronic diseases in identical twins showed that the genetic-related risks of developing one of five age-related diseases were 33.3%, 10.6%, 36.3%, 19.5%, and 33.9% for AD, PD, CAD, COPD, and T2DM, respectively, with a mean of only 26% [9].The results of over 400 genome-wide association studies (GWASs) have also elucidated that the heritability of degenerative diseases is only approximately 10% [10,11].Consequently, nongenetic drivers, such as environmental factors, are now recognized as major risk factors for age-related diseases.The contributions of environmental factors to the development of age-related diseases can be revealed by analyses of all of the factors to which individuals are exposed in their life and the relationships between these exposures and age-related diseases [12,13].",
+      "\t\n\nWith an aging population, there is a great and urgent need to develop approaches and therapies targeting the aging process and age-related diseases (Butler et al., 2008).Delaying the process of aging, even slightly, would have profound social, medical and economic benefits (Olshansky et al., 2006;Butler et al., 2008).For example, slowing aging by a mere 7 years would cut mortality of age-related diseases by half at every age.Therefore, the potential benefits from research on the basic biology and genetics of aging are unparalleled in terms of improving quality of life and health.Although much debate remains regarding the molecular causes of aging, findings from model organisms show that aging is surprisingly plastic and can be manipulated by both genetic and environmental factors (Finch and Ruvkun, 2001;Kenyon, 2010).In principle, therefore, it is possible to manipulate human aging.Unlocking this capacity to manipulate aging in people would result in unprecedented human health benefits, and it opens new opportunities for industry.\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\t\n\nThe remarkable discoveries of the past 2 decades showing that single genes can regulate aging in model organisms demonstrate that aging can be genetically manipulated (Finch and Ruvkun, 2001;Kenyon, 2010).Hundreds of genes that modulate longevity have now been identified in model organisms (de Magalha es et al., 2009a).In some cases (e.g., in worms), mutations in single genes can extend lifespan by almost 10-fold (Ayyadevara et al., 2008).Nonetheless, aging is a complex process that derives not from single genes but from the interactions of multiple genes with each other and with the environment.Evidence from animal systems shows a major impact of the environment on aging, yet environmental manipulations of aging act through genes and proteins, usually by triggering signaling pathways and modulating gene expression.In fact, some genes have been shown in model organisms to have varying effects on lifespan depending on diet (Heikkinen et al., 2009).Genes that can regulate aging in model organisms cannot be directly applied to humans through genetic manipulations for numerous legal, ethical, and technical reasons.If we could understand how the environment modulates these aging-related genes, we might be able to create antiaging therapies applicable to humans, potentially through diet, lifestyle, and even pharmacological interventions.Therefore, understanding genome-environment interactions in the context of aging can be a powerful approach to identify attractive targets for drug design.\t\n\nEven if sirtuins and resveratrol do not live up to their expectations, this research is pioneering in terms of genome-environment interactions and nutritional manipulations of aging.These studies also show the path from basic discovery on the biology of aging to potential antiaging and pharmacological interventions and can therefore be applied to other genes and pathways.The lessons learned from the pitfalls of SIRT1 and resveratrol research can also help others to translate basic research on the biology of aging to the clinic, such as avoiding the use of short-lived rodent strains (e.g., by using unhealthy diets), which may lead to findings that only apply to a subset of individuals.\t\n\nIt seems that organisms from yeast to mammals have evolved genetic programs to cope with periods of starvation that can also postpone aging and age-related diseases, but how can we take advantage of those mechanisms to improve human health?Because assaying the longevity effects of CR in humans is practically impossible, studying its molecular mechanisms in lower life forms could be beneficial to humans through the identification of candidate genes, pathways and molecular mechanisms.Although CR will not be suitable for everyone, targeting its mechanisms and developing CR mimetics may lead to drug development for a number of age-related and metabolic diseases.",
+      "\t\n\nMany factors contribute to aging, including genes.This is the first article in a 10-part series that highlight some of what is known about the influence of genes on aging and emerging treatment options that may slow down or potentially reverse the aging process.The series will address \\genes, adducts, and telomeres, decreased immune defenses, oxidation and inefficient mitochondria, toxins and radiation, glycosylation, caloric intake and sirtuin production, neurotransmitter imbalance, hormone mechanisms, reduced nitric oxide, and stem cell slowdown.Underpinning these factors are wear and tear on cells and aging as a result of inability to repair or replace these affected cells.These topics have been addressed in research, health magazines, and even by talk show hosts.There is even a LongevityMap website addressing significant and nonsignificant genetic association studies in aging across the human genome (http://genomics.senescence.info/longevity/).The series will address a scientific and clinical approach to genome-related aging topics.\tRelevance to nurse practitioner practice\n\nCurrently, there is no cure for genetic variants associated with rapid aging, but novel agents that may slow down the aging process are being tested.The authors of this article advocate individual participation in association studies of aging and pharmacologic risk mitigation or reversal of symptoms for those with known genetic disease risk.Direct to consumer epigenetic biological aging tests and telomere length tests are available; but they are not approved by the Food and Drug Administration.Health care providers may want to consider the simple but key clinical and personal changes, suggested above, to enhance DNA health, wellness, and longevity.Simple mindful changes in behavior, environmental exposure, food/supplement use, weight loss, and regular exercise can reduce adduct exposure damage and impact telomere length, potentially increasing longevity.A Mediterranean diet containing fruits and whole grains along with fiber, antioxidants, soy protein, and healthy fats (from avocados, fish, flax, and walnuts) is suggested to reduce DNA adducts and protect telomeres.In light of our current pandemic, focus on population health, and restrictions to health care access, especially in rural communities, health care providers could incorporate these lifestyle and dietary principles in telehealth visits with patients to reduce disease risk and optimize healthy aging.",
+      "\t\n\nTaking advantage of advances in genomics and bioinformatics, we have used the evidence available to argue for a new theory of aging.To test that theory, still more sophisticated experiments and analyses will be necessary, but we are sure that the talented and dedicated scientists of the future will rise to the challenge.Regardless of what they find, we are now seeing the dawn of a new age in aging research.Borrowing elements from both Szilard's and Orgel's models, somatic mutations increase at an accelerating rate with age, a feedback loop mediated partially by altered protein sequences but primarily by a dysregulation of gene expression.The redundancy of the organism, both cellular and genetic, may inhibit these consequences of somatic mutations from directly contributing to aging, but is itself subject to degradation by somatic mutations.This model may most accurately reflect human aging, predicting both a period of latency (reflecting the lack of an aging phenotype during development and early adulthood) and an accelerating decline afterwards (reflecting the slow-thenrapid deterioration that begins in middle age).",
+      "\t\n\nWith modern genomic technologies and largescale data analysis methods, it is possible to sift through the genes of populations to find the loci that act to postpone aging. [3]There are uncertainties with the comparison of populations with different rates of aging.However, it is superior to experimental designs that only consider age-dependence or dietary-response, without determining causal mechanisms.\tCONCLUSION: AGING DOES NOT HAVE TO BE UNSTOPPABLE\n\nThirty years ago, the genetic or biochemical postponement of aging was regarded as impossible in any organism.But the last few decades have seen aging become an easily ameliorated condition in model organisms, especially Drosophila.The toy electrical machines of Michael Faraday pointed to the future electrification of industry.The rockets of Robert Godard pointed toward space travel.Likewise, tiny Methuselahs show that aging can be substantially postponed.There is no biological necessity to any particular rate of aging, only the practical difficulty of changing that rate."
+    ],
+    [
+      "\tOxidative stress and mitochondrial DNA\n\nNot long after it was discovered that mitochondria have their own genetic apparatus, Harman proposed that mitochondria play a central role in the free radical theory of aging [16].This idea was developed further by Miquel et al. [330], and the notion that mtDNA mutagenesis played a role in aging took hold.The phenotypical importance of mutations in mtDNA was demonstrated by Wallace et al. [331] and Holt et al. [332], who first showed that Leber's hereditary optic neuropathy and mitochondrial myopathies were caused by mtDNA mutations (reviewed in [333]).Because mtDNA is so close to the site of mitochondrial ROS production, it is exposed to considerably higher oxidative stress, resulting in 3-fold higher levels of DNA oxidative damage (the previously quoted 20-fold figure is apparently due to an isolation artifact [334,335]).In the 1990s a series of papers reported that the frequency of mitochondrial DNA deletions increases dramatically with age, being essentially undetectable in young individuals and reaching levels as high as 2% of mtDNA in old individuals.This age-related increase in mtDNA deletions was found in organisms as diverse as worms, mice, and humans (reviewed in [24,336]).The same is also true with mtDNA point mutations [337,338].Certain mtDNA polymorphisms have been found in increased frequency in centenarians, implying a protective effect during aging [339][340][341].Similar protective effects of mtDNA polymorphisms have been reported for the age-related neurodegenerative condition, Parkinson's disease [342].",
+      "\t\n\ndoi: 10.1196/annals.1293.002cells and individuals.We previously identified a mitochondrial genotype, 5178C~A (ND2, Leu237Met), representing haplogroup D, to be associated with longevity in Japanese centenarians.Our proposal that certain mitochondrial polymorphisms are associated with longevity is further supported by observations that haplogroups J and U are overrepresented in European centenarians. 2Based on these findings, we have hypothesized that other haplogroups are associated with age-related neurodegeneration in Parkinson's disease or Alzheimer's disease.We also postulated that common metabolic disorders, such as obesity and type-2 diabetes mellitus, are attributable at least in part to mitochondrial polymorphisms.To examine these hypotheses, we have started comprehensive sequence analysis of the entire mitochondrial genome of centenarians, young obese or non-obese adults, patients with Parkinson's disease or Alzheimer's disease, and diabetic patients with or without angiopathy, using 96 individuals for each of these groups",
+      "\t\n\nBuilding on previous work in this system, the current study tests three primary hypotheses about how variation in mtDNA and mitochondrial function relate to variation in life-history traits and aging within this system (Fig. 1): (1) First, we test whether rates of cellular oxygen consumption in isolated immune cells exhibit patterns that are consistent with the hypothesis that cellular processes drive whole-organism senescence and aging, and if these patterns differ between the SA and FA ecotypes and between sexes.By measuring basal, ATP-production associated, and maximal rates of cellular oxygen consumption, we further test for evidence that phenotypic divergence is dependent on a specific aspect of oxidative phosphorylation within immune cells.The energetics of these cells are particularly important given their essential role in modulating disease and infection, important factors contributing to senescence (Metcalf et al., 2019).We predict that SA snakes will maintain levels of cellular oxygen consumption across age, whereas the FA snakes will show a decline with age, especially in ATP-associated rates, possibly due to continual degradation of electron transport chain functionality from accumulating oxidative damage and reduced DNA repair mechanisms (Robert and Bronikowski, 2010;Schwartz and Bronikowski, 2013). ( 2) Second, we expand our mitochondrial genomics dataset to quantify mtDNA genetic structure across the landscape and test whether mtDNA haplotypes, and alleles at a nonsynonymous SNP in the Cytochrome B (CytB) gene correlate with aging ecotypes. (3) Third, we test the hypothesis that variation in mtDNA correlates with whole-organism variation in metabolic rates, suggesting a pathway linking mitochondrial genetic variation in mtDNA to whole-organism energetics.We first test whether different haplotypes differ in resting metabolic rate.Then, we test the effects of the nonsynonymous SNP in CytB on resting metabolic rate.The CytB gene encodes a component of complex III of the ETC, and was previously found to segregate between these life-history ecotypes (Schwartz et al., 2015).This SNP results in an amino acid substitution from isoleucine (aliphatic, hydrophobic) to threonine (hydrophilic) on a region that comes into close contact with a nuclear-encoded subunit (Schwartz et al., 2015).We combine previously published and new data on whole-organism resting metabolic rates (oxygen consumption) to test for the effects of this nonsynonymous mutation in three populations where we find heterogeneity at this nucleotide, thus allowing us to disentangle the effects of shared environment (population) from sequence variation (SNP).We predict that this SNP will correlate with variation in whole-organism metabolic rate, demonstrating a putatively adaptive difference between the derived and ancestral sequence.By utilizing this integrative data setfrom genes to organelles to whole organisms to populationsin a known life-history context, we are able to test hypotheses across levels of organization to provide a more complete picture of the complicated story of mitochondria and life history (Havird et al., 2019).",
+      "\t\n\nEven with these levels of mtDNA protection, mtDNA mutation frequency increases with age in animal models and humans alike (Cortopassi and Arnheim 1990;Larsson 2010), although the role of mtDNA mutations remains unclear (Khrapko and Vijg 2009;Pohjoismaki et al. 2018;Theurey and Pizzo 2018).However, recent reports have shown that mtDNA point mutations in aged tissues largely arise from replication infidelity (i.e., DNA polymerase errors), rather than ROS-induced damage (Ameur et al. 2011;Kennedy et al. 2013;Vermulst et al. 2007).To test if replicative infidelity causes aging, mice with mutant mitochondrial DNA polymerase  that are deficient in proofreading during DNA replication, causing supraphysiological mutation loads (roughly 2500-fold in the homozygous polg mut/mut compared to 500-fold higher in the polg +/mut ), were examined (Vermulst et al. 2007).While the homozygous mice (polg mut/mut ) showed signs of accelerated aging phenotypes and significantly reduced lifespan, the heterozygous mice (polg +/mut ) had a normal lifespan albeit exhibiting premature aging phenotypes (Trifunovic et al. 2004).One plausible explanation for this discrepancy lies with increased mtDNA deletions in the homozygous mice (polg mut/mut ) (Vermulst et al. 2007(Vermulst et al. , 2008)).These cumulative results suggest that the connections between oxidative stress, mtDNA mutations, and aging are more complicated than originally appreciated and require further investigation to fully understand their relation (Pomatto and Davies 2018).It is evident, however, that the mtDNA mutations are linked to more than 300 diseases connected to aging, including Alzheimer's Disease, and that proper communication between the mitochondria and the nucleus plays a key role (DeBalsi et al. 2017;Grazina et al. 2006;Lane 2011;Onyango et al. 2006;Quirs et al. 2016;Swerdlow et al. 2017).",
+      "\t\n\nConclusions: Our population-based study indicates that both mtDNA quality and quantity are influenced by age.An open question for the future is whether interventions that would contribute to maintain optimal mtDNA copy number and prevent the expansion of heteroplasmy could promote healthy aging.\t\nBackground: The accumulation of mitochondrial DNA (mtDNA) mutations, and the reduction of mtDNA copy number, both disrupt mitochondrial energetics, and may contribute to aging and age-associated phenotypes.However, there are few genetic and epidemiological studies on the spectra of blood mtDNA heteroplasmies, and the distribution of mtDNA copy numbers in different age groups and their impact on age-related phenotypes.In this work, we used whole-genome sequencing data of isolated peripheral blood mononuclear cells (PBMCs) from the UK10K project to investigate in parallel mtDNA heteroplasmy and copy number in 1511 women, between 17 and 85 years old, recruited in the TwinsUK cohorts.Results: We report a high prevalence of pathogenic mtDNA heteroplasmies in this population.We also find an increase in mtDNA heteroplasmies with age ( = 0.011, P = 5.77e-6), and showed that, on average, individuals aged 70-years or older had 58.5% more mtDNA heteroplasmies than those under 40-years old.Conversely, mtDNA copy number decreased by an average of 0.4 copies per year ( = 0.395,P = 0.0097).Multiple regression analyses also showed that age had independent effects on mtDNA copy number decrease and heteroplasmy accumulation.Finally, mtDNA copy number was positively associated with serum bicarbonate level (P = 4.46e-5), and inversely correlated with white blood cell count (P = 0.0006).Moreover, the aggregated heteroplasmy load was associated with blood apolipoprotein B level (P = 1.33e-5), linking the accumulation of mtDNA mutations to age-related physiological markers.Conclusions: Our population-based study indicates that both mtDNA quality and quantity are influenced by age.An open question for the future is whether interventions that would contribute to maintain optimal mtDNA copy number and prevent the expansion of heteroplasmy could promote healthy aging.\t\n\nAging is commonly characterized as a time-dependent progressive loss of physiological integrity, leading to impaired function and increased vulnerability to death [14].One important factor in aging is the accumulation of DNA damage over time [15].mtDNA has been considered a major target of aging-associated mutation accumulation, possibly because it experiences higher oxidative damages, more turnover, and has lower replication fidelity compared to nuclear DNA (nDNA) [16][17][18].Mice carrying elevated mtDNA mutation burden present premature signs of aging including hair loss, kyphosis, and premature death (lifespan shortened by up to 50%) [19,20].In human studies, mtDNA heteroplasmy incidence increases with age [21][22][23], while lower mtDNA copy number has been reported in aged populations [12,24].Ding et al. reported an trend of increased heteroplasmies and decreased mtDNA copy number with age in their study population [25].However, previous studies were limited in one or more ways: i) limited power in detecting low-to-medium frequency heteroplasmies in blood due to low sequencing depth; ii) relatively small sample sizes, limiting statistical power; iii) small age range; iv) whole blood as the source of DNA, which contains several sources of contaminants for mtDNA analysis; and/or v) assessing either mtDNA mutation or copy number, but not both in the same biological samples.Thus, it is largely unknown whether the impacts of age on mtDNA mutation burden and on copy number are independent from each other.\t\n\nBackground: The accumulation of mitochondrial DNA (mtDNA) mutations, and the reduction of mtDNA copy number, both disrupt mitochondrial energetics, and may contribute to aging and age-associated phenotypes.However, there are few genetic and epidemiological studies on the spectra of blood mtDNA heteroplasmies, and the distribution of mtDNA copy numbers in different age groups and their impact on age-related phenotypes.In this work, we used whole-genome sequencing data of isolated peripheral blood mononuclear cells (PBMCs) from the UK10K project to investigate in parallel mtDNA heteroplasmy and copy number in 1511 women, between 17 and 85 years old, recruited in the TwinsUK cohorts.",
+      "\t\n\nHence, progressive age-dependent damage in mitochondrial genomes and functions is an important contributor to human aging.\t\n\nIn 1989, based on expanding molecular biology studies of diseases caused by mtDNA mutations, my colleagues and I (216) proposed the \"mitochondrial theory of aging\" that the somatic accumulation of mitochondrial mutations and the subsequent cytoplasmic segregation of these mutations during life is a major contributor to the gradual loss of cellular bioenergetic capacity within tissues and organs associated with general senescence and diseases of aging.The hypothesis encompasses the concept that a decline in bioenergetic capacity in tissues will contribute to age-associated diseases, such as those that affect the cardiac, vascular, and neuromuscular systems.\t\n\nAccumulated evidence to date exhorts to unify both ideas of the free radical theory of aging and mitochondrial theory of aging to be \"the redox mechanism of mitochondrial aging\" (281), that the mtDNA's oxidative damage results in cumulative increase in somatic mutations in mtDNA leading to bioenergetic deficit, cell death, and aging.The germline mutations in mtDNA as well as nDNA specific for the patients with mitochondrial diseases accelerate the oxidative damage and somatic mutations synergistically leading to their phenotypic expression as premature aging or death.",
+      "\t\n\nAging is a complex process as a time-dependent progressive loss of physiological integrity, leading to impaired function and increased vulnerability to death [74], and as we described above, aging is highly associated with mtDNA mutations; in fact heteroplasmy incidence increases with age, while lower mtDNA copy number has been reported in aged populations as well as mitochondria morphology, abundance, and oxidative phosphorylation activity [75,76].Interestingly, in aging the significant amount of these mutations converges in sites that encode structural subunits of the ETC such as complexes I and III [77], leading to OxPhos uncoupling and mitochondrial dysfunction in aged population.Since there are several limitations to study mitochondrial metabolism in human samples, in this section we briefly described the implications of mitochondrial metabolism for aging in the most studied and high energy demand human tissues, such as skeletal muscle, heart, and brain.",
+      "\tINTRODUCTION\n\nAbout 10 years ago it was proposed that aging is caused by life-long accumulation of somatic mitochondrial DNA (mtDNA) mutations (1), which compromises cellular energy metabolism and/or increases intracellular oxidative stress (2).Ultimately, this could result in the development of the multiple degenerative changes in tissues that become manifest in old age.It has been shown that mtDNA deletions and, with less certainty, mtDNA point mutations, increase with advancing age (recently reviewed in 3,4).These data are consistent with the mitochondrial theory of aging but do not exclude the possibility that accumulation of mtDNA mutations accompanies, but does not cause aging.",
+      "\t\nAging is an intricate phenomenon characterized by progressive decline in physiological functions and increase in mortality that is often accompanied by many pathological diseases.Although aging is almost universally conserved among all organisms, the underlying molecular mechanisms of aging remain largely elusive.Many theories of aging have been proposed, including the freeradical and mitochondrial theories of aging.Both theories speculate that cumulative damage to mitochondria and mitochondrial DNA (mtDNA) caused by reactive oxygen species (ROS) is one of the causes of aging.Oxidative damage affects replication and transcription of mtDNA and results in a decline in mitochondrial function which in turn leads to enhanced ROS production and further damage to mtDNA.In this paper, we will present the current understanding of the interplay between ROS and mitochondria and will discuss their potential impact on aging and age-related diseases.\t\n\nAging is an intricate phenomenon characterized by progressive decline in physiological functions and increase in mortality that is often accompanied by many pathological diseases.Although aging is almost universally conserved among all organisms, the underlying molecular mechanisms of aging remain largely elusive.Many theories of aging have been proposed, including the freeradical and mitochondrial theories of aging.Both theories speculate that cumulative damage to mitochondria and mitochondrial DNA (mtDNA) caused by reactive oxygen species (ROS) is one of the causes of aging.Oxidative damage affects replication and transcription of mtDNA and results in a decline in mitochondrial function which in turn leads to enhanced ROS production and further damage to mtDNA.In this paper, we will present the current understanding of the interplay between ROS and mitochondria and will discuss their potential impact on aging and age-related diseases.",
+      "\t\n\nMitochondrial genomes harboring large deletions are known to accumulate both in patients with heteroplasmic mtDNA mutations and in normal individuals during aging, particularly in postmitotic tissues such as muscle and brain (3).These observations support the mitochondrial theory of aging, which states that the slow accumulation of impaired mitochondria is the driving force of the aging process.This idea is attractive because it can be reconciled with the free radical theory of aging, which argues that oxidative damage plays a key role in senescence.Among the numerous mechanisms known to generate oxidants, leakage of superoxide anion and hydrogen peroxide from the mitochondrial electron transport chain are the chief candidates.Increased damage to mtDNA could exacerbate this leakage of reactive oxygen species (ROS) (4).",
+      "\t\n\nMitochondrial DNA (mtDNA) rearrangements have been shown to accumulate with age in the post-mitotic tissues of a variety of animals and have been hypothesized to result in the age-related decline of mitochondrial bioenergetics leading to tissue and organ failure.Caloric restriction in rodents has been shown to extend life span supporting an association between bioenergetics and senescence.In the present study, we use full length mtDNA amplification by long-extension polymerase chain reaction (LX-PCR) to demonstrate that mice accumulate a wide variety of mtDNA rearrangements with age in post mitotic tissues.Similarly, using an alternative PCR strategy, we have found that 2-4 kb minicircles containing the origin of heavy-strand replication accumulate with age in heart but not brain.Analysis of mtDNA structure and conformation by Southern blots of unrestricted DNA resolved by field inversion gel electrophoresis have revealed that the brain mtDNAs of young animals contain the traditional linear, nicked, and supercoiled mtDNAs while old animals accumulate substantial levels of a slower migrating species we designate age-specific mtDNAs.In old caloric restricted animals, a wide variety of rearranged mtDNAs can be detected by LX-PCR in post mitotic tissues, but Southern blots of unrestricted DNA reveals a marked reduction in the levels of the agespecific mtDNA species.These observations confirm that mtDNA mutations accumulate with age in mice and suggest that caloric restriction impedes this progress.\t\n\nIt has often been hypothesized that quantitation of a single mtDNA deletion from old tissue represents 'the tip of the iceberg', and that the cumulative mitochondrial somatic mutational load is large in senescent organisms (1).By observing an array of mitochondrial sequence rearrangements with age, our data lend strong experimental support to this hypothesis.Further, the observation that there are substantial mtDNA conformational variants with age, and that the regimen of CR can modulate the level of the conformational variant in the brain, may indicate that mtDNA from the brain is more sensitive to oxidative damage as a result of ROS production.The current results in mouse are consistent with our previous studies in aging humans, in skeletal muscle (10), heart (15), and brain (5).The association of somatic mtDNA changes with age regardless of organismal maximum or mean lifespan, and modulation of some of these changes via CR, are consistent with the hypothesis that mtDNA changes with age may play a role in the senescence of multicellular organisms.\t\n\nAs a further step toward determining if mtDNA rearrangements play a significant role in senescence, it would be important to demonstrate that the accumulation of mtDNA rearrangements is retarded when mortality rate is reduced through genetic, or environmental modifications which extend lifespan.One of the few experimental aging models in which lifespan can be genetically extended is the age-1 mutant of Caenorhabditis elegans.In this mutant, mtDNA rearrangements have been observed to accumulate at a slower rate than in wild-type animals (9).In mammals, the only reproducible treatment to date which extends lifespan is that of CR (32).When the total number of calories consumed by the animal is reduced over the lifespan relative to AL fed animals, the mean and maximum lifespan can be extended by up to 50% (33).The mechanism by which CR extends lifespan is unknown, but CR is associated with a decrease in total body fat, increased fitness, and decreased pathology.\t\nMitochondrial DNA (mtDNA) rearrangements have been shown to accumulate with age in the post-mitotic tissues of a variety of animals and have been hypothesized to result in the age-related decline of mitochondrial bioenergetics leading to tissue and organ failure.Caloric restriction in rodents has been shown to extend life span supporting an association between bioenergetics and senescence.In the present study, we use full length mtDNA amplification by long-extension polymerase chain reaction (LX-PCR) to demonstrate that mice accumulate a wide variety of mtDNA rearrangements with age in post mitotic tissues.Similarly, using an alternative PCR strategy, we have found that 2-4 kb minicircles containing the origin of heavy-strand replication accumulate with age in heart but not brain.Analysis of mtDNA structure and conformation by Southern blots of unrestricted DNA resolved by field inversion gel electrophoresis have revealed that the brain mtDNAs of young animals contain the traditional linear, nicked, and supercoiled mtDNAs while old animals accumulate substantial levels of a slower migrating species we designate age-specific mtDNAs.In old caloric restricted animals, a wide variety of rearranged mtDNAs can be detected by LX-PCR in post mitotic tissues, but Southern blots of unrestricted DNA reveals a marked reduction in the levels of the agespecific mtDNA species.These observations confirm that mtDNA mutations accumulate with age in mice and suggest that caloric restriction impedes this progress."
+    ],
+    [
+      "\t\n\nStudies of genes and molecular processes that are associated with segmental progeroid disorders, such as Hutchinson-Gilford progeria syndrome (HGPS, progeria, OMIM#176670), could be of importance when studying the genetic mechanisms of aging (Martin, 2005;Baker et al., 1981).For example, most cases of HGPS are caused by a de novo point mutation in the LMNA gene (LMNA c.1824C>T; p.G608G).This mutation activates a cryptic splice site that results in aberrant splicing of the lamin A transcript (Eriksson et al., 2003).Interestingly, it has been shown that the products of this aberrant splicing, the truncated transcript and resultant protein (named progerin), increase in number with aging in HGPS (Goldman et al., 2004;Cao et al., 2007;Rodriguez et al., 2009).In addition, several reports have found progerin, and increasing levels of progerin, in normal cells over the course of normal aging (Scaffidi & Misteli, 2006;McClintock et al., 2007;Cao et al., 2007;Rodriguez et al., 2009), which suggests a similar genetic mechanism in HGPS and normal aging.Moreover, genome-scale expression profiling in cells from HGPS patients, as well as in physiological aging, has revealed widespread transcriptional misregulation in multiple mammalian tissues (Ly et al., 2000;Csoka et al., 2004;Zahn et al., 2007;Scaffidi & Misteli, 2008;Cao et al., 2011;McCord et al., 2013).",
+      "\tDNA Repair and Accelerated Aging Syndromes\n\nThe association of human syndromes of accelerated aging with inherited mutations in DNA repair genes strongly implicates DNA damage in the human aging process.These disorders, known as segmental progeroid syndromes, are characterized by accelerated onset of a subset of human aging phenotypes that frequently include neurodegeneration (50).Mutations in genes involved in singleor double-strand DNA break repair result in cerebellar degenerative syndromes known as ataxias, which are manifested by movement disorders.The continued proliferation of cerebellar granule cells during postnatal development may underlie the vulnerability of the cerebellum to inherited deficits in genome stability.In contrast, inherited mutations in DNA helicases, such as Werner and Rothmund-Thomson syndromes, give rise to features of accelerated aging that often do not include nervous system dysfunction.This may reflect the role of RecQ-like helicases in recombinant events in replicating cells.Inherited mutations in enzymes involved in nucleotide and base excision repair, including xeroderma pigmentosum and Cockayne syndrome, are characterized by accelerated aging phenotypes that include neurodegeneration, mental retardation, and delayed psychomotor development (50).A new human progeroid syndrome that is caused by a loss of function mutation in the XPF-ERCC1 endonuclease that repairs helix-distorting DNA lesions was recently described.Mice deficient in ERCC1 recapitulate the progeroid features and exhibit a gene expression profile in the liver that overlaps with that of normal aging mice (correlation coefficient 0.32), suggesting that this type of DNA damage may contribute to the aging process (51).Segmental progerias typically have a short life span of less than 20 years, which may account for the absence of Alzheimer-type neuropathological Double-strand break (DSB): a severe form of DNA damage involving scission of both DNA strands, usually induced by ionizing radiation or ROS NHEJ: nonhomologous end joining changes.However, individuals with Werner syndrome, a longer-lived progeroid syndrome, can have variable neuropathology, with one 57-year-old case reportedly showing unusually high levels of amyloid -protein deposition in the brain (52).",
+      "\t\n\nHutchinson-Gilford progeria syndrome (HGPS) and Werner syndrome are rare human genetic disorders characterized by premature aging phenotypes with a shortened life span.This group of diseases resembles physiological aging to a certain extent, serving as excellent models to gain insight into the biology of aging in humans (24,25).These diseases are due to either a mutation in genes encoding the DNA repair machinery or the A-type lamin, leading to disorganized chromatin structures.The causative mutations behind these progeria syndromes indicate that genomic instability and chromatin deterioration are causes of human aging.Furthermore, the knowledge we gain from understanding the molecular pathology of these human premature aging diseases provides us with useful information to understand the complex aging process.Individuals with HGPS do not recapitulate all aging phenotypes because they usually show segmental progeria affecting multiple tissues.By recapitulating some molecular and cellular changes that are characteristics of the natural aging process, these models provide us with a unique opportunity to understand the aging process in a human model (24,25).",
+      "\t\n\nResearchers in recent studies have focused on gene mutations accompanying known progeroid syndromes, such as Hutchinson-Gilford progeria, Werner syndrome, Rothmund-Thomson syndrome, Cockayne syndrome, ataxia telangiectasia, and Down syndrome. 143The most common skin disorders of these syndromes, which are characterized by an acceleration of the aging phenotype, are alopecia, skin atrophy and sclerosis, telangiectasia, poikiloderma, thinning and graying of hair, and several malignancies.Most of these syndromes are inherited in an autosomal recessive way and mostly display defects in DNA replication, recombination, repair, and transcription.Expression gene patterns of skin cells derived from old and young donors with Werner syndrome, 144 show that 91% of the analyzed genes have similar expression changes in Werner syndrome and in normal aging, implying transcription alterations common to Werner syndrome and normal aging represent general events in the aging process.",
+      "\tDNA Repair-Related Progeroid Syndromes\n\nAs mentioned previously, premature aging syndromes are often caused by mutations in genes whose function is to preserve genomic integrity.In this respect, the RecQ family of DNA helicases has been found to function in DNA damage repair, including base excision repair and in DNA double-strand break (DBS) repair, as well as in DNA replication subjected to a normal or stressed state [36].Mutations in three RecQ genes (WRN, BLM, and RECQL4) give rise to the Werner syndrome (WS), Bloom syndrome (BS), and Rothmund-Thomson syndrome (RTS), respectively [37].Additional genetic defects in the DNA damage repair system also cause the following disorders: Cockayne syndrome (CS), xeroderma pigmentosum (XP), and trichothiodystrophy (TTD).\t\n\nAn alternative strategy to the investigation of aging using the humans themselves is the study of progeroid syndromes, a group of very rare genetic disorders characterized by accelerated aging and the presence of clinical features that resemble physiological aging, including osteoarthritis and osteoporosis, loss of muscle mass, hair loss, short stature, skin tightness, and cardiovascular diseases [4].In addition to the genuine medical interest in improving the quality of life of these patients, the study of progeroid syndromes has attracted great interest in the past 10 years, in that they constitute an invaluable source of information for understanding the molecular basis of human aging.\tConclusions\n\nRecent advances in the study of progeroid syndromes, especially HGPS, have provided novel insights into our understanding of the aging process in humans.The main progeroid syndromes revised in this chapter are caused by mutations in genes encoding for DNA repair enzymes or the nuclear lamina protein lamin A, which reinforces the notion that genome instability is a critical determinant of aging.The study models that recapitulate progeroid syndromes have dramatically stimulated aging research; while cellular models have allowed the dissection of basic cellular and molecular processes linked to aging, mice models have facilitated screening of therapeutic drugs.It is expected that upcoming technologies and the design of novel optimized animal models will help to accomplish a translational medicine approach in aging research, with HGPS being the ideal model for such a goal.",
+      "\tProgeroid syndromes\n\nPatients suffering from progeroid syndromes, or accelerated aging phenotypes, display an array of physical and biological features that vary widely between tissues and diseases and among individuals.Some of the main characteristics for the specific disorders of interest to this review are cited below (for further review of molecules involved and clinical presentation, see Ref. 96).A general dilemma in studies on the role of telomeres in progeroid syndromes (and aging) is that telomere involvement could be direct as well as indirect.For example, the increased cell death resulting from defective DNA repair could result in telomere shortening via increased compensatory (stem) cell turnover or via direct effects on (repair of) telomeric DNA.For many segmental aging disorders, it has proven to be very difficult to distinguish between direct and indirect effects on telomere length.Perhaps phenotypically the most striking segmental aging genetic disorder in humans, Hutchinson-Gilford Progeria syndrome (HGPS), is caused by point mutations in lamin A, a key component of nuclear scaffolding (34,72).Lamin A deficiency results in absence of hair, craniofacial deformities (\"pinched\" facial features), emaciated and wrinkled appearance, as well as cardiovascular defects that eventually lead to stroke or heart attack at a very young age.The disease is characterized by specific defects in FIG. 8. Defects in human telomerase.The human telomerase complex is minimally composed of two proteins, telomerase reverse transcriptase (hTERT, green) and dyskerin (or DKC1, blue), that both bind specifically to a folded RNA molecule (or hTERC, black) containing a telomere repeat anchoring sequence and a template (red box).Known mutations in each component have now been linked to autosomal dominant dyskeratosis congenita (AD DC), bone marrow failure (BMF), and idiopathic pulmonary fibrosis (IPF) (6,63,127,134,151,217,231,234).The telomerase complex is thought to dimerize, bind to the single-strand G-rich telomere end, and catalyze the addition of new repeats (see also Figs. 3 and 4).The complex translocates along (newly added) telomere tracts for further elongation.Mutations affecting telomerase function lead to failure to assemble a functional complex.In the majority of cases, the level of telomerase activity is reduced by 50%.Such a reduction in telomerase activity compromises telomere length maintenance and increases apoptosis and senescence in proliferating cells (see Fig. 4).nuclear shape (183).Because expression of (defective) lamin A is limited to certain cell types, some cells and tissues are more affected than others.While there is evidence that DNA damage responses in cells expressing mutant lamin A are abnormal (133), the role of telomeres in this disorders (if any) remains to be clarified.A number of other segmental aging disorders have been more directly linked to telomere (dys)function.Among these, Fanconi anemia (FA) and ataxia telangiectasia (AT) are generally autosomal recessive diseases caused by mutations in, respectively, Fanconi genes (encoding any of 12 Fanconi anemia complementation group proteins) and the ataxia telangiectasia mutated gene (encoding the ATM protein).These proteins are implicated in DNA damage and repair pathways; in addition, ATM is known to phosphorylate FANCD2 (for reviews, see Refs.64,118,190).Both diseases are associated with accelerated telomere shortening (29,121,123,146), and abnormalities in telomere replication or repair are thought to play a role in the pathogenesis, particularly in the progression of the disease to immunodeficiency and bone marrow failure, as well as in the increased predisposition to malignancy in young adults.Other syndromes related to the Fanconi DNA damage response pathway include Nijmegen breakage syndrome (NBS) and Seckel syndrome.Other \"progeroid\" genes that have been implicated in DNA replication and repair are the family of genes encoding the RecQ DNA helicases.One of the functions of these enzymes is to assist in the resolution and repair of broken or stalled replication forks.Telomeric DNA is known to readily form higher order DNA structures such as G quadruplex structures in vitro (159), and it seems plausible, based on work in C. elegans (42), that specialized helicases are required to resolve structures of G-rich DNA arising sporadically during lagging strand DNA synthesis (62).Helicases that could be involved include RecQ protein-like 2 (RecQL2), RecQL3, and RecQL4 with known mutations that give rise to Werner (WRN), Bloom (BLM), and Rothmund Thompson syndromes, respectively.Accelerated telomere shortening is observed in Werner's syndrome (51), and pathology in animal model systems is accentuated in the context of telomerase deficiency (40,156).",
+      "\t\n\nThe relationship between DNA damage accumulation and aging has gained maximum credibility through studies conducted on various human progeria syndromes, which are genetic disorders where patients precociously develop features resembling natural aging.Most of the reported progeria syndromes, including Werner syndrome (WS), Bloom's syndrome (BS), Rothmund-Thomson syndrome (RTS), Cockayne syndrome type A and type B (CSA and CSB), Xeroderma pigmentosum (XP), Trichothiodystrophy (TTD) and Hutchinson-Gilford progeria syndrome (HGPS) are caused by mutations of genes that are directly or indirectly involved in DNA repair.Of these, WS, BS and RTS are associated with defects in RecQ helicases, i.e.RECQL2 (WRN), RECQL3 (BLM) and RECQL4 respectively, whereas CS, XP and TTD shared similar defects in NER pathway.RecQ helicases are a group of highly conserved proteins from bacteria to humans.The roles of RecQ helicases in DNA metabolism, including DNA replication, transcription, repair and recombination, have been extensively investigated and are demonstrated to be the underlying pathological basis of WS, BS and RTS [139][140][141][142].Most recently, delayed DNA damage checkpoint response and defective DNA repair were found to contribute to the progeria phenotypes in HGPS as well [143].",
+      "\t\n\nThey arise from mutations in one or several genes involved in DNA metabolism or in its regulation.Accelerated aging also may result from partial genome imbalances as seen in the chromosomal disorders of Down, Klinefelter and Turner syndromes.\t\n\nThese defects result in part from accumulated damage to DNA.Such damage may result inability to maintain replicative fidelity of the genome [2][3][4].Thus, organisms with mutations to genes directly involved in basic genome structure, maintenance and replicative fidelity would understandably have an accelerated aging phenotype and/or shortened life spans.Individuals with a progeroid syndrome have a premature aging phenotype and, depending on the specific mutations involved, the effects on lifespan may range from moderate to severe.Examples include Werner syndrome (WS), Bloom syndrome (BLM), Cockayne syndrome (CS), ataxia-telangiectasia (AT), Hutchinson-Gilford progeria syndrome (HGPS), and restrictive dermopathy (RD).",
+      "\t\n\nThe identification of these diseases spurred the creation of numerous animal models, and the characterization of engineered laboratory mutants led to the identification of many new human diseases of systemic and segmental accelerated aging.The animal models are useful for discovering how, when, and where (in what tissues) DNA damage contributes to aging, an area in which much work is still needed.The models, because of their accelerated aging, are useful for rapid hypothesis and drug testing.The models for the large part faithfully recapitulate the human genetic diseases; however, it is notable that mice tend to display a milder phenotype than humans.This might arise from the environmental contribution to human disease, which is not well reproduced in experimental model systems.Collectively, however, these human diseases and their conservation in multiple animal model systems strongly support the role of DNA damage as a proximal contributor to aging.",
+      "\t\n\nThe number of identified genes associated with progeroid syndromes has increased in recent years, possibly shedding light as well on mechanisms underlying ageing in general.\t\n\nSeveral heritable premature aging syndromes have for a long time been linked to defects in genome maintenance, due to altered DNA repair mechanisms.These mainly include the following autosomal recessive syndromes: (i) Werner syndrome, due to mutations in RecQL2 DNA helicase; (ii) Cockayne syndrome (CS) type A and B, due to mutations in the genes encoding the group 8 or 6 excision-repair cross-complementing proteins (ERCC8 and ERCC6), respectively; (iii) Rothmund-Thomson syndrome (RTS), due to RecQL4 mutations; (iv) trichothiodystrophy (TTD), due to mutations in the genes ERCC2/XPD and ERCC3/XPB, encoding the two helicase subunits of the transcription/repair factor TFIIH, as well as in TFB5, encoding the tenth subunit of TFIIH (Giglia-Mari et al., 2004); (v) ataxia-telangiectasia, due to mutations in the ataxia-telangiectasia mutated gene (ATM); (vi) xeroderma pigmentosum (XP), a genetically heterogeneous autosomal recessive disorder in which can be distinguished at least seven complementation groups, due to mutations of different DNA excisionrepair proteins (Hasty et al., 2003;Kipling et al., 2004).All these progeroid diseases, involving heritable defects in DNA repair, suggest a central role of genome integrity maintenance in the aging process.\tConclusion\n\nFrom a pathophysiological point of view, the known Progeroid syndromes are caused either by mutations in genes encoding DNA repair proteins, such as in WS, Bloom syndrome (BS), Rothmund-Thomson syndrome, Cockayne syndrome, xeroderma pigmentosum or trichothiodystrophy (Hasty et al., 2003;Wood et al., 2005), or by mutations in genes encoding Lamins A/C or partners involved in their biological pathway, such as HGPS or RD (De Sandre-Giovannoli et al., 2003;Eriksson et al., 2003;Navarro et al., 2004Navarro et al., , 2005)).\t\nProgeroid syndromes are heritable human disorders displaying features that recall premature ageing.In these syndromes, premature aging is defined as ''segmental'' since only some of its features are accelerated.A number of cellular biological pathways have been linked to aging, including regulation of the insulin/growth hormone axis, pathways involving ROS metabolism, caloric restriction, and DNA repair.Different animal models, ranging from yeast, to nematodes, to mice, have been instrumental in obtaining evidence for these connections (Hasty et al., 2003).Several heritable premature aging syndromes have for a long time been linked to defects in genome maintenance, due to altered DNA repair mechanisms.These mainly include the following autosomal recessive syndromes: (i) Werner syndrome, due to mutations in RecQL2 DNA helicase; (ii) Cockayne syndrome (CS) type A and B, due to mutations in the genes encoding the group 8 or 6 excision-repair cross-complementing proteins (ERCC8 and ERCC6), respectively; (iii) Rothmund-Thomson syndrome (RTS), due to RecQL4 mutations; (iv) trichothiodystrophy (TTD), due to mutations in the genes ERCC2/XPD and ERCC3/XPB, encoding the two helicase subunits of the transcription/repair factor TFIIH, as well as in TFB5, encoding the tenth subunit of TFIIH (Giglia-Mari et al., 2004); (v) ataxia-telangiectasia, due to mutations in the ataxia-telangiectasia mutated gene (ATM); (vi) xeroderma pigmentosum (XP), a genetically heterogeneous autosomal recessive disorder in which can be distinguished at least seven complementation groups, due to mutations of different DNA excisionrepair proteins (Hasty et al., 2003;Kipling et al., 2004).All these progeroid diseases, involving heritable defects in DNA repair, suggest a central role of genome integrity maintenance in the aging process.The number of identified genes associated with progeroid syndromes has increased in recent years, possibly shedding light as well on mechanisms underlying ageing in general.Among these, premature aging syndromes related to alterations of the LMNA gene have recently been identified.LMNA encodes Lamins A/C, ubiquitous nuclear proteins belonging to the intermediate filament superfamily.These premature aging disorders have thus been classified as ''Laminopathies'', the large group of diseases associated to Lamin A/C defects.This group of heterogeneous disorders includes three main subgroups: (1) neuromuscular disorders (Emery-Dreifuss muscular dystrophy, limb-girdle",
+      "\t\n\nHowever, only those genetic disorders that exhibit premature aging, neurodegeneration (mental defects), and some form of chromosomal/DNA damage all together will be empha-sized here.Perhaps the most appropriate disorder under this category is Down's syndrome.It has several features of premature aging and the genetic defect is trisomy of the distal part of the long arm of chromosome 21.The critical segment of chromosome 21 is shown to have three genes coding for copper-and zinc-dependent superoxide dismutase, oncogene ets-2, and cystathione ~-synthase (Delabar et al., 1987).Since elevated levels of superoxide dismutase are found in various tissues of these individuals, it is postulated that the accelerated aging of these patients may be caused by overproduction of superoxide dismutase, which is responsible for the production of H20 2 while scavenging the oxygen-free radicals.The brains of Down's syndrome individuals are particularly vulnerable to oxidative DNA damage because the high levels of superoxide dismutase found in this tissue are not accompanied by an elevation in the glutathione peroxidase and catalase (Balazs and Brookshank, 1985) that would have normally helped in removing the overproduced H202.Other genetic syndromes characterized by signs of nervous debility, premature aging, and DNA damage/ decreased DNA-repair capacity, are Ataxia Telangiectasia (AT) and Cockayne syndrome (CS).",
+      "\tRare genetic disorders of aging\n\nProgeria, also known as Hutchinson-Gilford progeria syndrome, affects one in four million births worldwide with equal distribution between sex and race, causing a child's body to age more rapidly (Genetics Home Reference, 2019a).Symptoms typically occur within the first year of life, and most children do not live past 13 years.Mutation in the LMNA gene (not an adduct or telomere factor) contributes to abnormal lamin A protein, called progerin, causing cell instability and cells to easily breakdown (Genetics Home Reference, 2019a).There is no current cure for progeria but farnesyltransferase inhibitors, a cancer drug, has shown promise in reversing cell damage (Genetics Home Reference, 2019a).Other supportive treatments include cardiovascular diseaserelated issues, growth hormones, and bone/joint health.Adalia Rose has taken to social media, with multiple YouTube and Facebook postings, to help others understand her case of progeria.",
+      "\t\n\nMitochondrial DNA (mtDNA) mutations are thought to have a causal role in many age-related pathologies.Here we identify mtDNA deletions as a driving force behind the premature aging phenotype of mitochondrial mutator mice, and provide evidence for a homology-directed DNA repair mechanism in mitochondria that is directly linked to the formation of mtDNA deletions.In addition, our results demonstrate that the rate at which mtDNA mutations reach phenotypic expression differs markedly among tissues, which may be an important factor in determining the tolerance of a tissue to random mitochondrial mutagenesis.",
+      "\tINTRODUCTION\n\nIn genetics, identification of genotype-phenotype relationships relies on generated or selected mutants, which highlight underlying mechanisms.For the biology of aging, mutants that display delayed or accelerated aging have been invaluable.Rare heritable syndromes have been identified in the human population that exhibit multiple features of premature aging.A search in the Online Mendelian Inheritance in Man database (OMIM version February 25, 2015) using the keywords \"premature aging,\" \"progeria,\" or \"progeroid\" yielded 20 syndromes with at least one known mutated gene.Certainly this list is far from complete; for example, ataxia telangiectasia, fanconi anemia, and maternally transmitted mitochondrial syndromes such as maternally inherited diabetes and deafness and mitochondrial encephalomyopathy (MIDD/MELAS) are missing.Additionally, many more conditions await identification as unrecognized progeroid syndrome.The application of powerful exome and whole genome sequencing technologies will dramatically accelerate molecular resolution of genetic defects in rare patients with features of accelerated aging, and through this process, many new genes underlying these conditions will be identified.However, when we assign a primary function to each of the causally mutated genes in the known syndromes, it appears that the majority is linked to perturbed genome integrity, a second class represents metabolism, and one syndrome appears connected with cell adhesion (Figure 1).Recently, evidence has emerged for bidirectional interactions between the main aging-related processes: For instance, most DNA damage is derived from endogenous metabolic sources, and compromised genome function indirectly affects many cellular processes including metabolism (1, 2).This suggests the existence of a tightly interwoven network that underlies aging, which is the focus of this review.Progeria-associated syndromes classified by primary function of the causal genetic defect.These 20 human syndromes, listed outside of the circle, were selected from the OMIM database using the keywords \"premature aging,\" \"progeria,\" and \"progeroid. \"Related primary functions were combined in the categories genome integrity, metabolism, and adhesion (inner circle).Abbreviations: DSB, DNA double-strand break; MDPL, mandibular hypoplasia, deafness, progeroid features, and lipodystrophy; PI3K, phosphoinositide-3-kinase; PS, phosphatidylserine; XFE, XpF-Ercc1.GAPO indicates growth retardation, alopecia, pseudoanodontia, and optic atrophy.SHORT indicates short stature, hyperextensibility, hernia, ocular depression, Rieger anomaly, and teething delay."
+    ]
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_3.json
new file mode 100644
index 0000000..7c66ed3
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_3.json
@@ -0,0 +1,122 @@
+{
+  "question": [
+    "What recent discoveries have been made about the genetics of aging?",
+    "How do epigenetic changes affect aging?",
+    "What is the role of the gene FOXO3 in longevity?",
+    "How does the environment interact with genes to influence aging?",
+    "What are senescent cells and how do they contribute to aging?"
+  ],
+  "answer": [
+    "Recent discoveries in the genetics of aging include the identification of numerous genes that can alter the aging process in animal models and humans. Genetic research has also found that immune-related pathways might be critically involved in aging. Specific genes, such as the apoE polymorphisms, have been found to influence both cardiovascular disease and Alzheimer's disease. Additionally, whole-genome sequencing in centenarians has revealed genetic variants associated with longevity. Studies have also shown that aging can be influenced by the interactions of multiple genes with each other and the environment.",
+    "Epigenetic changes significantly influence the aging process. These changes occur at various levels, including alterations in DNA methylation, histone modifications, and noncoding RNA expression. They can lead to altered gene expression, reactivation of transposable elements, and genomic instability. These changes can also influence lifespan, with diet and environmental factors potentially altering epigenetic information. Importantly, these changes can be partially or fully reversible, suggesting potential avenues for therapeutic intervention in aging and age-associated diseases.",
+    "FOXO3, a transcription factor, is associated with lifespan extension in various species, including humans. It is regulated by the insulin/IGF signaling pathway, the nutrient sensor AMPK, and stress. This gene controls the expression of genes involved in stress response, metabolism, immunity, and neuronal function. The FOXO3 variant has been associated with extreme longevity in humans, particularly in centenarians. It's also involved in the response to DNA damage and apoptosis. However, the exact molecular mechanisms affecting longevity require further study.",
+    "The environment interacts with genes to influence aging through various factors such as diet, lifestyle, and exposure to certain elements. Environmental factors can trigger signaling pathways and modulate gene expression, which in turn can affect the aging process. For instance, diet can influence aging trajectories in humans, with early nutrition affecting late-life diseases. Environmental factors like caloric restriction and smoking can also impact the rate of aging. Furthermore, environmental exposure to elements like airborne particulates, smoking, and alcohol consumption can contribute to age-related diseases. Understanding these genome-environment interactions can help in the development of anti-aging therapies and interventions.",
+    "Senescent cells are cells that have permanently stopped dividing but remain metabolically active. They are a hallmark of aging and accumulate in tissues over time. Senescent cells contribute to aging and age-related diseases through several mechanisms. They secrete pro-inflammatory factors and proteases that can alter the local tissue environment, promoting chronic inflammation and inducing senescence in healthy cells. This can lead to tissue dysfunction, chronic disease, and a decrease in the regenerative potential of stem cells. Additionally, senescent cells are resistant to apoptosis, leading to their accumulation and disruption of the tissue microenvironment."
+  ],
+  "contexts": [
+    [
+      "\t\n\nRecent developments on the genetics of aging can be seen as several streams of effort.In general, humans show a relatively modest (<50%) heritability of life spans (results obtained from twin studies discussed below).The apoE polymorphisms are remarkable for their influence on both cardiovascular disease and Alzheimer disease.In contrast, rare mutant genes with high penetrance cause these same diseases but with early onset and a major shortening of the life span.Shortlived laboratory models (fruit flies, nematodes, mice) are yielding rapid advances, with the discovery of mutants that increase life spans in association with altered metabolism, which leads to questions on the physiological organization of aging processes.Although these early findings do not show that a conserved genetic program actually controls aging processes across animal phylogeny, it is striking how frequently findings of metabolic rate, insulin signaling, and free radicals have emerged from very different approaches to aging in nematodes and mammals, for example.These findings hint that the genetic control of life span was already developed in the common ancestor of modern animals so that subsequent evolution of life spans was mediated by quantitative changes in the control of metabolism through insulin and the production of free radicals.",
+      "\t\n\nBackground: Genetic research on longevity has provided important insights into the mechanism of aging and aging-related diseases.Pinpointing import genetic variants associated with aging could provide insights for aging research.\t\nBackground: Genetic research on longevity has provided important insights into the mechanism of aging and aging-related diseases.Pinpointing import genetic variants associated with aging could provide insights for aging research.Methods: We performed a whole-genome sequencing in 19 centenarians to establish the genetic basis of human longevity.Results: Using SKAT analysis, we found 41 significantly correlated genes in centenarians as compared to control genomes.Pathway enrichment analysis of these genes showed that immune-related pathways were enriched, suggesting that immune pathways might be critically involved in aging.HLA typing was next performed based on the whole-genome sequencing data obtained.We discovered that several HLA subtypes were significantly overrepresented.Conclusions: Our study indicated a new mechanism of longevity, suggesting potential genetic variants for further study.\tIntroduction\n\nWith the development of human genomics research, a large number of studies of the genetics of longevity have been conducted.Scientists from various countries have proposed many different theories concerning the mechanisms of aging from different perspectives, involving oxidative stress, energy metabolism, signal transduction pathways, immune response, etc. [1,2].These mechanisms interact with each other and are influenced by heredity to some degree [2,3].The identification of longevity-related biological markers is critical to an indepth understanding of the mechanisms of carrier protection against common disease and/or of the retardation of the process of aging.",
+      "\t\nAging is a complex process affecting different species and individuals in different ways.Comparing genetic variation across species with their aging phenotypes will help understanding the molecular basis of aging and longevity.Although most studies on aging have so far focused on short-lived model organisms, recent comparisons of genomic, transcriptomic, and metabolomic data across lineages with different lifespans are unveiling molecular signatures associated with longevity.Here, we examine the relationship between genomic variation and maximum lifespan across primate species.We used two different approaches.First, we searched for parallel amino-acid mutations that co-occur with increases in longevity across the primate linage.Twenty-five such amino-acid variants were identified, several of which have been previously reported by studies with different experimental setups and in different model organisms.The genes harboring these mutations are mainly enriched in functional categories such as wound healing, blood coagulation, and cardiovascular disorders.We demonstrate that these pathways are highly enriched for pleiotropic effects, as predicted by the antagonistic pleiotropy theory of aging.A second approach was focused on changes in rates of protein evolution across the primate phylogeny.Using the phylogenetic generalized least squares, we show that some genes exhibit strong correlations between their evolutionary rates and longevity-associated traits.These include genes in the Sphingosine 1-phosphate pathway, PI3K signaling, and the Thrombin/protease-activated receptor pathway, among other cardiovascular processes.Together, these results shed light into human senescence patterns and underscore the power of comparative genomics to identify pathways related to aging and longevity.",
+      "\t\n\nBefore the advent of NGS technologies, several scientists were interested in the study of allele variants associated with aging, but they were limited by the lack of aging rate biomarkers.Now with NGS technologies, these biomarkers have been emerged such as the epigenetic clock that is described in the DNA methylation sequencing section of this chapter.In this post-genomic era, different strategies have been developed in order to understand the genetic factors involved in aging [17].One strategy used is the study of aging in extreme longevity groups of people, called centenarians.Centenarians are a group that can reach an age above 100 years and has an incidence of 1 every 10,000 people [18].In a pioneering study using extreme longevity people (308 individuals belonging to 137 sibships showing extreme longevity), genome-wide scan analysis identified a region on chromosome 4 associated with extreme longevity [19] that corresponds to the microsomal transfer protein (MTP) [20], which is associated with abetalipoproteinemia and hypobeta lipoproteinemia in humans [21,22].Another approach to study the genetic factors involved in longevity consists in assessing allele frequencies from people of different ages, looking for those polymorphisms (SNPs) with enhanced allele frequencies in high-longevity individuals.Those alleles with diminished frequencies in aged individuals may be associated with age-related diseases.Using this approximation, an SNP that shifts isoleucine to valine was identified in the PKA-anchoring protein (AKAP2) gene.This polymorphism is associated with reduced longevity and cardiac disease [23].Genome-wide association studies (GWAS) have confirmed only three loci that affect longevity: FOXO3A, APOE, and an intergenic locus on chromosome 5q33.3[24][25][26].",
+      "\t\n\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.\t\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.",
+      "\t\n\nEven more disappointing result is that some genes predisposing to geriatric diseases discovered by GWAS appear to be not correlated with human longevity (Beekman et al. 2010;Deelen et al. 2011).This result questions whether findings obtained from GWAS may provide insights into the bio-genetic mechanisms underlying a healthy lifespan.In fact, this finding is very surprising because (1) genetic studies of non-human species have discovered numerous genes predisposing to aging-related processes (Cutler and Mattson 2006;Vijg and Suh 2005;Kenyon 2005;Johnson 2006;Greer and Brunet 2008), (2) nongenetic association studies show that the long-living individuals are typically in better health compared to the short-living individuals (Barzilai et al. 2003;Willcox et al. 2008b;Willcox et al. 2008a;Evert et al. 2003), and (3) candidate-gene studies (but not GWAS) document that the same genes can affect diseases and lifespan (Koropatnick et al. 2008;Kulminski et al. 2011).This is an apparent paradox which has to be carefully examined.A prominent geneticist and evolutionary biologist T. G. Dobzhansky asserts that \"nothing in biology makes sense except in the light of evolution. \"Evolution primarily maximizes fitness of individuals of reproductive age.The classical evolutionary biological theory of aging claims that aging occurs because of decline in the force of natural selection with age (Kirkwood and Austad 2000).Then, according to that theory, aging-related (senescent) phenotypes with post-reproductive manifestation are non-adaptive and subject to stochastic variation.Therefore, at a first glance evolution should not be relevant to senescent phenotypes (apart so-called grandmother hypothesis; Hawkes et al. 1998).Such phenotypes, however, can be caused by reproductive-age-related risk factors making, thus, evolution to be relevant to them (Vijg and Suh 2005;Di Rienzo and Hudson 2005;Drenos and Kirkwood 2010).",
+      "\t\n\nIn this light, we pursued a genomic study of an alternate but related aging phenotype-healthy aging-in order to expose its potential to uncover genetic factors for protection against age-associated disease.It is important to differentiate longevity from our healthy aging phenotype, which, as we have defined it for our healthy aging cohort (Wellderly), attempts to understand the genetics of disease-free aging in humans without medical interventions.Toward this end, we performed whole-genome sequencing (WGS) of the Wellderly and compared their genetic characteristics to an ethnicity-matched population control.Our findings suggest that healthy aging is associated with a diseaseprotective genetic profile that overlaps with but differs from that observed in exceptional longevity cohorts.These findings include no enrichment of true longevity variants, a lower genetic risk from common susceptibility alleles for Alzheimer and coronary artery disease, and no decrease in the rate of rare pathogenic variants.We identify suggestive common and rare variant genetic associations that implicate genetic protection against cognitive decline in healthy aging.Our data are made available for the discovery of additional disease protective genetic factors by the research community.",
+      "\t\n\nThe studies in lower animals made in recent years that have led to the view that genes are involved in aging have not revealed a reversal or arrest of the inexorable expression of molecular disorder that is the hallmark of aging.These studies are more accurately interpreted to have impact on our understanding of longevity determination because all of the experimental results have altered biological variables before the aging process begins.None of these studies in invertebrates has demonstrated that the manipulation of genes has slowed, stopped, or reversed recognized biomarkers of the aging process.",
+      "\tGENETIC ANALYSIS OF LONGEVITY, OF AGING, AND OF AGE-SENSITIVE TRAITS IN MICE\n\nBiogerontology has just begun to benefit from the attention and skills of professional geneticists.Geneticists can attack problems of aging from several related but fundamentally distinct directions.Studies of rare mutations at individual loci, such as the Werner's syndrome locus WRN, whose mutant form produces, in middle-aged people, several of the diseases typically not seen until old age, can give attractive points of entry into the pathophysiology of age-related diseases.In mice there are now four reports of mutations-two naturally occurring and two artificially produced-that lead to impressive increases in mean and maximal longevity (Miskin and Masos, 1997;Brown-Borg et al., 1996;Miller, 1999;Migliaccio et al., 1999), and thus provide extremely valuable models for testing mechanistic ideas and the control of aging.Some of these, such as the dw/dw and df/df dwarfing mutations that affect levels of growth hormone and thyroid hormone, provide clues to endocrine-dependent pathways that could regulate age effects in multiple cells and tissues.The recent report (Migliaccio et al., 1999) that mouse life span can be extended by an induced mutation that diminishes cell susceptibility to apoptotic death after injury should stimulate new inquiries into the effects of altered cell turnover on age-dependent changes.Each of these mutations, however, is exceptionally rare in natural populations; despite their effect on longevity, perhaps mediated by a direct effect on aging, each of the mutations is likely to have, overall, a negative effect on reproductive success and thus fail to become fixed in natural mouse populations.\t\n\nAny discovery about the biological determinants of the rate of aging raises the possibility of therapies to slow aging.Therefore the discovery of a gerontogene with even very rare mutations that increased longevity would cause speculation about future trends in mortality.However, the discovery of such a gene would be relevant only to long-term (and, therefore, very speculative) projections.",
+      "\t\n\nThe remarkable discoveries of the past 2 decades showing that single genes can regulate aging in model organisms demonstrate that aging can be genetically manipulated (Finch and Ruvkun, 2001;Kenyon, 2010).Hundreds of genes that modulate longevity have now been identified in model organisms (de Magalha es et al., 2009a).In some cases (e.g., in worms), mutations in single genes can extend lifespan by almost 10-fold (Ayyadevara et al., 2008).Nonetheless, aging is a complex process that derives not from single genes but from the interactions of multiple genes with each other and with the environment.Evidence from animal systems shows a major impact of the environment on aging, yet environmental manipulations of aging act through genes and proteins, usually by triggering signaling pathways and modulating gene expression.In fact, some genes have been shown in model organisms to have varying effects on lifespan depending on diet (Heikkinen et al., 2009).Genes that can regulate aging in model organisms cannot be directly applied to humans through genetic manipulations for numerous legal, ethical, and technical reasons.If we could understand how the environment modulates these aging-related genes, we might be able to create antiaging therapies applicable to humans, potentially through diet, lifestyle, and even pharmacological interventions.Therefore, understanding genome-environment interactions in the context of aging can be a powerful approach to identify attractive targets for drug design.",
+      "\t\n\nHere, we review advances in genomic analysis within and across species to help refine the genetic foundations of age-associated diseases and longevity.As such, independent evolutionary occurrences of this species-specific lifespan change can empower comparative approaches to refine the shared mechanisms associating with longevity phenotypes.These evolutionary-refined gene sets can then be leveraged to focus statistical analysis within human cases of extreme longevity to discover core mechanisms of regulation.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\t\n\nWith modern genomic technologies and largescale data analysis methods, it is possible to sift through the genes of populations to find the loci that act to postpone aging. [3]There are uncertainties with the comparison of populations with different rates of aging.However, it is superior to experimental designs that only consider age-dependence or dietary-response, without determining causal mechanisms.",
+      "\tGenAge: the aging gene database Philosophy and overview of resources\n\nIt is undisputed that genetic factors influence aging.In a remarkable series of recent breakthroughs, a number of genes capable of altering the aging process as a whole -or at least to a large degree -have been identified in animal models and even a few in humans (Finch & Ruvkun, 2001;de Magalhes, 2005;Kenyon, 2005).Furthermore, multiple alleles have been examined for their association with human exceptional longevity (Vijg & Suh, 2005).This is a fascinating and important area of research, yet there are now so many genes being associated with aging and longevity that keeping track of them all is becoming increasingly more difficult.Moreover, it is necessary now to study not only individual genes but their interactions with each other and with the environment, and how together genes give rise to a given phenotype: the so-called systems biology approach.To help researchers address these issues we created GenAge, a database of genes related to longevity and/or aging.",
+      "\tConclusions and prospects\n\nOver the past two decades the human aging field has built up the necessary resources to study the biology of aging and longevity by establishing human populations with a diversity of designs.Meta-analyses integrating genetic and phenotypic datasets have successfully identified variants associated with a range of age-related traits and diseases.Despite these accomplishments, the number of novel leads contributing to human lifespan regulation is limited.Although positive regions of linkage and suggestive GWAS hits have been reported, the field has not yet identified the loci that explain the clustering of longevity in families and the variation in biological aging rate in the population.As for animal models, down-signaling of the IIS and mTOR pathway appeared to be relevant in humans.These findings are being followed up by molecular and physiological profiling using skin, fat and muscle tissue of long-lived family members and controls.Human studies now also include the response of nutrient sensing systems to the application of dietary and physical challenges.",
+      "\t\n\nAlthough many theories have tried to explain aging, only few experimental advances were made prior to the last two decades.Since then rapid progress in the genetics of aging has been made in invertebrate models such as C. elegans and D. melanogaster, demonstrating the existence of regulatory pathways that control the rate of aging in these organisms [1][2][3][4][5][6][7][8][9][10][11][12][13][14].They include the insulin-like pathway, the Jun kinase pathway and the Sir2 deacetylase pathway.Moreover, it was rapidly shown that some of these pathways are conserved from yeast to humans."
+    ],
+    [
+      "\t\n\nIn summary, our data suggest that epigenetic mechanisms can be crucial for normal aging and be important players responsible for neuron-specifi c changes accumulated during this process.",
+      "\t\n\nTogether, the examples above provide strong evidence that epigenetics-both DNA methylation and histone modifications-influence aging and that these impacts can differ between the sexes.The data from human DNA methylation studies suggest that alterations to the epigenome occur at a slower pace in females than in males.The data from model organisms are limited; additional studies will be needed to get a clear picture of how age-associated epigenetic changes might contribute to the sex-differences in aging observed.\tEpigenetics\n\nIn addition to increased DNA damage, mutations, and telomere attrition, large-scale epigenetic changes have been associated with increased age in a number of species.The epigenetic changes seen in old compared to young animals are quite diverse and include changes in histone modifications, DNA methylation, and levels of chromatin remodeling and modifying enzymes [for recent reviews see (63) or (64)].Heterochromatin, the silent form of chromatin required for proper centromere and telomere function and repression of transposable elements, is often lost during aging.Increased transcriptional noise associated with epigenetic changes during aging has been proposed to cause at least some of the degenerative phenotypes observed with increased age.While a variety of epigenetic changes occur with age, the relative importance of each of these changes and the impact of sex and genetic background on these changes is poorly understood.",
+      "\t\n\nFigure1.Epigenetics of aging and aging-related diseases.During aging, various epigenetic alterations occur including accumulation of histone variants, changes in chromatin accessibility mediated by chromatin remodeling complexes, loss of histones and heterochromatin, imbalance of activating/repressing histone modifications and aberrant expression/activity of miRNAs.These deregulations can affect transcription and, subsequently, translation, as well as the stabilization or degradation of molecular components.Consequently, these aberrant epigenetic processes can promote morbidities, which are frequently observed in the elderly populations, including inflammation, cancer, osteoporosis, neurodegenerative diseases, and diabetes.\t\n\nFigure1.Epigenetics of aging and aging-related diseases.During aging, various epigenetic alterations occur including accumulation of histone variants, changes in chromatin accessibility mediated by chromatin remodeling complexes, loss of histones and heterochromatin, imbalance of activating/repressing histone modifications and aberrant expression/activity of miRNAs.These deregulations can affect transcription and, subsequently, translation, as well as the stabilization or degradation of molecular components.Consequently, these aberrant epigenetic processes can promote morbidities, which are frequently observed in the elderly populations, including inflammation, cancer, osteoporosis, neurodegenerative diseases, and diabetes.",
+      "\t\nOver the past decade, a growing number of studies have revealed that progressive changes to epigenetic information accompany aging in both dividing and nondividing cells.Functional studies in model organisms and humans indicate that epigenetic changes have a huge influence on the aging process.These epigenetic changes occur at various levels, including reduced bulk levels of the core histones, altered patterns of histone posttranslational modifications and DNA methylation, replacement of canonical histones with histone variants, and altered noncoding RNA expression, during both organismal aging and replicative senescence.The end result of epigenetic changes during aging is altered local accessibility to the genetic material, leading to aberrant gene expression, reactivation of transposable elements, and genomic instability.Strikingly, certain types of epigenetic information can function in a transgenerational manner to influence the life span of the offspring.Several important conclusions emerge from these studies: rather than being genetically predetermined, our life span is largely epigenetically determined; diet and other environmental influences can influence our life span by changing the epigenetic information; and inhibitors of epigenetic enzymes can influence life span of model organisms.These new findings provide better understanding of the mechanisms involved in aging.Given the reversible nature of epigenetic information, these studies highlight exciting avenues for therapeutic intervention in aging and age-associated diseases, including cancer.\t\n\nOver the past decade, a growing number of studies have revealed that progressive changes to epigenetic information accompany aging in both dividing and nondividing cells.Functional studies in model organisms and humans indicate that epigenetic changes have a huge influence on the aging process.These epigenetic changes occur at various levels, including reduced bulk levels of the core histones, altered patterns of histone posttranslational modifications and DNA methylation, replacement of canonical histones with histone variants, and altered noncoding RNA expression, during both organismal aging and replicative senescence.The end result of epigenetic changes during aging is altered local accessibility to the genetic material, leading to aberrant gene expression, reactivation of transposable elements, and genomic instability.Strikingly, certain types of epigenetic information can function in a transgenerational manner to influence the life span of the offspring.Several important conclusions emerge from these studies: rather than being genetically predetermined, our life span is largely epigenetically determined; diet and other environmental influences can influence our life span by changing the epigenetic information; and inhibitors of epigenetic enzymes can influence life span of model organisms.These new findings provide better understanding of the mechanisms involved in aging.Given the reversible nature of epigenetic information, these studies highlight exciting avenues for therapeutic intervention in aging and age-associated diseases, including cancer.\t\n\nFig. 1.Overview of epigenetic changes during aging.In young individuals, the cells within each cell type have a similar pattern of gene expression, determined in large part by each cell having similar epigenetic information.During aging, the epigenetic information changes sporadically in response to exogenous and endogenous factors.The resulting abnormal chromatin state is characterized by different histone variants being incorporated, altered DNA methylation patterns, and altered histone modification patterns, resulting in the recruitment of different chromatin modifiers.The abnormal chromatin state in old cells includes altered transcription patterns and transcriptional drift within the population.The abnormal chromatin state in old cells also leads to new transposable elements being inserted into the genome and genomic instability, including DNA mutations.\tTRANSGENERATIONAL EPIGENETIC CHANGES THAT AFFECT AGING\n\nAccording to biological dogma, genetics governs all the inherited traits across generations, and epigenetic modifications are reset upon passage through the germ line.However, over the years, this notion was challenged when evidence of epigenetic inheritance through meiosis became acknowledged in certain processes, such as flower symmetry and color in plants, or coat color and size in mice (198,199).Recently, longevity mediated by histone methylation was shown to be epigenetically inherited for several generations (198), implicating transgenerational epigenetic inheritance for the first time in the regulation of life span.Deficiencies in either of the three components of H3 K4me3 methylase complex (ASH-2, WDR-5, or SET-2), in only the parental generation, resulted in life span extension in C. elegans in the three subsequent generations, in the absence of methylase deficiency in these offsprings.However, only the parents with the deficiencies in the H3 K4me3 regulatory complex, and not their wild-type long-lived offspring, had reduced global H3 K4me3 levels.Hence, altered histone methylation per se was not transgenerationally inherited.Instead, microarray analysis revealed that there were persistent changes in gene expression throughout the generations upon manipulation of the H3 K4me3 regulatory complex in the parents (198), which could potentially be responsible for the transgenerational inheritance of long life span.Further experimentation is needed to identify the pathways responsible for the transgenerational inheritance of longevity and to explore whether this epigenetic memory is generalizable to other species.A useful approach to study the inheritance of aging phenotypes would be to follow the lead of a recent study examining epigenetic germ line inheritance of dietinduced obesity and insulin resistance in mice (200).This study used in vitro fertilization to ensure exclusive inheritance through the gametes and showed that the parental high-fat diet renders the offspring more susceptible to developing obesity and diabetes.It is tempting to speculate that this novel mode of inheritance may illustrate how epigenetics could have contributed to evolution, whereby the ancestors' environmental exposure determined the fate of the descendants.Given the intriguing nature of the subject, more studies will undoubtedly further explore this exciting direction in the near future.",
+      "\tEpigenetic modifications, most commonly in the form of changes in the methylation\nstatus of DNA and biochemical modifications of core histones, have been linked to the\naging process and are increasingly recognized as part of normal and pathologic aging\nphysiology (Issa, 2003). Manel Estellers group studied the epigenetic profiles of 80\npairs of monozygotic twins ranging in age from 3-74 years old and found that older twins\nexhibited large differences in their overall content and distribution of 5-methylcytosine\nDNA and histone acetylation compared to young twins which were largely\nindistinguishable epigenetically (Fraga et al. , 2005).",
+      "\t\n\nClearly, epigenetic changes are both responsive to and effectors of the aging process.With DNA damage and environmental stresses like inflammation leading to changes in chromatin, the epigenome clearly adapts to age-related changes in the genome and the local milieu.Perhaps the epigenome is a general sensor of cellular dysfunction, sensing metabolic and proteomic changes that accompany aging as well.However, the epigenome is also an effector of the aging process, enforcing different patterns of gene expression in old cells and young cells and, in many cases, resulting in cellular phenotypes associated with aging such as senescence and metaplasia (Martin, 2009).In that sense, the epigenome is rather like a lens through which genomic information is filtered (Figure 3), a lens that deteriorates with age because of both loss of integrity of genomic information and direct environmental stresses within and outside of the cell.Within the ''epigenome as lens'' metaphor, the process of rejuvenation is the restoration of a youthful state by actions on the epigenomic lens (Figure 3).The loss of integrity of the genomic information remains, but the rejuvenating interventions are sufficient to overcome and possibly reverse at least some of the agerelated epigenetic changes.Similarly, an altered epigenome and gene expression programs may also be able to reverse or compensate for some age-dependent biochemical changes, such as protein aggregation, macromolecular oxidation, and glycation, to maintain cellular functions (Douglas and Dillin, 2010).",
+      "\tRole of Epigenetic Alterations\n\nA wide range of epigenetic alterations affects the cells during the life span, which may modulate vascular aging phenotypes. 138Epigenetic changes that may contribute to vascular aging processes involve alterations in DNA methylation patterns, posttranslational modification of histones, microRNAs (miRNAs), long noncoding RNAs, and chromatin remodeling.",
+      "\tEpigenetics of aging\n\nIncreasing evidence supports a role for epigenetics in the biology of aging.X-inactivated genes in the mouse show an increased frequency of reactivation with aging, consistent with age-related epigenetic change [39,40].The frequency of epigenetic changes in mice may be one to two orders of magnitude greater than the rate of somatic DNA mutation [41].This fits with a role of epigenetics in late-onset disorders such as frailty, a syndrome of decreased resiliency and reserves, in which a mutually exacerbating cycle of declines across multiple systems results in negative energy balance, sarcopenia, and diminished strength and tolerance for exertion [42].Accumulation of DNA sequence changes might not occur at enough high rate during the lifespan to induce common disease, but epigenetic changes may occur at a frequency that could contribute to this effect.Very few studies have demonstrated epigenetic changes in humans with age due to technical and biosample limitations.A recent study has shown differences in local and global methylation by age by examining the similarity in methylation patterns between MZ twins aged 3 years old and MZ twins aged 50.Although these analyses were not in the same individuals (the same twins were not followed longitudinally), the similarity in methylation patterns between young twins compared to the dissimilar patterns among older twins argues strongly for age-related changes in the epigenome [43].Direct evidence comes from a recent study showing changes in DNA methylation in the same individual over time, described in more detail below.",
+      "\tIntroduction\n\nEpigenetics is destined to change across the lifespan.Loss of global DNA methylation and promoter hypermethylation of several specific genes occur during aging.Epigenetics plays an important role in cellular senescence, human tumorigenesis, and several agerelated diseases (Fraga et al. 2007;Bollati et al. 2009;Kim et al. 2010;Choi et al. 2009;Moore et al. 2008;Rakyan et al. 2010;Chambers et al. 2007).Indeed, epigenomic alterations are now increasingly recognized as part of aging and its associated pathologic phenotype (Petronis 2010;Bellizzi et al. 2011).However, the role of epigenetics in the modulation of healthy aging and longevity has not been clearly studied in humans.",
+      "\t\n\nEpigenetic changes linked to aging also impact specific diseases of aging, including cancer.While some age-associated epigenetic changes, such as increased abundance of histone modification H4K20me3 [10] and decreased H3K27me3 [38,39], may activate tumour suppressor mechanisms and prevent cancer, others may be tumour promoting.Like cancer, aged tissue has been reported to exhibit global DNA hypomethylation and more focal hypermethylation at CpG islands [10].Most notably, so-called bivalent gene promoters, marked with both activating H3K4me3 and repressing H3K27me3 (hence \"bivalent\") in embryonal stem (ES) cells, acquire DNA methylation in aged tissues and are also methylated and stably silenced in cancer [15][16][17][18][19].In ES cells, these bivalent-marked genes are thought to be poised for activation due to loss of the repressive H3K27me3 mark during stem and progenitor cell differentiation and development.By virtue of their pro-differentiation functions these genes tend to have tumour suppressor-like properties, meaning that their methylation and stable silencing may promote proliferation, self-renewal and malignancy.In the haematopoietic system, some CpG islands progressively increase methylation from young to old to neoplasia, namely myelodysplastic syndrome (MDS) and ultimately acute myeloid leukemia [40].Sf3b1, the mouse ortholog of a gene frequently mutated in human MDS, is methylated and underexpressed in aged mouse HSCs [36].Hence, age-associated methylation changes might predispose to transformation of aged cells by promoting silencing of tumour suppressor genes.\t\n\nAging is associated with changes to the epigenome [10,11].These changes include age-associated accumulation of histone variants, for example histone H3.3 in neurons and macroH2A in lung, liver and muscle, as well as other chromatin-associated proteins and changes to histone and DNA modifications [12][13][14].Aging also affects specific gene regulatory elements, such as enhancers, promoters and CpG islands [15][16][17][18][19][20][21][22][23].Underscoring the importance of such age-associated epigenetic changes, recent human studies have identified collections of specific CpGs whose age-associated change in methylation status in multiple tissues correlates strongly with chronological age.An advanced methylation age compared to actual chronological age is thought to reflect accelerated biological age and is linked to increased mortality [24][25][26][27][28].",
+      "\t\n\nVasily V. Ashapkin and coworkers studied a direct relationship on how aging affects the epigenetic phenomenon.It has been established that hypermethylation of genes associated with promoter CpG islands, and hypomethylation of CpG poor genes, repeat sequences, transposable elements and intergenic genome sections occur during aging in mammals.Moreover, the methylation levels of certain CpG sites display strict correlation with age and can be used as \"epigenetic clock\" to predict biological age.Multi-substrate deacetylases SIRT1 and SIRT6 affect aging via locus-specific modulations of chromatin structure and activity of multiple regulatory proteins involved in aging.In addition, the random changes in DNA methylation or chromatin remodeling on aging lead to gradual increase in transcriptional noise introducing phenotypic variation among cells.Therefore, most likely based on the author's interpretation, such variation could become detrimental to tissue functioning, leading to highly variable progressive decline in organ functions during aging.Multiple data of age-dependent induction of NF-B regulated gene sets in various tissues suggest NF-B to be a master regulator of gene expression programs in mammalian aging.Vasily V. Ashapkin and coworkers summarized how the upregulation of multiple miRNAs occurs at mid age leading to downregulation of genes functionally involved in the control of intermediate metabolism, apoptosis, DNA repair, oxidative defense, and mitochondrial oxidative phosphorylation.Strong evidence shows that all epigenetic systems contribute to the life span control in various organisms.Similar to other cell systems, epigenome is prone to gradual degradation due to the genome damage, stressful agents and other aging factors.Critical analysis by Vasily V. Ashapkin et al., demonstrated that unlike mutations and other kinds of the genome damage, age-related epigenetic changes could be fully or partially reversed to a \"young\" aged state and requires more detailed analysis in the context of the aged associated genetic modification especially during the courses of the development and maturation of human diseases.",
+      "\tEPIGENETIC REGULATION OF AGING\n\nIn addition to gene expression changes, the states of epigenetic modifications have emerged to be significantly important in modulating lifespan (see the accompanying review by Liu and Zhou in this issue [45]).Epigenetic modifications include DNA and histone modifications that are potentially heritable and reversible without changing the genetic code [46].With the application of recent high-throughput approaches, such as bisulfite sequencing, ChIP-seq or ChIPchip, etc. (Section 1), epigenetic controls have become wellrecognized as important regulatory mechanisms during the lifetime of an organism [46,47].For example, using the anti-O-GlcNAc ChIP-on-chip whole-genome tiling arrays on C.elegans, Love et al. [48] found 800 genes displaying differential cycling of O-GlcNAc which have functions closely related to aging.By examining DNA methylation at CpG sites throughout the human genome, Hernandez et al. [49] identified hundreds of CpG sites with levels of DNA methylation in the human brain highly correlated with chronological age.",
+      "\tThe impact of epigenetic changes accumulated during aging on the aging phenotype\n\nA key question about the role of epigenetics in aging is whether epigenetic changes accumulated during aging have a causal role in establishing the aging phenotype or if the two phenomena are unrelated.To settle this matter, it is important to consider the region in the genome/chromatin where these changes occur.Changes occurring in non-coding sequences will potentially have a smaller biological impact than those occurring in coding sequences as modifications of the latter type generally involve changes in gene expression.It is also important to consider the cells and tissues in which these occur because epigenetic patterns are celland tissue-specific so that changes occurring in a specific cell or tissue would not necessarily imply the same functional consequences in different cells or tissues.\tEpigenetic changes during ontogenic development and aging\n\nThe relationship between epigenetics and aging was proposed many years ago (Table 1).A pioneering study by Berdyshev et al. (1967) showed that genomic global DNA methylation decreases with age in spawning humpbacked salmon.Subsequently, Vanyushin et al. (1973) also detected a global loss of cytosine methylation during aging in rat brain and heart.More recently, Wilson et al. (1987) confirmed the gradual loss of DNA methylation with age in various mouse tissues and in human bronchial epithelial cells.Similarly, Fuke et al. (2004) recently found an agedependent decrease in global methylation levels in human leukocytes.The definitive corroboration on intra-individual epigenetic variation over time in humans, was recently provided in a longitudinal study of DNA methylation patterns in which successive DNA samples were collected more than 10 years apart in more than 100 individuals (Bjornsson et al., 2008)."
+    ],
+    [
+      "\t\n\nForkhead box O3a (mFoxo3a) is a transcription factor that is characterized by a fork head DNA-binding domain and has been associated with longevity in humans as well as with several cancers.Similar to the situation with mSirt1, no daily rhythm in expression was detected, and no differences among the ages of mice was determined (Figure 4B).",
+      "\tWillcox BJ, Donlon TA, He Q et al (2008) FOXO3A genotype is\nstrongly associated with human longevity. Proc Natl Acad Sci\nUSA 105(37):1398713992. doi:10.1073/pnas.0801030105\n4. Anselmi CV, Malovini A, Roncarati R et al (2009) Association of\nthe FOXO3A locus with extreme longevity in a southern Italian\ncentenarian study. Rejuvenation Res 12(2):95104. doi:10.1089/\nrej.2008.0827\n5. Flachsbart F, Caliebe A, Kleindorp R et al (2009) Association of\nFOXO3A variation with human longevity confirmed in German\ncentenarians. Proc Natl Acad Sci USA 106(8):27002705. doi:10. 1073/pnas.0809594106\n6.",
+      "\tCross-species, cross-condition comparisons reveal shared longevity gene-expression signatures\n\nBased upon the hypothesis that longevity may be mediated by common sets of target genes that are effectors of upstream signaling pathways, and that the transcriptional targets of FOXO are likely to include direct mediators of increased longevity, the gene expression profiles resulting from MnSOD over-expression in Drosophila were compared to those of genes regulated by daf-2 in a daf-16 dependent manner in C. elegans [74,75].Remarkably, comparison of MnSOD target genes (genes whose expression was altered at both time points) to those genes regulated by daf-2 in a daf-16 dependent manner [74] revealed 25 genes (Figure 7) out of 3,542 unique fly genes with a stringent worm ortholog that were upregulated in both conditions, and this overlap is non-random (p << 0.001; Additional data file 5).When the list of MnSODregulated genes was expanded to include those genes altered at the same chronological age, but not the same 'physiological age', five additional conserved genes (CG15099, Jra, PHGPx, n-syb, Hrb98DE) were identified (Additional data file 7).\tMnSOD-regulated targets downstream of dFOXO\n\nThe cross-species, cross-condition comparison described above was aimed at identifying genes and processes that broadly mediate lifespan and, hence, are robust signatures of longevity mechanisms.However, certain downstream targets of dFOXO may have been missed by a comparison of stringent orthologs.In order to identify species specific MnSODregulated targets that act downstream of dFOXO as well as potential lifespan promoting mechanisms that might be unique to Drosophila, the transcriptional profile of MnSOD over-expression was compared to those resulting from altered insulin signaling in Drosophila.These comparisons are described in Additional data file 10.",
+      "\t\n\nAge-associated changes in transcriptional factors represent a critical aspect of aging [2].Some conserved pro-longevity factors are FOXO/DAF-16, NRF/SKN-1, HSF-1, XBP-1, REST/SPR-4, and p53/CEP-1.FOXO/DAF-16 promotes longevity in a variety of species from worms to humans, and it is regulated by the insulin/IGF signaling pathway, the nutrient sensor AMPK, and stress [56,57].This transcription factor controls the expression of genes involved in stress response, metabolism, immunity, and neuronal function in a variety of organisms, and interestingly, the FOXO3 locus is associated with extreme longevity in humans (centenarians) [2,58,59].",
+      "\t\n\nIncreasing S-adenosylmethionine (SAM) synthesis by FOXO-dependent glycine N methyltransferase (Gnmt) extends the lifespan in Drosophila and thus overexpression of Gnmt increases longevity, cooperatively with Notes: These transcripts are significantly affected more than two-fold (>LogFC 1) dietary restriction and lowered IIS [137].We see a 6.3 LogFC (increase) in Gnmt in three week diapausing flies (Additional file 3: Dataset S1, Additional file 9: Table S4).Another gene implicated in Drosophila lifespan extension is Tequila a multiple-domain serine protease known to be upregulated during infection [138].These authors showed that knockdown of Tequila in insulin producing cells increases longevity, probably due to decreased systemic IIS.",
+      "\t\n\nIn addition to testing genes known to be associated with age-related diseases and phenotypes for association with longevity, genes known to promote longevity in model organisms have been examined in human populations.Mutations in insulin or insulinlike signalling pathway genes have been shown to extend lifespan in Caenorhabditis elegans [20], Drosophila melanogaster [21,22] and mice [23,24].The insulin-signalling pathway negatively regulates the forkhead (FOXO) transcription factor [25].When insulin or insulin-like growth factor signalling is low, FOXO is activated and lifespan extension occurs [26].An overrepresentation of rare insulin-like growth factor I receptor (IGFIR) mutations has been observed in centenarians [27].These mutations are associated with reduced activity of IGFIR as measured in transformed lymphocytes [27].",
+      "\tGiannakou, M., M. Goss, and L. Partridge. 2008. Role of dFOXO in lifespan extension by\ndietary restriction in Drosophila melanogaster: Not required, but its activity modulates the\nresponse. Aging Cell 7:187198. Gillespie, J. H. 1973. Natural selection with varying selection coefficients: A haploid model. Genetical Research 21:115120. Greenwood, M., and J. O. Irwin. 1939. Biostatistics of senility. Human Biology 11:123. Guarente, L., and C. Kenyon. 2000. Genetic pathways that regulate aging in model organisms. Nature 408:255262. Haldane, J. B. S. 1941. New Paths in Genetics. London: Allen and Unwin. Hamilton, W. D. 1966. The moulding of senescence by natural selection.",
+      "\t\n\nMuch work has been done implicating FOXO3 as an ageing gene in model organisms (Kenyon et al., 1993;Hwangbo et al., 2004), however we found the association in humans at that locus may be driven by expression of SESN1 (admittedly a finding restricted to peripheral blood tissue).SESN1 is a gene connected to the FOXO3 promoter via chromatin interactions and is involved in the response to reactive oxygen species and mTORC1 inhibition (Donlon et al., 2017).While finemapping studies have specifically found genetic variation within the locus causes differential expression of FOXO3 itself (Flachsbart et al., 2017;Grossi et al., 2018), this does not rule out the effect of co-expression of SESN1.More powered tissue-specific expression data and experimental work on SESN1 vs. FOXO3 could elucidate the causal mechanism.For now, results from model organisms seem to leave the preponderance of evidence for FOXO3.",
+      "\tHe, R. Chen, J. S. Grove,\nK. Yano, K. H. Masaki, D. C. Willcox, B. Rodriguez, and\n291\nBIBLIOGRAPHY\nJ. D. Curb. Foxo3a genotype is strongly associated with human longevity. Proceedings of the National Academy of Sciences,\n105(37):1398713992, Sep 2008. [370] David Withers, Edward Kawas, Luke McCarthy, Benjamin Vandervalk, and Mark Wilkinson. Semantically-guided workow construction in taverna: The sadi and biomoby plug-ins. Leveraging Applications of Formal Methods, Verification, and Validation,\npage 301312, 2010.",
+      "\t\n\nSeveral of the genes we identify have previously been shown to influence lifespan in experiments on model organisms.For example, knockouts of the orthologs of APOE, LDLR, CDKN2B, and RBM38 in mice shortens their lifespan [24][25][26][27] , while knockout of IGF1R has the opposite effect 28 .Similarly, overexpression of the FOXO3 orthologue in Drosophila melanogaster 29 and the SNCA orthologue in Caenorhabditis elegans 30 have shown to extend their respective lifespans.Many of our genes are also enriched for pathways previously related to ageing in eukaryotic model organisms, including genomic stability, cellular senescence, and nutrient sensing 31 .For example, FOXO3 and IGF1R are well-known players modulating survival in response to dietary restriction 32 , but we also highlight genes involved in the response to DNA damage and apoptosis, such as CDKN2B, USP28, E2F2, and BCL3.In addition to hallmarks discovered in model organisms, our results suggest that haem metabolism may play a role in human ageing.This pathway includes genes involved in processing haem and differentiation of erythroblasts 33 .Although the enrichment is largely driven by genes linked to the LDLR locus, genes linked to other loci of interest (such as FOXO3, CDKN2B, LINC02513) are involved in similar biological pathways: myeloid differentiation, erythrocyte homeostasis, and chemical homeostasis.\t\n\nImportantly, the genes we have highlighted show natural variation in the human population and some of them show altered levels of expression with increasing age, which makes them good candidates for therapeutic intervention.However, colocalisation of gene expression could be due to pleiotropy rather than causality, and there is a need to validate the effects of genetic variants in experimental models to confirm their role in disease aetiology.For example, we have found life-extending variants colocalise with decreased expression of FOXO3 in blood, which itself becomes increasingly expressed with increasing age, but experiments suggest the gene has many protective functions including detoxification of reactive oxygen species and DNA damage repair 15 .The observed inverse relationship between healthy life and FOXO3 expression may reflect healthy individuals have less oxidative damage and require less FOXO3 to mitigate this damage.\t\n\nTo determine the age-related expression of the identified cisand trans-acting genes, we performed a look-up in the dataset of Peters et al. 14 .This large dataset contains the associations of genes with age in whole blood, so we limited ourselves to the cis-and trans-acting genes identified in the whole-blood datasets.We found that FOXO3 expression is increased with age in this dataset, which is in line with the life-extending variant decreasing expression (Supplementary Data 6).Moreover, one cis-(ILF3) and two trans-acting genes (E2F2 and PDZK1IP1) in the LDLR locus show a similar effect (i.e.increased or decreased expression with age combined with the life-extending variant decreasing or increasing expression, respectively).The most interesting, however, seems to be the LINC02513 locus, which showed multiple trans-acting genes to be strongly downregulated with age, while the lead life-extending variant increases expression.LEF1, CCR7, and ABLIM1 even belong to the most significantly affected genes in the whole transcriptomic dataset.This indicates that this long intergenic non-protein coding RNA may serve as a master regulator of age-related transcription in whole blood.",
+      "\t\n\nIt is thought that inflammatory triggers during aging may induce the loss of muscle cells and myonuclei during the process of human aging through an apoptotic mechanism (9,30).Indeed, several genes known to play a role in the regulation of apoptosis are components of the upregulated genes in this signature.The forkhead box O3A (FOXO3A) is one such gene upregulated in the aged signature.FOXO3A activation has been shown to induce apoptosis by activating the expression of genes necessary for cell death (14,48).Recent studies have shown the influence of FOXO transcription factors in the transcriptional activation of the ubiquitin protein ligase atrogin-1 during fasting-and glucocorticoid-induced atrophy (45).Welle et al. ( 59) also found increased FOXO1 mRNA in aged muscle using standard microarray analysis.Another recent study has shown that nuclei of aged muscle contain more FOXO1 than those of young muscle (35), and another shows increased atrogin mRNA in aged rats (39).Thus the FOXO proteins may very well play a role in the loss of muscle mass or muscle nuclei with aging.",
+      "\tGiannakou, M., M. Goss, and L. Partridge. 2008. Role of dFOXO in lifespan extension by\ndietary restriction in Drosophila melanogaster: Not required, but its activity modulates the\nresponse. Aging Cell 7:187198. Gillespie, J. H. 1973. Natural selection with varying selection coefficients: A haploid model. Genetical Research 21:115120. Greenwood, M., and J. O. Irwin. 1939. Biostatistics of senility. Human Biology 11:123. Guarente, L., and C. Kenyon. 2000. Genetic pathways that regulate aging in model organisms. Nature 408:255262. Haldane, J. B. S. 1941. New Paths in Genetics. London: Allen and Unwin. Hamilton, W. D. 1966. The moulding of senescence by natural selection.",
+      "\tB. Prioritizing Targets for Drug Discovery and Network Approaches\n\nGenome analyses from CR, aging, and human longevity genes provide biological targets for drug discovery.Screening natural products, existing drugs, and chemical libraries for molecules that affect \"druggable\" targets associated with aging may lead to compounds of therapeutic value.Given the hundreds of genes associated with aging and CR, however, it is important to identify the most promising targets.Integrating information from different datasets can help prioritize candidates (Fig. 2).It is interesting to note the two genes shown in model organisms to be related with aging, associated with human longevity, and essential to CR effects: IGF1R and FOXO3 (Fig. 2).IGFR1 is part of the insulin/ IGF1/GH pathway, the down-regulation of which has been associated with life-extension in several model systems and, as mentioned above, is already a target of pharmacological interventions.The FOXO transcription factor FOXO3 is a homolog of dFOXO and of daf-16, in which mutations suppress the life-extending effects of daf-2 (Kenyon et al., 1993).FOXO transcription factors are, in fact, part of the same insulin/IGF1/GH pathway (Fig. 1) that modulates lifespan across organisms (Kenyon, 2010).A strong association between FOXO3 and human longevity has been reported (Willcox et al., 2008) and subsequently validated in other populations (for review, see Kenyon, 2010).FOXO3 was also associated AGING GENES AS TARGETS FOR DRUG DISCOVERY with insulin levels and prevalence of cancer, heart disease, and type 2 diabetes (Willcox et al., 2008).Further work is necessary to understand the modulation of FOXO3 and its molecular mechanisms affecting longevity, but it is a promising target for drug development.",
+      "\t\n\nThe effect of reduced IIS signalling on lifespan extension in model systems is through changes in gene expression and especially genes orthologous to human FOXO transcription factor, HSF-1, a heat shock transcription factor, and NFE2L2 [25], a xenobiotic response factor.The initial human candidate longevity gene studies were dominated by contradictory results [26].The more consistent evidence obtained by repeated observation in independent cohort studies for association to longevity was found for the APOE locus and, more recently, the FOXO1 and 3 [27 -29] and AKT1 loci [30].The effect size of the association of the FOXO3 variant appears to vary with the age of the cases, being most prominent in centenarians.Other intriguing observations that need to be replicated but fit observations in humans at the phenotype level discussed above were made in the Ashkenazi Jewish Centenarian Study in which a higher serum thyroid-stimulating hormone level and TSHR genetic variation marked the centenarian population [31].Recently, an association with longevity was found for genetic variation in RNA-editing genes [32].",
+      "\t\n\nStudies have shown that ageing is accompanied by increased insulin/IGF signalling (IIS).FOXO (forkheadrelated transcription factor) is a transcription factor downstream of IIS that transcriptionally regulates longevityrelated genes such as hsp (heat-shock factor), inhibits ageing-related genes, and participates in feedback control of IIS (Hwangbo et al. 2004).However, the transcriptional activity of FOXO can be inhibited by increased IIS in ageing Drosophila.Several classic landmark studies have revealed that reduced signalling by insulin-like peptides through loss of CHICO (a Drosophila insulin receptor substrate protein) (Clancy et al. 2001) or mutation of InR (a Drosophila gene insulin-like receptor) (Tatar et al. 2001) can increase the lifespan of D. melanogaster (Tatar et al. 2003).Therefore, FOXO is considered an important contributor to extreme The data are presented as the mean  SEM. ***P < 0.001 versus 3-day-old Drosophila.n = 100 per group Fig. 5 Relative mRNA expression of genes in the longevity-regulating pathway, the peroxisome pathway, and the mTOR-signalling pathway in 3-day-old/30-day-old Drosophila.The relative mRNA levels of the genes were normalized to the levels of tubulin and are expressed as the fold changes relative to the levels in the 3-day group.n = 6 per group.The data are presented as the mean  SEM. *P < 0.05, **P < 0.01 versus 3-day-old Drosophila Fig. 6 Relative mRNA expression of predicted genes in sub-network 1 of Fig. 3 in 3-day-old/30-day-old Drosophila.The relative mRNA levels of key genes were normalized to the levels of tubulin and are expressed as the fold changes relative to the levels in the 3-day group.n = 6 per group.The data are presented as the mean  SEM. *P < 0.05, **P < 0.01 versus 3-day-old Drosophila longevity and health.Akt1, Bsk, Cat and P38b are functionally crucial in the FOXO-signalling pathway.Moreover, food-finding latency is shortened in old D. melanogaster with increased IIS, leading to lower fat reserves and lower starvation resistance (Egenriether et al. 2015).It was confirmed that starvation resistance was significantly reduced in 30-day-old D. melanogaster strain w 1118 , indicating that the 30-day-old D. melanogaster strain w 1118 showed a tendency toward senescence.",
+      "\tFOXO3A and EXO1\n\nThe recently confirmed longevity gene FOXO3A (Anselmi et al., 2009;Flachsbart et al., 2009;Li et al., 2009;Pawlikowska et al., 2009;Soerensen et al., 2010;Willcox et al., 2008) and the longevity candidate EXO1 (Nebel et al., 2009) yielded comparatively high P CCA values of 0.007 and 0.035, respectively, and were therefore far too large to qualify for follow-up in stage 2.",
+      "\t\n\nIn addition to testing genes known to be associated with age-related diseases and phenotypes for association with longevity, genes known to promote longevity in model organisms have been examined in human populations.Mutations in insulin or insulinlike signalling pathway genes have been shown to extend lifespan in Caenorhabditis elegans [20], Drosophila melanogaster [21,22] and mice [23,24].The insulin-signalling pathway negatively regulates the forkhead (FOXO) transcription factor [25].When insulin or insulin-like growth factor signalling is low, FOXO is activated and lifespan extension occurs [26].An overrepresentation of rare insulin-like growth factor I receptor (IGFIR) mutations has been observed in centenarians [27].These mutations are associated with reduced activity of IGFIR as measured in transformed lymphocytes [27]."
+    ],
+    [
+      "\tINTRODUCTION\n\nHuman aging is affected by genes, life style, and environmental factors.The genetic contribution to average human aging can be modest with genes explaining 20-25% of the variability of human survival to the mid-eighties (Herskind et al., 1996;Fraser and Shavlik, 2001).By contrast, genetic factors may have greater impact on survival to the ninth through eleventh decades (Tan et al., 2008).Notably, exceptional longevity is rare and may involve biological mechanisms that differ from those implicated in usual human aging.",
+      "\t\n\nIn addition, environmental factors influence the organism's ability to withstand the increase in entropy with aging: for example, caloric restriction and smoking can exert opposite effects on the rate of aging (Colman et al. 2009;Fraser and Shavlik 2001).Both protective alleles and a benevolent environment contribute to excess physiological capacity, which in turn indirectly determines an individual's healthy life span and longevity (Martin et al. 2007).The wellrecognized increase in variability with aging reflects the precarious balance between the stochastic destruction, environmental influences, and correcting effect of genes responsible for repair.",
+      "\tStochasticity in Aging\n\nAging has a strong nongenetic and apparently nonenvironmental component.The nongenetic, nonenvironmental component of life span is evident from studies of isogenic organisms aged in the same environment, because the animals have different life spans.For example, individual isogenic C. elegans aged on the same Petri dish can have an order of magnitude difference in life span (36).This nongenetic, nonenvironmental component is comprised of experimentally difficult-to-track variables including chance events centered around the partitioning of resources and epigenetic information between cells, accumulated molecular damage, and differences in the perception of environmental or biological signals (37).These differences can begin as early as gametogenesis (38,39).Importantly, these differences affect the biological program of gene expression.",
+      "\tIndividual Genotype\n\nIndividual differences in biological ageing may be due in part to the specific variations of the genotype but also genome-environment interactions [21,37].The maintenance of genomic stability and integrity is considered an essential factor required for cell viability and the overall longevity of an organism.The accumulation of physical damage is one of the leading causes of the ageing process.When considering oxidative damage as one of the causes of the damage of genetic material, these changes alter vital processes, such as replication, transcription, and translation, leading to genomic instability and personalized processes of ageing [38,39].",
+      "\t\nThe underlying cause of aging remains one of the central mysteries of biology.Recent studies in several different systems suggest that not only may the rate of aging be modified by environmental and genetic factors, but also that the aging clock can be reversed, restoring characteristics of youthfulness to aged cells and tissues.This Review focuses on the emerging biology of rejuvenation through the lens of epigenetic reprogramming.By defining youthfulness and senescence as epigenetic states, a framework for asking new questions about the aging process emerges.",
+      "\t\n\nAging is an extremely complex process associated with interplay of genetic, biochemical, and metabolic factors in an organism in a given environment.Although genetic studies of various animal models suggest that even a single-gene mutation can remarkably extend lifespan (Kenyon 2005;Johnson 2006) and, thus, modulate aging, no such genes are revealed in humans so far.Given that a human organism is a much more complex system than a model organism (Christensen et al. 2006), it is evident that genetic effects on the aging process should be mediated via coordinate action of a large number of inter-related processes (Kirkwood 2011).Coordinated function is rather relevant to complex biological (Soltow et al. 2010;Slagboom et al. 2011) and genetic (Bloss et al. 2011) networks than to individual genes.\t\n\nInvolvement of genes in a wide range of fundamental biological processes suggests also a broad role of these genes in regulating the aging-related phenotypes.",
+      "\t\n\nGenes significantly affected by age (P  0.05) in both the active and sedentary environment",
+      "\t\n\nGenes do not drive the aging process but by governing the levels of excess physiological capacity, repair, and turnover they indirectly determine potential longevity.There are no genes that specifically drive longevity but there are genes that govern biological processes that increase the likelihood of survival to reproductive maturity.The variations in excess physiological capacity, repair, and turnover accounts for the variations found in longevity both within and between species.",
+      "\t\n\nIn the most general terms, three types of environmental factors can influence human health during aging: physical, chemical, and biological.Physical factors include temperature and solar radiation.Chemical factors from natural and biological sources include trace toxins (asbestos, lead, tobacco smoke), but also trace morphogens that can cause subtle abnormalities in development.Biological factors include diet and infectious organisms, but also stress from social interactions.We know little about the concentrations of a vast number of bioactive substances that may be present sporadically in the environment.It seems fair to say that our concept of the environment will evolve rapidly with new technical developments and may come to include multigenerational effects.For example, in the case of diabetes, the maternal physiological state existing before pregnancy can influence fetal growth.Moreover, the ovary acquires its full stock of eggs in the fetus: thus, the egg cell from which all of our cells stem was exposed to the environment of our maternal grandmother (Finch and Loehlin, 1998).The depth of the transgenerational environment is a completely obscure aspect of human experience.",
+      "\t\n\nIn 2021, Science published a special issue entitled \"125 Questions: Exploration and Discovery.\" One of these 125 questions was \"Can we stop ourselves from aging? \"The U.S. National Institute on Aging (NIA) at the National Institutes of Health (NIH) states that \"aging is associated with changes in dynamic biological, physiological, environmental, psychological, behavioral, and social processes.\" Although geneticists and epidemiologists have long debated the relative importance of the role played by genotype or the environment in the development of age-related diseases, it is apparent that both can play substantial roles in this process [6,7].However, most etiological studies have concentrated on the role of genotype and have considered the environment to play a secondary role.Nevertheless, an analysis of GBD data showed that nearly 50% of deaths worldwide are attributable to environmental exposure, primarily exposure to airborne particulates (including household air pollution and occupational exposure; 14% of all deaths), smoking and secondhand smoke (13%), plasma sodium concentrations (6%), and alcohol consumption (5%) [8].In contrast, a recent analysis of 28 chronic diseases in identical twins showed that the genetic-related risks of developing one of five age-related diseases were 33.3%, 10.6%, 36.3%, 19.5%, and 33.9% for AD, PD, CAD, COPD, and T2DM, respectively, with a mean of only 26% [9].The results of over 400 genome-wide association studies (GWASs) have also elucidated that the heritability of degenerative diseases is only approximately 10% [10,11].Consequently, nongenetic drivers, such as environmental factors, are now recognized as major risk factors for age-related diseases.The contributions of environmental factors to the development of age-related diseases can be revealed by analyses of all of the factors to which individuals are exposed in their life and the relationships between these exposures and age-related diseases [12,13].",
+      "\t\n\nIn this review, we give an overview of the major environmental factors that modulate aging in animals, in particular those with underlying gene-environment interactions with potential for improving human health and drug discovery.Moreover, we provide a snapshot of the relevance of these to human biology and to antiaging applications in diet, industry, pharmacy, and healthcare.\t\n\nThe remarkable discoveries of the past 2 decades showing that single genes can regulate aging in model organisms demonstrate that aging can be genetically manipulated (Finch and Ruvkun, 2001;Kenyon, 2010).Hundreds of genes that modulate longevity have now been identified in model organisms (de Magalha es et al., 2009a).In some cases (e.g., in worms), mutations in single genes can extend lifespan by almost 10-fold (Ayyadevara et al., 2008).Nonetheless, aging is a complex process that derives not from single genes but from the interactions of multiple genes with each other and with the environment.Evidence from animal systems shows a major impact of the environment on aging, yet environmental manipulations of aging act through genes and proteins, usually by triggering signaling pathways and modulating gene expression.In fact, some genes have been shown in model organisms to have varying effects on lifespan depending on diet (Heikkinen et al., 2009).Genes that can regulate aging in model organisms cannot be directly applied to humans through genetic manipulations for numerous legal, ethical, and technical reasons.If we could understand how the environment modulates these aging-related genes, we might be able to create antiaging therapies applicable to humans, potentially through diet, lifestyle, and even pharmacological interventions.Therefore, understanding genome-environment interactions in the context of aging can be a powerful approach to identify attractive targets for drug design.\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\tIII. Diet, Health, and Aging\n\nThe previous examples of how diet can modulate aging (e.g., social insects and the dauer pathway) are extreme cases not observed in humans.There is evidence, however, that the environment, and diet in particular, can influence aging trajectories in humans.Such environmental influences can be observed from an early age with long-lasting effects.Early nutrition can affect latelife diseases, such as cardiovascular disease (Barker and Osmond, 1986) and mortality (Gluckman et al., 2008;Hanson and Gluckman, 2008).Likewise, infections in early life can increase inflammatory levels and, together with diet, contribute to late-life diseases (Finch, 2010).The specific genes and mechanisms involved are largely unknown, but these epidemiological studies clearly demonstrate that early life environment can affect aging, and these effects are most likely mediated by geneenvironment interactions.",
+      "\t\nAs our society is growing older, the consequences of aging have begun to gain particular attention.Improvement of quality of life at old age and prevention of age-associated diseases have become the main focus of the aging research.The process of aging in humans is complex and underlies multiple influences, with the probable involvement of heritable and various environmental factors.In particular, hormones are decisively involved in the generation of aging.Over time, important circulating hormones decline due to a reduced secretion of the pituitary, the adrenal glands and the gonads or due to an intercurrent disease.Among them, serum levels of growth factors and sexual steroids show significant aging-associated changes.Within the scope of the Explorative Project 'Genetic aetiology of human longevity' supported by the German National Genome Research Network 2 (NGFN-2) an in vitro model of human hormonal aging has been developed.Human SZ95 sebocytes were maintained under a hormone-substituted environment consisting of growth factors and sexual steroids in concentrations corresponding to those circulating in 20-and in 60-year-old women.Eight hundred and ninety-nine genes showed a differential expression in SZ95 sebocytes maintained under the 20-and 60-year-old hormone mixture, respectively.Among them genes were regulated which are involved in biological processes which are all hallmarks of aging.The most significantly altered signaling pathway identified was that of the transforming growth factor-b (TGF-b).A disturbed function of this cascade has been associated with tumorigenesis, i.e. in pancreatic, prostate, intestine, breast, and uterine cancer.Interestingly, genes expressed in signaling pathways operative in age-associated diseases such as Huntington's disease (HD), dentatorubral-pallidoluysian atrophy (DRPLA), and amyotrophic lateral sclerosis (ALS) were also identified.These data demonstrate that skin and its appendages may represent an adequate model for aging research.Hormones interact in a complex fashion, and aging may be partly attributed to the changes in their circulating blood levels.Furthermore, a disturbed hormone status may partially act towards the manifestation of neurodegenerative diseases.Thus, these results could be a basis for an integrated and interdisciplinary approach to the analysis of the aging process.",
+      "\tTranslational\n\nA LTHOUGH there is much debate about the processes driving human aging, there is little doubt that genetic influences play a significant role (1).Humans clearly live very much longer than the currently favored laboratory models of aging, and such interspecies differences in reproductively 'fit' life span must have an inherited genetic foundation.Within human populations, environmental and behavioral exposures are important but at least a quarter of life expectancy variation in twin or family studies is attributable to inherited genetic or epigenetic factors (2).Age-related conditions such as type 2 diabetes, myocardial infarction, common cancers, and Alzheimer's disease (AD) typically have onsets after the fourth decade of life; \"successful\" agers delay these onsets until relatively late in life (3).Many aging traits and diseases show moderate heritability, including cardiovascular disease (CVD) (4) and impaired physical functioning (5), independent of known environmental risk factors.",
+      "\t\n\nMany factors contribute to aging, including genes.This is the first article in a 10-part series that highlight some of what is known about the influence of genes on aging and emerging treatment options that may slow down or potentially reverse the aging process.The series will address \\genes, adducts, and telomeres, decreased immune defenses, oxidation and inefficient mitochondria, toxins and radiation, glycosylation, caloric intake and sirtuin production, neurotransmitter imbalance, hormone mechanisms, reduced nitric oxide, and stem cell slowdown.Underpinning these factors are wear and tear on cells and aging as a result of inability to repair or replace these affected cells.These topics have been addressed in research, health magazines, and even by talk show hosts.There is even a LongevityMap website addressing significant and nonsignificant genetic association studies in aging across the human genome (http://genomics.senescence.info/longevity/).The series will address a scientific and clinical approach to genome-related aging topics.",
+      "\t[PubMed: 18208581]\n3. de Magalhes JP, Wuttke D, Wood SH, Plank M & Vora C Genome-environment interactions that\nmodulate aging: Powerful targets for drug discovery. Pharmacol. Rev. 64, 88101 (2012). [PubMed:\n22090473]\n4. McDaid AFet al.Bayesian association scan reveals loci associated with human lifespan and linked\nbiomarkers. Nat. Commun. 8, 15842 (2017). [PubMed: 28748955]\n5. Fontana L & Partridge L Promoting health and longevity through diet: From model organisms to\nhumans. Cell 161, 106118 (2015). [PubMed: 25815989]\n6.",
+      "\tGenAge: the aging gene database Philosophy and overview of resources\n\nIt is undisputed that genetic factors influence aging.In a remarkable series of recent breakthroughs, a number of genes capable of altering the aging process as a whole -or at least to a large degree -have been identified in animal models and even a few in humans (Finch & Ruvkun, 2001;de Magalhes, 2005;Kenyon, 2005).Furthermore, multiple alleles have been examined for their association with human exceptional longevity (Vijg & Suh, 2005).This is a fascinating and important area of research, yet there are now so many genes being associated with aging and longevity that keeping track of them all is becoming increasingly more difficult.Moreover, it is necessary now to study not only individual genes but their interactions with each other and with the environment, and how together genes give rise to a given phenotype: the so-called systems biology approach.To help researchers address these issues we created GenAge, a database of genes related to longevity and/or aging."
+    ],
+    [
+      "\tSenescence and apoptosis are thought to contribute\nto aging and age-related disorders by decreasing the proliferative potential of progenitor\nstem cells, altering tissue regenerative capacity, decreasing tissue function and by altered\ntissue architecture and microenvironment caused by altered gene expression and secretion of\ninflammatory cytokines, growth factors, and proteases (Campisi 2003; Coppe et al. 2008;\nGarfinkel et al. 1994; Krtolica and Campisi 2002; Kuilman et al. 2008; Novakova et al. 2010; Ohtani and Hara 2013).",
+      "\tIntroduction\n\nReplicative cellular senescence was first described as an irreversible growth arrest triggered by the accumulation of cell divisions (Hayflick & Moorhead, 1961).Subsequently it has emerged as a potent tumor suppression mechanism, and recent evidence points to important connections with aging (Collado et al., 2007;Baker et al., 2011).Progression of both cancer and aging includes a significant epigenetic component, such as changes in DNA methylation and chromatin remodeling (Decottignies & d'Adda di Fagagna, 2011).",
+      "\t\nAccumulation of senescent cells over time contributes to aging and age-related diseases.However, what drives senescence in vivo is not clear.Here we used a genetic approach to determine if spontaneous nuclear DNA damage is sufficient to initiate senescence in mammals.Ercc1 -/ mice with reduced expression of ERCC1-XPF endonuclease have impaired capacity to repair the nuclear genome.Ercc1 -/ mice accumulated spontaneous, oxidative DNA damage more rapidly than wild-type (WT) mice.As a consequence, senescent cells accumulated more rapidly in Ercc1 -/ mice compared to repair-competent animals.However, the levels of DNA damage and\t\n\nAccumulation of senescent cells over time contributes to aging and age-related diseases.However, what drives senescence in vivo is not clear.Here we used a genetic approach to determine if spontaneous nuclear DNA damage is sufficient to initiate senescence in mammals.Ercc1 -/ mice with reduced expression of ERCC1-XPF endonuclease have impaired capacity to repair the nuclear genome.Ercc1 -/ mice accumulated spontaneous, oxidative DNA damage more rapidly than wild-type (WT) mice.As a consequence, senescent cells accumulated more rapidly in Ercc1 -/ mice compared to repair-competent animals.However, the levels of DNA damage and",
+      "\t\n\nCellular senescence is one of the hallmarks of aging [87] and the accumulation of senescent cells in human tissues with age has been implicated as a driver of agingrelated diseases.Indeed, pharmacological approaches targeting senescent cells, like senolytics, are a major and timely area of research that could result in human clinical applications [5,88].It is imperative that we fully understand and deconstruct cellular senescence in order to target aging-related diseases.We hope that CellAge will help researchers understand the role that CS plays in aging and aging-related diseases and contributes to the development of drugs and strategies to ameliorate the detrimental effects of senescent cells.\tBackground\n\nIn the 1960s, Leonard Hayflick and Paul Moorhead demonstrated that human fibroblasts reached a stable proliferative growth arrest between their fortieth and sixtieth divisions [1].Such cells would enter an altered state of \"replicative senescence,\" subsisting in a nonproliferating, metabolically active phase with a distinct vacuolated morphology [2].This intrinsic form of senescence is driven by gradual replicative telomere erosion, eventually exposing an uncapped free double-stranded chromosome end and triggering a permanent DNA damage response [3,4].Additionally, acute premature senescence can occur as an antagonistic consequence of genomic, epigenomic, or proteomic damage, driven by oncogenic factors, oxidative stress, or radiation [5].Initially considered an evolutionary response to reduce mutation accrual and subsequent tumorigenesis, the pleiotropic nature of senescence has also been positively implicated in processes including embryogenesis [6,7], wound healing [8], and immune clearance [9,10].By contrast, the gradual accumulation and chronic persistence of senescent cells with time promotes deleterious effects that are considered to accelerate deterioration and hyperplasia in aging [11].Senescent cells secrete a cocktail of inflammatory and stromal regulators-denoted as the senescence-associated secretory phenotype, or SASP-which adversely impact neighboring cells, the surrounding extracellular matrix, and other structural components, resulting in chronic inflammation, the induction of senescence in healthy cells, and vulnerable tissue [12,13].Mice expressing transgenic INK-ATTAC, which induces apoptosis of p16-positive senescent cells, also have increased lifespan and improved healthspan [14].It is, therefore, no surprise that in recent years gerontology has heavily focused on the prevention or removal of senescent cells as a means to slow or stop aging and related pathologies [15][16][17].\t\n\nBackground: Cellular senescence, a permanent state of replicative arrest in otherwise proliferating cells, is a hallmark of aging and has been linked to aging-related diseases.Many genes play a role in cellular senescence, yet a comprehensive understanding of its pathways is still lacking.",
+      "\tJ\nAm Geriatr Soc 45: 482-8. Campisi J (2005). Senescent cells, tumor suppression, and organismal aging: good\ncitizens, bad neighbors. Cell 120: 513-22. Chambers SM, Boles NC, Lin KY, Tierney MP, Bowman TV, Bradfute SB et al (2007a). Hematopoietic Fingerprints: An Expression Database of Stem Cells and Their Progeny. Cell Stem Cell 1: 578-591. 128\nChambers SM, Shaw CA, Gatza C, Fisk CJ, Donehower LA, Goodell MA (2007b). Aging hematopoietic stem cells decline in function and exhibit epigenetic dysregulation. PLoS Biol 5: e201. Chen DJ, Nirodi CS (2007).\tMany stimuli\nhave been shown to induce the senescence response including, but not limited to,\ntelomere erosion, certain types of DNA damage, such as DNA breaks and oxidative\nlesions, epigenetic changes to chromatin organization, as well as exposure to ionizing\nirradiation (Campisi, 2005; Wang et al. , 2006). There is increasing evidence that\nsenescent cells accumulate with age. Senescence-associated -galactosidase, an enzyme\ncommonly used as a marker to detect the senescent phenotype, was shown to increase\nwith age in various mammalian tissues (Krtolica and Campisi, 2002).",
+      "\tDissecting the Role of Cellular Senescence\n\nAnother hallmark of the ageing process is the induction and accumulation of cells in a senescent state [2].Cellular senescence is characterised by a stable arrest of the cell cycle while maintaining viability and metabolic activity.Senescent cells are also known to activate what is known as the senescence-associated secretory phenotype (SASP), which is a plethora of secreted factors comprising pro-inflammatory cytokines, chemokines, growth factors and matrix remodelling enzymes [88,89].Beyond telomere attrition in the case of replicative senescence, cellular senescence can be induced by many other cellular stresses like oncogene activation, loss of tumour suppressors, oxidative stress, persistent DNA damage response, ionising radiation and cytotoxic chemicals [88,89].Cellular senescence is thought to primarily act as a potent cell-autonomous tumour-suppressive mechanism by preventing the expansion of pre-malignant cells.However, research over the past decade has revealed that cellular senescence is a pleiotropic phenotype that has many context-dependent paracrine effects mediated by the SASP, such as aiding in tissue regeneration or, paradoxically, promoting tumorigenesis and the acquisition of malignancy [88][89][90].",
+      "\t\n\nHow might apoptosis and senescence be antagonistically pleiotropic and contribute to aging?In the case of apoptosis, this process clearly is beneficial because it culls damaged or defective cells from tissues.However, it also eventually depletes tissues of cells and/or depletes stem cell reserves.In the case of senescence, this process is beneficial because it prevents the proliferation of preneoplastic, damaged or defective cells.However, senescent cells persist and adopt an altered phenotype in conjunction with the senescence growth arrest (Krtolica & Campisi, 2002;Rinehart & Torti, 1997).This phenotype includes the secretion of degradative enzymes, cytokines and growth factors that can perturb the surrounding tissue, leading to a loss of tissue homeostasis and development of age related pathologies.",
+      "\t\n\nSeveral representative applications merit an integrative genomics approach to aging.One application is to determine which molecular and cellular factors responsible for the process of cellular senescence also underlie functional cognitive decline.Cellular senescence is an anticancer and wound healing mechanism characterized by arrested cellular proliferation and secretion of pro-inflammatory cytokines, chemokines, growth factors, and proteases (the senescence associated secretory phenotype, or SASP).Senescent cells accumulate with age in many tissues, where the SASP promotes chronic inflammation and exacerbates age-associated degeneration and hyperplasia.Recent evidence suggests that neurological aging and neurodegeneration are accompanied by an accumulation of secretory cells in brain, suggesting that cellular senescence may contribute to brain aging [2] through a shared mechanism.Overlapping mechanisms can be detected using functional genomics studies of both the biology of cellular senescence and cognitive aging.",
+      "\t\n\nMarkers of senescence are detected at higher levels in tissues of older mice, humans, and other primates, including skin, liver, pancreatic islets, bone marrow, intestine, kidney, ovary, heart, and retina tissues.Senescent cells have altered metabolism (83).They also secrete proinflammatory factors and proteases able to alter the local tissue environment (84), providing plausible mechanisms by which senescent cells could promote aging and age-related degenerative diseases.Indeed, senescent cells are found at sites of numerous tissue-specific, age-related diseases, including atherosclerosis, osteoarthritis, sarcopenia, ulcer formation, cancer, and Alzheimer disease, which is suggestive of a causative role.However, the most convincing evidence that senescent cells cause aging comes from recent genetic (85) and pharmacologic studies (86) revealing that clearance of senescent cells can prevent or delay tissue dysfunction and extend health span.\t\n\nOf note, senescent cells accumulate with age in mammals (51).Compelling evidence shows that BER (47), NER (52), and NHEJ (53) are reduced in senescent cells relative to earlier passage nonsenescent cells.Thus, DNA repair may be reduced in a subset of cells that increase in number as an organism ages.Furthermore, genotoxic stress and ex vivo culture conditions induce senescence of cells, which impacts measurement of DNA repair.New tools to measure DNA repair in vivo are needed to determine if diminution of repair occurs in all cells and cell types as an organism ages.",
+      "\tCellAge--a database of cell senescence genes\n\nCell senescence, also known as cellular senescence (CS), is the irreversible cessation of cell division of normally prolif-erating cells.Senescent cells accumulate as an organism ages and may be an important contributor to ageing and agerelated disease (34).However, the connection between organismal ageing and CS remains controversial (35).CellAge (http://genomics.senescence.info/cells/) is a new database of CS-associated genes, built to elucidate mechanisms of CS and its role in ageing.It is described here for the first time.",
+      "\t\n\nInterestingly, when senescent cells are abolished either through genetic manipulation or via senolytic drugs, biological aging is significantly halted in mice [53,54].Therefore, trials are now under way to test the ability of senolytics to postpone age-associated pathologies in humans [55].Notably, multiple drugs are being pursued that either directly or indirectly impact DNA repair or the consequence of DNA damage.",
+      "\t\n\nIrreparably damaged cells may also enter senescence.Senescence occurs in response to various insults, including genotoxic (e.g., oxidative) stress, telomere erosion, and oncogenic and replicative stress, which often occur as a result of persistent DNA lesions (111).Cellular senescence is elevated in many accelerated-aging mouse models and in a plethora of human age-associated pathologies, including osteoporosis, atherosclerosis, glomerular disease, diabetic venous ulcers, chronic obstructive pulmonary disease and emphysema, osteoarthritis, herniated intervertebral discs, and vascular calcification (112).Senescent cells are resistant to apoptosis and accumulate exponentially with age as a consequence of inefficient clearance.Unlike apoptotic tissues, senescent tissues largely retain their function.Therefore, senescence is thought to be antagonistically pleiotropic: It is beneficial early in life during development and later in life during wound healing after injury, but it becomes deleterious late in life, as the tissue increasingly accumulates nondividing senescent cells, which disturb the tissue microenvironment (113).This disruption is primarily caused by the secretion of a range of proinflammatory cyto-and chemokines, a state that has been defined as the senescence-associated secretory phenotype (SASP) (103).Major SASP factors include IL1, IL6, IL8, and various matrix metalloproteases (MMPs), all of which individually are thought to drive aging and age-related diseases.Thus, DNA damage is a major determinant in controlling cell death, stem cell exhaustion, and cellular senescence, which are considered important events in the development of age-related pathology and aging.",
+      "\t\n\nAnother group of studies concentrated on a classic in vitro model for aging: the replicative senescence of primary cultured cells.The process of cellular senescence was first described in a seminal study by Hayflick and Moorhead (1961), who observed that normal human fibroblasts were able to enter a state of irreversible growth arrest after serial cultivation in vitro, while cancer cells were able to proliferate indefinitely.They proposed that there were some factors whose gradual loss through cell proliferation limited the number of cell divisions and that this process could contribute to organismal aging.It is still not completely clear how the latter might occur, but two main processes have been suggested: the accumulation of senescent cells in tissues and the limitation of regenerative potential of adult stem cell pools (Fraga et al., 2007).Wilson and Jones (1983) first showed how global DNA methylation also decreased with the number of cell passages in cultures of diploid fibroblasts of mice, hamsters and humans, while immortal cell lines had stable levels of methylation.The greatest loss of methylation was observed in mouse cells, which survived the fewest divisions, implying that the rate of methylation loss may be correlated with functional senescence.",
+      "\t\n\nSenescence primarily occurs in the G0/G1 phase of the cell cycle and is a vital tumor suppressive mechanism that prevents passing damaged DNA to daughter cells or potential neoplastic transformation of damaged cells [144,145].Since being first described by Leonard Hayflick as an in vitro phenomenon in human fibroblasts, the potential role of senescence in in vivo aging and disease has been difficult to assess and somewhat controversial [146].However, recent studies have shown that senescent cells accumulate in normal arterial tissue over the lifespan of humans [147,148].Likewise, the accumulation of senescent cells has been reported in diseased tissues, such as atherosclerotic plaques [149] and abdominal aortic aneurysms [150].Baker et al. showed that clearance of senescent cells reversed aged and diseased phenotypes in a mouse model of accelerated aging [151].This important study strongly suggested that there were phenotypic properties of senescent cells that were problematic to tissues, and potentially contribute to aging and chronic disease.",
+      "\tConcluding remarks and future perspectives\n\nAging research has rapidly expanded over the past two decades, with studies ranging from lifespan-extending  [68,69,71].However, when their effect on cell death and senescence leads to stem cell loss and tissue degeneration, they might contribute to aging [66,67]."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "C5BB60D5C5515AB310E870B4FC5C4CF9"
+    },
+    {
+      "task_id": "6B836AD417A7B5B70185949BC5CB9E7B"
+    },
+    {
+      "task_id": "70EBE57343443E5779A736414CEA2EF4"
+    },
+    {
+      "task_id": "3DD38AA2307344E3FD450E5C57A7C7BF"
+    },
+    {
+      "task_id": "5321131FE834527EC39E714C50359EF4"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_4.json
new file mode 100644
index 0000000..9bb53f4
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_aging_4.json
@@ -0,0 +1,105 @@
+{
+  "question": [
+    "Are there any known lifestyle interventions that can positively impact genes related to aging?",
+    "What is the 'epigenetic clock,' and how is it used in aging research?",
+    "How do researchers use model organisms like yeast or worms to study human aging?",
+    "Are there any promising anti-aging therapies being developed based on genetic research?",
+    "How do caloric restriction and diet impact the genetics of aging?"
+  ],
+  "answer": [
+    "Yes, there are several lifestyle interventions that can positively impact genes related to aging. These include mindful changes in behavior, environmental exposure, food/supplement use, weight loss, and regular exercise. A Mediterranean diet containing fruits, whole grains, fiber, antioxidants, soy protein, and healthy fats is also suggested to reduce DNA damage and protect telomeres, potentially increasing longevity.",
+    "The 'epigenetic clock' is a predictive tool that uses DNA methylation patterns at specific sites, known as CpG sites, to estimate biological age. It is used in aging research to predict the age of unknown samples, calculate",
+    "Researchers use model organisms like yeast or worms to study human aging due to their short lifespan and well-characterized genetic structures. These organisms allow for genome-wide studies and genetic manipulation to identify genes and pathways that influence lifespan. The findings can then be translated into mammalian models. The assumption is that if a gene or pathway modulates longevity in these simple organisms, it might have a similar function in more complex organisms like humans. This approach aids in the identification of potential therapeutic targets for age-associated diseases in humans.",
+    "Yes, there are promising anti-aging therapies being developed based on genetic research. These include nutritional supplements that target genes/pathways involved in aging, drugs that mimic the life-extension effects of caloric restriction, and multitarget drugs and combinatorial therapies developed through network approaches. Additionally, genomic methods are being used to identify biochemical pathways for increasing lifespan, which can then be targeted for pharmaceutical development.",
+    "Caloric restriction (CR) has been shown to extend lifespan and reduce the incidence of age-related diseases and tumors in mammals. It also delays the onset of many features of aging, including age-related diseases. CR increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes, which directly intervenes in the repair of DNA damage. It also impacts metabolism, particularly the insulin/insulin-like growth factor 1 (IGF-1) pathways. Many genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development. Therefore, understanding these pathways could lead to potential therapeutic applications for age-related diseases."
+  ],
+  "contexts": [
+    [
+      "\t\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.\t\n\nGenomic analysis of longevity offers the potential to illuminate the biology of human aging.Here, using genome-wide association meta-analysis of 606,059 parents' survival, we discover two regions associated with longevity (HLA-DQA1/DRB1 and LPA).We also validate previous suggestions that APOE, CHRNA3/5, CDKN2A/B, SH2B3 and FOXO3A influence longevity.Next we show that giving up smoking, educational attainment, openness to new experience and high-density lipoprotein (HDL) cholesterol levels are most positively genetically correlated with lifespan while susceptibility to coronary artery disease (CAD), cigarettes smoked per day, lung cancer, insulin resistance and body fat are most negatively correlated.We suggest that the effect of education on lifespan is principally mediated through smoking while the effect of obesity appears to act via CAD.Using instrumental variables, we suggest that an increase of one body mass index unit reduces lifespan by 7 months while 1 year of education adds 11 months to expected lifespan.",
+      "\t\n\nStudies revealed from 300 to 750 genes related to longevity that are critically involved in a variety of life activities, such as growth and development, energy metabolism, oxidative stress, genomic stability maintenance, and neurocognition [4].These candidate genes include mainly APOE, a gene involved in lipoprotein metabolism [5,6].Others are those involved in cell cycle regulation, cell growth and signal transduction, the maintenance of genome stability, and the endocrine-related pathway [7][8][9].In addition, the candidates for longevity encompass genes related to drug metabolism, the ones involved in protein folding, stabilization, and degradation, as well those related to coagulation and regulation of circulation [10], etc.In most cases, these genes or their polymorphic sites were examined in multiple population replication studies, which discovered certain longevity-associated genes or pathways [4][5][6][7][8][9][10].",
+      "\t\nStudies of the basic biology of aging have identified several genetic and pharmacological interventions that appear to modulate the rate of aging in laboratory model organisms, but a barrier to further progress has been the challenge of moving beyond these laboratory discoveries to impact health and quality of life for people.The domestic dog, Canis familiaris, offers a unique opportunity for surmounting this barrier in the near future.In particular, companion dogs share our environment and play an important role in improving the quality of life for millions of people.Here, we present a rationale for increasing the role of companion dogs as an animal model for both basic and clinical geroscience and describe complementary approaches and ongoing projects aimed at achieving this goal.",
+      "\t\n\nAdditional association studies with these families and replication of these results with an independent data set should facilitate the positional cloning of a gene that influences the ability to age well and achieve exceptional longevity.Identification of the genes in humans that allow certain individuals to live to extreme old age should lead to insights on cellular pathways that are important to the aging process.",
+      "\t\n\nsmall number of genes or interventions are known to increase life span in different model organisms.A selection of these are shown here.\t\n\nThe most direct method to address how well the features that determine longevity have been conserved is to identify genes or interventions that function similarly to modulate life span in different organisms.Components of insulin/IGF-1like signaling pathway, the sirtuin family of protein deacetylases, and the nutrient-responsive TOR kinase, among others, have been found to have this property (Table 1).Until recently, however, the genetic analysis of longevity was largely limited to mutagenesis screens for secondary phenotypes (such as stress resistance) or targeted studies of specific *Address correspondence to this author at the Department of Pathology, University of Washington, Seattle, WA 98195, USA; Tel: 206-543-4849; Fax: 206-543-3644; E-mail: kaeber@u.washington.edugenes, based on prior knowledge.While many important insights were gained from such studies, they, by necessity, self-selected for mutants with specific properties that are (at best) secondarily related to longevity.Thus, it remains unclear to what degree the pathways regulating longevity are evolutionarily conserved and whether the known longevity genes represent most of the important players or only a small fraction.\t\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.\t\n\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.",
+      "\tIntroduction\n\nThe recent, remarkable extension of life expectancy is largely attributed to the postponement of mortality at old age (Vaupel, 1997(Vaupel, , 2010)).The years of life gained in the older population residing in developed nations are a success story of public health measures and improved health care.In addition to such external factors, longevity and healthy aging consistently show a modest heritability between 20% and 50% and aging-associated genetic research may provide further insights into the mechanisms of aging (Herskind et al., 1996;McGue et al., 1993;Reed and Dick, 2003).It has been postulated that genes involved in pathways associated with aging identified in animal models, such as insulin-like growth factor (IGF)-insulin signaling, regulation of lipoprotein metabolism, the mTOR pathway, and the oxidative stress response may also influence survival to old or even exceptionally old age in humans (Christensen et al., 2006;Kenyon, 2010;Vellai et al., 2003).However, in humans, common variants within genes involved in these pathways have not been consistently associated with lifespan (Chris-tensen et al., 2006;Kenyon, 2010;Kuningas et al., 2008;Vijg and Suh, 2005).",
+      "\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\t\n\nEven if sirtuins and resveratrol do not live up to their expectations, this research is pioneering in terms of genome-environment interactions and nutritional manipulations of aging.These studies also show the path from basic discovery on the biology of aging to potential antiaging and pharmacological interventions and can therefore be applied to other genes and pathways.The lessons learned from the pitfalls of SIRT1 and resveratrol research can also help others to translate basic research on the biology of aging to the clinic, such as avoiding the use of short-lived rodent strains (e.g., by using unhealthy diets), which may lead to findings that only apply to a subset of individuals.\t\n\nThe remarkable discoveries of the past 2 decades showing that single genes can regulate aging in model organisms demonstrate that aging can be genetically manipulated (Finch and Ruvkun, 2001;Kenyon, 2010).Hundreds of genes that modulate longevity have now been identified in model organisms (de Magalha es et al., 2009a).In some cases (e.g., in worms), mutations in single genes can extend lifespan by almost 10-fold (Ayyadevara et al., 2008).Nonetheless, aging is a complex process that derives not from single genes but from the interactions of multiple genes with each other and with the environment.Evidence from animal systems shows a major impact of the environment on aging, yet environmental manipulations of aging act through genes and proteins, usually by triggering signaling pathways and modulating gene expression.In fact, some genes have been shown in model organisms to have varying effects on lifespan depending on diet (Heikkinen et al., 2009).Genes that can regulate aging in model organisms cannot be directly applied to humans through genetic manipulations for numerous legal, ethical, and technical reasons.If we could understand how the environment modulates these aging-related genes, we might be able to create antiaging therapies applicable to humans, potentially through diet, lifestyle, and even pharmacological interventions.Therefore, understanding genome-environment interactions in the context of aging can be a powerful approach to identify attractive targets for drug design.",
+      "\tINTRODUCTION\n\nGenomic studies into human longevity are inspired by the fact that, in animal models, healthy lifespan has proved to be remarkably plastic, and major pathways of lifespan regulation have been identified.Considerable lifespan extension has been induced in models as diverse as yeast, worms, fish, flies and rodents by applying genetic manipulation and dietary restriction (DR) (see [1] for review).Reduced activity of nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling (IIS) and target of rapamycin (TOR) signalling mediated lifespan extension, and also the extension of lifespan by DR [2].An interesting observation from the perspective of human ageing is that, in rodents and monkeys, diets restricted in glucose, fat or protein uptake reduced or delayed the risk of cancer and metabolic disease, thus extending the healthspan of the animals [2].Following the discovery of genes and pathways involved in animal lifespan extension, human research has focused on the corresponding candidate human genes with genetic, genomic and epigenetic studies into ageing and longevity.The designs of these studies differ with respect to the selection of naturally occurring phenotypes and the study populations, which include population-based, patient-based, family-based and exposure-based cohorts.\t\nIn animal models, single-gene mutations in genes involved in insulin/IGF and target of rapamycin signalling pathways extend lifespan to a considerable extent.The genetic, genomic and epigenetic influences on human longevity are expected to be much more complex.Strikingly however, beneficial metabolic and cellular features of long-lived families resemble those in animals for whom the lifespan is extended by applying genetic manipulation and, especially, dietary restriction.Candidate gene studies in humans support the notion that human orthologues from longevity genes identified in lower species do contribute to longevity but that the influence of the genetic variants involved is small.Here we discuss how an integration of novel study designs, labour-intensive biobanking, deep phenotyping and genomic research may provide insights into the mechanisms that drive human longevity and healthy ageing, beyond the associations usually provided by molecular and genetic epidemiology.Although prospective studies of humans from the cradle to the grave have never been performed, it is feasible to extract life histories from different cohorts jointly covering the molecular changes that occur with age from early development all the way up to the age at death.By the integration of research in different study cohorts, and with research in animal models, biological research into human longevity is thus making considerable progress.\t\n\nIn animal models, single-gene mutations in genes involved in insulin/IGF and target of rapamycin signalling pathways extend lifespan to a considerable extent.The genetic, genomic and epigenetic influences on human longevity are expected to be much more complex.Strikingly however, beneficial metabolic and cellular features of long-lived families resemble those in animals for whom the lifespan is extended by applying genetic manipulation and, especially, dietary restriction.Candidate gene studies in humans support the notion that human orthologues from longevity genes identified in lower species do contribute to longevity but that the influence of the genetic variants involved is small.Here we discuss how an integration of novel study designs, labour-intensive biobanking, deep phenotyping and genomic research may provide insights into the mechanisms that drive human longevity and healthy ageing, beyond the associations usually provided by molecular and genetic epidemiology.Although prospective studies of humans from the cradle to the grave have never been performed, it is feasible to extract life histories from different cohorts jointly covering the molecular changes that occur with age from early development all the way up to the age at death.By the integration of research in different study cohorts, and with research in animal models, biological research into human longevity is thus making considerable progress.",
+      "\tRelevance to nurse practitioner practice\n\nCurrently, there is no cure for genetic variants associated with rapid aging, but novel agents that may slow down the aging process are being tested.The authors of this article advocate individual participation in association studies of aging and pharmacologic risk mitigation or reversal of symptoms for those with known genetic disease risk.Direct to consumer epigenetic biological aging tests and telomere length tests are available; but they are not approved by the Food and Drug Administration.Health care providers may want to consider the simple but key clinical and personal changes, suggested above, to enhance DNA health, wellness, and longevity.Simple mindful changes in behavior, environmental exposure, food/supplement use, weight loss, and regular exercise can reduce adduct exposure damage and impact telomere length, potentially increasing longevity.A Mediterranean diet containing fruits and whole grains along with fiber, antioxidants, soy protein, and healthy fats (from avocados, fish, flax, and walnuts) is suggested to reduce DNA adducts and protect telomeres.In light of our current pandemic, focus on population health, and restrictions to health care access, especially in rural communities, health care providers could incorporate these lifestyle and dietary principles in telehealth visits with patients to reduce disease risk and optimize healthy aging.",
+      "\t[PubMed: 18208581]\n3. de Magalhes JP, Wuttke D, Wood SH, Plank M & Vora C Genome-environment interactions that\nmodulate aging: Powerful targets for drug discovery. Pharmacol. Rev. 64, 88101 (2012). [PubMed:\n22090473]\n4. McDaid AFet al.Bayesian association scan reveals loci associated with human lifespan and linked\nbiomarkers. Nat. Commun. 8, 15842 (2017). [PubMed: 28748955]\n5. Fontana L & Partridge L Promoting health and longevity through diet: From model organisms to\nhumans. Cell 161, 106118 (2015). [PubMed: 25815989]\n6.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\t\n\nWith modern genomic technologies and largescale data analysis methods, it is possible to sift through the genes of populations to find the loci that act to postpone aging. [3]There are uncertainties with the comparison of populations with different rates of aging.However, it is superior to experimental designs that only consider age-dependence or dietary-response, without determining causal mechanisms."
+    ],
+    [
+      "\t\n\nThe first generation of epigenetic aging clocks used penalized regression models to predict chronological age on the basis of DNA methylation data, e.g., the widely used clocks from Hannum (2013) and Horvath (2013) apply to blood and 51 human tissues/ cell types, respectively [12][13][14].A derivative of the Horvath clock, intrinsic epigenetic age acceleration (IEAA) has since been developed, conditioning out (i.e., removing) estimates of blood cell composition.An increasing literature supports the view that IEAA relates to properties of hematopoietic stem cells [2,8,15].The second generation of epigenetic clocks move beyond estimating chronological age by incorporating information on morbidity and mortality risk (e.g., smoking, plasma protein levels, white blood cell counts), and chronological age.Two such predictors, termed PhenoAge (a DNAm predictor trained on a measure that itself was trained on mortality, using 42 clinical measures and age as input features) and GrimAge (trained on mortality, including a DNAm measure of smoking as a constituent part), outperform both Hannum and Horvath clocks in predicting mortality and are associated with various measures of morbidity and lifestyle factors [16,17].DNAm GrimAge outperforms PhenoAge and the first generation of epigenetic clocks when it comes to predicting time to death [8,18,19].\t\nBackground: Biological aging estimators derived from DNA methylation data are heritable and correlate with morbidity and mortality.Consequently, identification of genetic and environmental contributors to the variation in these measures in populations has become a major goal in the field.Results: Leveraging DNA methylation and SNP data from more than 40,000 individuals, we identify 137 genome-wide significant loci, of which 113 are novel, from genome-wide association study (GWAS) meta-analyses of four epigenetic clocks and epigenetic surrogate markers for granulocyte proportions and plasminogen activator inhibitor 1 levels, respectively.We find evidence for shared genetic loci associated with the Horvath clock and expression of transcripts encoding genes linked to lipid metabolism and immune function.Notably, these loci are independent of those reported to regulate DNA methylation levels at constituent clock CpGs.A polygenic score for GrimAge acceleration showed strong associations with adiposityrelated traits, educational attainment, parental longevity, and C-reactive protein levels.Conclusion: This study illuminates the genetic architecture underlying epigenetic aging and its shared genetic contributions with lifestyle factors and longevity.",
+      "\tDiscussion\n\nWe developed precise epigenetic clocks (ABEC and eABEC) using blood-based DNAm data from EPIC.Our epigenetic clocks showed a more precise chronological age prediction than existing blood-based epigenetic clocks (e.g., the Hannum Blood-based clock and Horvath Skin & Blood clock; Fig. 5).The reason for the higher precision is more likely due to the large training set (n = 2227, Table 1) and the wide age-span of the samples (19 to 88 years for the training set of eABEC, Table 1), which is consistent with the findings by Zhang and colleagues [34].Compared to eABEC, both Hannum Blood-  [3,19].Other clocks (the Horvath Pan-tissue clock and Levine PhenoAge clock) may not be directly comparable to eABEC for chronological age prediction.For instance, the Horvath Pan-tissue clock was designed to measure epigenetic aging not only in blood but in multiple tissues [20], and the Levine Pheno-Age was designed to predict phenotypic age (estimated using 10 clinical biomarkers, e.g., albumin, creatinine, serum glucose, and seven others) based on DNAm [16].",
+      "\tAn Epigenetic Clock\n\nThe aging transcriptome could be used to gauge the physiological age of worms, and in that way serve as an epigenetic clock revealing how much of life span has been spent and how much remains (23).Middle-aged worms show an aging transcriptome half-way between the aging expression profiles of young and old worms.This provides an independent way to assess the age of an animal independent of its life span.This is important as there are at least 2 explanations to account for increased life span due to a longevity mutation.One is that the mutation slows down the process of aging so that worms die at the same physiological age, but that it takes worms longer to reach old age.According to this possibility, the aging transcriptome of a longevity mutant at 2 weeks might resemble the aging transcriptome of wild-type worms at 1 week of age.Another is that the longevity mutant allows the worm to survive damage accumulation in old age, so that the worms age at a normal rate but they avoid death until succumbing at a later time.For instance, improved health care increases life span by enabling people to avoid disease and live longer, not by aging slower.In this scenario, the rate of aging in the longevity mutant and wild-type worms at 2 weeks could be similar, but with higher survivability in the longevity mutant due to an ability to better withstand damage accumulation.",
+      "\tEpigenetic Clock\n\nChronological age is the number of years a person has lived, and biological or physiological age refers to a measure of how well your body functions compared to your chronological age.Biological age is influenced by multiple factors (genes, lifestyle, behavior, environment, among others) and correlates with mortality and health status.The epigenetic clock is one potentially reliable predictor of biological age.\t\n\nA recent study conducted in the Dunedin cohort [73] combined measurements of telomere lengths, epigenetic clocks and composite biomarkers and compared them to clinically relevant outcomes, such as health status, physical function, cognitive decline, and personal signs of ageing.The 71-cytosine-phosphate-guanine epigenetic clock and biomarker composites were consistently related to these outcomes.In another study, neural networks were applied to predict an age by using measurements from necessary blood tests, such as albumin, glucose, alkaline phosphatase, urea, and erythrocytes [74].",
+      "\tThe changing ticking rate of the epigenetic clock\n\nThe linear combination of the 353 clock CpGs (resulting from the regression coefficients) varies greatly across ages as can be seen from Figure 6B,C.The red calibration curve (formula in Additional file 2) reveals a logarithmic dependence until adulthood that slows to a linear dependence later in life (Figure 6B).I interpret the rate of change (of this red curve) as the ticking rate of the epigenetic clock.Using this terminology, I find that organismal growth (and concomitant cell division) leads to a high ticking rate that slows down to a constant ticking rate (linear dependence) after adulthood.",
+      "\tBackground\n\nRecently, a great deal of work has been performed in an effort to understand the nature of aging, the mechanisms that drive the process, and the biomarkers that may be predictive of, or affected by, age.In this effort, a seminal manuscript was published in 2013 which described the ability to use DNA methylation signatures in somatic tissues to predict an individual's chronological age [1].In this work, Dr. Horvath demonstrated that the epigenetic mechanisms that reflect the aging process are tightly conserved between individual tissues and across multiple species.Remarkably, these patterns are sufficiently consistent to enable accurate age prediction with Horvath's age calculator despite the significant contrast in epigenetic profiles between various somatic tissues.",
+      "\tRelationship to mortality prediction\n\nAlthough the epigenetic clock method was only published in 2013, there is already a rich body of literature that shows that it relates to biological age.Using four human cohort studies, we previously demonstrated that both the Horvath and Hannum epigenetic clocks are predictive of all-cause mortality [23].Published results in Marioni et al. [23] show that DNAm age adjusted for blood cell counts (i.e.IEAA) is prognostic of mortality in four cohort studies.We recently expanded our original analysis by analyzing 13 different cohorts (including three racial/ethnic groups) and by evaluating the prognostic utility of both IEAA and EEAA.All considered measures of epigenetic age acceleration were predictive of age at death in univariate Cox models (p AgeAccel = 1.9  10 -11 , p IEAA = 8.2  10 -9 , p EEAA = 7.5  10 -43 ) and multivariate Cox models adjusting for risk factors and pre-existing disease status (p AgeAccel = 5.4  10 -5 , p IEAA = 5.0  10 -4 , p EEAA = 3.4  10 -19 ) where the latter adjusted for chronological age, body mass index, education, alcohol, smoking pack years, recreational physical activity, and prior history of disease (diabetes, cancer, hypertension).These results will be published elsewhere.Further, the offspring of centenarians age more slowly than age matched controls according to Age Accel and IEAA [26] which strongly suggests that these measures relate to heritable components of biological age.Two independent research groups have shown that epigenetic age acceleration predicts mortality [24,25].\t\n\nWe addressed this concern in multiple ways.First, we re-analyzed the WHI data by removing the 47 CpGs (out of 353 epigenetic clock CpGs) from the analysis.The epigenetic clock software imputes the 47 missing CpGs using a constant value (the mean value observed in the original training set).Using the resulting modified epigenetic clock, we validate our findings of racial/ethnic differences in terms of IEAA and EEAA (Additional file 8A-C).However, this type of robustness analysis is limited because the removal of a subset of DNA methylation probes, potentially influenced by proximal genetic variation, is not as good a control as directly having matched genetic data.Second, we used a completely independent epigenetic biomarker based on a published signature of age-related CpGs from Teschendorff et al. [13].Again, these results corroborate our findings (Additional file 8D, E).Third, we validated our findings using the original blood-based aging measure by Hannum [19] (Additional file 8F, G).Fourth, we highlight that both the Horvath and Hannum age estimators were developed based on training data from mixed populations.The training data underlying the Horvath clock involved four racial/ethnic groups (mainly Caucasians, Hispanics, African Americans, and to a lesser extent East Asians).The Hannum clock was trained on Caucasians and Hispanics.While race/ethnicity can lead to a significant offset between DNAm age and chronological age (which is interpreted as age acceleration), these two variables are highly correlated in all racial/ethnic groups.\t\n\nThe following evidence shows that the epigenetic clock captures aspects of biological age.First, the epigenetic age of blood has been found to be predictive of all-cause mortality even after adjusting for chronological age and a variety of known risk factors [23][24][25].Second, the blood of the offspring of Italian semi-supercentenarians (i.e.participants who reached an age of at least 105 years) has a lower epigenetic age than that of age-matched controls [26].Third, the epigenetic age of blood relates to frailty [27] and cognitive/physical fitness in the elderly [28].The utility of the epigenetic clock method has been demonstrated in applications surrounding obesity [29], Down's syndrome [30], HIV infection [31], Parkinson's disease [32], Alzheimer's disease-related neuropathologies [33], lung cancer [34], and lifetime stress [35].Here, we apply the epigenetic clock to explore relationships between epigenetic age and race/ethnicity, sex, risk factors of coronary heart disease (CHD), and the CHD outcome itself.",
+      "\t\n\nConclusions: This study indicates that the epigenetic clock can be improved by increasing the training sample size and that its association with mortality attenuates with increased prediction of chronological age.",
+      "\tBackground:\n\nThe Horvath epigenetic clock is widely used.It predicts age quite well from 353 CpG sites in the DNA methylation profile in unknown samples and has been used to calculate \"age acceleration\" in various tissues and environments.\t\nBackground:The Horvath epigenetic clock is widely used.It predicts age quite well from 353 CpG sites in the DNA methylation profile in unknown samples and has been used to calculate \"age acceleration\" in various tissues and environments.Results: The model systematically underestimates age in tissues from older people.This is seen in all examined tissues but most strongly in the cerebellum and is consistently observed in multiple datasets.Age acceleration is thus agedependent, and this can lead to spurious associations.The current literature includes examples of association tests with age acceleration calculated in a wide variety of ways. Conclusions:The concept of an epigenetic clock is compelling, but caution should be taken in interpreting associations with age acceleration.Association tests of age acceleration should include age as a covariate.\tDiscussion\n\nThe Horvath epigenetic clock [8] has been of practical use in predicting the age of unknown samples and as a quality check in epigenetic research.Additional widely used age predictors specific for blood were published by Hannum [6] and Levine [42] (phenotype-based).Here we analyze the Horvath model, but the methods and many of the conclusions may be more widely applicable, in particular the Hannum clock model shows a similar underestimation of ages in elderly subjects.\t\n\nIn addition to age prediction, the Horvath [8] paper also featured the idea of \"age acceleration\" in which discrepancies between DNA methylation (DNAm) age and chronological age might tell us something about the biological aging status of the organism.A number of positive association findings with age association, particularly mortality [43], make it compelling to think of the epigenetic clock as an index of an underlying aging program that adapts to health and environment.In light of the methodological variety though, we are concerned that the different epigenetic clocks, and the variety of age acceleration methods to choose from, lay a trap of potentially hidden multiple testing, as the temptation will be to survey the available methods for interesting results.\tConclusions:\n\nThe concept of an epigenetic clock is compelling, but caution should be taken in interpreting associations with age acceleration.Association tests of age acceleration should include age as a covariate.",
+      "\tEpigenetic clocks\n\nFour epigenetic clocks were studied: the blood clock developed by Hannum et al. (Hannum Bld) [2], the multi-tissue clock developed by Horvath (Horvath MT) [3], the skin/ blood clock developed by Horvath et al. (Horvath Skn/Bld) [4], and the blood/saliva clock developed by Zhang et al. (Zhang Bld/Slv) [5].These clocks are described in Table 1.Together, the four epigenetic clocks comprised 1147 unique CpGs.One CpG from Horvath Skn/Bld (cg14614643) did not pass QC in our DNAm data and was therefore excluded from our analyses (i.e., 1146 CpGs were included).The four epigenetic clocks were used to predict chronological age in all 3132 samples for which methylome data were available.To this end, the coefficients of all clock CpGs were downloaded (available in their respective publications [2][3][4][5]).Beta-values of the clock CpGs were used as input for all clocks.For Horvath MT and Horvath Skn/Bld, predicted ages were transformed according to the authors' instructions [3,4].For Zhang Bld/Slv, DNAm values were normalized according to the authors' instructions, so that all samples had a mean of 0 and a standard deviation of 1 across all 450K CpGs [5].\tEpigenetic clocks accurately predict chronological age and show high similarity\n\nOur analyses were performed on whole blood samples from 3132 unrelated individuals, aged 18 to 87, originating from 6 Dutch cohorts (Table 2), for which both DNAm data and gene expression data were obtained, measured by Illumina 450K arrays and RNAseq, respectively.Only samples for which both DNAm and gene expression data passed QC were analyzed.First, we applied 4 epigenetic clocks (Table 1) to the DNAm data to predict age.All clocks accurately predicted age in our data.The Pearson correlation (r) between chronological age and predicted age was greater than 0.90 for all clocks, but there were differences in the prediction errors (Fig. 1A).Hannum Bld and Horvath MT showed the highest age prediction error (mean absolute error (MAE) = 4.5 years), followed by Horvath Skn/Bld (MAE = 3.1 years), and the prediction error was lowest for Zhang Bld/Slv (MAE = 2.7 years).We found that the errors in age prediction of the epigenetic clocks were highly correlated between clocks, with the pairwise correlation coefficients ranging from 0.57 to 0.79 (Fig. 1B).Thus, a person whose predicted age exceeds their chronological age according to one clock was likely to have a similar deviation according to another clock.However, this was not the case for extreme differences between predicted and chronological age, which were generally not reproduced between clocks (Additional file 1: Fig. S1A-B).For example, of the individuals for whom the prediction error of Hannum Bld was 10 years or higher, 32% had a prediction error above 10 years according to Horvath MT, and only 4% according to Zhang Bld/Slv (Additional file 1: Fig. S1A-B, top row).However, the individuals marked as extreme by Zhang Bld/Slv were more consistent with the other clocks, with up to 91% overlap (Additional file 1: Fig. S1A-B, bottom row).These findings indicate that extreme deviations between chronological and predicted age should be interpreted with caution.\tConclusions\n\nThe ability of epigenetic clocks to predict chronological age involves their ability to detect changes in proportions of naive and activated immune blood cells.This finding may contribute to the interpretation of associations between clock-derived measures and age-related health outcomes."
+    ],
+    [
+      "\t\nYeast is a useful model organism to study the genetic and biochemical mechanisms of aging.Genomic studies of aging in yeast have been limited, however, by traditional methodologies that require a large investment of labor and resources.In this chapter, we describe a newly-developed method for quantitatively measuring the chronological life span of each strain contained in the yeast ORF deletion collection.Our approach involves determining population survival by monitoring outgrowth kinetics using a Bioscreen C MBR shaker/incubator/plate reader.This method has accuracy comparable to traditional assays, while allowing for higher throughput and decreased variability in measurement.\t\n\nYeast is a useful model organism to study the genetic and biochemical mechanisms of aging.Genomic studies of aging in yeast have been limited, however, by traditional methodologies that require a large investment of labor and resources.In this chapter, we describe a newly-developed method for quantitatively measuring the chronological life span of each strain contained in the yeast ORF deletion collection.Our approach involves determining population survival by monitoring outgrowth kinetics using a Bioscreen C MBR shaker/incubator/plate reader.This method has accuracy comparable to traditional assays, while allowing for higher throughput and decreased variability in measurement.",
+      "\t\nThe genetic analysis of life span has only begun in mammals, invertebrates, such as Caenorhabditis elegans and Drosophila, and yeast.Even at this primitive stage of the genetic analysis of aging, the physiological observations that rate of metabolism is intimately tied to life span is supported.In many examples from mice to worms to flies to yeast, genetic variants that affect life span also modify metabolism.Insulin signaling regulates life span coordinately with reproduction, metabolism, and free radical protective gene regulation in C. elegans.This may be related to the findings that caloric restriction also regulates mammalian aging, perhaps via the modulation of insulin-like signaling pathways.The nervous system has been implicated as a key tissue where insulin-like signaling and free radical protective pathways regulate life span in C. elegans and Drosophila.Genes that determine the life span could act in neuroendocrine cells in diverse animals.The involvement of insulin-like hormones suggests that the plasticity in life spans evident in animal phylogeny may be due to variation in the timing of release of hormones that control vitality and mortality as well as variation in the response to those hormones.Pedigree analysis of human aging may reveal variations in the orthologs of the insulin pathway genes and coupled pathways that regulate invertebrate aging.Thus, genetic approaches may identify a set of circuits that was established in ancestral metazoans to regulate their longevity.",
+      "\tIntroduction\n\nThe budding yeast Saccharomyces cerevisiae has been used as a model of cellular aging for more than 6 decades (Fabrizio and Longo 2007;Jazwinski 2005;Kaeberlein et al. 2007;Steinkraus et al. 2008).S. cerevisiae has several features that make it useful as a model organism for aging research, including short life span, well-characterized genetic and molecular methods, low relative cost, cell type homogeneity, and a vast organismal information base.These advantages have facilitated unbiased screens for genes that influence life span in yeast, as well as candidate gene approaches.Several dozen genetic determinants of yeast longevity have been identified from these studies, at least some of which appear to play a conserved role in the aging of multicellular eukaryotes.\t\n\nSince these early morphology-based studies, yeast replicative aging has become a prominent model for aging genetics and has been instrumental in the discovery and characterization of several of the best studied genetic pathways involved in life span determination.These pathways include dietary restriction (DR), sirtuins, TOR signaling, and mitochondrial metabolism (Table 12.1).\t\nIn the past several decades the budding yeast Saccharomyces cerevisiae has emerged as a prominent model for aging research.The creation of a single-gene deletion collection covering the majority of open reading frames in the yeast genome and advances in genomic technologies have opened yeast research to genome-scale screens for a variety of phenotypes.A number of screens have been performed looking for genes that modify secondary age-associated phenotypes such as stress resistance or growth rate.More recently, moderate-throughput methods for measuring replicative life span and high-throughput methods for measuring chronological life span have allowed for the first unbiased screens aimed at directly identifying genes involved in determining yeast longevity.In this chapter we discuss large-scale life span studies performed in yeast and their implications for research related to the basic biology of aging.",
+      "\t\n\nThe use of humans in aging studies is complicated due to several factors, including ethical, environmental, and social issues, and even economic reasons, and more importantly, due to the human long natural life span.The human aging process takes decades to develop, making it virtually impossible to perform longitudinal studies by following subjects throughout their lives.Thus, the most widely employed models of aging are short-lived organisms, including yeast, roundworm, fruit fly, and mice.Indeed, large-scale genetic screenings have identified numerous genes and drugs that significantly lengthen life span in these organisms; however, the biological relevance of such longevity genes to human aging remains not fully established [3].\tIntroduction\n\nResearch into the underlying mechanisms of organismal ageing has advanced at a tremendous rate over the past decade.Studying the ageing process presents a significant challenge as it is a systemic phenomenon that affects numerous organs and tissue systems in humans.Due to the complex nature of the ageing process, it has been most extensively modelled using short-lived non-vertebrate systems such as nematode worms (C.elegans), yeast (C.cerevisiae) and flies (D. melanogaster), as well as longer-lived vertebrate models, such as the mouse (M.musculus) and zebrafish (D. rerio) [1].Importantly, research using these model organisms alongside both traditional and novel genetic manipulation techniques has delineated nine hallmarks of ageing that are common across various species, including humans [2].Tremendous effort is now being expended into understanding the relationship between these different hallmarks and how their interactions impact on the ageing process.This has created a constant necessity for studying multiple interactions between complex genetic pathways, sometimes under the influence of fluctuating factors, such as epigenetic mechanisms, and especially in vertebrate models where traditional genetic engineering techniques are less efficient or involve higher costs due to longer lifespans (the maximal lifespan of mice is around 3-4 years and 5 years for zebrafish).It has therefore become of great interest for the ageing research community to develop new in vivo and in vitro genetically engineered models capable of addressing complex research questions in a time-cost efficient manner.",
+      "\tCONCLUSION\n\nOur understanding of the basic mechanisms of aging have benefited greatly from the use of simple model systems such as yeast and worms.The development of technologies that allow direct analysis of longevity on a genome-wide scale in these organisms has provided a wealth of new data regarding the genes and pathways that modulate longevity.Some of these genes and pathways are specific to each organism; however, others appear to be evolutionarily conserved.Future efforts will move toward translating the data from genomic longevity studies in yeast and worms into mammalian models.Any gene that functions similarly to modulate longevity and disease in yeast, worms, and mice will be an outstanding candidate for therapeutic intervention targeting age-associated diseases in people.\t\n\nGenomic comparisons of longevity across species also provide an opportunity to identify novel factors that modulate aging and age-associated disease in humans.The evolutionary distance between yeast and worms is approximately equivalent to the evolutionary distance between worm and humans.Therefore, if an ortholog pair has maintained a conserved longevity determining function between yeast and worms, it is reasonable to speculate that the function will also be retained in mammals.At lease one effort is underway to directly test this assumption (http://www.pathology.washington.edu/research/bioage/ellison/).A consortium of laboratories at the University of Washington is utilizing the data from the genome-wide yeast and worm longevity screens described above to identify candidate genes for longevity studies as gene knock-outs in mice [1].A CRE-based conditional knock-out system is being employed for these studies, to allow either complete knock-out of a particular gene or tissue specific (or post-development) gene deletion.Along with longevity, a select group of potential agingrelated biomarkers will be assayed for each of these mouse models.In addition, it should be possible to assay several of these mouse lines for resistance to specific age-associated diseases, such as diabetes and neurological disorders, by crossing them into the appropriate transgenic disease background.\t\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.\t\n\nUnbiased genome-wide studies of longevity in S. cerevisiae and C. elegans have led to the identification of more than one hundred genes that determine life span in one or both organisms.Key pathways have been uncovered linking nutrient and growth factor cues to longevity.Quantitative measures of the degree to which aging is evolutionary conserved are now possible.A major challenge for the future is determining which of these genes play a similar role in human aging and using that information to develop therapies toward age-associated diseases.\t\n\nWhen considering the use of simple eukaryotes to study aging and age-related disease, it is pertinent to ask whether, and to what degree, the aging process is evolutionarily conserved.Does a yeast cell age by the same mechanism(s) as a mouse?Is the longevity of a nematode determined in the same way as that of a person?The complete answers to these questions remain largely unknown; however, discoveries made over the last several years have unequivocally demonstrated that at least some of the factors regulating longevity are shared between yeast, worms, flies, and mice.The degree to which these pathways will be relevant to human longevity and age-associated disease is an important unanswered question.",
+      "\t\n\nMany of the genes and gene networks that modulate aging are conserved across animal phyla.For this reason, the highly tractable model systems Drosophila and Caenorhabditis have provided fundamental advances in our understanding of the genetic control of cellular processes that affect aging.There is a growing realization that increasing the evolutionary breadth in animal systems used in aging studies will lead to discovery of effects and mechanisms that are more likely to be robust and reveal fundamental principles of aging.The use of diverse models may also reveal previously unknown genetic factors involved in healthy aging in humans.The lineages leading to Drosophila melanogaster and Caenorhabditis elegans have each undergone significant genome reduction, and these standard model systems lack many vertebrate gene homologs that are present in other invertebrates [2][3][4][5][6][7][8][9].In addition, arthropods and nematodes are more closely related to each other than originally thought [10,11], limiting the evolutionary range in comparative studies of aging [12] and thus the degree to which conclusions can be reliably generalized from these models to humans.",
+      "\t\n\nIt seems that organisms from yeast to mammals have evolved genetic programs to cope with periods of starvation that can also postpone aging and age-related diseases, but how can we take advantage of those mechanisms to improve human health?Because assaying the longevity effects of CR in humans is practically impossible, studying its molecular mechanisms in lower life forms could be beneficial to humans through the identification of candidate genes, pathways and molecular mechanisms.Although CR will not be suitable for everyone, targeting its mechanisms and developing CR mimetics may lead to drug development for a number of age-related and metabolic diseases.",
+      "\tINTRODUCTION\n\nGenomic studies into human longevity are inspired by the fact that, in animal models, healthy lifespan has proved to be remarkably plastic, and major pathways of lifespan regulation have been identified.Considerable lifespan extension has been induced in models as diverse as yeast, worms, fish, flies and rodents by applying genetic manipulation and dietary restriction (DR) (see [1] for review).Reduced activity of nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling (IIS) and target of rapamycin (TOR) signalling mediated lifespan extension, and also the extension of lifespan by DR [2].An interesting observation from the perspective of human ageing is that, in rodents and monkeys, diets restricted in glucose, fat or protein uptake reduced or delayed the risk of cancer and metabolic disease, thus extending the healthspan of the animals [2].Following the discovery of genes and pathways involved in animal lifespan extension, human research has focused on the corresponding candidate human genes with genetic, genomic and epigenetic studies into ageing and longevity.The designs of these studies differ with respect to the selection of naturally occurring phenotypes and the study populations, which include population-based, patient-based, family-based and exposure-based cohorts.",
+      "\tINTRODUCTION A Brief History of Longevity Genetics Research in C. elegans\n\nProgress in aging research has identified genetic and environmental factors that regulate longevity across species [1][2][3].The nematode worm Caenorhabditis elegans has become an invaluable model system for investigating the molecular mechanisms of aging and longevity, offering the advantages of its relatively low cost, short lifespan, and conservation of key nutrient and stress-responsive signaling pathways in mammals.",
+      "\t\n\nIn addition to these advanced tools, new studies in emerging aging models, such as eusocial insects, and in yet-uncharacterized models will provide additional opportunities for insight into key epigenetic mechanisms in aging.In the case of the Indian jumping ant Harpegnathos saltator, a worker can replace a queen in the colony, resulting in a change in longevity, acquisition of reproductive function, and loss of worker behavior, all of which can ultimately be reversed.The epigenetic mechanisms that underlie this transition are of great interest, including characterization and manipulation of epigenetic patterning during development, which lead to key behavioral differences in these organisms (Simola et al., 2016).Particularly long lifespans have been observed in several types of deepwater fishes, various crustaceans, bow head whales, several turtles, and naked mole rats (relative to other rodents) among others.While some may be unfeasible for creation of laboratory models, tissue and cellular studies of these or similar organisms may prove to be insightful.In addition, short-lived model organisms such as yeast, worms, and killifish are useful for quick lifespan estimations (Table 1).Together with the technological advances highlighted above, new experimental avenues and models in aging research will provide key insight into the epigenetic pathways that underlie longevity and aging and will likely identify factors and pathways that can be targeted to improve health and lifespan in humans.",
+      "\t\n\nSaccharomyces cerevisiae has directly or indirectly contributed to the identification of arguably more mammalian genes that affect aging than any other model organism.Aging in yeast is assayed primarily by measurement of replicative or chronological life span.Here, we review the genes and mechanisms implicated in these two aging model systems and key remaining issues that need to be addressed for their optimization.Because of its well-characterized genome that is remarkably amenable to genetic manipulation and highthroughput screening procedures, S. cerevisiae will continue to serve as a leading model organism for studying pathways relevant to human aging and disease.",
+      "\t\n\nAlthough many theories have tried to explain aging, only few experimental advances were made prior to the last two decades.Since then rapid progress in the genetics of aging has been made in invertebrate models such as C. elegans and D. melanogaster, demonstrating the existence of regulatory pathways that control the rate of aging in these organisms [1][2][3][4][5][6][7][8][9][10][11][12][13][14].They include the insulin-like pathway, the Jun kinase pathway and the Sir2 deacetylase pathway.Moreover, it was rapidly shown that some of these pathways are conserved from yeast to humans."
+    ],
+    [
+      "\t\n\nKnowledge of genetic interrelationship between the biomarkers of aging may lead to the discovery of a downstream common pathway that summarizes aging processes; the list of biomarkers should be as comprehensive as possible via incorporating other well-known systems involved in aging in addition to the musculoskeletal system.Further development of the pleiotropy-based approaches will be useful for other studies of multiple related phenotypes which employ genome-wide associations to decipher genetics in the absence of disease endophenotypes, which is the case of human aging.With the advent of these approaches, new candidate genes may emerge for further pursuit.In its turn, discovery of the \"phenome of aging\" may translate into innovative diagnostic and therapeutic interventions to improve the overall health of older men and women.",
+      "\t\n\nFig. 4. Functional genomics technologies promise to go deeply into the understanding and the development of therapeutic strategies for sarcopenia.",
+      "\tRejuvenation without Dedifferentiation\n\nRecent studies have begun to test the potential of different interventions to restore youthfulness to aged cells or tissues.",
+      "\tWhat does this study add?  Combining genomics with in vitro human skin cell cultures is a promising approach for the identification of new antiageing and antidiscoloration compounds.\tWhat's already known about this subject?  Genomics data from the study of skin biopsies has identified new biomarkers for targeting skin ageing and discoloration for therapeutic intervention. In vitro human skin cell cultures are routinely used for the rapid evaluation of cosmetic compounds.",
+      "\tImplications and Interventions for Antiaging Medicine\n\nOne of the aims of this work is to make others aware that age-related changes and pathologies can derive from early-onset developmental mechanisms, as supported by recent results (1, 2).Hopefully, researchers and clinicians will try to understand age-related pathologies by looking at the physiology and genetics of normal developmental processes.Assuming a link between development and aging also has major implications for how experiments are designed and interpreted in gerontology.If we see aging as triggered by development, rather than a mere accumulation of damage, then to study aging it is necessary to understand the life span as a whole and not merely its last segment.Herein, we offer a few ideas about how this can be achieved, including suggestions for experiments.",
+      "\t\n\nKnowledge of genetic and molecular pathways related to aging and its modulation can also be translated into predictions on health effects of dietary components (Mu ller and Kersten, 2003).Therefore, in addition to pharmaceuticals, another marketplace for basic aging research involves supplements, which avoids the need for clinical trials.Indeed, companies are now focusing on nutritional supplements that target genes/pathways involved in aging.One example is Genescient (http://www.genescient.com/), a biotechnology company; its strategy involves choosing supplements that affect pathways that may be important in long-lived flies as assayed from gene expression analyses (Rose et al., 2010).\t\n\nWe now know of hundreds of genes that regulate aging in model organisms, dozens associated with longevity in humans, and hundreds differentially expressed with age.This vast amount of information yields increased power for personalized and stratified medicine, for identifying biomarkers of aging, and for drug development to extend lifespan and ameliorate age-related diseases.Overall, it gives us a blueprint (albeit still imperfect) of how aging is controlled that we can use to potentially manipulate the basic aging process, whatever its underlying molecular mechanisms may be.Moreover, our knowledge of nutrient-sensing pathways that mediate the effects of CR has greatly increased in recent years, opening new opportunities for drug discovery and ultimately for perhaps developing an antiaging pill that retards aging with minimal side effects.\t\nAging is the major biomedical challenge of this century.The percentage of elderly people, and consequently the incidence of age-related diseases such as heart disease, cancer, and neurodegenerative diseases, is projected to increase considerably in the coming decades.Findings from model organisms have revealed that aging is a surprisingly plastic process that can be manipulated by both genetic and environmental factors.Here we review a broad range of findings in model organisms, from environmental to genetic manipulations of aging, with a focus on those with underlying gene-environment interactions with potential for drug discovery and development.One well-studied dietary manipulation of aging is caloric restriction, which consists of restricting the food intake of organisms without triggering malnutrition and has been shown to retard aging in model organ-isms.Caloric restriction is already being used as a paradigm for developing compounds that mimic its life-extension effects and might therefore have therapeutic value.The potential for further advances in this field is immense; hundreds of genes in several pathways have recently emerged as regulators of aging and caloric restriction in model organisms.Some of these genes, such as IGF1R and FOXO3, have also been associated with human longevity in genetic association studies.The parallel emergence of network approaches offers prospects to develop multitarget drugs and combinatorial therapies.Understanding how the environment modulates aging-related genes may lead to human applications and disease therapies through diet, lifestyle, or pharmacological interventions.Unlocking the capacity to manipulate human aging would result in unprecedented health benefits.\t\n\nCurrent progress in genomics, high-throughput methods, informatics, and systems biology should help to develop network approaches that test target combinations resulting in the emerging paradigm of network pharmacology (Keith et al., 2005;Hopkins, 2008).Systematic drug-design strategies directed against multiple targets hold much promise in the field of aging (Csermely et al., 2005), although challenges remain in developing accurate computer models of relevant pathways and suitable in vitro and in vivo models for testing.In the same vein, progress in personalized medicine and in predicting individual responses (e.g., using SNPs) to the environment (including diet, lifestyle, and drugs), will be key to maximizing environmental interventions that improve health and counteract aging.Therefore, network approaches to both aging and pharmacology are promising future avenues (Simko et al., 2009).\t\n\nAging is the major biomedical challenge of this century.The percentage of elderly people, and consequently the incidence of age-related diseases such as heart disease, cancer, and neurodegenerative diseases, is projected to increase considerably in the coming decades.Findings from model organisms have revealed that aging is a surprisingly plastic process that can be manipulated by both genetic and environmental factors.Here we review a broad range of findings in model organisms, from environmental to genetic manipulations of aging, with a focus on those with underlying gene-environment interactions with potential for drug discovery and development.One well-studied dietary manipulation of aging is caloric restriction, which consists of restricting the food intake of organisms without triggering malnutrition and has been shown to retard aging in model organ-isms.Caloric restriction is already being used as a paradigm for developing compounds that mimic its life-extension effects and might therefore have therapeutic value.The potential for further advances in this field is immense; hundreds of genes in several pathways have recently emerged as regulators of aging and caloric restriction in model organisms.Some of these genes, such as IGF1R and FOXO3, have also been associated with human longevity in genetic association studies.The parallel emergence of network approaches offers prospects to develop multitarget drugs and combinatorial therapies.Understanding how the environment modulates aging-related genes may lead to human applications and disease therapies through diet, lifestyle, or pharmacological interventions.Unlocking the capacity to manipulate human aging would result in unprecedented health benefits.\t\n\nIn conclusion, we now know of many target genes that either individually or collectively could be used for screening molecules (nutritional compounds and drugs) that may modulate aging.Even if proving that a particular diet or drug can delay aging is not feasible from a scientific and regulatory perspective, there is a huge potential to identify molecules that ameliorate age-related diseases and/or dysfunction.This represents a tremendous opportunity for companies working in nutrition and pharmacology in a field on an upward trajectory.\t\n\nMarred by decades of \"quackery\" (including grafting testicles from young animals into men), the science of aging has come a long way in gaining respectability (Stipp, 2010).Already more than 20 companies worldwide are focusing specifically on the aging process (http://whoswho.senescence.info/corp.php), in addition to \"big pharma,\" with agingoriented research and development projects.Although this number is modest, it shows the growing potential of a field that is bound to increase.In 2008, GlaxoSmithKline purchased Sirtris for $720 million (Sipp, 2008), a huge amount for a company with no clinical data; presumably the purchase was based on the extraordinary potential suggested by a compound capable of delaying aging.Even though questions have been raised about their efficiency, resveratrol and other drugs targeting SIRT1 showcase how a gene initially identified as a regulator of aging in yeast can be used as a pharmaceutical target for multiple human diseases.It demonstrates confidence in the field and in the idea that aging is not immutable.The recent problems raised concerning SIRT1 and resveratrol research also serve as a cautionary tale of the hurdles in translation of laboratory discoveries to the clinic.\tVI. Concluding remarks\n\nAging is the major driving factor of disease in the 21st century.Manipulation of aging-related genes by diet, lifestyle, and pharmaceuticals could dramatically improve human health and could be used to develop drugs against age-related diseases such as cancer, heart disease, type 2 diabetes, obesity, and neurodegenerative diseases.The hundreds of aging-related genes and genes related to CR already identified offer enormous opportunities for target discovery (Fig. 2).Although agingrelated genes cannot be modified in humans, understanding how these can be manipulated by diet or pharmaceuticals can have a profound impact on health.In other words, work on the genetics of aging allows the identification of novel genomic targets for drug development, opening the door for aging pharmacogenomics.\tC. Translation to Extend Human Healthspan\n\nAlthough a number of genes and even a few drugs have emerged as candidates for targeting the aging process pharmacologically, several problems are associated with translation to human aging.In principle, human clinical trials on aging cannot be performed.One major problem is that aging cannot be quantified, and even a trial running for several years would struggle to identify endpoints.Lifespan or survival could be quantified, as well as health biomarkers such as low blood pressure, insulin sensitivity, inflammatory markers, glucose metabolism, etc., but these may or may not reflect alterations in the aging process.\t\n\nOverall, demonstrating that a particular intervention is affecting human aging, as done in model organisms, is virtually impossible.Interventions, including drugs, emerging from basic research on aging will probably target specific age-related pathological conditions and/or dysfunction.Subsequent studies of health biomarkers and multiple age-related diseases may reveal broader effects.Success in animal models or short-term human studies may be sufficient to convince potential patients of the usefulness of particular dietary supplements or approaches, as exemplified by those voluntarily undergoing CR (http://www.crsociety.org/),which can serve as basis for further studies (Soare et al., 2011).",
+      "\tConcluding Remarks\n\nGenome instability plays a significant role in the progression of aging and protecting our aging genomes is therefore of fundamental importance for healthy aging.A major issue for the development of interventions targeting aging is the long trial time and difficulty in determining positive outcomes (see Outstanding Questions).Premature-aging diseases could represent an interesting group of disorders where aging interventions could be tested and outcomes could be determined at a much lower cost and potentially in less time.Here, treatments such as rapamycin, dietary interventions, sirtuin-activating compounds, metformin, NAD precursors, and senolytics could be more diligently tested in DNA repair disorders.A large number of therapies are emerging that may directly or indirectly lead to less DNA damage and the vast ongoing research across the globe will undoubtedly eventually be able to target this for the benefit of humankind.In sum, the future is bright.",
+      "\t\n\nAging is a multifold process affected by many genes and thus many biochemical pathways.This conclusion is underscored by the failure to find simple central controls for the aging process during the 20th Century.This situation poses a fundamental challenge to anti-aging medicine: how to develop effective therapies for a genomically complex pathology.We propose such a strategy.As a first step, we recommend the use of model systems in which significant genetic intervention is not proscribed or impractical.Second, we propose that work with such model systems begin with selected lines that have genetic enhancements that allow increased lifespan.Third, genomic methods should be used to identify a number of biochemical pathways for increasing lifespan.Fourth, biochemical pathways that have been identified in model systems would then be available for pharmaceutical development, first in rodents, eventually in a clinical human population.This may seem to be a cumbersome R&D strategy, but starting with human populations or inadequately pre-screened compounds would be unlikely to succeed because of the complexity of the aging problem.\t\nAging is a multifold process affected by many genes and thus many biochemical pathways.This conclusion is underscored by the failure to find simple central controls for the aging process during the 20th Century.This situation poses a fundamental challenge to anti-aging medicine: how to develop effective therapies for a genomically complex pathology.We propose such a strategy.As a first step, we recommend the use of model systems in which significant genetic intervention is not proscribed or impractical.Second, we propose that work with such model systems begin with selected lines that have genetic enhancements that allow increased lifespan.Third, genomic methods should be used to identify a number of biochemical pathways for increasing lifespan.Fourth, biochemical pathways that have been identified in model systems would then be available for pharmaceutical development, first in rodents, eventually in a clinical human population.This may seem to be a cumbersome R&D strategy, but starting with human populations or inadequately pre-screened compounds would be unlikely to succeed because of the complexity of the aging problem.",
+      "\tIntegrating genomics and biomarker research\n\nOnce the use of established biomarkers of biological age is standardized, the biomarker information can be integrated into studies aimed at finding causal determinants of aging and longevity.An example of an integrated approach to identify lifespan regulating loci is represented by testing whether genetic variants associated with potential biomarkers also associate with longevity.To date, GWAS have identified many genetic variants that associate with age-associated traits, such as leukocyte telomere length and features from glycome and metabolome profiles [84][85][86].The joint effect of the majority of these variants on aging and longevity still needs to be determined.One study identified a haplotype in the TERT gene that was associated with increased telomere length and longevity, which indicates that genetic variants associated with telomere length regulation might also play a role in longevity [87]."
+    ],
+    [
+      "\t\nThe genetic analysis of life span has only begun in mammals, invertebrates, such as Caenorhabditis elegans and Drosophila, and yeast.Even at this primitive stage of the genetic analysis of aging, the physiological observations that rate of metabolism is intimately tied to life span is supported.In many examples from mice to worms to flies to yeast, genetic variants that affect life span also modify metabolism.Insulin signaling regulates life span coordinately with reproduction, metabolism, and free radical protective gene regulation in C. elegans.This may be related to the findings that caloric restriction also regulates mammalian aging, perhaps via the modulation of insulin-like signaling pathways.The nervous system has been implicated as a key tissue where insulin-like signaling and free radical protective pathways regulate life span in C. elegans and Drosophila.Genes that determine the life span could act in neuroendocrine cells in diverse animals.The involvement of insulin-like hormones suggests that the plasticity in life spans evident in animal phylogeny may be due to variation in the timing of release of hormones that control vitality and mortality as well as variation in the response to those hormones.Pedigree analysis of human aging may reveal variations in the orthologs of the insulin pathway genes and coupled pathways that regulate invertebrate aging.Thus, genetic approaches may identify a set of circuits that was established in ancestral metazoans to regulate their longevity.",
+      "\tConclusions\n\nIn the absence of a consensus phenotype for aging, genetic research is impeded (Melzer et al. 2007).At present, it is difficult to determine whether preventative and therapeutic strategies (such as calorie restriction) have beneficial effects in humans because there are no validated biomarkers that can serve as surrogate markers of aging (Matkovic et al. 1990).To have the \"phenome of aging\" (Xue et al. 2007) much better defined, we propose using the musculoskeletal aging phenotypes as an example and starting point.",
+      "\t\n\nHistorically, the effects of CR have been viewed as being associated with the aging process [1][2][3].This standpoint argues that effects of CR extend beyond any one disease process (e.g., tumorigenesis), but that CR has multiplex effects on a range of physiological systems, ultimately amounting to an inhibitory effect on the progression of aging.The association between CR and aging, however, remains poorly understood, largely because the aging process itself remains poorly defined [17].While an uncontroversial definition of aging may not be developed anytime soon, it should be possible to add rigor to the concept by generating quantitative models of aging that are operationally useful.In this regard, whole-genome microarray datasets would seem especially valuable [18], and can be used to generate models that test, quantitatively, the assertion that CR acts to oppose the progression of aging [11].Conclusions generated from previous investigations conflict regarding the association between the effects of CR and aging.On the one hand, an early investigation revealed that age-associated expression patterns in muscle were \"either completely or partially prevented by caloric restriction\" [19], and this conclusion was supported in subsequent studies [14,20,21].Other investigations, however, have yielded different conclusions.For instance, effects of CR were entirely unrelated to those of aging in muscle tissue from Rhesus monkeys [22], and in one aptly designed experiment examining mouse cardiac tissue, only 79 of 1075 age-responsive genes (7.3%) were significantly altered by CR [23].Clearly, experimental design and statistical methodology are two important considerations for evaluating this diverse set of results.Many studies, for instance, have not evaluated whether the observed overlap between CR and aging effects is larger than expected by chance alone.This statistical evaluation would not be straight-forward in many cases, since experiments involved a shared control treatment that was used to evaluate the effects of both aging and CR (e.g., a young control treatment, an old control treatment, and an old CR treatment).Given this design, the effect of CR is not estimated independently of the effect of aging, and some correspondence between CR and aging effects would be expected by chance [12].\t\n\nThe association between CR and aging was next examined at the global scale, among all genes, and also with respect to each of the four most well-studied tissue types (liver, heart, muscle and central nervous system) (Figure 8).In liver, there was a slight, positive association between the effects of CR and aging (r = 0.04) (Figure 8A).This association was significant (P < 6.72  10 -12 ), although given the large number of genes involved in the comparison, this Relationship between caloric restriction and aging in liver, heart, muscle and the central nervous system Figure 8 Relationship between caloric restriction and aging in liver, heart, muscle and the central nervous system.The association between CR and aging was evaluated for the (A) liver, (B) heart, (C) muscle and (D) central nervous system (hippocampus + cortex).The CR effect is positive for genes up regulated by CR and negative for genes down regulated by CR (see Figure 7 legend).Likewise, the age effect is positive for genes up regulated with age and negative for genes down regulated with age (see Figure 7 legend).The abundance of genes in relation to the CR and age effect is reflected by the color intensity, with deep blue colors corresponding to regions with the largest number of genes.The dashed red line is based upon a least-squares regression fit that quantifies the overall relationship between the CR and aging effects.In each panel, the estimated Pearson correlation is shown in the upper-right, and the percentage values (green font) indicate the fraction of genes that belong to each quadrant.The effects of CR and aging were computed in each organ system based upon p-values generated by combining results from at least 3 independent experiments.In liver, CR and aging effects are based upon 9 and 7 experiments, respectively.In heart, CR and aging effects are based upon 5 and 10 experiments, respectively.For muscle and central nervous system, CR and aging effects are each based upon 3 -6 experiments.For each organ, distinct sets of data were used to estimate the CR and aging effects, such that CR and aging effects are a priori independent.significance test was not too informative.In the heart, muscle and central nervous system, the expected negative association between CR and aging did emerge, albeit weakly, with the estimated correlation coefficient less than or equal to -0.10 in each case.The strongest association was found in heart (Figure 8B), in which age-related expression patterns were weakly opposed by CR (r = -0.096;P = 2.20  10 -16 ).In muscle and central nervous system (Figures 8C and 8D), the association between CR and aging was again weak (r < -0.048), and non-significant in the case of muscle (P = 0.054), despite the large number of genes upon which the association was based.With respect to central nervous system, a large fraction of genes (56.6%) were both increased by CR and decreased with age (i.e., within the lower-right quadrant of Figure 8D), although very few genes (8.9%) were decreased by CR and increased with age (i.e., within the upper-left quadrant of Figure 8D).",
+      "\t\n\nThen we have those pharmaceutical strategies that are www.impactaging.combased on emulating the pathways implicated in the response of lifespan to dietary restriction, particularly sirtuin-targeting agents like resveratrol [e.g.25].Again, like hormone manipulation, these pathways are heavily bound up with the regulation of reproduction, making the curtailment of the cost of reproduction the most likely mechanism by which the beneficial effects of emulating dietary restriction are achieved [cf. 26].This is a strategy in which longevity is increased by metabolic refrigeration, pseudo-hibernation, or curtailing functions [11].From the standpoint of evolutionary biology, this is, again, not an extension of the period of adaptation.It is instead trading one set of adaptations off against another.Most people do not regard curtailing their metabolism, cognition, affective stability or reproductive functions as a useful approach to the problem of aging.Nonetheless, some are willing to trade-off some of their adaptive functions for an increased lifespan, and for them this \"anti-aging\" strategy will have its attractions.",
+      "\tMetabolism\n\nStudies show that calorie restriction is the most consistent means to prolong life expectancy and health across several experimental models [55], ranging from yeasts to primates.It not only increases life expectancy, but it also delays the onset of many features and hallmarks of ageing, including age-related diseases.Transcriptional profiles are currently being applied and investigated.One of them is a caloric restriction (CR), which increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes; this has a direct intervention in the repair of DNA damage.Data from human trials (such as CALERIE, Biosphere-2 and CRON) indicate that moderate CR accompanied by adequate nutrition has positive effects on health and dramatically reduces the multiple metabolic factors involved in the pathogenesis of disease chronicles, including type 2 diabetes, heart and cerebrovascular diseases, and cancer [56].",
+      "\t\n\nOn the other hand, the beneficial effects of caloric restriction are associated with alterations in metabolism, particularly the insulin/insulin-like growth factor 1 (IGF-1) pathways, which could reflect an evolution mechanism to ensure survival of a species during period of food shortage [3].Many genetic manipulations affecting nutrient-sensing pathways including the insulin and mTOR (mammalian target of rapamycin) pathways mimic the effect of caloric restriction on lifespan in yeast, worm, flies and mice and support this hypothesis [3].This review will firstly discuss in general terms how trace elements affect ageing and then use Selenium (Se) as an example to illustrate how trace elements influence the ageing process.Furthermore, the review will also illustrate how the so-called \"Omics technologies\" can be used to unravel the modes of action of trace elements and to identify biomarkers to define the optimal intake for health at the molecular level.\t\n\nEvidence is building up showing that caloric restriction, without malnutrition, extends lifespan in species ranging from yeast to non-human primates [3], but it appears, on the contrary, that inadequate/sub-optimal intake of micronutrients contribute to the development of chronic diseases.In his \"Triage theory\", B. Ames suggested that this could reflect the need for an organism to re-allocate micronutrients according to triage priorities to favour short-term survival over long-term wellbeing [4,5].The consequences of this re-allocation may remain unnoticed in the day-to-day experience but are likely to show up late in life as cancers, Alzheimer's disease, Parkinson's disease, diabetes and cardiovascular diseases.",
+      "\t\n\nCaloric restriction (CR) is the only intervention shown to extend lifespan in mammals (5).It is also the most effective means known of reducing cancer incidence and increasing the mean age of onset of age-related diseases and tumors (6).Our studies made use of an experimental design that allowed us to clearly distinguish the effects of diet from those of age on genome-wide expression patterns.Another distinctive aspect of the study allowed us to resolve changes in gene expression induced directly by CR from those that arise over time as a consequence of the interaction between CR and aging.",
+      "\tGenDR-genomics of DR\n\nDR, of which caloric restriction is the most widely studied regimen, is the most robust non-genetic intervention shown to extend lifespan in a multitude of species, from yeast to mammals (12,14).However, the exact mechanisms of how DR extends lifespan remain unknown.To decipher the mechanisms of DR in a systematic fashion, we established GenDR (http://genomics.senescence.info/diet/), the first database of DR-associated genes.Because GenDR and related analysis of DR networks have been recently described elsewhere (15), they will only be briefly described herein.To create GenDR, we compiled from the literature a list of DR-essential genes from model organisms.DR-essential genes were defined as those which, if genetically modified, interfere with DR-mediated lifespan extension and, ideally, do not affect the lifespan of animals on an ad libitum diet (or at least do not appear to be merely causing disease).A subset of these genes act as genetic DR mimetics, as their manipulation leads to an increased lifespan for ad libitum fed animals, which is not further extended by DR.One such example is the growth hormone receptor gene in mice (16), in fact the only mouse gene currently in GenDR.In GenDR, the respective homologues of DR-essential genes are included for all the common model organisms, as well as for humans (15).A complementary data set in GenDR is a list of genes consistently differentially expressed in mammals under DR.In a recent meta-analysis, a common signature of genes differentially expressed in DR across different mammalian species, strains, tissues and experiments was derived.This signature provides a set of genes that are most robustly responding to DR (17).",
+      "\t\n\nBackground: Dietary restriction (DR), a reduction in food intake without malnutrition, increases most aspects of health during aging and extends lifespan in diverse species, including rodents.However, the mechanisms by which DR interacts with the aging process to improve health in old age are poorly understood.DNA methylation could play an important role in mediating the effects of DR because it is sensitive to the effects of nutrition and can affect gene expression memory over time.",
+      "\tIV. Genome-Environment Interactions as Targets for Dietary Interventions and Drug Discovery\n\n\"[It's] possible that we could change a human gene and double our life span. \"-CynthiaKenyon (Duncan, 2004) According to the GenAge database of aging-related genes (http://genomics.senescence.info/genes/),more than 700 genes have been identified that regulate lifespan in model organisms (de Magalha es et al., 2009a).Many of these genes and their associated pathways-such as the insulin/IGF1/GH pathway-have been shown to affect longevity across different model organisms (Kenyon, 2010).Therefore, at least some mechanisms of aging are evolutionarily conserved and may have potential therapeutic applications (Baur et al., 2006).For example, evidence suggests the use of lowered IGF signaling (e.g., by targeting IGF receptors) to treat certain age-related diseases such as cancer (Pollak et al., 2004), Alzheimer's disease (Cohen et al., 2009), and autoimmune diseases (Smith, 2010).Moreover, a number of genes and pathways associated with longevity and CR are part of nutrient-sensing pathways that also regulate growth and development, including the insulin/IGF1/GH pathway (Narasimhan et al., 2009;Stanfel et al., 2009).Many of these genes modulate the response to environmental signals, such as food availability, and act in signaling pathways that if understood can be targeted (Fig. 1).The genetic regulation of aging is therefore an emerging field with multiple applications in the human nutrition, cosmetic, and pharmaceutical industries.\t\n\nBy far the most widely studied dietary manipulation of aging is caloric restriction (CR), also called dietary restriction.CR consists of restricting the food intake of organisms normally fed ad libitum without triggering malnutrition and is the only dietary intervention shown, to date, to increase longevity and modulate the process of aging in several model organisms (Bishop and Guarente, 2007;Fontana et al., 2010;Spindler, 2010).Even in mammals, such as mice and rats, CR can extend longevity by up to 50%, delay physiological aging, and postpone or diminish the morbidity of most age-related diseases (Masoro, 2005).Ongoing studies in rhesus monkeys suggest that CR can lower the incidence of aging-related deaths in primates (Colman et al., 2009).",
+      "\tGenDR--a database of dietary restriction-related genes\n\nDietary restriction (DR) delays the ageing process and extends lifespan in a multitude of species from yeast to mammals (22).However, the exact mechanisms of how DR extends lifespan are still unknown.As previously described (23), GenDR (http://genomics.senescence.info/diet/) is a database of DR-related genes.Herein, the use and function of GenDR will be briefly outlined along with updates since the 2013 HAGR paper (3).",
+      "\tINTRODUCTION\n\nGenomic studies into human longevity are inspired by the fact that, in animal models, healthy lifespan has proved to be remarkably plastic, and major pathways of lifespan regulation have been identified.Considerable lifespan extension has been induced in models as diverse as yeast, worms, fish, flies and rodents by applying genetic manipulation and dietary restriction (DR) (see [1] for review).Reduced activity of nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling (IIS) and target of rapamycin (TOR) signalling mediated lifespan extension, and also the extension of lifespan by DR [2].An interesting observation from the perspective of human ageing is that, in rodents and monkeys, diets restricted in glucose, fat or protein uptake reduced or delayed the risk of cancer and metabolic disease, thus extending the healthspan of the animals [2].Following the discovery of genes and pathways involved in animal lifespan extension, human research has focused on the corresponding candidate human genes with genetic, genomic and epigenetic studies into ageing and longevity.The designs of these studies differ with respect to the selection of naturally occurring phenotypes and the study populations, which include population-based, patient-based, family-based and exposure-based cohorts.",
+      "\tIn comparison, caloric\nrestriction, intermittent fasting, or a ketogenic diet generally improve lifespan and health\n811 These dietary effects are not solely dependent on patterns of caloric intake, but are\nmodulated by dietary macro- and micronutrient composition, the amount of time spent in\ndifferent metabolic states, age of onset, periodicity of access to food, sex, and of greatest\nimportance to us in this studydifferences in genometype (strain) and gene-by-dietary\ninteractions 12,13. While the effects of differences in dietary composition and caloric restriction on lifespan\nhave been studied extensively, key results remain controversial 1416.",
+      "\tNutrition, phenotype and longevity\n\nNo issue so 'vividly' illustrates the power of diet to alter health as the consistent observation of the effect of caloric restriction (CR) on longevity.To date, neither drug, gene nor environmental intervention have been successfully demonstrated to prolong longevity in animals; however, the simple reduction of food calories can increase life span by 30-40% across a number of model organisms, including yeast, Drosophilia, Caenorhabditis elegans, rodents and monkeys [5][6][7].This effect of CR raises one of the most intriguing questions facing life scientists today.Despite the demonstrated positive age-related benefits of a reduction in energy intake -including decreased insulin resistance [8], increased production of glucocorticoids [9] and increased production of heat-shock proteins [10] -the mechanisms by which CR contributes to increased longevity remain unknown.How CR leads to longer life span cannot be attributed to any single factor without considering the simultaneous effects of the others.CR could alter multiple age-related processes, from energy metabolism to oxidative stress and DNA repair.Unravelling the multiparametric links of CR and aging led to the seminal genomic experiment for nutrition: the gene expression analysis of young and old tissues in normal and CR animals [11   ] is a pioneering example of the use of DNA arrays to explore the effects of CR and aging on gene expression in mouse skeletal muscle.The experiment is compelling for its simplicity and its implications, that is, the gene expression profiles for a clear phenotypic difference were compared (young versus old versus CR old mice).The power of the technique was evident by the discovery of a wide range of affected genes, including those involved in protein and energy metabolism, biosynthesis (e.g. of fatty acids), and macromolecular damage, implying immediately that the effects of aging and CR are broad, yet interrelated.More detailed experiments are now being pursued around the world following the identification of the genes that are altered during aging and protected by CR.The publication of this experiment also followed the now routine approach of supplying the raw database through an accessible internet site.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\tWe present a metabolic model in which the anti-aging effects of DR\nare consistent with the ability to efficiently utilize dietary resources. NIH-PA Author Manuscript\n\nKeywords\naging; food restriction; lifespan; fertility; metabolic efficiency; quantitative trait loci; genetic\nmapping; physiology\n\nIntroduction\nDietary restriction (DR) extends lifespan and slows aging across a variety of taxa and also\ncauses myriad other physiological changes (Weindruch and Walford, 1998; Mobbs et al. ,\n2007).",
+      "\t\n\nIn summary, we postulate that due to metabolic changes and the subsequent increase in stress response, physiological processes evoked by starvation show strong correlation with anti-aging processes (Table 2).These observations suggest that starvation may evoke the same stress response reaction as caloric restriction, which is the only treatment known to prolong lifespan in all organisms tested to date.The difference is that starvation results in a much stronger or prolonged induction.This accentuated response during starvation may facilitate the experimental identification of basic molecular mechanisms linking nutrition and health using a nutrigenomic approach."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "4BA9088EE51B4FEB12D723A3AA9E1585"
+    },
+    {
+      "task_id": "1883A6F02376841E63AE392D386836D7"
+    },
+    {
+      "task_id": "CC48E25A01F0D10FF57B5E5B9EC8F179"
+    },
+    {
+      "task_id": "5E49F30B15AA7350275E583CF98E70BF"
+    },
+    {
+      "task_id": "94989E7D750B3FB87B9E5DA1F47DFD1F"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_1.json
new file mode 100644
index 0000000..53e8b1e
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_1.json
@@ -0,0 +1,127 @@
+{
+  "question": [
+    "How do genetic mutations in the insulin gene affect glucose metabolism?",
+    "What are the most common genetic loci associated with an increased risk of Type 2 diabetes?",
+    "How does genome-wide association studies (GWAS) help in identifying diabetes-related genes?",
+    "What is the role of the HLA region in the genetic predisposition to Type 1 diabetes?",
+    "How do genetic differences contribute to variations in diabetes prevalence among different populations?"
+  ],
+  "answer": [
+    "Genetic mutations in the insulin gene can affect glucose metabolism by disrupting insulin secretion, insulin action, and insulin processing. For instance, mutations in genes like IGF2BP2, SLC30A8, and CDKN2A/CDKN2B can lead to a lower disposition index, affecting insulin secretion. Variants in genes like GCKR can influence fasting glucose levels, insulin levels, and triglyceride levels. Additionally, mutations in genes like TCF7L2, KCNJ11, and HHEX, which are involved in -cell metabolism, can affect glucose-sensing and insulin secretion. Furthermore, a variant of the MTNR1B gene can lead to a reduction of the early insulin response to glucose, affecting insulin secretion over time.",
+    "The most common genetic loci associated with an increased risk of Type 2 diabetes include TCF7L2, PPARG, FTO, KCNJ11, NOTCH2, WFS1, CDKAL1, IGF2BP2, SLC30A8, JAZF1, and HHEX.",
+    "Genome-wide association studies (GWAS) help in identifying diabetes-related genes by scanning the genomes of many people to find genetic variations associated with the disease. These studies have identified numerous risk loci, or regions of the genome, associated with type 2 diabetes. The identified loci contain genes that may influence the disease's pathophysiology. GWAS also help in understanding the genetic basis of inter-individual variation in glycemic traits, such as levels of glucose, insulin, and hemoglobin A1c. The insights gained from these studies can contribute to the development of novel strategies for patient care.",
+    "The HLA region on chromosome 6p21.3 plays a significant role in the genetic predisposition to Type 1 diabetes. This region contains the HLA class II genes (HLA-DRB1, DQB1, and DQA1), which are the most potent diabetes-predisposing genes in the entire genome. These genes encode the highly polymorphic antigen-presenting proteins that are central to susceptibility to Type 1 diabetes. Certain alleles of these genes, particularly HLA-DR3, DR4, and DQB1*0302, are associated with a higher risk of developing the disease. However, the exact mechanism by which these genes confer susceptibility to diabetes is not yet fully understood.",
+    "Genetic differences contribute to variations in diabetes prevalence among different populations through the presence of different risk alleles and allele frequencies. Certain genetic loci associated with type-2 diabetes (T2D) and obesity have been subject to recent selection pressures, leading to population-specific genetic risk factors. For instance, East Asians and sub-Saharan Africans show pronounced differentiation at T2D loci, suggesting natural selection at these loci. Similarly, South Asians and Europeans show an excess of obesity loci with evidence of recent positive selection. These genetic variations, combined with environmental and lifestyle factors, contribute to the different rates of diabetes prevalence among various populations."
+  ],
+  "contexts": [
+    [
+      "\tNature 503, 290294 (2013). 33. Dimas, A. S. et al. Impact of type 2 diabetes susceptibility variants on\nquantitative glycemic traits reveals mechanistic heterogeneity. Diabetes 63,\n21582171 (2014). 34. Dupuis, J. et al. New genetic loci implicated in fasting glucose homeostasis and\ntheir impact on type 2 diabetes risk. Nat. Genet. 42, 105116 (2010). 35. Lotta, L. A. et al. Integrative genomic analysis implicates limited peripheral\nadipose storage capacity in the pathogenesis of human insulin resistance. Nat. Genet. 49, 1726 (2017). 36. Manning, A. K. et al.",
+      "\t\n\nGenes reviewed were categorized into three groups: genes affecting insulin secretion, genes affecting insulin resistance, and genes affecting mitochondria function.Findings from these studies are summarized in Tables 12.2-12.4.Polymorphisms of genes, such as plasminogen activator inhibitor type 1 (PAI-1) gene and forkhead box C2 (FOXC2) gene, studied in women with GDM (Leipold, Knoefl er, Gruber, Klein, et al., 2006;Pappa et al., 2011;Shaat et al., 2007) but not associated with T2DM (Carlsson, Groop, & Ridderstrle, 2005;Osawa et al., 2003) were not included in this review.",
+      "\t\n\nMost of the diabetes-associated SNPs were found in non-coding regions of the genome and are thus likely to affect gene regulation.In order to understand how these genes affect type 2 diabetes and how the SNPs associated with diabetes affect gene expression, we need to first understand the physiological processes that regulate the expression of these genes.We examined the expression patterns of these potential new diabetes-susceptibility genes to determine which are expressed in tissues important for the development of type 2 diabetes.This may also suggest the potential mechanism(s) by which alterations in these genes affect diabetes risk (e.g.insulin secretion versus insulin sensitivity).We also sought to determine whether any of these genes are regulated by conditions known to alter the expression of metabolically relevant genes.We examined the expression of these genes under fasting and non-fasting conditions (e.g. in response to insulin), which might be altered if they affect peripheral insulin sensitivity.Consumption of diets high in fats and sugars is associated with risk of developing type 2 diabetes [34] and many genes that are critical for -cell function are regulated by glucose [35].Thus, we also compared their expression in fasted mice consuming a normal chow diet or a diet high in fat and sugar, and examined the expression of these genes in mouse pancreatic islets cultured under low and high glucose concentrations.Here we show that most of the diabetesassociated genes are expressed in many metabolically relevant tissues and the expression levels of several of these genes were decreased by high fat feeding or were increased in the fed state in the brain.In addition, we found most of these genes are down-regulated by increased glucose concentrations in mouse islets.",
+      "\t\n\nThese studies provide valuable insights into the molecular circuitry of the beta cell and pinpoint pathways crucial for the maintenance of normal glucose homeostasis.Could (a more subtle) variation in the same genes inuence susceptibility to multifactorial T2D?In the case of glucokinase and the hepatocyte nuclear factor (HNF) genes (see Chapter 4), this does not seem to be so, although regions of linkage to T2D overlapping the HNF-1a and HNF-4a loci 35,36 hint at the possibility of variants in regulatory regions not yet scanned.",
+      "\t\n\nMutations in transcription factors have also been reported to contribute to the genetic risk for T2DM through various mechanisms: dysregulation of target genes involved in glucose or lipid metabolism (HNFs, PPARG , IPF -1 , IB1, TIEG2/KLF11 ), impaired  -cell development and differentiation ( IPF -1 , NEUROD1 /  2, TIEG2/KLF11 ), and increased  -cell apoptosis ( IB1 / MAPK8IP1 ).Deleterious mutations that signifi cantly impair the transactivation activity of these transcription factors can be responsible in some families for monogenic -like forms of diabetes with late age of onset, which may represent an intermediary phenotype between MODY and the most common forms of T2DM.This is the case for the TIEG2/KLF11 gene encoding the Kr  ppel -like factor 11 (KLF11), an SP1 -like pancreas expressed transcription factor that is induced by the transforming growth factor  (TGF ) and regulates cell growth in the exocrine pancreas.A common polymorphism (Q62R) in KLF11 was reported to be associated with polygenic T2DM developing in adulthood and to affect the function of KLF11 in vitro [99] .Insulin levels were found to be lower in carriers of the minor allele at Q62R [99] but attempts of replication in other populations only found a minor, or no detectable effect of the Q62R common variant on diabetes risk [100] .Sequencing of KLF11 gene in families enriched for earlyonset T2DM uncovered two missense mutations which segregated with diabetes in three pedigrees [99] , but proof of their causality was only based on in vitro experiments.These fi ndings suggest a role for the TGF - signaling pathway in pancreatic diseases affecting endocrine islets (diabetes) or exocrine cells (cancer) [101] .",
+      "\t\n\nIn studies where overt T2D has been the phenotype the majority of associated polymorphisms have encoded proteins known to be involved in -cell metabolism; for example TCF7L2, KCNJ11 and HHEX have shown robust association [170,171].This suggests that these genes could prove useful in predicting -cell preservation during the course of T2D.The glucokinase gene (GCK) coding for the initial glucose-sensing step in the -cell can have activating mutations causing hypoglycemia that might provide structural and functional models leading to drug targets for treating T2D [172].In the GoDARTs study, investigators examined the medication response of metformin and sulphonylurea based on the TCF7L2 variants mainly affecting the -cell.The carriers of the at risk 'T' allele responded less well to sulphonylurea therapy than metformin [173].Also it is of significant public health interest that in the Diabetes Prevention Program, lifestyle modifications were shown to reduce the risk of diabetes conferred by risk variants of TCF7L2 at rs7093146, and in placebo participants who carried the homozygous risk genotype (TT), there was 80% higher risk for developing diabetes compared to the lifestyle intervention group carrying the same risk genotypes [35].These findings could herald significant future progress in the field of T2D pharmacogenomics, possibly leading to the development and use of agents tailored on the basis of genotype.",
+      "\t\n\nImportantly, our findings demonstrate that more than 50% of the genes in which genetic variants have been known to increase risk of T2DM showed altered expression in different tissues.The perturbation was highest, as expected, in pancreatic islets, where eight genes i.e.HHEX, HNF1B, KCNQ1, NOTCH2, TCF7L2, THADA, TSPAN8 and WFS1, showed aberrant expression.All of these genetic loci, apart from the less studied TSPAN8, have been implicated in pathways primarily involved in insulin secretion, cell proliferation and regeneration [30].Of note, genetic variants in the THADA and WFS1 have recently been shown to impair glucagon-like peptide-1stimulated insulin secretion [31,32].Furthermore, many of these loci have also shown effects on insulin sensitivity [33].In line with this, five genes, i.e.HNF1B, IRS1, KCNJ11, NOTCH2 and WFS1, were also differentially expressed in skeletal muscle.Of all T2DM genes, IRS1 seems to have a clear effect on insulin sensitivity; the T2DM-associated allele was associated with decreased IRS1 protein expression as well as reduced phosphatidylinositol-3-kinase-activity and insulin-stimulated glucose uptake in humans [12].",
+      "\t\nThe intersection of genome-wide association analyses with physiological and functional data indicates that variants regulating islet gene transcription influence type 2 diabetes (T2D) predisposition and glucose homeostasis.However, the specific genes through which these regulatory variants act remain poorly characterized.We generated expression quantitative trait locus (eQTL) data in 118 human islet samples using RNA-sequencing and highdensity genotyping.We identified fourteen loci at which cis-exon-eQTL signals overlapped active islet chromatin signatures and were coincident with established T2D and/or glycemic trait associations.At some, these data provide an experimental link between GWAS signals and biological candidates, such as DGKB and ADCY5.At others, the cis-signals implicate genes with no prior connection to islet biology, including WARS and ZMIZ1.At the ZMIZ1 locus, we show that perturbation of ZMIZ1 expression in human islets and beta-cells influences exocytosis and insulin secretion, highlighting a novel role for ZMIZ1 in the maintenance of glucose homeostasis.Together, these findings provide a significant advance in the mechanistic insights of T2D and glycemic trait association loci.\t\n\nThe intersection of genome-wide association analyses with physiological and functional data indicates that variants regulating islet gene transcription influence type 2 diabetes (T2D) predisposition and glucose homeostasis.However, the specific genes through which these regulatory variants act remain poorly characterized.We generated expression quantitative trait locus (eQTL) data in 118 human islet samples using RNA-sequencing and highdensity genotyping.We identified fourteen loci at which cis-exon-eQTL signals overlapped active islet chromatin signatures and were coincident with established T2D and/or glycemic trait associations.At some, these data provide an experimental link between GWAS signals and biological candidates, such as DGKB and ADCY5.At others, the cis-signals implicate genes with no prior connection to islet biology, including WARS and ZMIZ1.At the ZMIZ1 locus, we show that perturbation of ZMIZ1 expression in human islets and beta-cells influences exocytosis and insulin secretion, highlighting a novel role for ZMIZ1 in the maintenance of glucose homeostasis.Together, these findings provide a significant advance in the mechanistic insights of T2D and glycemic trait association loci.",
+      "\t\n\nIn conclusion, our study in the DESIR prospective cohort shows that carriers of the GCKR-L446 variant have lower fasting glycemia and insulin resistance and are protected against the development of diabetes despite higher TG levels and a risk of dyslipidemia.This suggests, for the first time, a molecular mechanism by which these two components of the so-called metabolic syndrome can be dissociated.Based on rodent models, such as the adenoviral-mediated hepatic overexpression of GCK or GCKR in mice with diet-induced diabetes (5,19), more active GCKR may result in improved interaction with GCK, leading to more efficiently releasable pools of GCK enzyme, with subsequent beneficial effects on glucose metabolism but otherwise with a concomitant alteration of lipid profile.",
+      "\t\n\nAgainst this background, it is intriguing that we and others have found that a variant of the MTNR1B gene is associated with elevated plasma glucose levels, a reduction of the early insulin response to both oral and intravenous glucose, a faster deterioration of insulin secretion over time, and increased future risk of T2D (Bouatia-Naji et al., 2009;Lyssenko et al., 2009;Prokopenko et al., 2009).This association has subsequently been confirmed in other populations (Jonsson et al., 2013;Renstro m et al., 2015;Ro nn et al., 2009).Despite the very robust genetic association, a molecular understanding of why melatonin signaling is involved in the pathogenesis of T2D has still not been reached.To resolve this issue, we performed experimental studies in human islets, INS-1 832/13 b cells, and mice, as well as clinical studies in humans.We show that the rs10830963 risk variant of MTNR1B is an expression quantitative trait locus (eQTL) conferring increased expression of MTNR1B mRNA in human islets.Experiments in INS-1 832/13 b cells and Mt2 knockout mice (Mt2 / ) establish that melatonin signaling results in inhibition of insulin release.Translation to humans in a recallby-genotype study demonstrates that melatonin treatment inhibits insulin secretion in all subjects, but carriers of the risk variant are more sensitive to this inhibitory effect of melatonin.Together, these observations support a model in which a genetically determined increase in melatonin signaling underlies impaired insulin secretion, a pathogenetic hallmark of T2D.",
+      "\tChange in Body-Mass Index and Insulin Secretion and Action\n\nWe examined the effect of the genotyped DNA variants on changes in the BMI and insulin secretion (disposition index) and action over time in 2444 subjects from the Botnia study who did not have diabetes.At baseline, carriers of risk genotypes in the IGF2BP2 and SLC30A8 genes and at the CDKN2A/CDKN2B locus had a lower disposition index, which was maintained unchanged throughout the 8-year observation period (P<0.05) (Fig. 3H, 3I, and 3M in the Supplementary Appendix).",
+      "\t\n\nWhile the above findings show no evidence of association between relevant mitochondrial gene sets and T2D, these genes could still display causal associations with specific intermediate phenotypes linked to the disease.Support for this comes from reported mitochondrial dysfunction in insulin-resistant individuals [8].Therefore, we tested the same three gene sets described above for enrichment of associations with seven different glucose and insulin-related traits characteristic of T2D, using GWA metaanalyses of up to 46,186 non-diabetic individuals [37,38] (Soranzo N. et al., unpublished data).The quantitative traits analyzed include fasting levels of glucose and insulin, glucose and insulin levels 2 hours following a 75-gram oral glucose tolerance test, indices of b-cell function (HOMA-B) and insulin resistance (HOMA-IR) [49], and glycated hemoglobin levels (HbA 1C ), which reflect long-term plasma glucose concentrations (see Materials and Methods).",
+      "\t\n\nUsing the same data, the DIAGRAM investigators were also able to extend previous analyses which derive biological insights from the association effects of T2D-risk variants on related traits, such as body mass index, fasting glucose (in non-diabetic individuals), and indices of betacell function and insulin action [6, 27, 28].They were able to confirm: (1) partial, but not complete, overlap between variants that influence individual risk of T2D, and those that modulate physiological variation in fasting glucose amongst healthy individuals; (2) that the only signals which are driven by a primary effect on obesity are those at FTO and MC4R; and (3) that, whilst most risk loci operate via beta-cell dysfunction, a growing number (see Table 1) exert their T2D-risk effects through an obesity-independent deterioration in insulin sensitivity.This list of \"insulin resistance\" loci offers interesting insights into key players mediating the actions of insulin in peripheral tissues.In the case of the GRB14 locus for example, which emerged from GWAS in South Asians as well as Europeans [8], RNA expression data from fat confirms GRB14 as the strongest candidate transcript at the locus: its product is an adaptor protein that binds to the insulin receptor to inhibit tyrosine kinase signaling [29].",
+      "\t\n\naffected by genetic factors (5) with an estimated heritability of 0.53 (0.33-0.70) (6).These findings indicate that genetic factors exert substantial effects on GLP-1-induced insulin response and, as a consequence, may affect an individual's response to the GLP-1-based therapies.",
+      "\t\nAims/hypothesis: Impaired insulin secretion, insulin action, insulin-independent glucose effectiveness, glu-cose tolerance and the associated abnormalities in insulin and glucose metabolism phenotypes are precursors of type 2 diabetes.Genome-wide multipoint variance component linkage scans were carried out using 654 markers to identify quantitative trait loci for insulin sensitivity, acute insulin response to glucose, disposition index and glucose effectiveness training responses in whites and blacks in the HERITAGE Family Study.Methods: These phenotypes were obtained from an IVGTT with the minimal model.The distributions of insulin sensitivity, acute insulin response to glucose and disposition index training responses (posttraining minus baseline) were approximately normalised using a square-root transformation.All phenotypes were adjusted for the effects of age, BMI and their respective baseline values within sex and generation by race prior to linkage scans.Results: In blacks, a promising linkage with a maximum lod score of 3.1 on 19q (54-62 Mb) for glucose effectiveness training response was found.Six interesting linkages with lod scores of at least 1.0 were found for disposition index training response in whites.They included 1p (30 Mb), 3q (152 Mb),.Conclusions/ interpretation: Quantitative trait loci for 20 weeks of endurance exercise training responses in insulin action and glucose metabolism phenotypes were found on chromosome 19q as well as 6p and 7q, with nominal (6p, 7q) but consistent (6p) linkages across the races.Keywords Acute insulin response to glucose .Disposition index .Exercise training response .Glucose effectiveness .Insulin sensitivity .IVGTT .Minimal model .Quantitative trait loci Abbreviations AIR g : acute insulin response to glucose .DI: disposition index .GYS1: glycogen synthase 1 gene .LDB: location database .PPAR: peroxisome proliferatoractivated receptor .S I : insulin sensitivity .S G : glucose effectiveness P.An (*) .T. Rice .\t\n\nAims/hypothesis: Impaired insulin secretion, insulin action, insulin-independent glucose effectiveness, glu-cose tolerance and the associated abnormalities in insulin and glucose metabolism phenotypes are precursors of type 2 diabetes.Genome-wide multipoint variance component linkage scans were carried out using 654 markers to identify quantitative trait loci for insulin sensitivity, acute insulin response to glucose, disposition index and glucose effectiveness training responses in whites and blacks in the HERITAGE Family Study.Methods: These phenotypes were obtained from an IVGTT with the minimal model.The distributions of insulin sensitivity, acute insulin response to glucose and disposition index training responses (posttraining minus baseline) were approximately normalised using a square-root transformation.All phenotypes were adjusted for the effects of age, BMI and their respective baseline values within sex and generation by race prior to linkage scans.Results: In blacks, a promising linkage with a maximum lod score of 3.1 on 19q (54-62 Mb) for glucose effectiveness training response was found.Six interesting linkages with lod scores of at least 1.0 were found for disposition index training response in whites.They included 1p (30 Mb), 3q (152 Mb),.Conclusions/ interpretation: Quantitative trait loci for 20 weeks of endurance exercise training responses in insulin action and glucose metabolism phenotypes were found on chromosome 19q as well as 6p and 7q, with nominal (6p, 7q) but consistent (6p) linkages across the races.Keywords Acute insulin response to glucose .Disposition index .Exercise training response .Glucose effectiveness .Insulin sensitivity .IVGTT .Minimal model .Quantitative trait loci Abbreviations AIR g : acute insulin response to glucose .DI: disposition index .GYS1: glycogen synthase 1 gene .LDB: location database .PPAR: peroxisome proliferatoractivated receptor .S I : insulin sensitivity .S G : glucose effectiveness P.An (*) .T. Rice .",
+      "\t\n\nCell Metabolism 21, March 3, 2015 2015 Elsevier Inc. 359 Cell Metabolism Perspective ADCY5, which were primarily found to be associated with the variation of fasting glucose levels (Bouatia-Naji et al., 2009;Dupuis et al., 2010;Prokopenko et al., 2009), and GCKR, which was primarily found to be associated with the variation of fasting glucose levels, fasting insulin levels, and triglyceride levels (Saxena et al., 2007;Dupuis et al., 2010) (Figure 2).Interestingly, the overlap between loci influencing glucose-or insulin-related traits and T2D-susceptibility loci was unexpectedly limited (Dupuis et al., 2010).This result suggests that genes and related pathways that influence normal physiological levels of metabolic traits can be different from those leading to pathophysiological levels of metabolic traits that define T2D.A recent study strengthened this conclusion showing that the combination of established SNPs raising fasting glucose levels was significantly associated with the incidence of impaired fasting glucose levels over the 9-year follow-up of the study, but not with the risk of developing overt T2D (Vaxillaire et al., 2014).",
+      "\t\n\nPatients with established type 2 diabetes display both b-cell dysfunction and insulin resistance.To define fundamental processes leading to the diabetic state, we examined the relationship between type 2 diabetes risk variants at 37 established susceptibility loci, and indices of proinsulin processing, insulin secretion, and insulin sensitivity.We included data from up to 58,614 nondiabetic subjects with basal measures and 17,327 with dynamic measures.We used additive genetic models with adjustment for sex, age, and BMI, followed by fixed-effects, inverse-variance meta-analyses.Cluster analyses grouped risk loci into five major categories based on their relationship to these continuous glycemic phenotypes.The first cluster (PPARG, KLF14, IRS1, GCKR) was characterized by primary effects on insulin sensitivity.The second cluster (MTNR1B, GCK) featured risk alleles associated with reduced insulin secretion and fasting hyperglycemia.ARAP1 constituted a third cluster characterized by defects in insulin processing.A fourth cluster (TCF7L2, SLC30A8, HHEX/IDE, CDKAL1, CDKN2A/2B) was defined by loci influencing insulin processing and secretion without a detectable change in fasting glucose levels.The final group contained 20 risk loci with no clear-cut associations to continuous glycemic traits.By assembling extensive data on continuous glycemic traits, we have exposed the diverse mechanisms whereby type 2 diabetes risk variants impact disease predisposition.",
+      "\t\n\nIn conclusion, having only considered subjects with a BMI less than 25 kg/m 2 provides strong evidence of the importance of the genetic effect of Gly972Arg on diabetes risk.Although its contribution to the overall risk in the general population could be minimal, this evidence supports the line of research seeking to clarify the role of IRS1 in lean patients with diabetes.Further studies of this genetic effect are needed to evaluate its potential interaction with other factors-especially with genetic variation, risk factor as obesity-that participate in the same metabolic pathway."
+    ],
+    [
+      "\t\n\nFigure2| effect sizes of the 11 common variants confirmed to be involved in type 2 diabetes risk.The x axis gives the year that published evidence reached the levels of statistical confidence that are now accepted as necessary for genetic association studies.CDKAL1, CDK5 regulatory subunitassociated protein 1-like 1; CDKN2, cyclin-dependent kinase inhibitor 2A; FTO, fat mass and obesity-associated; HHEX, haematopoietically expressed homeobox; IDE, insulin-degrading enzyme; IGF2BP2, insulin-like growth factor 2 mRNA-binding protein 2; KCNJ11, potassium inwardly-rectifying channel, subfamily J, member 11; PPARG, peroxisome proliferator-activated receptor- gene; SLC30A8, solute carrier family 30 (zinc transporter), member 8; TCF2, transcription factor 2, hepatic; TCF7L2, transcription factor 7-like 2 (T-cell specific, HMg-box); WFS1, Wolfram syndrome 1.",
+      "\tCorrelation of the Susceptibility Loci with the Pathogenesis of T2D\n\nWith the large number of aforementioned genetic loci susceptible to T2D, the question pertains to how they participate in the pathogenesis of T2D.A great number of studies have suggested that genetic variants in or near KCNJ11, TCF7L2, WFS1, HNF1B, IGF2BP2, CDKN2A-CDKN2B, CDKAL1, SLC30A8, HHEX/IDE, KCNQ1, THADA, TSPAN8/LGR5, CDC123/CAMK1D, JAZF1, MTNR1B, DGKB/TMEM195, GCK, PROX1, ADCY5, SRR, CENTD2, ST6GAL1, HNF4A, KCNK16, FITM2-R3HDML-HNF4A, GLIS3, GRB14, ANK1, BCAR1, RASGRP1, and TMEM163 may confer T2D risk through impaired -cell function [16,24,44,68,[111][112][113][114], whereas PPAR, ADAMTS9, IRS1, GCKR, RBMS1/ITGB6, PTPRD, DUSP9, HMGA2, KLF14, GRB14, ANKRD55, and GRK5 have an impact on insulin action [21,24,115,116] (Tables 1, 2, and 3).FTO and MC4R, previously identified genes associated with obesity, appear to confer T2D risk through their primary effects on BMI, but recent GWAS have shown that their effects on T2D were independent of BMI, though FTO may have a small but detectable influence on T2D risk through insulin action [117,118].\t\n\nIn 2010, a meta-analysis of 21 genome-wide association studies performed by Dupuis and colleagues identified ADCY5, PROX1, GCK, GCKR, and DGKB/TMEM195 as new genetic loci for T2D susceptibility [22].Among these loci, DGKB/TMEM195, GCK, PROX1, and ADCY5 mainly affect -cell functions, whereas the locus mapped in GCKR shows a primary effect on insulin action [22].In the same year, another genome-wide association study by Qi and colleagues discovered new variants near RBMS1 and ITGB6 genes at 2q24, and these variants were found to affect glucose metabolism and insulin resistance [23].In addition, an expanded meta-analysis of existing GWAS by Voight and colleagues identified 12 new signals with a combined  < 5  10 8 , including BCL11A, ZBED3, KLF14, TP53INP1, TLE4, CENTD2, HMGA2, HNF1A, PRC1, ZFAND6, DUSP9, and KCNQ1 [24].HNF1A was previously recognized as the causal gene of MODY3 [62] and also harbored the common variant (G319S) that contributes to early-onset T2D [63,64].DUSP9, mapped on chromosome X, encodes a member of the family of mitogen-activated protein kinase phosphatase 4, MKP4, which is important in cell cycle regulation and plays pivotal roles in regulating insulin action [65][66][67].",
+      "\t\n\nOne obvious locus to consider is TCF7L2 in the context of type 2 diabetes.Common genetic variation located within the gene encoding transcription factor 7 like 2 (TCF7L2) has been consistently reported to be strongly associated with the disease.Such reports range from 2006, when we first published the association [3], to the recent transethnic meta-analysis GWAS of type 2 diabetes [4].",
+      "\t\n\nTesting of these loci for association with T2D as a dichotomous trait in up to 40,655 cases and 87,022 nondiabetic controls demonstrated that the fasting glucose-raising alleles at seven loci (in or near ADCY5, PROX1, GCK, GCKR and DGKB-TMEM195 and the known T2D genes TCF7L2 and SLC30A8) are robustly associated (P < 5  10 8 ) with increased risk of T2D (Table 2).The association of a highly correlated SNP in ADCY5 with T2D in partially overlapping samples is reported by our companion manuscript 29 .We found less significant T2D associations (P < 5  10 3 ) for variants in or near CRY2, FADS1, GLIS3 and C2CD4B (Table 2).These data clearly show that loci with similar fasting glucose effect sizes may have very different T2D risk effects (see, for example, ADCY5 and MADD in Table 2).",
+      "\t\n\nDespite identification of many putative causative genetic variants, few have generated credible susceptibility variants for type 2 diabetes.Indeed, the most important finding using linkage studies is the discovery that the alteration of TCF7L2 (TCF-4) gene expression or function (33) disrupts pancreatic islet function and results in enhanced risk of type 2 diabetes.Candidate gene studies have also reported many type 2 diabetes-associated loci and the coding variants in the nuclear receptor peroxisome proliferator-activated receptor-g (34), the potassium channel KCNJ11 (34), WFS1 (35), and HNF1B (TCF2) (36) are among the few that have been replicated (Table 2).Recently, there have been great advances in the analysis of associated variants in GWA and replication studies due to highthroughput genotyping technologies, the International HapMap Project, and the Human Genome Project.Type 2 susceptibility loci such as JAZF1, CDC123-CAMK1D, TSPAN8-LGR5, THADA, ADAMTS9, NOTCH2, and ADCY5 (37,38) are among some of the established loci (Table 2).CDKN2A/B, CDKAL1, SLC30A8, IGF2BP2, HHEX/IDE, and FTO are other established susceptibility loci for diabetes (Table 2) (34,39,40).GWA studies have also identified the potassium voltage-gated channel KCNQ1 (32) as an associated gene variant for diabetes.A recent GWA study reporting a genetic variant with a strong association with insulin resistance, hyperinsulinemia, and type 2 diabetes, located adjacent to the insulin receptor substrate 1 (IRS1) gene, is the C allele of rs2943641 (41).Interestingly, the parental origin of the single nucleotide polymorphism is of importance because the allele that confers risk when paternally inherited is protected when maternally transmitted.GWA studies for glycemic traits have identified loci such as MTNR1B (42), GCK (glucokinase) (42), and GCKR (glucokinase receptor) (42); however, further investigation of genetic loci on glucose homeostasis and their impact on type 2 diabetes is needed.Indeed, a recent study by Soranzo et al. (42) using GWA studies identified ten genetic loci associated with HbA 1c .Genetic factors affecting expression, turnover, and abnormal glycation of hemoglobin may be associated with changes in levels of HbA 1c .",
+      "\t\n\nG enome-wide association studies (GWAS) have iden- tified several type 2 diabetes mellitus (T2DM) susceptibility loci including CDKAL1, CDKN2B, IGF2BP2, HHEX, SLC30A8, PKN2, LOC387761 (1)(2)(3)(4)(5), and KCNQ1, which was recently identified by similar GWAS approach in two independent Japanese samples (6,7).Although these associations have been well replicated in Japanese populations (8), the role of these loci in other East Asian populations remains less clear.For example, a study in China by Wu et al. (9) did not find significant associations between single-nucleotide polymorphisms (SNPs) in IGF2BP2 and SLC30A8 with T2DM, whereas an association between SNPs at the HHEX locus and T2DM was reported among Chinese living in Shanghai, but not among Chinese in Beijing.Another study in Hong Kong Chinese (10) also did not find an association with SNPs at the IGF2BP2 locus; however, they reported an association between T2DM with SNPs at the HHEX and SLC30A8 loci.",
+      "\t\n\nMinor susceptibility might operate in some populations from other genes, including insulin receptor substrate 1 ( IRS -1 ), adiponectin ( ACDC ) or ectonucleotide pyrophosphatase/phosphodiesterase 1 enzyme ( ENPP1 ) in a context of obesity or diabesity. In genome scans of diabetic families, loci for T2DM have been found at several sites, including chromosomes 1q, 2q ( NIDDM1 ), 2p, 3q, 12q, 11q, 10q and 20.NIDDM1 has been identifi ed as coding for calpain 10, a non -lysosomal cysteine protease with actions at the mitochondria and plasma membrane, and also in pancreatic  -cell apoptosis. In 2007, fi ve large genome -wide association studies in European descent populations have identifi ed new potential T2DM genes, including the Wnt signaling related transcription factors TCF7L2 and HHEX , the zinc transporter ZnT8 ( SLC30A8 ), the CDK5 regulatory subunit -associated protein 1 -like 1 ( CDKAL1 ) and a regulatory protein for IGF2 ( IGF2BP2 ).A consensus of close to 20 confi rmed T2DMsusceptibility loci to date provided novel insights into the biology of T2DM and glucose homeostasis, but individually with a relatively small genetic effect.Importantly, these genes implicate several pathways involved in  -cell development and function. Compared with clinical risk factors alone, the inclusion of common genetic variants (at least those identifi ed to date) associated with the risk of T2DM has a small effect on the ability to predict future development of T2DM.At the individual level, however, a combined genotype score based on 15 risk alleles confers a 5 -8 fold increased risk of developing T2DM.Identifying the subgroups of individuals at higher risk is important to target these subjects with more effective preventative measures.",
+      "\t\n\nTesting of these loci for association with T2D as a dichotomous trait in up to 40,655 cases and 87,022 nondiabetic controls demonstrated that the fasting glucose-raising alleles at seven loci (in or near ADCY5, PROX1, GCK, GCKR and DGKB-TMEM195 and the known T2D genes TCF7L2 and SLC30A8) are robustly associated (P < 5  10 8 ) with increased risk of T2D (Table 2).The association of a highly correlated SNP in ADCY5 with T2D in partially overlapping samples is reported by our companion manuscript 29 .We found less significant T2D associations (P < 5  10 3 ) for variants in or near CRY2, FADS1, GLIS3 and C2CD4B (Table 2).These data clearly show that loci with similar fasting glucose effect sizes may have very different T2D risk effects (see, for example, ADCY5 and MADD in Table 2).",
+      "\tType 2 Diabetes\n\nCommon variants in 11 genes were significantly associated with the risk of future type 2 diabetes in the MPP cohort, including TCF7L2 (odds ratio, 1.30; P = 9.510 13 ), PPARG (odds ratio, 1.20; P = 4.010 4 ), FTO (odds ratio, 1.14; P = 9.210 5 ), KCNJ11 (odds ratio, 1.13; P = 3.610 4 ), NOTCH2 (odds ratio, 1.13; P = 0.02), WFS1 (odds ratio, 1.12; P = 0.001), CDKAL1 (odds ratio, 1.11; P = 0.004), IGF2BP2 (odds ratio, 1.10; P = 0.008), SLC30A8 (odds ratio, 1.10; P = 0.008), JAZF1 (odds ratio, 1.08; P = 0.03), and HHEX (odds ratio, 1.07; P = 0.03) (Table 2).Although these findings could not be fully replicated in the smaller Botnia study, there was little heterogeneity between the studies with respect to the risk conferred by different genotypes.\t\n\nOf the 16 loci that have been associated with type 2 diabetes previously, [8][9][10][11][12][13][14][15] we showed that 11 -TCF7L2, PPARG, FTO, KCNJ11, NOTCH2, WFS1, CDKAL1, IGF2BP2, SLC30A8, JAZF1, and HHEXwere associated with an enhanced risk of future diabetes.Many of the variants that we genotyped appear to influence beta-cell function, possibly through effects on proliferation, regeneration, and apoptosis.There was a time-dependent increase in the BMI and a decrease in insulin sensitivity in the subjects from the Botnia study, an increase in insulin resistance that was reflected by an increase in insulin secretion.However, this increase was inadequate to compensate for the increase in insulin resistance in carriers with a high genetic risk, which resulted in a markedly impaired disposition index.Only variants in FTO were associated with an increased BMI.Both FTO and PPARG together with TCF7L2 and KCNJ11 predicted transition from impaired fasting glucose levels or impaired glucose tolerance to manifest diabetes, which suggests that a combination of increased obesity and insulin resistance with a deterioration in beta-cell function contribute to the manifestation of diabetes in these subjects.Collectively, our findings emphasize the critical role of inherited defects in beta-cell function for the development of type 2 diabetes.",
+      "\t\n\nTo date, more than 70 genes have been identified as involved in T2DM, primarily by association analysis [34].In addition, via GWAS arrays, more than 100 SNPs have been identified for T2DM [35].From the 50 novel loci associated with T2DM previously identified, more than 40 loci have been associated with T2DM-related traits, including fasting proinsulin, insulin and glucose (Table 1) [36][37][38][39].However, for T2DM-related traits, such as the HOMA index or pancreatic  cell function, there are virtually no published data examining the relationship between these traits or the genotype and environment interactions.Clinical investigations of some loci have suggested that the genetic components of T2DM risk act preferentially through  cell function [40].Among all 40 loci associated with T2DM-related traits, only transcription factor-7-like 2 (TCF7L2) was shown to clearly contribute to T2DM risk [41].Several studies in white European [42], Indian [43], Japanese [44], Mexican American [45] and West African [46] individuals have shown a strong association between TCF7L2 and T2DM.It is also noteworthy that these populations represent the major racial groups with a high prevalence of T2DM.In all populations, TCF7L2 showed a strong association, with the odds of developing T2DM increased by 30%-50% for each allele inherited.This finding indicates an approximately double odds ratio compared to most other diabetes susceptibility polymorphisms.TCF7L2 is a transcription factor involved in the Wnt signaling pathway that is ubiquitously expressed, and it has been observed that TCF7L2 risk alleles result in the overexpression of TCF7L2 in pancreatic  cells.This overexpression causes reduced nutrient-induced insulin secretion, which results in a direct predisposition to T2DM as well as an indirect predisposition via an increase in hepatic glucose production [47].",
+      "\tCommon Variants\n\nThe development of GWAS spurred considerable progress identifying common variants [minor allele frequency (MAF)>0.05]associated with T2D (Table 1) and glycemic traits (Table 2).After early candidate gene and linkage studies identified common variants associated with T2D in PPARG, KCNJ11-ABCC8 and TCF7L2, the first five GWAS for T2D detected six additional loci, and by early 2008, GWAS and meta-analyses had identified 15 loci for T2D and G6PC2 as a locus for fasting glucose (10).Also in 2008, reports of the first non-European-based GWAS for T2D established KCNQ1 as a T2D locus with variants common in East Asians (MAF = 0.33) but low frequency in Europeans (MAF 0.01) (11,12).KCNQ1 risk variants showed similar effect sizes in both populations, demonstrating the role of allele frequency in power to detect loci (13).In 2010, a meta-analysis of European-ancestry individuals identified a second signal of T2D-associated variants near KCNQ1 that are not in marked linkage disequilibrium (LD) with the initial variants (r 2 < 0.05) and independent from them based on conditional analyses (14).By the end of 2011, further GWAS and meta-analyses in several populations had identified 55 loci for T2D (15,16).Also by 2011, GWAS had identified 32 total loci for one or more glycemic traits, including 17 for fasting glucose (15,17), 2 for fasting insulin (18), 5 for 2hGlu (19), 11 for HbA1c (20)(21)(22) and 9 for proinsulin, including 1 identified only in women (23).Incomplete overlap of loci between T2D and glycemic traits showed that not all effects on glucose levels in healthy individuals translate to the risk of T2D and vice versa.Based on the overlap between traits and the biological function of nearby genes, most identified T2D loci appeared to have a primary role in pancreatic islet -cell function, with far fewer impacting insulin resistance.",
+      "\t\n\nThe most replicated locus for susceptibility to T2D is TCF7L2, in which two intronic markers, rs12255372 and rs7903146, are associated with the disease across multiple, ethnically diverse populations [87][88][89][90][91][92][93][94][95][96][97][98][99][100].Because TCF7L2 is expressed in pancreatic -cells, and insulin secretion is reduced in individuals with the risk alleles at rs12255372 and rs7903146, carriers of these alleles may respond sub-optimally to sulfonylurea therapy due to decreased -cell function [101].A study involving 4469 participants from the Genetics of Diabetes Audit and Research Tayside (GoDARTs) provided evidence in support of this hypothesis by finding that individuals with the variant TT genotype at rs12255372 were less likely to respond to sulfonylurea treatment with a target HbA1c < 7% compared to carriers of the GG genotype (57% vs. 40%) [101].Further, individuals with the TT genotype were much less likely to achieve a target HbA1c of 7% within one year of initiating sulfonylurea treatment compared with carriers of the GG genotype [101].Similar results were observed with marker rs7903146.These results suggest that the TCF7L2 locus may not only affect susceptibility to T2D, but may also modulate response to sulfonylurea therapy; in both cases, the pathophysiology likely stems from impaired insulin secretion due to deteriorating -cell function.",
+      "\t\n\nThrough genome-wide association meta-analyses of up to 133,010 individuals of European ancestry without diabetes, including individuals newly genotyped using the Metabochip, we have increased the number of confirmed loci influencing glycemic traits to 53, of which 33 also increase type 2 diabetes risk (q < 0.05).Loci influencing fasting insulin concentration showed association with lipid levels and fat distribution, suggesting impact on insulin resistance.Gene-based analyses identified further biologically plausible loci, suggesting that additional loci beyond those reaching genome-wide significance are likely to represent real associations.This conclusion is supported by an excess of directionally consistent and nominally significant signals between discovery and follow-up studies.Functional analysis of these newly discovered loci will further improve our understanding of glycemic control.",
+      "\tRESULTS-\n\nWe confirmed the associations of TCF7L2, SLC30A8, HHEX, CDKAL1, CDKN2A/CDKN2B, IGF2BP2, and FTO with risk for type 2 diabetes, with odds ratios ranging from 1.13 to 1.35 (1.3  10 12  P unadjusted  0.016).In addition, the A allele of rs8050136 at FTO was associated with increased BMI in the control subjects (P unadjusted  0.008).However, we did not observe significant association of any genetic variants with surrogate measures of insulin secretion or insulin sensitivity indexes in a subset of 2,662 control subjects.Compared with subjects carrying zero, one, or two risk alleles, each additional risk allele was associated with 17% increased risk, and there was an up to 3.3-fold increased risk for type 2 diabetes in those carrying eight or more risk alleles.Despite most of the effect sizes being similar between Asians and Europeans in the metaanalyses, the ethnic differences in risk allele frequencies in most of these genes lead to variable attributable risks in these two populations.",
+      "\t\n\nRESULTS-We confirmed the association of all eight loci with type 2 diabetes with odds ratio (OR) ranging from 1.18 to 1.89 (P  1.6  10 3 to 4.6  10 34 ).The strongest association with the highest effect size was observed for TCF7L2 (OR 1.89 [95% CI 1.71-2.09],P  4.6  10 34 ).We also found significant association of PPARG and TCF7L2 with homeostasis model assessment of -cell function (P  6.9  10 8 and 3  10 4 , respectively), which looked consistent with recessive and under-dominant models, respectively.CONCLUSIONS-Our study replicates the association of wellestablished common variants with type 2 diabetes in Indians and shows larger effect size for most of them than those reported in Europeans.Diabetes 59:2068-2074, 2010 T ype 2 diabetes is a complex metabolic disorder with both genetic and environmental factors such as food habits and lifestyle contributing to its pathogenesis (1).Due to its complex etiology, the progress of discovery of genetic components for type 2 diabetes had been very slow until the advent of high throughput genome-wide association (GWA) studies (2).Until recently, only a few common variants in PPARG (3), KCNJ11 (4), and TCF7L2 (5) were shown to be associated with type 2 diabetes.With the advent of GWA studies, there are at least 20 loci identified today that are associated with the risk of type 2 diabetes (6).The first GWA study in the French population revealed SLC30A8 and HHEX as new loci for type 2 diabetes in addition to replicating the strong association with TCF7L2 (7).Further, GWA studies added several new genes including CDKAL1, CDKN2A, IGF2BP2, and FTO to the list of type 2 diabetes-associated loci and confirmed the associations for PPARG, KCNJ11,.\t\n\nOBJECTIVE-Common variants in PPARG, KCNJ11, TCF7L2, SLC30A8, HHEX, CDKN2A, IGF2BP2, and CDKAL1 genes have been shown to be associated with type 2 diabetes in European populations by genome-wide association studies.We have studied the association of common variants in these eight genes with type 2 diabetes and related traits in Indians by combining the data from two independent case-control studies.",
+      "\t\n\nFG-associated loci from GWAS studies have also helped define the relationship between T2D and abnormal insulin processing and secretion in -cells.Among other glycemic trait analyses by the MAGIC, nine genome-wide significant loci were described for corrected insulin response (CIR), seven of which were previously associated with both T2D and other glycemic traits (MTNR1B, GCK, HHEX/ IDE, CDKAL1, CDKN2A/2B, ANK1, C2CD4A/B) (Prokopenko et al. 2014).Two other loci included G6PC2 associated with glycemic trait variability in nondiabetic individuals and the novel GRB10 association, which showed potential tissuespecific methylation and parental imprinting that might mask its association with T2D).Meta-analysis of GWA studies by MAGIC for fasting proinsulin levels adjusted for FI identified eight loci, of which four demonstrated that both proinsulin-raising (for TCF7L2, SLC30A8, and VPS13C/C2CD4A/B) and proinsulin-lowering alleles (for ARAP1) influenced T2D risk through a decrease in insulin secretion caused by distal or proximal impairment of proinsulin conversion, respectively (Strawbridge et al. 2011).Similarly, Dimas and colleagues described associations at the HHEX/IDE and MTNR1B loci with defects in early insulin secretion through reduced insulinogenic index for the T2D risk allele and showed that the T2D risk allele at ARAP1 was related to defects in the first steps of insulin production, through association with 32,33 split proinsulin (Dimas et al. 2014).",
+      "\tUnderstanding the biology of T2D-susceptibility loci\n\nThis analysis takes the number of independent loci showing genomewide significant associations with T2D beyond 35.For some, such as those at KCNJ11 and SLC30A8, the molecular mechanisms responsible for the susceptibility effect can be assigned with some confidence 42 .At others, the identities of the causal variants, the genes through which they act and the pathophysiological processes which they influence remain obscure.We used several approaches designed to link DIAGRAM+ and previously reported T2D association signals to biological insights relevant to T2D pathogenesis."
+    ],
+    [
+      "\tGenome-Wide Association Study (GWAS). With the advent of GWAS, exploration of the genetic basis for T2D susceptibility has made significant breakthroughs.In 2007, the results of five genome-wide association studies were published.These studies increased the number of confirmed T2D susceptibility loci to nine (PPAR, KCNJ11, TCF7L2, CDKAL1, CDKN2A/B, IGF2BP2, HHEX/IDE, FTO, and SLC30A8) [13][14][15][16][17][18].Except for PPAR and FTO, which mainly affect insulin sensitivity, all the other genes may affect cell function, although the exact mechanisms remain largely unknown [16].HHEX, which is located on chromosome 10q, is a member of the homeobox family and encodes a transcription factor that maybe involved in Wnt signaling [58].Nevertheless, these studies established the utility of GWAS approach in elucidating complex genetic traits.",
+      "\t\n\nThe application of genome wide association studies (GWAS) has robustly revealed dozens of genetic contributors to T1D [23][24][25][26][27][28][29], the results of which have largely been independently replicated [30][31][32][33][34][35][36].The most recently reported meta-analysis of this trait identified in excess of forty loci [29], including 18 novel regions plus confirmation of a number of loci uncovered through crossdisease comparisons [34][35][36].As such, the risks conferred by these additional loci are relatively modest compared to the 'low-hanging fruit' described in the first studies and could only be ultimately uncovered when larger sample sizes were utilized.",
+      "\t\n\nBy contrast, knowledge of the genetic basis of diabetes is incomplete, despite Herculean efforts (8)(9)(10)(11)(12).Genome-wide association studies have accelerated the discovery of single-nucleotide polymorphisms (SNPs) at numerous loci.Comparison of the frequencies of these SNPs in case-control studies has enabled the calculation of the odds of their association with specific disease phenotypes.To date, genome-wide studies have added more than 4,000 SNPs involving some 200 diseases, including .30diabetes-related SNPs (diabetoSNPs).The analysis of dia-betoSNPs has intrinsic appeal as a tool for diabetes prediction, and could also yield potential clues to ethnic disparities in the susceptibility to type 2 diabetes.Because the diabetoSNPs individually confer modest effects, investigators have adopted an approach based on cumulative genetic risk score (GRS) at several loci to improve sensitivity (13)(14)(15)(16).Using available information on the relative odds of diabetes per risk allele (11,12), investigators can further calculate a weighted GRS.",
+      "\t\n\nGenomic variations and DNA profiling of those at risk for type 2 diabetes Despite many candidate gene studies and genome-wide linkage studies, very few susceptibility loci for type 2 diabetes have been identified until the recent emergence of genomic-wide association (GWA) data and large-scale replication studies (Table 2).Meta-analysis of GWA studies provides the unique opportunity to investigate the heterogeneity or consistency of genomic associations across diverse datasets and study populations.Recently, Voight et al. (32), using large-scale association analyses combining the data from eight GWA studies, identified 12 new susceptibility loci for type 2 diabetes.",
+      "\t\n\nBackground: Genome-wide association studies (GWAS) identify regions of the genome that are associated with particular traits, but do not typically identify specific causative genetic elements.For example, while a large number of single nucleotide polymorphisms associated with type 2 diabetes (T2D) and related traits have been identified by human GWAS, only a few genes have functional evidence to support or to rule out a role in cellular metabolism or dietary interactions.Here, we use a recently developed Drosophila model in which high-sucrose feeding induces phenotypes similar to T2D to assess orthologs of human GWAS-identified candidate genes for risk of T2D and related traits.Results: Disrupting orthologs of certain T2D candidate genes (HHEX, THADA, PPARG, KCNJ11) led to sucrose-dependent toxicity.Tissue-specific knockdown of the HHEX ortholog dHHEX (CG7056) directed metabolic defects and enhanced lethality; for example, fat-body-specific loss of dHHEX led to increased hemolymph glucose and reduced insulin sensitivity.",
+      "\tGenome-Wide Association Studies (GWAS)\n\nCompletion of the Human Genome Project in 2003 [44] led to subsequent advances in biomedical research.Since 2007, a new technology in the form of 'genome-wide chips' has facilitated remarkable progress in T2D genetic research with the first publication of five large GWA scans within the span of four months, showing that more than 500,000 SNP markers distributed across the genome [45][46][47][48][49].This approach has been successful in locating genes for other diseases besides T2D and obesity [40] namely, type 1 diabetes [50], prostate cancer [51], rheumatoid arthritis [52], Crohns disease [53,54], and cardiovascular disease [55] and is being applied to other complex disorders.Use of this 'hypothesis-free' approach involved in GWAS has opened new areas of biology to explore as discoveries of more than seventy entirely new T2D loci clearly suggest that associations are not limited to candidate genes and by applying GWAS and re-sequencing approaches, new genes involved in disease pathogenesis can be identified [56] (Table 1).",
+      "\t\n\nGenome-wide association studies (GWAS) have made a significant contribution to our current knowledge of the role(s) of genetic variation in population-level susceptibility to T1D (Mychaleckyj et al., 2010).",
+      "\t\n\nOver the past few years, genome-wide association studies (GWAS) have been extremely successful in detecting loci associated with complex disease traits such as obesity and T2D.GWAS is a hypothesis-free method where many genetic markers (usually more than one million single nucleotide polymorphisms [SNPs]) spread over the entire genome are tested for association with disease traits.This method differs from the traditional biologic candidate gene approach in that it is agnostic to prior biological knowledge about a specific gene's role in disease and is hence unbiased in this respect.This approach instead relies heavily on replication of association signals across multiple populations and generally requires very large sample sizes to overcome the power constraints inherent in conducting so many association tests [72].GWAS have confirmed the three previously identified signals for T2D which localize to transcription factor 7-like 2 (TCF7L2), peroxisome proliferative activated receptor, gamma (PPARG), and potassium inwardly rectifying channel, subfamily J, member 11 (KCNJ11), and identified many new susceptibility loci [73][74][75][76][77][78].More than 40 T2D loci have been discovered and replicated to date, most of which localize to genes that appear to influence beta-cell function [79].These findings highlight the role of inherited defects in beta-cell function rather than defects in genes causing insulin resistance in the etiology of T2D [80,81].",
+      "\tIntroduction\n\nGenome-wide association studies (GWAS) have identified approximately 80 loci robustly associated with predisposition to type 2 diabetes (T2D) [1][2][3] and a further 70 influencing a range of continuous glycemic traits [4][5][6][7][8][9][10] in non-diabetic subjects.There is substantial, though far from complete, overlap between these two sets of loci.Physiological studies in non-diabetic individuals indicate that most of these loci primarily influence insulin secretion rather than insulin sensitivity, highlighting a key role for the pancreatic islets of Langerhans in the mechanistic underpinnings of these association signals [11,12].These findings have motivated efforts to catalogue the epigenomic and transcriptional landscape of human islets and to apply these findings to deliver biological insights into disease pathogenesis.Recently, it has been shown, for example, that GWAS signals for T2D and fasting glucose show significant co-localization with islet enhancers [13,14].",
+      "\t\nIt has proven to be challenging to isolate the genes underlying the genetic components conferring susceptibility to type 1 and type 2 diabetes.Unlike previous approaches, 'genome-wide association studies' have extensively delivered on the promise of uncovering genetic determinants of complex diseases, with a number of novel disease-associated variants being largely replicated by independent groups.This review provides an overview of these recent breakthroughs in the context of type 1 and type 2 diabetes, and outlines strategies on how these findings will be applied to impact clinical care for these two highly prevalent disorders.",
+      "\t\n\nGenome-wide association studies (GWAS) have discovered germline genetic variation associated with type 2 diabetes risk (1)(2)(3)(4).One of the largest GWAS, involving DNA taken from individuals of European descent and conducted by the DIAGRAM (DIAbetes Genetics Replication And Meta-analysis) consortium, identified 65 loci associated with type 2 diabetes risk (1).However, for most of these loci, the precise identity of the affected gene and the molecular mechanisms underpinning the altered risk are not known.",
+      "\t\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.\t\n\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.",
+      "\t\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.",
+      "\t\nGenome-wide association (GWAS) and sequencing studies are providing new insights into the genetic basis of type 2 diabetes (T2D) and the inter-individual variation in glycemic traits, including levels of glucose, insulin, proinsulin and hemoglobin A1c (HbA1c).At the end of 2011, established loci (P < 5  10 8 ) totaled 55 for T2D and 32 for glycemic traits.Since then, most new loci have been detected by analyzing common [minor allele frequency (MAF)>0.05]variants in increasingly large sample sizes from populations around the world, and in trans-ancestry studies that successfully combine data from diverse populations.Most recently, advances in sequencing have led to the discovery of four loci for T2D or glycemic traits based on low-frequency (0.005 < MAF  0.05) variants, and additional low-frequency, potentially functional variants have been identified at GWAS loci.Established published loci now total 88 for T2D and 83 for one or more glycemic traits, and many additional loci likely remain to be discovered.Future studies will build on these successes by identifying additional loci and by determining the pathogenic effects of the underlying variants and genes.\t\n\nGenome-wide association (GWAS) and sequencing studies are providing new insights into the genetic basis of type 2 diabetes (T2D) and the inter-individual variation in glycemic traits, including levels of glucose, insulin, proinsulin and hemoglobin A1c (HbA1c).At the end of 2011, established loci (P < 5  10 8 ) totaled 55 for T2D and 32 for glycemic traits.Since then, most new loci have been detected by analyzing common [minor allele frequency (MAF)>0.05]variants in increasingly large sample sizes from populations around the world, and in trans-ancestry studies that successfully combine data from diverse populations.Most recently, advances in sequencing have led to the discovery of four loci for T2D or glycemic traits based on low-frequency (0.005 < MAF  0.05) variants, and additional low-frequency, potentially functional variants have been identified at GWAS loci.Established published loci now total 88 for T2D and 83 for one or more glycemic traits, and many additional loci likely remain to be discovered.Future studies will build on these successes by identifying additional loci and by determining the pathogenic effects of the underlying variants and genes.",
+      "\t\n\nGenome-wide association (GWA) studies represent the single most effective technique for identifying genetic risk loci causing complex diseases.Since the publication of the first GWA studies for type 2 diabetes (T2D) in 2007, nearly 90 statistically robust risk loci have been identified.The T2D risk loci identified by GWA studies contained several genes that are targets of current diabetic therapies; however, the majority of genes in these loci had not previously been implicated in the pathophysiology of T2D.Mechanistic insights about the physiological role of T2D loci in the disease predisposition have been gained from investigation of their contribution into glycemic trait variability in nondiabetic individuals.Current efforts to identify the causative genetic mutations in these loci and the molecular mechanisms through which they exert their effects have the potential to make far-reaching contributions to our understanding of molecular basis of T2D and the development of novel strategies for patient care.\t\nGenome-wide association (GWA) studies represent the single most effective technique for identifying genetic risk loci causing complex diseases.Since the publication of the first GWA studies for type 2 diabetes (T2D) in 2007, nearly 90 statistically robust risk loci have been identified.The T2D risk loci identified by GWA studies contained several genes that are targets of current diabetic therapies; however, the majority of genes in these loci had not previously been implicated in the pathophysiology of T2D.Mechanistic insights about the physiological role of T2D loci in the disease predisposition have been gained from investigation of their contribution into glycemic trait variability in nondiabetic individuals.Current efforts to identify the causative genetic mutations in these loci and the molecular mechanisms through which they exert their effects have the potential to make far-reaching contributions to our understanding of molecular basis of T2D and the development of novel strategies for patient care. IntroductionType 2 diabetes (T2D) is a common, chronic disorder whose prevalence is increasing rapidly across the globe.Like other complex diseases, T2D represents a challenge for genetic studies aiming to uncover the underlying pathophysiological mechanisms.It is predicted that T2D will affect 592 million individuals by 2035 (Federation 2013) in developed and low-and middle-income countries.While the recent increase in T2D prevalence has been attributed to a sedentary \"westernized\"",
+      "\t\n\nFamily-based studies of the genetic determinants of type 2 diabetes and related precursor quantitative traits (QTs, e.g.plasma insulin and glucose levels)  and GWA studies have now provided an abundance of evidence for potentially causative genes.These results have been drawn together onto a single map of the human genome sequence [86].The goal is to look for genomic locations where the presence of a potential underlying type 2 diabetes gene has been attested to repeatedly-diabetes genetic 'hot spots'.Such replication increases our confidence of the presence of an underlying gene.While GWA studies look for diabetes genes using a different approach to linkage analysis, the ultimate goal is the same-to find the genetic determinants of the disease.Therefore, the results of linkage and association must eventually match each other.The current analysis identifies multiple linkage locations that differ from those found in the recent GWA studies [87-89], and suggests the location of additional major type 2 diabetes susceptibility genes.",
+      "\tINTRODUCTION\n\nMultiple genome-wide association studies (GWASs) have correlated type 2 diabetes mellitus (T2DM) with genetic variants, yielding a large number of loci and associated gene products that are linked to the disease phenotype-often with little or no insight into the mechanism underlying that link (Hivert et al., 2014).The current challenge is to establish robust systems to systematically evaluate the role of these loci using disease-relevant cells.Previous studies have used patient samples, cell lines, or animal models to seek mechanistic insight but with significant limitations.Large variation is observed in primary patient samples, perhaps due to genetic heterogeneity, whereas animal models present major physiological and metabolic differences that hamper understanding of the precise function of human genes in T2DM.Therefore, a robust system to systematically evaluate the role of T2DM-associated genes using disease-relevant human cells will provide an important tool for diabetes research and spur the development of precision (allele-specific) therapies, exemplified by the use of sulfonylurea drugs to treat patients carrying certain KCNJ11 mutations (Gloyn et al., 2004)."
+    ],
+    [
+      "\tB. HLA Genes\n\nEarly studies indicated that the HLA region on chromosome 6p21 (commonly termed IDDM1, for insulin-dependent diabetes mellitus locus) is a critical susceptibility locus for many human autoimmune diseases, including T1D (305,399).These initial findings revolutionized our understanding of T1D etiology in two ways, as stated by Nerup et al. (305) in conclusion of their 1974 report: 1) T1D is a distinct disease entity, corroborating histopathological evidence; and 2) an aberrant cellular immune response, potentially triggered by viral infection, instigates onset.Numerous new susceptibility loci have emerged since, but none of them matches the strong association found with the HLA region.It is unlikely that new loci will ever be discovered that confer such a dramatic risk to T1D development (96).In genetic studies, the odds ratio is the statistic used to calculate whether a single nucleotide polymorphism (SNP) given is associated with the disease.An odds ratio of one implies that the event is equally likely in both patient and control groups.Odds ratios of alleles predisposing to complex disorders are typically modest, often in the range of 1.2-1.3,and even the HLA region has a predicted value of only 6.8.This suggests that if genetic predisposition is indeed a dominant factor in T1D development, a vast amount of common SNPs are still waiting to be discovered (96,159).After several decades of continuous progress since the discovery of HLA association (for historical perspective, see Ref. 285), the class II genes remain the strongest genetic contributor (138,323,429,433,439).Several HLA class II genes are pivotal as their alleles were found to determine a susceptibility hierarchy ranging from protection to strongly at-risk (15,73,105,134,135,237,309,393).The DRB1*1501-DQA1*0102-DQB1*0602 haplotype, found in 20% of the population but only 1% of patients, confers dominant protection against T1D (134).At the susceptible end of this spectrum are individuals with the DR3/4-DQ8 heterozygous haplotype (DR3 is DRB1*03-DQB1*0201, DR4 is DRB1*04-DQB1*0302, DQ8 is DQA1*0301, DQB1*0302).It is important to note that only 30 -50% of patients with T1D have the DR3/4-DQ2/8 genotype.A study in the Denver, Colorado area (15) identified this high-risk haplotype in 2.4% of newborns and more than 20% of the children affected by T1D, and its presence marks a 55% risk of developing overt diabetes by age 12. DR3/4-DQ2/8 siblings who are HLA identical to a diabetic proband have a risk as high as 80% for persistent anti-islet autoantibodies and 60% for progression to diabetes by age 15 (15).",
+      "\t\n\nIt has been long established that approximately half of the genetic risk for T1D is conferred by the genomic region harboring the HLA class II genes (primarily HLA-DRB1, -DQA1 and -DQB1 genes), which encode the highly polymorphic antigen-presenting proteins.Other established loci prior to the application of GWAS are the genes encoding insulin (INS) [9][10][11][12], cytotoxic Tlymphocyte-associated protein 4 (CTLA4) [13][14][15][16], protein tyrosine phosphatase, non-receptor type 22 (PTPN22) gene [17,18], interleukin 2 receptor alpha (IL2RA) [19][20][21] and ubiquitinassociated and SH3 domain-containing protein A (UBASH3A) [22].",
+      "\tDiscussion\n\nThe study of the HLA region in type 1 diabetes is a model for the identification of the actual diseasepredisposing variants in complex diseases, as well as for determining when all the genetic factors in a region have been identified (17) .\tIntroduction\n\nIt long has been established that approximately half of the genetic risk for T1D is conferred by the genomic region harboring the human leukocyte antigen HLA class II genes (primarily HLA-DRB1, -DQA1 and -DQB1 genes), which encode the highly polymorphic antigen-presenting proteins.The greatest risk arises when both haplotypes are present in the same individual (1,2,3,4) .",
+      "\t\n\nStudies by Valdes et al. have reported that HLA class I alleles associate with age-of-onset of T1D (Valdes et al., 2012(Valdes et al., , 1999)).Several alleles in the HLA class I region (Table 2) appear to confer high risk, but this effect is modified when accounting for LD with class II haplotypes (Noble et al., 2002).The HLA-B*39:06 allele, for instance, has the strongest risk of T1D susceptibility with an odds ratio of 10.31, while HLA-B*57:01 appears to be highly protective with an OR of 0.19 even after considering the LD with DQ and DR (Noble et al., 2010).Notably, Mikk et al. suggested that B*39:06 can significantly improve the prognosis of T1D disease, especially in patients with the DRB1*04:04-DQA1*03:01-DQB1*03:02 class II haplotypes (Mikk et al., 2014).Therefore, it is important to account for LD when elucidating for genetic risk within the class I locus.\t\n\nAs such, the HLA-encoding region is the most strongly associated T1D locus (Mychaleckyj et al., 2010).However, the molecular understanding of how HLA contributes to T1D remains unclear due the large number of distinctive HLA alleles and unusual frequencies that make the overall mechanism difficult to interpret (Sanchez-Mazas and Meyer, 2014).This has raised new questions, particularly with respect to the approximation of genetic distances, and other significant statistics in population genetics studies (Buhler and Sanchez-Mazas, 2011;Sanchez-Mazas and Meyer, 2014).As such, improving our understanding of the basic biology of the HLA locus is an essential facet of research into the mechanisms and causes of T1D.",
+      "\t\n\nAssociation to T1D at the HLA Prior to the advent of genome-wide linkage scans, the role of the Human Leukocyte Antigen (HLA) gene region in immune regulation, and ready availability of serologic markers, led investigators to discover the association between certain HLA alleles and T1D in the early 1970s (33,130,158).The global importance of the HLA on T1D has since been confirmed in genome-wide scans for linkage: All such scans performed to date show a major locus at the HLA (28,32,36,78,119).The fraction of all genetic risk, which can be attributed to the contribution of HLA genes to T1D susceptibility, is about 44%, with a  S of 3.4 (160).",
+      "\tGenetic association studies in type 1 diabetes\n\nThe first locus to be successfully associated with type 1 diabetes susceptibility was the HLA locus on chromosome 6p (94)(95)(96).HLA genes fall into two major classes, class I and class II [see Redondo et al. (20) for review of nomenclature].Other genes, many related to the immune system, are also located in the HLA region.Early studies indicated that the strongest associations were with class II genes and, in particular, the HLA-D genes (97) encoding DRb (HLA-DRB), DQa (HLA-DRA) and DQb (HLA-DQB).The focus was initially narrowed to the DR3 and DR4-containing chromosomes, which confer strong risk (see, e.g., Platz et al. (98) and Schober et al. (99); DR2 was found to be protective (98).These findings have been consistently reproducible, with very strong associated risks: 90% of patients carry a DR3-or DR4-containing haplotype compared with 20% of the general population (20), for an odds ratio of approximately (0.9  0.8)/ (0.1  0.2)  36.The odds ratio for compound heterozygotes carrying both DR3 and DR4 is even higher, estimated at approximately 75 (35% of patients vs. 2.4% of controls).\t\n\nSubsequent studies attempting to further localize the risk alleles have been complicated by long-range linkage disequilibrium, which can extend for 500 kb to over 1 Mb in the case of DR3 (104).Thus, an allele at one location in the HLA may show association with diabetes because of correlation with a causal allele elsewhere.For example, it seems likely that the HLA region contains additional alleles, outside the class II genes, that affect diabetes risk (105).However, linkage disequilibrium makes it difficult to localize these genes precisely (106).One approach is to compare individuals who are identical for the major associated haplotypes but differ at other regions in the HLA (107,108).By examining the HLA regions of such individuals in detail, it may be possible to eventually sort out the intricacies of the relationship between alleles in HLA and type 1 diabetes susceptibility.However, large numbers of patients will be needed to identify the few people in whom linkage disequilibrium has broken down, and these individuals will need to be extensively characterized, perhaps by complete resequencing, before definitive conclusions can be drawn.Once the relevant alleles are definitively identified, the next challenge will be to elucidate the mechanisms by which these alleles mod-ulate autoimmunity and lead to diabetes.Given the known function of class II genes in antigen presentation, a probable explanation is differing efficiency in presentation of either islet cell antigens or foreign peptides that mimic islet cell antigens.",
+      "\t\n\nGenetic, functional, structural, and animal model studies all indicate that the highly polymorphic HLA class II molecules, namely the DR and DQ - heterodimers, are central to susceptibility to type 1 diabetes (4,5).The genes encoding these proteins are located in the HLA region, which spans 4,000 kb of DNA on human chromosome 6p21.3.The HLA region comprises 200 genes, and 40% of the expressed genes are predicted to have immune re-sponse functions (6,7).In addition to the class II genes HLA-DRB1 and HLA-DQB1, any one (or more) of these MHC genes, including the other HLA genes, could contribute to the overall risk for type 1 diabetes.The exact mechanism(s) by which the HLA class II molecules confer susceptibility to immune-mediated destruction of the pancreatic islets is still not known in its entirety, but the binding of key peptides from autoantigens (preproinsulin, GAD, insulinoma-associated 2 antigen, and zinc transporter, ZnT8, so far identified) to HLA class II molecules in the thymus and in the periphery are likely to play an important role.Theoretically, targeting this process of antigen presentation and T-cell activation may be an effective therapeutic approach to preventing type 1 diabetes.In practice, HLA screening is used to identify people at risk for developing type 1 diabetes, for inclusion in, and exclusion from, clinical studies (8) and clinical trials (9).\t\n\nOther features of the HLA-type 1 diabetes association were also examined; however, only support for an HLA effect by age at diagnosis was found (15)(16)(17)(18).Presumably, the risk conferred by specific HLA class I and class II alleles and haplotypes reflects the specificity of peptide binding and presentation (19,20).New genomic knowledge will better define the naturally processed peptides from autoantigens in type 1 diabetes.Intriguingly, a decrease in high-risk HLA genetic contribution in new-onset cases over the last decades has been observed in several studies, suggesting a change in environmental impact on penetrance as the incidence of type 1 diabetes increases (21)(22)(23).",
+      "\t\n\nLinkage studies have demonstrated that the HLA re- gion, termed IDDM1, is the major genetic determinant of IDDM susceptibility (see, e.g., Davies et al. 1994).From affected-sib-pair HLA haplotype sharing data, Risch (1987) estimated that the HLA component of IDDM susceptibility (Xs for HLA) accounts for a 3.42- fold increased risk in siblings over the population prevalence, compared to an observed 15-fold increased risk in siblings due to all genetic factors (Xs).Under a multi- plicative model, Risch calculated that HLA contributes -44% to the genetic risk for IDDM.",
+      "\t\n\n1. Finding the region does not readily give you the gene or mechanism.More than 25 years ago, it was discovered that alleles at the human leukocyte antigen (HLA) class I HLA-B locus were associated with Type I diabetes, using case-control association studies [4850].HLA loci were candidates for predisposition to autoimmunity because HLA molecules have a critical role in the regulation of the immune response by binding and presenting foreign or selfantigens to T lymphocytes.Later studies showed that HLA class II loci, including HLA-DRB1, DQB1 and DQA1, were even more strongly associated with diabetes.As a result of several genome-wide linkage screens [61,62,73,83], it is now clear that the most potent diabetes-predisposing genes in the entire genome are located in the HLA region on chromosome 6p21.3(these HLA region susceptibility genes are now collectively referred to as IDDM1).However, because of the extensive degree of linkage disequilibrium among the various HLA loci, it has been difficult to determine which precise locus produces diabetes susceptibility (for review, see [92]).Many studies have shown that diabetics of European ancestry have higher frequencies of HLA-DR3 and DR4 (variants at DRB1).For example, 96 % of Cana-dian Type I diabetic children had at least one of these alleles, compared with 46 % of the general population [93].However, DR4 haplotypes in diabetics were found to have a higher frequency of DQB1*0302 at the nearby HLA-DQB1 locus than DR4 haplotypes in control subjects [51], which suggested that DQB1 rather than DRB1 might be the primary diabetes susceptibility locus.Similarly, several HLA haplotypes positively associated with Type I diabetes (including DR4-DQB1*0302) were found to encode an amino acid other than aspartate at position 57 of the DQB1 chain, again implying that DQB1 was the primary susceptibility locus [52].However, an elegant study showed that DR4 haplotypes encoding both DRB*0401 (a subtype of DR4) and DQB*0302 were more diabetogenic than DR4 haplotypes encoding only one of these [53]  thus, DRB1 and DQB1 together could confer susceptibility.The HLA-DQA1 locus also appears to be involved in susceptibility [54,55].In addition to susceptibility alleles, there are also protective alleles.For example, DR2 haplotypes carrying DRB1*1501 and DQB1*0602 confer strong (apparently dominant) protection against diabetes.Because it is not yet known which antigens (presented with HLA to the immune system) are critical to initiating autoimmune diabetes, the mechanism by which HLA genes produce susceptibility to (or protection from) diabetes has not yet been established.One recent model is that susceptible HLA-DR and DQ molecules bind diabetogenic antigens with low affinity and allow escape from the thymus into the periphery of self-reactive T cells, while protective HLA molecules bind with high affinity, resulting in thymic negative selection of autoreactive T cells [94].This model could explain the dominant effect of protective alleles.It has also been suggested that, in addition to HLA, other genes within the HLA region are associated with Type I diabetes [9597], but these associations could be secondary to linkage disequilibrium with HLA [98101].Numerous linkage studies have also shown the existence of susceptibility genes in the HLA region.In 538 diabetic sibpairs, 54 % shared two HLA haplotypes and only 7.3 % shared zero haplotypes, both frequencies significantly different from the 25 % expected [102].From these data, one can estimate the increased risk to siblings of diabetics attributable to HLA region genes to be about 3.4 (HLA l sib = ratio of expected to observed sharing of zero haplotypes in siblings = 0.25/0.073= 3.4) [3].Because the total increase in risk to siblings is about 15 (see above), the HLA contribution to total familial clustering of diabetes is about 44 % (assuming that l sib values are multiplicative, 15/3.4 = 4.4, and 3.4/[3.4+ 4.4] = 44 %).In summary, it appears that the largest genetic contribution to Type I diabetes is through HLA-DRB, DQB and DQA alleles, which confer varying degrees of susceptibility or resistance.However, after more than 25 years of study, it is still not clear how and in which combinations the HLA genes produce their predisposing or protective effects.",
+      "\t\n\nIn humans, certain alleles of DR and DQ loci of the HLA region (human MHC) have been shown to be associated with, and linked to, IDDM (4).Recent studies indicated that up to 50% of IDDM susceptibility is determined by genes in the HLA region (5,6) and that genetic markers located as far as 20 centiMorgan (cM) away from the class II HLA region still show linkage with putative susceptibility genes (5).These data indicate the importance of MHC-linked genes-in the predisposi- tion to the disease.",
+      "\t\n\nFollowing decades of effort to unravel the \"enigma\" of T1D genetics, nearly 50 loci have (thus far) been associated with susceptibility to the disease (Fig. 3) (Cooper et al. 2008;Concannon et al. 2009;Pociot et al. 2010).Nevertheless, no single gene is in-and-of-itself either necessary or sufficient to predict the development of T1D.The first T1D susceptibility locus identified, the Human Leukocyte Antigen (HLA) complex, provides the greatest contribution (i.e., 60%) to the overall genetic susceptibility.There are three classes of HLA genes, with class II genes having the strongest association with T1D (Redondo et al. 2001).Because class II HLA genes encode for molecules that participate in antigen presentation, the effect of MHC allelic variability on T1D risk may, for example, be explained by differences in the presentation of b-cell antigens, either by promoting anti-self-reactivity or by the failure to impart regulated immune responses (Mallone et al. 2005).The great majority of T1D patients carry the HLA-DR3 or -DR4 class II antigens, with 30% being DR3/DR4 heterozygous.In Caucasians, the DR3/DR4 genotype confers the highest T1D risk, followed by DR4 and DR3 homozygosity, respectively.Conversely, the class II allele, DQB1  0602, in linkage disequilibrium with DR2, is associated with protection from the development of T1D and is found in ,1% of patients with T1D (Redondo et al. 2001).",
+      "\t\n\nThe major genetic risk factors are the HLA class II haplotypes HLA-DR3-DQ2 and HLA-DR4-DQ8 on chromosome 6 (REFS 49-51).The risk of develop ing celltargeted autoimmunity on the extended HLADRDQ haplotype is complicated by a large number of HLA-DRB1 alleles in humans.Specifically, on the HLA-DQ8 haplotype, HLA-DRB1*04:01 and HLA-DRB1*04:05 are associated with greater suscep tibility to T1DM than is HLA-DRB1*04:04, whereas HLA-DRB1*04:03 is protective [52][53][54] .These haplotypes are often associated with insulin autoantibodies 55 , but the extended haplotype HLA-DRB1*03:01-DQ2 (HLA-DQA1*05:01-DQB1*02:01) was associated with GAD65 autoantibody 55,56 .These genetic risk factors are common in western populations and have a low pene trance 57,58 , which might explain why many people do not develop islettargeted autoimmunity or T1DM despite having these T1DM risk factors.",
+      "\t\n\nOf the 49 T1D susceptibility region, the HLA association is the strongest with Odd Ratios (ORs) ranging from 0.02 to >11 for specific haplotypes (Noble and Erlich, 2012;Todd et al., 2010).This region contributes to about 50% of genetic susceptibility to T1D, specifically the HLA class II DR-DQ haplotypes (Erlich et al., 2008).Particularly, the DR4-DQ8 and DR3-DQ2 haplotype combinations are present in about 90% of children with T1D (Held et al., 1999;Tait and Boyle, 1986;Deschamps et al., 1980).A genotype containing both haplotypes (DR4-DQ8/DR3-DQ2) carries the highest risk of diabetes, and is commonly seen in 5% of early-onset disease (Gale and Gillespie, 2014).Other strong associations to T1D susceptibility come from polymorphisms in the insulin INS gene (OR = 3.5), the PTPN22 gene (OR = 3.8), the IL2RA and COBL genes (OR = 2.5; 2.4, respectively) (Gillespie, 2014;Pociot et al., 2010;Todd et al., 2010).The rest of the genomic regions that confer susceptibility to T1D have smaller effects with ORs between 8 Put together, the haplotype is the group of genes that a progeny inherits from one parent 1.1 and 1.9 (Gillespie, 2014;Todd et al., 2010).The names of the T1D susceptibility regions are listed in Table 1 along with the names of the disease associated SNPs and genes.T1D has also been shown to be associated with some other autoimmune conditions like Rheumatoid arthritis, Graves' disease and Malignant anaemia (Heras et al., 2010;Knip and Siljandera, 2008).Markers for these other diseases can be found within the susceptibility regions forT1D.The names of diseases that share T1D susceptibility regions are shown in Table 2.",
+      "\t\n\nIn the first case-control set, having conditioned on HLA-DQB1, HLA-DRB1 and HLA-B using allele HLA-A*02 as a reference, HLA-A*01, HLA-A*11 and HLA-A*31 were protective and HLA-A*24 was predisposing for type 1 diabetes; HLA-A*03 was more predisposing than HLA-A*11 and HLA-A*31 (Supplementary Table 4).Once these alleles were accounted for, there was no further detectable HLA-A effect in the case-control set (P 5 0.15).In the second case-control set, having conditioned on HLA-DRB1 and HLA-DQB1, both HLA-A*01 and HLA-A*11 were again more protective than HLA-A*02.HLA-A*24 was still the most predisposing for type 1 diabetes and may also be associated with an earlier age-at-diagnosis (P 5 0.01; Supplementary Tables 4 and 5).\t\n\nThe major histocompatibility complex (MHC) on chromosome 6 is associated with susceptibility to more common diseases than any other region of the human genome, including almost all disorders classified as autoimmune.In type 1 diabetes the major genetic susceptibility determinants have been mapped to the MHC class II genes HLA-DQB1 and HLA-DRB1 (refs 1-3), but these genes cannot completely explain the association between type 1 diabetes and the MHC region [4][5][6][7][8][9][10][11] .Owing to the region's extreme gene density, the multiplicity of disease-associated alleles, strong associations between alleles, limited genotyping capability, and inadequate statistical approaches and sample sizes, which, and how many, loci within the MHC determine susceptibility remains unclear.Here, in several large type 1 diabetes data sets, we analyse a combined total of 1,729 polymorphisms, and apply statistical methods-recursive partitioning and regression-to pinpoint disease susceptibility to the MHC class I genes HLA-B and HLA-A (risk ratios .1.5;P combined 5 2.01 3 10 219 and 2.35 3 10 213 , respectively) in addition to the established associations of the MHC class II genes.Other loci with smaller and/or rarer effects might also be involved, but to find these, future searches must take into account both the HLA class II and class I genes and use even larger samples.Taken together with previous studies [4][5][6][7][8][10][11][12][13][14][15][16] , we conclude that MHC-class-I-mediated events, principally involving HLA-B*39, contribute to the aetiology of type 1 diabetes.\t\nThe major histocompatibility complex (MHC) on chromosome 6 is associated with susceptibility to more common diseases than any other region of the human genome, including almost all disorders classified as autoimmune.In type 1 diabetes the major genetic susceptibility determinants have been mapped to the MHC class II genes HLA-DQB1 and HLA-DRB1 (refs 1-3), but these genes cannot completely explain the association between type 1 diabetes and the MHC region [4][5][6][7][8][9][10][11] .Owing to the region's extreme gene density, the multiplicity of disease-associated alleles, strong associations between alleles, limited genotyping capability, and inadequate statistical approaches and sample sizes, which, and how many, loci within the MHC determine susceptibility remains unclear.Here, in several large type 1 diabetes data sets, we analyse a combined total of 1,729 polymorphisms, and apply statistical methods-recursive partitioning and regression-to pinpoint disease susceptibility to the MHC class I genes HLA-B and HLA-A (risk ratios .1.5;P combined 5 2.01 3 10 219 and 2.35 3 10 213 , respectively) in addition to the established associations of the MHC class II genes.Other loci with smaller and/or rarer effects might also be involved, but to find these, future searches must take into account both the HLA class II and class I genes and use even larger samples.Taken together with previous studies [4][5][6][7][8][10][11][12][13][14][15][16] , we conclude that MHC-class-I-mediated events, principally involving HLA-B*39, contribute to the aetiology of type 1 diabetes.The MHC spans 4 megabases (Mb) and contains 149 genes, of which eight (the class II loci HLA-DRB1, HLA-DQB1, HLA-DQA1, HLA-DPB1, HLA-DPA1; the class I loci HLA-A, HLA-B and HLA-C) are the highly polymorphic immune response genes.There are many other candidate genes with common variants-any one of which or a combination thereof-that might also be involved in disease susceptibility.We studied 850 type-1-diabetes-affected sibling-pair (ASP) families from the United Kingdom and the United States and a first set of 2,049 type 1 diabetes patients and 1,912 controls from across Great Britain, in which we genotyped a combined total of 254 polymorphic MHC loci, including HLA-DQB1, HLA-DRB1, HLA-A and HLA-B (Table 1 and Supplementary Table 1).A second independent set of 1,050 type 1 diabetes cases and 1,125 controls was used for validation.After these analyses were completed, 1,475 additional single nucleotide polymorphisms (SNPs) in 1,964 of our type 1 diabetes cases and 2,923 controls became available as part of our collaboration with the Wellcome Trust Case Control Consortium (WTCCC) 17 (Table 1)."
+    ],
+    [
+      "\t\n\nThe genetic influences on the prevalence of type 2 diabetes in the Asian population are mainly related to insulin secretion capacity [4] ; other genes involved in the risk of type 2 diabetes are not substantially different in other ethnic groups [5] .The most relevant genes contributing to ethnic differences are associated with insulin secretion capacity, and they are GLIS3 , PEPD , KCNK16 , HNF4A and KCNQ1 according to meta-analyses of genome-wide association studies [4,6] .The risk allele of the KCNQ1 polymorphism is associated with impairment of insulin secretion.KCNK16 and GLIS3 have been reported to be associated with decreased -cell function and -cell mass, leading to the prevalence of type 2 diabetes [4] .These genetic differences are related to the much lower insulin secretory capacity in Asians than Caucasians.The ancestral Asian diets consisted largely of complex carbohydrates with high fiber and very low fat content, and these people had very efficient insulin utilization.In Asians, the insulin secretion capacity has been consistently very low in early ages.However, eating patterns and lifestyles have changed rapidly over the last 20 years and insulin resistance has markedly increased.Therefore, the ethnic differences may be related not only to environmental factors such as eating patterns, physical activity, and stress, but also to genetic factors.Moreover, the interaction between genetic and environmental factors plays an important role in the prevalence of type 2 diabetes [7] .",
+      "\t\n\nAs described above, genetic studies of T2D in European populations have made significant progress in our understanding of T2D susceptibility.However, existing data can only provide partial explanation for the heritability of T2D.It is well known that discrepancies exist in allelic frequencies and effect sizes in different ethnic groups.It is, therefore, important to understand whether these variants are also applicable to other ethnic populations.Asians.Epidemiological studies have documented consistent increases in the prevalence of diabetes in Asia, especially in China, with diabetes prevalence having increased from 2.6% in 2000 to 9.7% in 2010 [69].However, our understanding of the genetic basis of T2D in East Asia remains limited.It is therefore imperative to identify specific genes associated with this disease in East Asians.",
+      "\t\n\nGenetic explorations in traditionally understudied populations have succeeded in identifying novel T2D variants in Mexican populations (6,14), as well as in East Asians (15), Greenlanders (16), and African Americans (8).In Mexico, T2D is one of the leading causes of death and has a prevalence twice that of non-Hispanic whites in the U.S. and is among the highest worldwide (17,18).Although different environmental and lifestyle risk factors in Mexico partially explain the increased prevalence of T2D, unique genetic influences also contribute (6,14).Here, we explored protein-coding variants present at higher frequency in people of Latino descent to shed further light on genetic risk factors for T2D in Mexico.We identified a novel T2D association with a protective, splice-acceptor variant that disrupts expression of IGF2 isoform 2, providing a clear hypothesis for future mechanism of action and therapeutic inquiries.",
+      "\t\n\nDespite heterogeneity across populations in risk allele frequency or effect size in type 2 diabetes genes, the combined effects of multiple genetic variants using genetic scores based on the number of risk alleles appear to be similar across different ethnic groups.Typically, each risk allele increment is associated with a 10-20% increased risk of type 2 diabetes (41,42).These data suggest that the overall contribution of the identified genetic loci to type 2 diabetes is similar between Caucasians and other ethnic groups, and that these loci do not appear to explain ethnic differences in diabetes risk.In predicting future risk of diabetes, the clinical utility of these cumulative genetic risk scores appears to be limited in either high-or low-risk populations.\tGENETIC SUSCEPTIBILITY AND GENE-ENVIRONMENT INTERACTIONS-\n\nThe recent advent of genome-wide association studies (GWAS) has led to major advances in the identification of common genetic variants contributing to diabetes susceptibility (40).To date, at least 40 genetic loci have been convincingly associated with type 2 diabetes, but these loci confer only a modest effect size and do not add to the clinical prediction of diabetes beyond traditional risk factors, such as obesity, physical inactivity, unhealthy diet, and family history of diabetes.Many diabetes genes recently discovered through GWAS in Caucasian populations have been replicated in Asians; however, there were significant interethnic differences in the location and frequency of these risk alleles.For example, common variants of the TCF7L2 gene that are significantly associated with diabetes risk are present in 20-30% of Caucasian populations but only 3-5% of Asians (41,42).Conversely, a variant in the KCNQ1 gene associated with a 20-30% increased risk of diabetes in several Asian populations (43,44) is common in East Asians, but rare in Caucasians.It is intriguing that most diabetes susceptibility loci that have been identified are related to impaired b-cell function, whereas only a few (e.g., peroxisome proliferator-activated receptor-g, insulin receptor substrate 1, IGF-1, and GCKR) are associated with insulin resistance or fasting insulin, which points toward b-cell dysfunction as a primary defect for diabetes pathogenesis.It should be noted that most of the single nucleotide polymorphisms uncovered may not be the actual causal variants, which need to be pinpointed through fine-mapping, sequencing, and functional studies.",
+      "\t\n\nIn addition to these environmental and lifestyle risk factors, genetic predisposition towards T2D may provide additional insights into the differences in T2D prevalence observed between populations in SSA.At present, there are around 100 loci for which there is robust (genome-wide significant) evidence of association with traits related to T2D, including obesity and fasting hyperglycaemia, identified in predominantly European and Asian populations.However, the relevance of many recent genomic findings to populations in SSA has not been systematically studied.Given the marked genomic diversity among populations in SSA, understanding the genomic basis of T2D, its complications, and its risk factors in populations of African descent is likely to provide additional insights into disease aetiology and potential therapeutic strategies [8,9].These observations highlight the need for epidemiological studies with the statistical resolution to reliably assess the burden and epidemiology of T2D and inform potential preventative and therapeutic strategies relevant to SSA.",
+      "\tII. Genetics of Type 2 Diabetes\n\nType 2 diabetes clearly represents a multifactorial disease, and several findings indicate that genetics is an important contributing factor.First, certain ethnic minorities and indigenous groups with low population admixture (e.g., Pima Indians, Micronesians and other Pacific Islanders, Australian Aborigines, and Mexican-Americans) show exceptionally high type 2 diabetes prevalence (up to 21% in Pima Indians) (10 -12).Second, type 2 diabetes clusters within families and first-degree relatives have, compared with the general population, an up to 3.5-fold higher risk to develop the disease (13,14).Finally, twin studies demonstrated a markedly higher concordance for type 2 diabetes in monozygotic compared with dizygotic twins (70 vs. 10%) (15).Type 2 diabetes does not follow simple Mendelian inheritance and, therefore, is considered a polygenic disease.According to the generally accepted common variant-common disease hypothesis (16), complex diseases, such as type 2 diabetes, are caused by the simultaneous occurrence of common DNA sequence variations (minor allele frequencies 5%) in many genes.Each of these DNA alterations is supposed to exert only moderate effects on the affected genes' function and/or expression, but in their sum, these variations confer an increased susceptibility toward the adverse environmental factors mentioned above.Single nucleotide polymorphisms (SNPs), exchanges of single base pairs, cover approximately 90% of the sequence variation within the human genome (SNP Fact Sheet of the Human Genome Project; available at http://www.ornl.gov/sci/techresources/Human_Genome/faq/snps.shtml) and are therefore regarded as the major determinants of the individual predisposition to complex diseases.Thus, strong efforts are currently ongoing to map and catalog these sequence variations (The International HapMap Project at http://www.hapmap.org/index.html.en).However, the less frequent copy number variations (due to deletion and/or duplication of DNA segments one kilobase to several megabases in size) and smaller DNA insertions, deletions, duplications, and inversions may also play a role.All of these findings initiated an intensive search for the genes, or better gene variants, responsible for the genetic predisposition to type 2 diabetes.",
+      "\t\n\nDespite comparatively limited cohort sizes, analyses of type 2 diabetes risk in Hispanic populations have driven diabetes gene discovery by leveraging high disease prevalence, population-specific haplotypic variation, and a private mutation spectrum.There is evidence that these findings are relevant across ancestry: effects of variation in Hispanic populations are significantly directionally consistent with analyses in European ancestry, even at fairly modest levels of significance (p < 0.01) [12, 42, 43].Furthermore, due to differential LD structure, inclusion of Hispanic populations in trans-ethnic fine mapping and meta-analyses provides an opportunity to narrow windows of association and localize causal alleles [12].",
+      "\t\n\nThe genetic structure of the Arab population and prevalence of consanguineous marriages predispose them to T2D risk.There is a requirement for carrying out genome analysis and association studies for identification of T2D risk genes so that at-risk individuals can be identified early and appropriate measures can be taken to prevent disease progression.Environmental factors also play a significant role in T2D development.Gene variants that are too rare to be picked up by GWAS may have relatively large effects on the risk of developing T2D.Moreover, variants which are considered to be rare across populations may be more common in a particular subpopulation [106].Recent advances in next-generation sequencing technologies allow vast amounts of genetic data to be analyzed and processed rapidly, thus substantially saving time and facilitating progress in genetic studies.\t\n\nAlthough initial GWAS were mainly carried out in European populations [30][31][32], more studies focused on other ethnic groups such as Hispanics [33], Asians [34,35], African-Americans [36], Asian-Americans [37] and Arabs [38], among others, are also coming up.A catalogue of all major GWAS is maintained by The National Human Genome Research Institute and can be accessed through their website [39].Meta-analysis and comparison of results of GWAS across populations can also help identify additional statistically significant genetic associations of relevance to T2D [40,41].Since obesity predisposes to T2D, the FTO gene vari-ant which affects BMI is also considered as a risk factor for T2D [42].Variants in other genes which influence glucose and insulin levels have also been investigated for their role in conferring susceptibility to diabetes, for example, glucose-raising genes such as MTNR1B, GCK, MADD and insulin-related genes such as GCKR, IGF1, IRS1 [27,43,44].Other than GWAS, case-control association studies in different ethnic groups have also helped identify haplotypes which may predispose to diabetes in the affected individuals [45,46].",
+      "\tGenetic Predisposition\n\nThe fact that type 2 diabetes is a genetic disease is well known to clinicians by how it occurs in families, and by there being ethnic populations who are particularly high risk.The genetic link was clearly shown more than two decades ago by a famous study of identical twins in the U.K. that found essentially a 100% concordance rate for this diseaseif one twin developed type 2 diabetes, then the other one invariably developed it (9).However, this kind of study provides no insight into how genetics act in the disease.Is there a defective gene that directly impairs the glucose homeostasis system?Alternatively, does it cause insulin resistance or some other defect that acts indirectly by exceeding the capacity of an otherwise normal glucose homeostasis system to compensate?Also, are there one or many genetic defects that predispose to this disease?",
+      "\tEvidence from population studies\n\nThe high prevalence of T2D in some populations, such as Nauruan Islanders and Pima Indians, is also consistent with a genetic aetiology.1011 Neel proposed the `thrifty genotype' hypothesis to explain the persistence at a high frequency of genotypes associated with adverse phenotypes in modern societies, on the basis that those same genes, by promoting ecient energy storage, had proved benecial in times of intermittent food supply. 12igration studies provide additional ammunition for the nature  nurture debate.Individuals from the Indian subcontinent, for example, have high prevalence rates of T2D whether in urban India 13 or as migrants. 14Migrant populations do not, however, immediately acquire all of the environmental attributes of their new homes, so these eects may reect dietary and cultural as well as genetic factors.",
+      "\t\n\nGenome-wide association studies (GWAS) have made a significant contribution to our current knowledge of the role(s) of genetic variation in population-level susceptibility to T1D (Mychaleckyj et al., 2010).",
+      "\t\n\nAnother caveat is that most genome-wide association and prediction studies have been conducted in populations of European descent [44, 51, 52], and case-control and prospective genetic studies in African-American [57,58] or Asian [59-61] populations are still rare.It has been hypothesised that different risk alleles and allele frequencies in various ethnic groups could contribute to global differences in incidence rates of type 2 diabetes [62], but this needs to be corroborated in further studies.",
+      "\t\n\nWhilst the activities of the DIAGRAM consortium have focused on samples of European descent, the past year has seen considerable expansion of efforts to identify common variants influencing T2D-risk in other populations, including those of South and East Asian origin, and African-Americans.For example, Kooner and colleagues [8] completed a GWA metaanalysis in over 5500 T2D cases and 14,400 controls from the UK, Singapore, and Pakistan, all with origins in the Indian subcontinent.This analysis identified 6 novel association signals, including variants near the genes encoding the GRB14 adaptor protein and hepatocyte nuclear factor-4A, the latter already implicated in monogenic forms of diabetes [8].Equivalent efforts in East Asian subjects have been similarly productive, adding a further 8 loci to the global tally [9,10].Studies in individuals of African descent are of particular interest given their extensive genetic diversity, and during the past year the first large-scale association studies from African-American subjects have emerged [11,12].These studies have highlighted some of the particular challenges associated with genetic studies in African-descent populations (such as limited linkage disequilibrium, and genetic admixture) but did reveal a number of novel genome-wide significant signals, including those mapping near RND3 and BCL2.",
+      "\tDISCUSSION\n\nA number of genetic variants have recently been identified as associated with T2DM (1-6).Most of these variants were identified in GWASs in Europeans, but associations for many are consistent in other ethnic groups, including American Indians (18,19).However, some associations are heterogeneous across ethnic groups (5,6,20).In Pima Indians, for example, TCF7L2 variants, which are strongly associated in most ethnic groups, show little association with diabetes (20).In addition because of ethnic differences in allele frequencies, relative importance of different diabetessusceptibility alleles varies.For these reasons, GWASs in non-European populations might yield additional T2DM susceptibility variants.Indeed, studies in East Asians and South Asians have identified additional diabetes associations (4-6).",
+      "\t\n\nIf only a subset of type 2 diabetes susceptibility genes was required for the disease in any individual and the frequencies of these susceptibility genes were different in each population, linkage results would be variable.This might easily arise if hyperglycaemia was a collection of subtly different phenotypes, each resulting from different subsets of underlying genes.Heterogeneity for diabetes as a broad phenotype is already apparent in the distinct features of type 1 diabetes, type 2 diabetes and MODY/monogenic diabetes [114].The non-monogenic form of type 2 diabetes is likely to feature further levels of heterogeneity.Phenotypic heterogeneity may be largely independent of the ethnic background however, since there was a mixture of racial groups in all replication clusters (Tables 1 and 2).Even though association studies [88,115] suggest that there will be some differences in the frequency of individual type 2 diabetes genes between ethnic backgrounds, many type 2 diabetes genes may be shared between individuals of different continents of origin.",
+      "\t\nDifferent populations suffer from different rates of obesity and type-2 diabetes (T2D).Little is known about the genetic or adaptive component, if any, that underlies these differences.Given the cultural, geographic, and dietary variation that accumulated among humans over the last 60,000 years, we examined whether loci identified by genome-wide association studies for these traits have been subject to recent selection pressures.Using genomewide SNP data on 938 individuals in 53 populations from the Human Genome Diversity Panel, we compare population differentiation and haplotype patterns at these loci to the rest of the genome.Using an ''expanding window'' approach (100-1,600 kb) for the individual loci as well as the loci as ensembles, we find a high degree of differentiation for the ensemble of T2D loci.This differentiation is most pronounced for East Asians and sub-Saharan Africans, suggesting that these groups experienced natural selection at loci associated with T2D.Haplotype analysis suggests an excess of obesity loci with evidence of recent positive selection among South Asians and Europeans, compared to sub-Saharan Africans and Native Americans.We also identify individual loci that may have been subjected to natural selection, such as the T2D locus, HHEX, which displays both elevated differentiation and extended haplotype homozygosity in comparisons of East Asians with other groups.Our findings suggest that there is an evolutionary genetic basis for population differences in these traits, and we have identified potential group-specific genetic risk factors.\t\n\nDifferent populations suffer from different rates of obesity and type-2 diabetes (T2D).Little is known about the genetic or adaptive component, if any, that underlies these differences.Given the cultural, geographic, and dietary variation that accumulated among humans over the last 60,000 years, we examined whether loci identified by genome-wide association studies for these traits have been subject to recent selection pressures.Using genomewide SNP data on 938 individuals in 53 populations from the Human Genome Diversity Panel, we compare population differentiation and haplotype patterns at these loci to the rest of the genome.Using an ''expanding window'' approach (100-1,600 kb) for the individual loci as well as the loci as ensembles, we find a high degree of differentiation for the ensemble of T2D loci.This differentiation is most pronounced for East Asians and sub-Saharan Africans, suggesting that these groups experienced natural selection at loci associated with T2D.Haplotype analysis suggests an excess of obesity loci with evidence of recent positive selection among South Asians and Europeans, compared to sub-Saharan Africans and Native Americans.We also identify individual loci that may have been subjected to natural selection, such as the T2D locus, HHEX, which displays both elevated differentiation and extended haplotype homozygosity in comparisons of East Asians with other groups.Our findings suggest that there is an evolutionary genetic basis for population differences in these traits, and we have identified potential group-specific genetic risk factors.\t\n\nIn conclusion, our results have shown that genetic regions surrounding loci associated with T2D, and to a lesser extent, obesity, have been subject to unusually high levels of change in the last 50,000-100,000 years.Most notably, sub-Saharan Africans and East Asians appear to have undergone selection at T2D loci.Identifying specific targets of recent selection in the human genome can aid in determining population-specific risk variants, especially insofar as disease prevalence differs between populations (Ayodo et al. 2007).We anticipate that future studies will be at a finer scale at both the population, genetic, and phenotypic level, potentially further elucidating the genetic basis of obesity and T2D, and the population-specific genetic or non-genetic mechanisms that lead to different rates, types, and consequences of obesity and T2D."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "B1A85353B8F0C564B15AF8E6B6D708C0"
+    },
+    {
+      "task_id": "3E94104D45BE34898C8D1B5C06B58819"
+    },
+    {
+      "task_id": "93CA11DFBD60356B4FFE11BC1849E39A"
+    },
+    {
+      "task_id": "2C4FCD7775AE2DCD883C6FC8D003B420"
+    },
+    {
+      "task_id": "6981D9024FEBEA26E2FBED088BCA6DE5"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_2.json
new file mode 100644
index 0000000..28b935c
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_2.json
@@ -0,0 +1,103 @@
+{
+  "question": [
+    "What is the function of the PPAR-gamma gene in diabetes, and how do its variants impact the disease?",
+    "How can CRISPR/Cas9 technology be used to study or treat genetic forms of diabetes?",
+    "What is the significance of genetic polymorphisms in the GLUT4 gene for Type 2 diabetes?",
+    "How do microRNAs regulate gene expression related to diabetes?",
+    "What insights have been gained from studying the genetic basis of MODY (Maturity Onset Diabetes of the Young)?"
+  ],
+  "answer": [
+    "The PPAR-gamma gene (PPARG) is a key regulator of adipocyte differentiation and insulin sensitivity, playing a significant role in glucose and lipid metabolism. Variants of this gene can influence the risk of type 2 diabetes (T2D). For instance, loss-of-function (LOF) mutations in PPARG are associated with lipodystrophy and insulin resistance. The common P12A variant is associated with a decreased risk of T2D. However, some rare variants can increase the risk of T2D. Additionally, these genetic variants can influence the effectiveness of antidiabetic medications targeting PPARG, such as thiazolidinediones.",
+    "CRISPR/Cas9 technology can be used to study genetic forms of diabetes by editing genes that are associated with the disease. This allows researchers to understand the impact of these genes on cell function, growth, and survival. In terms of treatment, CRISPR/Cas9 might be used to genetically",
+    "The text does not provide specific information on the significance of genetic polymorphisms in the GLUT4 gene for Type 2 diabetes.",
+    "MicroRNAs (miRNAs) regulate gene expression related to diabetes by binding to the mRNA of target genes, which can inhibit their translation and lead to a decrease in the production of the corresponding proteins. These miRNAs can influence various biological processes such as insulin production and secretion, glucose homeostasis, cell growth and death, and immune response. For example, miR-29 has been shown to inhibit insulin-stimulated glucose uptake and downregulate gluconeogenesis. Other miRNAs like miR-18a and miR-206 can regulate genes like IGF-1, which is involved in glucose metabolism and insulin signaling. Dysregulation of these miRNAs can lead to the development of type 2 diabetes.",
+    "Studying the genetic basis of MODY has led to the identification of several genes associated with the disease, including the most common ones: glucokinase, HNF1A, and HNF4A. This has helped in understanding the disease's autosomal dominant inheritance pattern and its onset at a young age due to -cell dysfunction. The genetic subtypes have also aided in identifying patients who will respond to specific therapies, opening the possibility of tailored drug therapy. Furthermore, the genetic research has moved physicians and patients towards precision genomic medicine, taking into account individual genetic data for diagnosis and treatment."
+  ],
+  "contexts": [
+    [
+      "\tAt the skeletal muscle level in particular, the total mass\nof muscle and its function as the site of 70% of insulin-mediated glucose disposal\nsuggest physiologically important effects of PPAR (Semple et al 2006). Furthermore, synthetic PPAR agonists, the insulin-sensitizing thiazolidinediones (TZDs),\nare therapeutic agents used in the treatment of type 2 diabetes. However, clinical\nuse of TZDs is limited by the occurrence of fluid retention, haemodilution, and\nheart failure in up to 15% of the patients (Mudaliar et al 2003). By far the most studied PPAR polymorphism is the Pro12Ala in the unique\nPPAR 2 N-terminal domain.\tEndocr Pract\n9:406416\nMuller Y, Bogardus C, Beamer B, Shuldiner A, Baier L 2003 A functional variant in the peroxisome proliferator-activated receptor  2 promoter is associated with predictors of obesity and\ntype 2 diabetes in Pima Indians. Diabetes 52:18641871\nNelson T, Fingerlin T, Moss L, Barmada M, Ferrell R, Norris J 2007 Association of the peroxisome proliferatoractivated receptor  gene with type 2 diabetes mellitus varies by physical\nactivity among non-Hispanic whites from Colorado. Metabolism 56:388393\nNewton-Cheh C, Hirschhorn JN 2005 Genetic association studies of complex traits: design\nand analysis issues.\tPPAR is a fatty acid- and eicosanoiddependent nuclear receptor that binds to specific DNA response elements (PPREs)\nas heterodimer with the retinoid X receptor and, in the presence of ligands, regulates the expression of the target gene. Although the role of PPAR in adipose\ntissue development and function is established, its low levels in tissues important\nto glucose homeostasis, including skeletal muscle, liver, and pancreatic  cells, raise\nthe question of its possible physiological and pharmacological importance at those\nGENEENVIRONMENT INTERACTION AND THE METABOLIC SYNDROME\n\n105\n\nsites (Semple et al 2006).\tPPAR is considered as a strong, if not the strongest, candidate gene for\nthe metabolic syndrome. The PPAR gene is located at 3p25, a region showing\nevidence for linkage with diabetes and obesity susceptibility. Frameshift and missense heterozygous mutations have been liked to insulin resistance and type 2\ndiabetes, obesity, lipodystrophy and hypertension (Ristow et al 1998, Barroso et al\n1999, Hegele et al 2002, Savage et al 2002).",
+      "\tInteractions with the peroxisomeproliferator-activated receptors\n\nThe transcription factor peroxisome-proliferatoractivated receptor gamma (PPARg) is known to influence insulin sensitivity, and acts partly via a modulation of the circulating adiponectin level (PPARg agonists increase the adiponectin level) (Ref.38).The PPARgP12A SNP is a wellestablished genetic variant that modulates insulin sensitivity and the risk of type 2 diabetes (Ref.39).In a Chinese family study, Yang et al. demonstrated a genetic interaction between the ADIPOQ exon 2 45TG SNP and the P12A SNP of the PPARg gene with respect to insulin sensitivity (Ref.40).Likewise Tanko et al. reported a similar interaction between the PPARg P12A SNP and the 211377CG SNP of the ADIPOQ gene promoter (Ref.41).Indeed, a significant interaction was detected between the PPARg Ala12 and the ADIPOQ 211377C alleles and higher BMI, and the two alleles were associated with higher insulin sensitivity and displayed interaction with respect to insulin sensitivity.Such associations of 'insulinsensitising' alleles with increased BMI is not uncommon: it was previously reported for the UCP3 and the Isl1 genes in obese subjects ( Refs 42,43) and interpreted as a protective effect that delays the occurrence of type 2 diabetes and thus contributes to the reaching of a higher degree of obesity.",
+      "\t\n\nPeroxisome proliferator-activated receptor gamma (PPARG) is a master transcriptional regulator of adipocyte differentiation and a canonical target of antidiabetic thiazolidinedione medications.In rare families, loss-of-function (LOF) mutations in PPARG are known to cosegregate with lipodystrophy and insulin resistance; in the general population, the common P12A variant is associated with a decreased risk of type 2 diabetes (T2D).Whether and how rare variants in PPARG and defects in adipocyte differentiation influence risk of T2D in the general population remains undetermined.By sequencing PPARG in 19,752 T2D cases and controls drawn from multiple studies and ethnic groups, we identified 49 previously unidentified, nonsynonymous PPARG variants (MAF < 0.5%).Considered in aggregate (with or without computational prediction of functional consequence), these rare variants showed no association with T2D (OR = 1.35;P = 0.17).The function of the 49 variants was experimentally tested in a novel high-throughput human adipocyte differentiation assay, and nine were found to have reduced activity in the assay.Carrying any of these nine LOF variants was associated with a substantial increase in risk of T2D (OR = 7.22; P = 0.005).The combination of large-scale DNA sequencing and functional testing in the laboratory reveals that approximately 1 in 1,000 individuals carries a variant in PPARG that reduces function in a human adipocyte differentiation assay and is associated with a substantial risk of T2D.",
+      "\tPPARG\n\nPeroxisome proliferator-activated receptor gamma (PPARG) gene, located at 3p25, encodes peroxisome proliferator-activated receptor gamma protein, which is important in the control of insulin sensitivity, glucose homeostasis, and blood pressure (Barroso et al., 1999).Similar to previous meta-analyses, data from a recent meta-analysis involving 32,849 cases and 47,456 controls in 60 studies showed that PPARG polymorphism rs1801282 (Pro12Ala) was associated with a reduction in T2DM risk ( OR  0.86, 95%; CI  0.81  0.90; Gouda et al., 2010).Most recently, other variant genotypes, including rs3856806 (1431C  T), have been associated with T2DM in a Chinese Han population (Lu et al., 2011).\tPPARGC1A\n\nPeroxisome proliferator activated receptor gamma coactivator 1-alpha (PPARGC1A) gene, located at 4p15.1, codes peroxisome proliferator activated receptor gamma coactivator 1 protein.Its expression might infl uence insulin sensitivity as well as energy expenditure, thereby contributing to the development of obesity, a risk factor for diabetes mellitus (Esterbauer, Oberkofl er, Krempler, & Patsch, 1999).The most recent meta-analysis showed that rs8192678 (Gly482Ser) and rs2970847 (Thr394Thr) polymorphisms of PPARGC1A were signifi cantly associated with the risk of T2DM, especially in the Asian Indian population (Yang, Mo, Chen, Lu, & Gu, 2011).Studies on PPARGC1A genetic polymorphisms and GDM are limited.Polymorphisms, rs8192678 and rs2970847, have not been associated with GDM in European Whites living in Vienna (Leipold, Knoefl er, Gruber, Huber, et al., 2006) or Scandinavian women (Shaat et al., 2007).",
+      "\tSUMMARY\n\nIn just over a decade, PPARg has evolved from somewhat humble beginnings as a simple regulator of adipogenesis to become a key therapeutic target in the fight against the 21st Century epidemics of obesity, insulin resistance and the metabolic syndrome.Whilst pharmacological and animal studies have yielded a wealth of information regarding the role of this receptor in the regulation of energy, glucose and lipid homeostasis, there can be no doubt that defining the metabolic consequences induced by polymorphisms and mutations in the human PPARg gene has contributed significantly to our understanding of the biology of this receptor.To this end, PPARg has proved to be a fruitful 'hunting ground' with many different genetic variants already identified, each providing novel insights into the role of PPARg in normal physiology and disease.Given the significant species-specific differences that exist in metabolism, particularly in relation to lipid homeostasis, it is critical that we continue to identify and study these human 'experiments of nature' in order to complement the impressive pharmacological and functional genomic approaches that are currently being employed to permit the development of more superior ligands with enhanced therapeutic impact.Given the apparent inexorable rise in the prevalence of obesity, insulin resistance and T2DM, the need for such novel therapies could not be more urgent.",
+      "\t\n\nAnother biologic candidate gene that was extensively studied is the peroxisome proliferator -activated receptor  gene ( PPARG ), where mutations that severely decrease the transactivation potential were found to cosegregate with extreme insulin resistance, diabetes and hypertension in two families, with autosomaldominant inheritance [89] .A common amino -acid polymorphism (Pro12Ala) in PPARG has been associated with T2DM; homozygous carriers of the Pro12 allele are more insulin resistant than those having one Ala12 allele and have a 1.25 -fold increased risk of developing diabetes [90] .This common polymorphism has a modest, yet extensively replicated effect on the risk of T2DM.There is also evidence for interaction between this polymorphism and the insulin secretion in response to fatty acids [91] , and BMI [92] ; the protective effect of the alanine allele was lost in subjects with a BMI greater than 35 kg/m 2 .A widespread Gly482Ser polymorphism of PGC1 - (known as PPARGC1 ), a transcriptional coactivator of a series of nuclear receptors including PPARG , has been associated with a 1.34 genotype relative risk of T2DM [93] .In this study, a test for interaction with the Pro12Ala variant in PPARG gave no indication for additive effects on diabetes status.",
+      "\t\n\nHere, we report the most relevant PPAR SNPs, mutations, and rare variants, discussing their role on PPAR activity in adipose tissue and their association with T2D and obesity.In addition, we describe the role of alternative splicing and post-translational modifications on PPAR activity, with a specific focus on their impact on human metabolic disorders.Finally, considering PPAR as a pharmacological target, we discuss how nucleotide changes, PTMs, and alternative splicing can affect drug responsiveness in patients.\t\n\nPPAR is the most studied member of the PPAR family due to its primary role in dictating the expression of a network of genes responsible for lipid and glucose homeostasis as well as inflammation [17][18][19][20][21][22].Most importantly, PPAR is sufficient and essential for adipocyte formation and, as such, it is widely considered the master regulator of adipogenesis [9,[23][24][25].Because of its central role in many biological processes, different single-nucleotide polymorphisms (SNPs) and/or rare variants and mutations in the PPARG gene, or posttranslational modifications (PTMs; e.g., phosphorylation and SUMOylation), have been associated with alterations of the metabolic status including insulin resistance, obesity, and type 2 diabetes (T2D) [26][27][28][29][30].In this regard, PPAR has been the focus of intense research as a therapeutic target, and diverse synthetic partial or full agonists targeting this receptor have so far been developed [17,[31][32][33][34][35][36].Thiazolidinediones (TZDs), included in FDA-approved insulin-sensitizing drugs, are used in type 2 diabetes (T2D) treatment due to their positive action on glycemic control, on adipocyte differentiation, and on blood-circulating fatty acids levels [37][38][39][40].Nevertheless, adverse or side effects such as weight gain, edema, and fluid retention [41,42] have been reported, indicating that further knowledge on PPAR activity is needed and that new drugs targeting PPAR should be designed and tested.\tPPARG Genetic Variants and Their Effects on Drug Effectiveness in Metabolic Dysfunctions\n\nThe role of PPARG in the regulation of lipid and glucose homeostasis [20,49,50], inflammatory pathways [21], and its master role in governing the genesis of adipose tissue [19,25] indicate why it is so relevant in the etiology of metabolic diseases.Nucleotide variants in PPARG, alone or in combination (i.e., haplotype), can strongly affect PPAR activity in light of its functioning as a transcription factor.Therefore, its ability to orchestrate gene expression in different tissues can be compromised by nucleotide variations [51].In this regard, only a few studies have addressed the impact of nucleotide variants on the expression of PPAR itself or of its target genes.Instead, most of the effort has focused on identifying single-nucleotide polymorphisms (SNPs) or mutations in the PPARG gene with significant associations with complex traits and/or metabolic disorders [52][53][54][55][56][57][58][59][60][61][62].Moreover, as PPAR is targeted by synthetic agonists, (TZDs or glitazones) used in T2D treatment, different studies in the era of personalized medicine have attempted to demonstrate whether and how pharmacological efficacy can be affected by the presence of such variations in patients with diabetes [63].\tGain-and Loss-of-Function Mutations Affecting Metabolic Phenotype\n\nPPARG low frequency (~1:500) variants and rare point mutations, mostly associated with metabolic dysfunctions by independent studies, have also been extensively tested for their ability to affect PPAR activity, adipocyte differentiation, and TZD efficacy [54,58,61,[107][108][109][110][111][112][113].Among them, a very rare heterozygous PPAR mutation, P113Q (in PPAR2), has been identified in a German cohort [110,113,114] but not detected in French and American individuals or in Icelandic children [115][116][117].Ristow and colleagues [113] reported marked obesity (BMI 37.9-47.3)and T2D in patients carrying this mutation, also showing that it reduces PPAR phosphorylation in Ser112, in turn inducing PPAR transactivation capacity, adipocyte differentiation, and triglycerides accumulation [113].Subsequently, this gain-offunction mutation has been related to a marked reduction of body glucose uptake, suggesting it to be a rare cause of severe insulin resistance [114].However, insulin resistance and T2D have been mostly associated with loss-of-function (LOF) PPAR mutations [54,61,111], frequently identified as causing familial partial lipodystrophy type 3 (FPLD3).This autosomal dominant-inherited disorder is characterized by gradual loss of subcutaneous adipose tissue from limbs and the gluteal region, and is accompanied by dramatic metabolic complications, such as severe insulin resistance and early onset of T2D [108,112].A group of FPLD3-associated mutations resides within PPAR LBD and affects the protein structure to variable degrees.In particular, the heterozygous mutation in PPARG exon 6 R425C (in PPAR2) was identified in a patient who developed diabetes mellitus and hypertriglyceridemia at a young age and lipodystrophy of the extremities and face in adulthood [112].Interestingly, R425 is a wellconserved amino acid residue involved in the formation and stabilization of the tertiary structure, falling in a domain that is crucial for the interaction with RXR [112].Therefore, the R425C substitution strongly modifies receptor activity by altering the ability of the protein to form a functional heterodimer [112].Consequently, the mutated receptor strongly reduces the capacity of precursor cells to differentiate in mature adipocytes, also reducing rosiglitazone responsiveness, even at high doses [110].\t\nPurpose of Review Full and partial synthetic agonists targeting the transcription factor PPAR are contained in FDA-approved insulin-sensitizing drugs and used for the treatment of metabolic syndrome-related dysfunctions.Here, we discuss the association between PPARG genetic variants and drug efficacy, as well as the role of alternative splicing and post-translational modifications as contributors to the complexity of PPAR signaling and to the effects of synthetic PPAR ligands.Recent Findings PPAR regulates the transcription of several target genes governing adipocyte differentiation and glucose and lipid metabolism, as well as insulin sensitivity and inflammatory pathways.These pleiotropic functions confer great relevance to PPAR in physiological regulation of whole-body metabolism, as well as in the etiology of metabolic disorders.Accordingly, PPARG gene mutations, nucleotide variations, and post-translational modifications have been associated with adipose tissue disorders and the related risk of insulin resistance and type 2 diabetes (T2D).Moreover, PPAR alternative splicing isoformsgenerating dominant-negative isoforms mainly expressed in human adipose tissue-have been related to impaired PPAR activity and adipose tissue dysfunctions.Thus, multiple regulatory levels that contribute to PPAR signaling complexity may account for the beneficial as well as adverse effects of PPAR agonists.Further targeted analyses, taking into account all these aspects, are needed for better deciphering the role of PPAR in human pathophysiology, especially in insulin resistance and T2D.Summary The therapeutic potential of full and partial PPAR synthetic agonists underlines the clinical significance of this nuclear receptor.PPARG mutations, polymorphisms, alternative splicing isoforms, and post-translational modifications may contribute to the pathogenesis of metabolic disorders, also influencing the responsiveness of pharmacological therapy.Therefore, in the context of the current evidence-based trend to personalized diabetes management, we highlight the need to decipher the intricate regulation of PPAR signaling to pave the way to tailored therapies in patients with insulin resistance and T2D.Keywords PPARG genetic variants .Dominant-negative isoforms .Post-tranlational modifications .Adipose tissue dysfunctions .Drug responsiveness .Type 2 diabetes This article is part of the Topical Collection on Genetics * Alfredo Ciccodicola\t\n\nPurpose of Review Full and partial synthetic agonists targeting the transcription factor PPAR are contained in FDA-approved insulin-sensitizing drugs and used for the treatment of metabolic syndrome-related dysfunctions.Here, we discuss the association between PPARG genetic variants and drug efficacy, as well as the role of alternative splicing and post-translational modifications as contributors to the complexity of PPAR signaling and to the effects of synthetic PPAR ligands.Recent Findings PPAR regulates the transcription of several target genes governing adipocyte differentiation and glucose and lipid metabolism, as well as insulin sensitivity and inflammatory pathways.These pleiotropic functions confer great relevance to PPAR in physiological regulation of whole-body metabolism, as well as in the etiology of metabolic disorders.Accordingly, PPARG gene mutations, nucleotide variations, and post-translational modifications have been associated with adipose tissue disorders and the related risk of insulin resistance and type 2 diabetes (T2D).Moreover, PPAR alternative splicing isoformsgenerating dominant-negative isoforms mainly expressed in human adipose tissue-have been related to impaired PPAR activity and adipose tissue dysfunctions.Thus, multiple regulatory levels that contribute to PPAR signaling complexity may account for the beneficial as well as adverse effects of PPAR agonists.Further targeted analyses, taking into account all these aspects, are needed for better deciphering the role of PPAR in human pathophysiology, especially in insulin resistance and T2D.Summary The therapeutic potential of full and partial PPAR synthetic agonists underlines the clinical significance of this nuclear receptor.PPARG mutations, polymorphisms, alternative splicing isoforms, and post-translational modifications may contribute to the pathogenesis of metabolic disorders, also influencing the responsiveness of pharmacological therapy.Therefore, in the context of the current evidence-based trend to personalized diabetes management, we highlight the need to decipher the intricate regulation of PPAR signaling to pave the way to tailored therapies in patients with insulin resistance and T2D.Keywords PPARG genetic variants .Dominant-negative isoforms .Post-tranlational modifications .Adipose tissue dysfunctions .Drug responsiveness .Type 2 diabetes This article is part of the Topical Collection on Genetics * Alfredo Ciccodicola",
+      "\t\n\nThere is substantial evidence that PPAR- contributes to the risk for type 2 diabetes by influencing insulin sensitivity, insulin secretion and susceptibility to obesity [6].The 12Ala allele of the PPAR-2 gene, that has been shown to have a decreased transcriptional activity, is also associated with improved insulin sensitivity and lower risk for diabetes [17].This finding is in agreement with results from heterozygous PPAR- null mice exhibiting increased insulin sensitivity compared with wild-type mice [46].The 12Ala allele was associated with a higher reduction in the 2-h serum insulin level, probably indicating an increase in insulin sensitivity.However, it cannot be excluded that a decrease in insulin levels could also be due to impaired insulin secretion, because the 12Ala allele has been associated with reduced insulin secretion capacity in previous studies [20,47].\t\n\nPPAR is a ligand-activated transcription factor, a member of the nuclear hormone receptor superfamily, that functions as a heterodimer with a retinoid X receptor (RXR) to promote transcription of numerous target genes [5,6].PPAR-2, an isoform of PPAR- with 28 additional amino acids at its N-terminus, is expressed almost exclusively in adipose tissue [7].It plays a key role in adipogenesis [8,9,10,11], is involved in the regulation of insulin sensitivity [12,13], and is the major functional receptor for the thiazolidinedione class of insulin-sensitising drugs [11,14].Therefore, the PPAR- gene has been viewed as a \"thrifty gene\", with an important role in the development of type 2 diabetes and diabetes-related traits [7,15].Additionally, the Pro12Ala substitution in exon B of the PPAR-2 gene, first reported in Caucasians [16], has been associated with diabetes mellitus [17,18,19,20,21,22,23,24,25,26,27,28].Although not all associations have been consistent, a meta-analysis of published studies has confirmed a modest (1.25-fold), but statistically significant, increase in diabetes risk for the Pro12Pro genotype [4,19].\t\n\nIn summary, we have demonstrated that the Pro12Pro genotype of the PPAR-2 gene and the 482Ser allele of the PGC-1 gene predict the conversion from IGT to type 2 diabetes.Our study also shows that the interaction between drug treatment (acarbose) and genetic variation may be significant with respect to the conversion from impaired glucose tolerance to type 2 diabetes.\t\n\nPPAR- plays a key role in adipocyte differentiation [10,11], and can therefore influence body fat mass and obesity.In our study subjects, those with the 12Ala allele had a somewhat higher BMI at baseline, and tended to lose more weight.This finding is in accordance with our results from the Finnish Diabetes Prevention Study [48].In that study, subjects belonging to the intervention group (lifestyle changes) and who had the Ala12 allele lost significantly more weight (and were protected from type 2 diabetes) than subjects with the Pro12Pro genotype, although in the control group the 12Ala allele did not confer protection against diabetes.In the present study, the effect of the Pro12Pro genotype in increasing the risk for diabetes was independent of baseline weight change and other OR=odds ratio.Smoking was coded as 0 = never smokers and ex-smokers and 1 = current smokers at baseline.PPAR-2 genotypes were coded as 0 = the 12Ala allele and 1 = the Pro12Pro genotype confounding factors in women in the acarbose group, indicating that women possessing the Pro12Pro genotype were less responsive to acarbose treatment.This implies that the effect of acarbose treatment was modified by the Pro12Ala polymorphism.Several mechanisms could explain why the Gly482Ser polymorphism of the PGC-1 gene regulates the conversion from IGT to diabetes.PGC-1 increases and coordinates the expression of different genes that stimulate mitochondrial biogenesis, adaptive thermogenesis, fibre-type switching [32], expression of GLUT-4 in skeletal muscle [33], and regulation of gluconeogenesis in the liver [34].Thus, a reduction in the activity of PGC-1, possibly also as a result of the Gly482Ser mutation, might lead to insulin resistance in skeletal muscle.Additionally, a quantitative trait linkage analysis in Pima Indians suggested a link between basal insulin concentrations and chromosome 4p15. 1 [49] in cases where the PGC-1 gene has been mapped [50].In the present study the Gly482Ser variant was not related to fasting and 2-h plasma glucose, serum insulin, or their changes, or to BMI and weight change.However, compared to the Gly482Gly genotype, the 482Ser allele was associated with a 1.6-fold higher risk for diabetes in the placebo group but not in the acarbose group.The 482Ser allele had a significant interaction with treatment and acarbose treatment was able to reduce the risk of diabetes particularly among carriers of the 482Ser allele."
+    ],
+    [
+      "\t\n\nThe advancements in both differentiation protocols and genome-editing technologies make it now possible to study the effect of genetic perturbations on human -cell development.\tA measure of -cell exocytosis based on electrical current. the scalability of such studies.Moreover, a genome-wide CRISPR loss-of-function screen performed in 2019 identified 373 potential regulators of insulin production in the mouse insulinoma-derived Min6 -cell line 178 .Extending genome-wide screens to human -cell models and increasing the diversity of cellular read-outs will provide orthogonal data sets for integration with existing genetic and genomic resources, in order to elucidate downstream biology.As the current protocols for hiPSC differentiation are expensive, are time-consuming and have variability in differentiation efficiency, continued advancements in differentiation protocols will enable similar approaches in these cell models.",
+      "\tRegulation of GWAS diabetes genes by glucose in pancreatic islets\n\nMany of the recently discovered type 2 diabetes genes have been suggested to affect the development and/or function of pancreatic islets [6].The function, growth and survival of -cells can be regulated acutely and chronically by glucose [34].Thus, we examined whether the new type 2 diabetes susceptibility genes are regulated by overnight incubation in low (5 mM) or high (25 mM) glucose (Figure 5).Most genes were significantly or tended to be downregulated under conditions of high glucose.Cdkal1, Cdkn2a (Arf, P = 0.07), Ide, Jazf1, Camk1d, and Tspan8 (P = 0.06) expression levels were decreased ~50-60%.Meanwhile, the expression of Cdkn2b, Hhex (P = 0.10), Cdc123, Adamts9 (P = 0.09), and Thada were reduced 30-40%.To ensure the islets incubated in high glucose did not have globally decreased expression, we examined the expression of Txnip, which has been shown to be highly upregulated by glucose [35] and found that its expression was still significantly elevated in the islets cultured in high glucose (Figure 5).Mouse islets consist of -cells and other cell types.Thus, the MIN6 -cell line was also examined.We found that all the genes were expressed in this cell line (not shown), although this does not preclude that they also are expressed in other cell types within the islet.",
+      "\tEmploying hPSCs and genome editing tools to study diabetes and metabolic syndromes\n\nIn general, the strategy to carry out in vitro disease modeling of diabetes and related metabolic syndromes with hPSCs and genome editing tools would be to 1) derive hiPSCs from patients with these conditions, 2) generate \"repaired/corrected\" isogenic controls [53] and then 3) differentiate them into pancreatic cells or target cells of relevance, such as immune cells in the case of T1D or myocytes, adipocytes and hepatocytes in the case of T2D (Figure 2).If patient material is inaccessible, one could introduce (naturally occurring) mutations or gene variants into hESCs and differentiate them accordingly to study disease mechanisms.Since excellent reviews have been published recently, we will provide a brief overview to familiarize the reader with the classification of diabetes and metabolic disorders.\tCONCLUSIONS\n\nhPSCs and the advancing genome editing tools appear to be a timely and potent combination for probing molecular mechanism(s) underlying diseases such as diabetes and metabolic syndromes.Studying monogenic forms of diabetes and syndromes of insulin resistance using these tools would be extremely useful given the lack of an autoimmune attack and confounding effects of insulin resistance and obesity.One caveat of this methodology at the moment is the \"low\" efficiency of deriving human beta cells in vitro [75,76], possibly due to our incomplete knowledge on human pancreatic development.Another explanation would be the lack of in vivo environmental cues emanating from proximal tissues such as the vasculature.Nonetheless, successful disease modeling of MODY2 [7] and Wolfram Syndrome [8] already suggests a high possibility of success.These technologies have the potential to elucidate the underlying pathophysiology that stem from defects in 1) beta cell development, metabolism or survival or 2) development of adipocyte.For instance in the case of MODY2, it is now clear that GCK mutation affects glucose-stimulated insulin secretion but not insulin synthesis or beta cell proliferation [7].With the latest advances in the derivation of mature and functional human pancreatic beta-like cells from hPSCs in vitro [75e77], eventually circumventing the requirement for in vivo maturation, disease modeling of diabetes is expected to progress exponentially.The knowledge gained from these hiPSC-based disease modeling studies can potentially be translated into the clinics by guiding clinicians on the appropriate type of medication to use for each condition based on the mechanism of action of the disease.Findings from these proposed studies could also offer clues to the pathophysiology of the \"garden variety\" of type 2 diabetes which is known to manifest defects in each of these tissues.hPSCs and genome editing tools may also provide an opportunity to better understand the relevance of gene variants identified from GWAS studies, in causing T1D, T2D, obesity and metabolic syndromes, given that they exhibit only modest effects and w85% of the variants map onto noncoding regions such as enhancers or regulatory elements [104].Investment into hPSCs and genome editing would allow a better mechanistic understanding of the pathophysiology of monogenic and complex diseases relevant for organismal homeostasis and therefore an improved approach to stratified personalized medicine.By identifying the impact of gene variants on disease predisposition, prophylactic measures in the form of lifestyle alterations or medication could be adopted early on in life to delay or even prevent the onset of diabetes and/or metabolic diseases.It is also likely that these hiPSCbased disease modeling studies would provide insights into approaches to predict the susceptibility of disease.Henceforth, the translational potential of studying human diabetes and metabolic syndrome disease mechanisms is huge, with opportunities for early prophylactic intervention that could have long-term implications for global health care and reduction of economic burden.While the derivation of hiPSCs from human tissues is relatively easier and gaining popularity compared to just a few years ago [2], it is likely that the modern technology of generating site-specific nucleases will also rapidly mature to make in vitro disease modeling a routine approach.\tEmploying hPSCs and genome editing tools to study type 1 diabetes (T1D)\n\nPatients with T1D are unable to secrete insulin due to near complete destruction of their pancreatic beta cells.More than 50 risk variants/ susceptibility alleles have been found to be associated with susceptibility to this disease [71] (https://www.niddkrepository.org/studies/t1dgc/) (Table 1).The strongest association is with the human leukocyte antigens (HLAs), which accounts for a large proportion of the genetic risk for T1D [71].Most of the T1D genes affect adaptive and innate autoimmunity leading to incomplete self-tolerance to beta cell antigens and immune-mediated destruction of beta cells [71].T1D-hiPSCs can be differentiated into T lymphocytes [72e74] and pancreatic beta cells [75e77] to allow co-culture experiments aimed at progressively evaluating their interactions in vitro (Figure 2) [78].A similar strategy can be applied to hiPSCs derived from T1D-susceptible patients to examine the impact of susceptible gene variants (Table 1) on the vulnerability of pancreatic beta cells to immune attack.For instance, hiPSCs derived from patients with a gene variant in PTPN22 can be differentiated into lymphocytes to study lymphocyte function [79e81].hiPSCs from subjects with gene variants in ERBB3, which is expressed in monocytes and dendritic cells, and may affect antigen presenting cell (APC) function [82], can be differentiated into selective immune cells to study how they affect APC function.hiPSCs from patients with gene variants in UBASH3A (also known as STS2), which is specifically expressed in lymphocytes [83], are well suited for differentiation into lymphocytes to study the function of this gene.\t\n\nBackground: Diabetes and metabolic syndromes are chronic, devastating diseases with increasing prevalence.Human pluripotent stem cells are gaining popularity in their usage for human in vitro disease modeling.With recent rapid advances in genome editing tools, these cells can now be genetically manipulated with relative ease to study how genes and gene variants contribute to diabetes and metabolic syndromes.Scope of review: We highlight the diabetes and metabolic genes and gene variants, which could potentially be studied, using two powerful technologies e human pluripotent stem cells (hPSCs) and genome editing tools e to aid the elucidation of yet elusive mechanisms underlying these complex diseases.Major conclusions: hPSCs and the advancing genome editing tools appear to be a timely and potent combination for probing molecular mechanism(s) underlying diseases such as diabetes and metabolic syndromes.The knowledge gained from these hiPSC-based disease modeling studies can potentially be translated into the clinics by guiding clinicians on the appropriate type of medication to use for each condition based on the mechanism of action of the disease.\t\n\nOne strategy to study these monogenic syndromes would be to derive hiPSCs from these patients, differentiate them into pancreatic progenitors and then transplant these progenitors into immunocompromised (SCID-Beige or NSG) mice for in vivo maturation (Figure 2).This methodology has been recently used to successfully model MODY2, demonstrating that beta cells derived from hiPSCs with GCK mutation are indeed less sensitive to glucose levels [7].Endoplasmic reticulum (ER) stress-related diabetes in patients with Wolfram syndrome has also been modeled using hiPSC-derived beta cells, demonstrating that WFS1 protein maintains ER function in beta cells by acting upstream of the unfolded protein response (UPR) pathways [8].phenotypes occurring in humans.Likewise, the stepwise analysis of human pancreatic development with this strategy would likely provide mechanistic insights into the ability of a single gene mutation (PDX1, PTF1A, HNF1B, GATA6 and GATA4) to promote pancreatic agenesis/ atrophy.Further, studying mutations in KCNJ11 and ABCC8 using hiPSC-derived beta cells may elucidate the mechanistic differences between permanent and transient neonatal diabetes [64].Overall, insulin production and secretion could be compared between diseased and gene-corrected pancreatic cells to understand the underlying cause of each type of monogenic diabetes (Figure 2).",
+      "\t\n\nMoving beyond cancer phenotypes, indirect in vivo screens are beginning to be used in other disease models.A genome-scale knockout screen in pancreatic beta-cells transplanted into a mouse model for Type 1 Diabetes identified genetic factors preventing autoimmune clearance of transplants.Inhibition of an identified gene hit, Rnls , with pargyline [101] prevented an autoimmune reaction and confirmed that the screen was able to identify candidates of therapeutic relevance [11] .",
+      "\t\n\nunderstand each cell type's genomic architecture and better characterize their roles in islet resilience and failure.Experimental manipulation of the regulatory elements and/or the target genes identified by (epi)genomic approaches described above and modeling the putative pathways and processes they implicate in human islet cell lines (e.g., EndoC-bH1-H3) is essential to progress from correlation to causation.Similarly, transitioning from \"the\" mouse (C57BL/6) to multiple mouse models for insights into the effects of naturally occurring genetic variation on islet function and physiology [61] and for manipulation of key genomic elements should also help characterize the dynamic range of islet behavior and response.T2D is a heterogeneous, complex, and progressive disorder, as multiple subtypes have been identified and associated with different genetic risk and clinical outcome profiles.Future islet genomics studies that focus on identifying the distinct subgroups of individuals with distinct genes/pathways that are disrupted and/or contributing to islet (dys)function at basal and/or responsive states are needed.Furthermore, priority should be given to profiling more islets from pre-diabetic and T2D individuals to characterize the transition between basal to stressed to T2D state and determine if there are intermediate signatures for islet failure and T2D onset.Together, this multi-pronged approach toward studying T2D genetics and islet pathophysiology will help identify additional targets and opportunities for intervention that can be exploited for more precise and effective preventative, treatment, and management options for T2D.",
+      "\t\n\nIn addition, knock-out and transgenic mice have become powerful tools in elucidating the influence of specific genes in glucose metabolism and the pathogenesis of diabetes.This includes understanding which transcription factors are involved in pancreas development (Habener et al., 2005) and elucidation of insulin signalling pathways (Kahn, 2003;Wang and Jin, 2009).Tissue-specific knockouts have proven to be particularly useful in studying insulin signalling (Neubauer and Kulkarni, 2006) as the global insulin receptor knock-out is non-viable (Accili et al., 1996).",
+      "\t\n\nA recent sequencing study provides an example of detection of rare variants in type 1 diabetes.Targeted sequencing in a series of candidate coding regions resulted in IFIH1 being identified as the causal gene in a region associated with type 1 diabetes by GWA studies (58).IFIH1 encodes a cytoplasmic helicase that mediates induction of the interferon response to viral RNA.The discovery of IFIH1 as a contributor to susceptibility to type 1 diabetes has strengthened the hypothesis (70) about a mechanism of disease pathogenesis involving virusgenetic interplay and raised type 1 interferon levels as a cofactor in -cell destruction.Nonetheless, it should be recognized that a component of the missing heritability (familial aggregation) in type 1 diabetes could well be due to unrecognized intra-familial environmental factors.Disease pathogenesis.Contemporary models of pathogenesis of type 1 diabetes support the involvement of two primary dramatis personae: the immune system and the -cell.The known and newly identified genetic risk factors for type 1 diabetes present exciting opportunities to build on to the current cast of disease mechanisms and networks.Most of the listed genes of interest (Table 2) and those in extended regions are assumed to regulate immune function.Some of these genes, however, may also have roles in the -cell (insulin being the most obvious example).Another gene, PTPN2, encoding a protein tyrosine phosphatase, was identified as affecting the risk for type 1 diabetes as well as for Crohn disease (47,71).PTPN2 is expressed in immune cells, and its expression is highly regulated by cytokines.However, PTPN2 is expressed also in -cells, where it modulates interferon (IFN)- signal transduction and has been shown to regulate cytokineinduced apoptosis (72).Other candidate genes, such as NOS2A, IL1B, reactive oxygen species scavengers, and candidate genes, identified in large GWA studies of type 2 diabetes, have not been found to be significant contributors to the susceptibility of type 1 diabetes (73).",
+      "\t\n\nHuman genetic studies have emphasised the dominant contribution of pancreatic islet dysfunction to development of Type 2 Diabetes (T2D).However, limited annotation of the islet epigenome has constrained efforts to define the molecular mechanisms mediating the, largely regulatory, signals revealed by Genome-Wide Association Studies (GWAS).We characterised patterns of chromatin accessibility (ATAC-seq, n = 17) and DNA methylation (whole-genome bisulphite sequencing, n = 10) in human islets, generating high-resolution chromatin state maps through integration with established ChIP-seq marks.We found enrichment of GWAS signals for T2D and fasting glucose was concentrated in subsets of islet enhancers characterised by open chromatin and hypomethylation, with the former annotation predominant.At several loci (including CDC123, ADCY5, KLHDC5) the combination of fine-mapping genetic data and chromatin state enrichment maps, supplemented by allelic imbalance in chromatin accessibility pinpointed likely causal variants.The combination of increasingly-precise genetic and islet epigenomic information accelerates definition of causal mechanisms implicated in T2D pathogenesis.",
+      "\tGene Therapy in Diabetes\n\nThe series of experiments leading to cloning and expression of insulin in the cultures cells in the 1970s was a tremendous revolution in the field of medicine and application of gene therapy in the treatment of diabetes was suggested as a possible cure.Regulating the sugar levels is the most important aspect in the treatment which also reduces the complications associated with the disease.Somatic gene therapy involving the somatic cells of the body includes two methods of gene delivery.The first one known as ex vivo gene therapy is described as the one in which the tissues are removed from the body; the therapeutic gene is inserted in vitro and then reimplanted back in the body while the in vivo therapy involves the insertion of gene therapy vectors directly to the patients by subcutaneous, intravenous, or intrabronchial routes, or by local injection [57].The application of ex vivo therapy aims at the generation of cells which possess the properties of  cells, for example, insulin producing cells [58].This therapy has also been used to generate  cells for transplantation.However, the concern lies in the aspect of surgically removing the tissue from the patient and reimplantation of the genetically modified tissues back into the body of the patients [57].Furthermore, type 1 diabetes results from autoimmune destruction of insulin synthesizing pancreatic  cells and islet transplantation has been explored as a possible solution for the treatment.The invention of insulin gene therapy substitutes  cell function by generating insulin secretory non- cells, not vulnerable to autoimmune reactions, offering a prospective therapeutic approach for type 1 diabetes [59].",
+      "\t\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\t\n\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\tGWAS-Identified Genes\n\nFollowing the successful identification of genetic loci by GWAS, several candidate genes within or surrounding genetic loci which are thought to play roles in b cell function, in particular, in proinsulin processing and secretion, have been examined in mechanistic studies.Gene editing tools have quickly replaced techniques such as shRNA-based silencing and HDR-mediated deletion to become a mainstream technique in studies of gene function.For example, the critical b cell-enriched NEUROD1 and SLC30A8 genes were deleted in EndoC-bH1 cells using these approaches in recent studies (243).Similarly, pancreatic duodenum homeobox-1 (PDX1), an important regulator of the INS gene, was also mutated by CRISPR-Cas9 resulting in a line with defective glucose-induced Ca 2+ influx and insulin secretion (244).Our laboratory has inactivated the type 2 diabetes-related STARD10 and FCHSD2 genes in EndoC-bH1 cells using a lentiviral approach and demonstrated effects on insulin secretion (and see above) (117).Furthermore, Fang et al. used CRISPR screening technology and identified several genes involved in insulin regulation in mouse MIN6 cells (172).\t\n\nIn vivo delivery of CRISPR editing tools into pancreatic b cells in people with diabetes is likely to face enormous challenges for two main reasons: 1. b cells are postmitotic, thus disfavouring HDR-mediated CRISPR editing.2. Selective targeting to these cells will be required, likely involving cell type-tropic viruses (272), raising evident concerns over off-target effects and toxicity.Hence, the most likely and feasible way of CRISPR editing has to be an ex vivo system where b cells can first be engineered by CRISPR editing and then transplanted into patients (Figure 2).\t\n\ninsulin secretion.We begin by providing examples of genes and loci associated with altered T2D risk.Finally, we review the CRISPR tools that may offer the potential to correct these variants in the human b cell.\tIn Vitro and In Vivo b Cell Models for Studying Genetic Variants\n\nIn order to understand the pathogenic role of diabetes-associated genetic variants, tractable b cell models are essential.Mouse models, either transgenic or knock-out, are valuable for examining the roles of single genes, but their use is more limited in studies of intergenic regions given more substantial inter-species (mouse versus human) differences in these regions.As sources of human b cells, there are currently three possibilities.Firstly, primary islets isolated from organ donors: This source is, however, limited in terms of the availability and quality of islets (226).Secondly, clonal human b cells.Immortalized human EndoC-bH1 cells were developed in recent years after infection of foetal islets with large T antigen and further inoculation of islets in immunocompromised mice (227).Later generation EndoC-bH2 (228) and EndoC-bH3 (229) cell lines were subsequently established with more advanced features including regulated deletion of the immortalizing gene.The limitation of these cell lines, however, is their extremely slow growth rate which hampers their use.Given this slow growth rate -and the fact that these lines poorly tolerate expansion from a single cell-it is virtually impossible to modify them by HDR via CRISPR editing.A third possibility are therefore islet-like cells differentiated from human embryonic stem cells (hESC) or patient-derived induced pluripotent stem cells (iPSC).In light of the limitations of the above cellular models, laboratories are now focusing on hESC or iPSC in studies of gene function throughout b cell development by differentiating hESC/iPSC cells into mature b cells (230,231).Such directed differentiation protocols have recently been improved (21,159)."
+    ],
+    [
+      "\t\n\nThe insulin receptor substrate 1 (IRS-1) expressed in tissues sensitive to insulin is crucial to glucose transporter 4 translocation (GLUT-4).IRS-1 polymorphism has been found related to insulin resistance, obesity and type 2 diabetes mellitus.In a study on GDM, the frequency of IRS-1 gene polymorphism was significantly higher in women with GDM than in pregnant women with a normal glucose tolerance, suggesting a role for this polymorphism in the onset of GDM as well as type 2 diabetes mellitus (17).The switch on IRS-1 of the amino acid GLY972 Arg (rs1801278) impairs insulin secretion, and a study on 1306 GDM patients and 1973 pregnant women without GDM found a significant association between the presence of this polymorphism and the risk of GDM (18).",
+      "\t\n\nAssociation of ADIPOQ gene polymorphisms with Type 2 diabetes.",
+      "\t\n\nThese six variants of PGC-1 gene were first studied to be associated with changes in insulin/glucose levels among Danish Caucasians (Ek et al. 2001).In the present study, genetic association analysis revealed increased risk of the A-allele (2.7-fold risk) and AA genotype (3.78-fold risk) of rs3736265 polymorphism towards T2D susceptibility in Jat Sikhs only, which can be attributed to ethnic heterogeneity.In contrast, a study on Danish Caucasians (Ek et al. 2001) revealed protective role of this allele while Han Chinese population (Zhu et al. 2009) showed no association.The AA genotype of rs3755863 polymorphism tends to pose 2.7-fold T2D risk in Jat Sikh group.On the other hand, studies on Caucasians showed protective effect whereas Chinese population failed to report any association with T2D (Barroso et al. 2003;Zhang et al. 2007).",
+      "\t\n\nType 2 diabetes (T2DM) is a complex disease resulting from the contribution of both environmental and genetic factors.Recently, the list of genes implicated in the susceptibility to T2DM has substantially grown, also as a consequence of the great development of the genome-wide association studies in the last decade.Common polymorphisms in TCF7L2 gene have shown to have a strong effect with respect to many other involved genes.The aims of our study were to confirm the role of TCF7L2 in the susceptibility to T2DM in the Italian population and to investigate whether TCF7L2 genotypes also contribute to the clinical phenotypes variability and to diabetic complications development.Three TCF7L2 polymorphisms (rs7903146, rs7901695 and rs12255372) have been analyzed by allelic discrimination assays in a cohort of 154 Italian patients with T2DM and 171 healthy controls.A case-control association study and a genotype-phenotype correlation study have been carried out.Consistent with previous studies, all three SNPs showed a strong association with susceptibility to T2DM, both at genotypic (P = 0.003, P = 0.004 and P = 0.012) and at allelic level (P = 0.0004, P = 0.0004 and P = 0.003).Moreover, we observed associations between TCF7L2 variants and the following diabetic complications: diabetic retinopathy, cardiovascular disease and coronary artery disease.We also found a strong correlation between the rs7903146 and the presence of cardiovascular autonomic neuropathy (P = 0.02 with a high OR = 8.28).",
+      "\t\n\nIn a GWAS of the French population, polymorphism rs13266634 of SLC30A8 gene has been associated with T2DM (Sladek et al., 2007).In a large meta-analysis including 42,609 cases and 69,564 controls from various ethnic groups from Europe, Asia, and Africa, polymorphism rs13266634 was also associated with T2DM in both Europeans and Asians (Jing, Sun, Bi, Shen, & Zhu, 2011).",
+      "\t\n\nGene polymorphisms affecting drug response for some commonly used antidiabetic agents.",
+      "\t\n\nIn fact, only two of the many candidate-gene associations claimed for T2D have stood the test of time.The Pro12Ala variant in the peroxisome proliferator-activated receptor gamma (PPARG) gene (encoding the target for the thiazolidinedione class of drugs used to treat T2D) [11] and the Glu23Lys variant in KCNJ11 (the potassium inwardly rectifying channel, subfamily J, member 11, which encodes part of the target for another class of diabetes drug, the sulphonylureas) [12] are both common polymorphisms shown in multiple studies to influence risk of T2D.Their effect sizes are only modest, each copy of the susceptibility allele increasing risk of disease by 15-20%.Interestingly, rare mutations in both KCNJ11 and PPARG are also known to be causal for certain rare monogenic syndromes (neonatal diabetes and lipodystrophies) characterized by severe metabolic disturbance of b-cell function and insulin resistance, respectively [13,14].",
+      "\t\n\nNo other recent associations of polymorphisms with T2D have been replicated to date (Table 5).However, a recent meta-analysis (106) identified some early reproducibility of an association between variation in GLUT1 and T2D, originally reported in 1988 (104).It is likely that this association has not been pursued further for several reasons, but one possibility is a study that reported the rejection of linkage to GLUT1 at high levels of significance (46).However, linkage has limited power to assess associations with common variants and modest effect (and hence low  S ); complete evaluation of this association would require comprehensive testing of variation in this gene in large samples.",
+      "\t\n\nbutions of these four common polymorphisms in type 2 diabetes patients were similar to those of normal nondiabetic controls.However, these four common polymorphisms were variably associated with several diabetes-related phenotypes, such as high-density lipoprotein (HDL) cholesterol, fasting plasma glucose, and homeostasis model assessment of insulin resistance.In particular, subjects harboring g.1062C were associated with a lower serum HDL cholesterol level after adjusting for other variables (P  0.0004 or 0.01 after Bonferroni correction for 24 tests).",
+      "\t\n\nHowever, there have been some successes.In T2D, the presence of common polymorphisms in known diabetes drug targets has presented obvious candidates for pharmacogenetic analysis.Evidence of a relationship between ABCC8/KCNJ11 genotype and sulfonylurea response is encouraging.Recent analyses in large cohorts have reported, for example, a 45% increased risk of glibenclamide treatment failure amongst risk compared to non-risk allele homozygotes (Sesti et al. 2006) and a greater decrease in fasting plasma glucose following gliclazide treatment amongst risk allele carriers (Feng et al. 2008).An effect upon gliclazide response is consistent with functional data which demonstrates that the risk variant K ATP channel has 3.5 times increased sensitivity to gliclazide inhibition (Hamming et al. 2009).",
+      "\tDNA polymorphisms associated with type 2 diabetes\n\nWe found 7 known genes (GPC1, ATSV, AGXT, HDLBP, NEDD5, PPP1R7 and serine/threonine (S/T) kinase-like), none of which were obvious candidates, and 15 ESTs in the NIDDM1 interval (Fig. 1).We identified single-nucleotide polymorphisms (SNPs) and other types of DNA polymorphism in the 7 known genes and in 4 of the 15 ESTs (Fig. 1).We carried out the initial analyses, examining association of alleles and haplotypes comprised of alleles at adjacent polymorphisms with type 2 diabetes, using just the random sample and the two groups of patients described above.There was a nominally significant difference (P=0.003,uncorrected for the 44-haplotype/group comparisons) in the haplotype frequency distribution of markers UCSNP-1, -2 and -19 between the group of patients with evidence for linkage at NIDDM1 and the random sample (Table A, see http://genetics.nature.com/supplementary_info/). The characterization of additional SNPs in the interval between UCSNP-19 and UCSNP-1 and -2 (Figs 1 and 2) revealed a cluster of four SNPs having significant differences in allele frequencies between the random sample and patients: UCSNP-26, P=0.02; UCSNP-25, P=0.03; UCSNP-23, P=0.02; and UCSNP-22, P=0.01 (Table 1).These results, however, cannot be considered independent observations of association due to linkage disequilibrium among the four SNPs.We also observed significant differences in allele frequencies at UCSNP-29, -35, -37, -38 and -40 between patient and random samples.These results suggested there might be a diabetes-susceptibility gene in the vicinity of these SNPs, thus prompting us to examine this region in more detail.We therefore resequenced this region in ten diabetic Mexican American subjects to gain a better understanding of all of the genetic variation that was present and the relationship between each polymorphism and type 2 diabetes (Fig. 2; and Table B, see http://genetics.nature.com/supplementary_info/).",
+      "\t\n\nwww.nature.com/clinicalpractice/endmetPPARG (peroxisome proliferator-activated receptor  gene; this encodes the target for thiazolidinediones) 11 and the Glu32Lys variant in KCNJ11 (which encodes part of another diabetes therapeutic target, this time for sulfonyl ureas) 4 are both common single-nucleotide polymorphisms (SNPs) that have been shown to influence risk of diabetes in multiple studies.Their effect sizes are modest (each extra copy of a susceptibility allele increases the risk of disease by about 15-20%), however, and their contribution to the observed familial aggregation of diabetes limited. ][14] The harvest of equivalent efforts in obesity has been even more limited.The only locus contributing to a respectable proportion of cases of severe adult obesity is the one that includes MC4R (melanocortin 4 receptor gene). 6The variants responsible are themselves rare, however, and have limited impact on variation in weight within the wider population. 5,6",
+      "\tConclusions\n\nIn this Review, we have summarized the available evidence on the role of polymorphisms in the genes encoding for insulin-signaling inhibitors molecules in determining genetic predisposition to T2D and related diseases.Overall, solid evidence seems to exist only for rs1044498 of the ENPP1 gene and for rs2295490 of the TRIB3 gene, whose association with T2D risk and insulin resistance, even if not confirmed (for ENPP1) [33] or not yet investigated (for TRIB3) [33] by GWAS studies, has been consistently reported by several original studies [16-20, 22-33, 38-43, 100, 101, 103, 104] and large meta-analyses [32,104].It is worth underlining that both rs1044498 and rs2295490 have been reported to be associated not only with defective insulin action in peripheral target tissues but also with impaired insulin secretion and decreased beta-cell homeostasis [14,15,101,103,104].These observations suggest that the two major pathogenic defects of T2D share common genetic causes and support the hypothesis that they should be seen as different aspects of the same process rather than as separate events [105].In addition, several studies have shown that the effect of rs1044498 and rs2295490 is more evident on early-onset T2D [26,28,104]; notably similar data have been obtained for rs1801278 of IRS1 gene [106]; these data hint to the possibility that focusing on early-onset cases may represent a successful strategy to study the contribution of insulin-signaling gene variants to T2D pathogenesis.Interestingly, a very recent study [107] has investigated the combined role of rs1044498 of the ENPP1 gene and for rs2295490 of the TRIB3 gene together with rs1801278 of IRS1 gene, on CVD, age at MI, and in vivo insulin sensitivity reporting a significant additive effect among the risk variants; notably the joint predictive power of ENPP1 rs1044498, IRS1 rs1801278, and TRIB3 rs 2295490 SNPs was even more evident among obese individuals [107].These results not only further reinforce the importance of rs1044498 and rs2295490 in determining the risk of insulin resistance and related diseases but further underlie that in any single individual the effect of each specific variant is also significantly influenced by the interaction with other variants as well as by environmental factors [108,109].Indeed T2D, CVD, IR, obesity, and related metabolic disorders are characterized by extremely heterogeneous phenotypes; thus some of the earlier positive findings reported in this Review that were not confirmed in subsequent, larger studies may have been \"real\" associations, even if limited to a specific subset of subjects in a definite environmental and genetic setting.In fact the extreme hetereogeneity of T2D and related diseases may represent one of the main reasons for the apparent discrepancy between the results of GWAS and those of classical \"candidate-gene\" studies, as the design of GWAS does not take into account several factors, including sexual dimorphism, age at disease onset, and obesity status, that have been shown to have an important role in the pathogenesis of metabolic diseases.In recent years, several methods for screening gene-environment interaction have been proposed [110] and their wider implementation is likely to shed further light on the genetics of metabolic diseases.Furthermore, novel technologies, such as next generation sequencing, that allow to address the role of relatively rare variants, will significantly contribute to obtain a clearer picture of the genetics basis of T2D and related diseases [111].Finally, the data on the genetics of insulin-signaling inhibitors molecules, recapitulated in this Review article, may supply useful elements to interpret the results of novel, more technically advanced, genetic studies; indeed it is becoming increasingly evident that genetic information on complex metabolic diseases should be interpreted taking into account the composite biological pathways underlying their pathogenesis [112].In addition, as suggested by recent studies on ENPP1 rs1044498 [35][36][37], a deeper knowledge of the genetic variants affecting the pathogenesis of T2D and related metabolic diseases may have important implications also for the implementation of tailored therapeutical approaches.\t\n\nA small Iranian study evaluated the specific contribution of seven polymorphisms found in the 2 Kb at the 3  extension of PTPN1 (plausibly, the promoter region) to the development of T2D [84].Only rs6126029A/C (g.-1023) showed nominal association with T2D, but this association was not confirmed after correction for established T2D risk factors [84].Functional analyses in HepG2 cell lines also showed that rs6126029A/C did not influence PTPN1 expression [84].The IVS5+3666del-/T SNP was only found in one study, and it was associated with morbid obesity in a French cohort, with no effects on T2D development or on glucose/insulin parameters [80].",
+      "\t\n\nTaken together, it seems therefore reasonable to believe that minor changes in a single enzyme or protein function due to a single nucleotide polymorphism are unlikely to generate defects in blood glucose and insulin concentrations across a population as a major clinical outcome.This is in contrast to insulin secretion where relatively minor effects due to gene polymorphism on b-cell viability, survival or function would, over time, have a measurable effect on the rate of insulin secretion from pancreatic islets, and present clinically as hyperglycemia.",
+      "\t\n\nWe recognize that our study has limitations as the limited size of the sample in the groups of study.The functional effect of the polymorphisms only was determined by informatics tools, so experimental designs are needed in order to corroborate this functional effect.In spite of these limitations, our study contributes to a new argument in which the 5UTR 44 C/G polymorphism may have a role as a risk factor for T2DM.",
+      "\tDiscussion\n\nThe main result of our study shows that, among lean individuals, carriers of polymorphism Gly972Arg of the IRS1 gene are at 3 times greater odds of having T2D, as compared with noncarriers.This association with T2D exists independently of potentially associated environmental factors like BMI, family history of diabetes, and sex.This observation suggests a possible relationship of polymorphism Gly972Arg in the pathogenesis of T2D.The other 3 tested SNPs on this gene were not associated with the presence of T2D.The SNP-SNP and SNP-environment interactions were not significant.\t\n\nBased on our previous observation suggesting a greater genetic predisposition among lean diabetics [20], in the present analysis, we aimed to evaluate the association of the Gly972Arg polymorphism and other polymorphic variants on the IRS1 gene with T2D in a representative sample of the Mexican population with body mass index (BMI) less than 25 kg/m 2 .",
+      "\t\n\nPrevious attempts to relate the Gly482Ser polymorphism to type 2 diabetes have shown an 1.34-fold increase in risk among Danish Caucasians [38] and a significant association among Japanese subjects [39].In contrast, the 482Ser allele did not predict diabetes in French Caucasians or Pima Indians [40,41].These studies were carried out in single populations.Because several different populations were used in the STOP-NIDDM trial, our data provides strong evidence that the Gly482Ser polymorphism of the PGC-1 gene contributes to the risk of type 2 diabetes.In agreement with this, the reduced expression of PGC-1 in adipose tissue has been associated with insulin resistance [51].Moreover, recent studies have reported that down-regulation of the PGC-1 gene and coordinated changes in other genes involved in oxidative phosphorylation in man are associated with IGT, diabetes mellitus [35] and insulin resistance [37].",
+      "\tCONCLUsION\n\nTo conclude, rs7903146 and rs680 polymorphisms were found independently to be significantly associated with T2DM risk in Indian adults.MDR identified the gene-gene interaction between TCF7L2 and SLC30A8 polymorphisms in confirming T2DM risk.Further studies should address the biological mechanisms affecting glucose homeostasis."
+    ],
+    [
+      "\tDISCUSSION\n\nIn this study, we employed high throughput sequencing to identify differentially expressed miRNAs associated with IGT and untreated diabetes in whole blood of South African mixed ancestry women, which in an earlier study we had established a high prevalence of undiagnosed IGT and DM [18).We observed evidence for differential expression of 61 in IGT, 109 in screendetected diabetes both when compared to individuals with normal glucose tolerance, of which 25 were common in both conditions.Although several of these dysregulated miRNAs have been linked to diabetic and non-diabetic hyperglycaemia, we also uncovered 57 novel miRNAs.Of note is hsa-miR-novel-chr2_50989 which had the highest fold change in screen-detected DM and remained in the top ten differentially expressed miRNAs in IGT.Functional annotation of genes that are potentially regulated by the miRNAs implicated showed that signal transduction pathways (PI3K-Akt, MAPK, HIF-1, cAMP, FoxO, ErbB, Ras, Rap1 and insulin resistance); carbohydrate metabolism; glycan biosynthesis and metabolism, cell communication, cell growth and death; immune system; endocrine system and metabolic diseases are likely involved in the development of hyperglycaemia in this population.\t\n\nA number of miRNAs such as the let-7 family, 30ep-5p [26,31,32] found in this study and others have been shown to be involved in these pathways.These miRNAs have be reported to exert their function by suppressing the expression of insulin receptor genes [17,32].Although many similarities were found between this study and others, our study is unique for uncovering that some of these miRNAs were differentially expressed between diabetic and non-diabetic dysglycaemia.Indeed, using OGTT to characterise asymptomatic participants, we identified three miRNAs that potentially distinguish between diabetic and non-diabetic hyperglycaemia.For example, miR-126-3p, and miR-28-3p were upregulated in IGT when compared to screen-detected DM, whilst miR-486-5p was down-regulated in screen-detected DM in comparison to either IGT or NGT.miR-126 is expressed by cells that modulate inflammatory response and vascular homeostasis through enhanced production of anti-inflammatory chemokines, and has been shown to be reduced in T2DM [33][34][35][36][37].The downgrelation of miR-126 has been shown to be mostly pronounced in poorly controlled T2DM and in T2DM with complications when compared to sujects with T2DM without complication [38].Similarly, in a study that investigated miR-126 in serum of DM patients with varying degrees of retinopathy, miR-126 was reduced in patients versus the controls, but lowest in patients with proliferative diabetic retinopathy [39].Taken together, our findings of upregulated miR-126 and others in IGT versus screen-detected DM most probably point towards a cascading reduction with respect to diabetes related complications suggesting a potential role for miR-126 in distinguishing prediabetes from diabetes.Indeed, Liu et al [40]), examined the usefulness of miR-126 in predicting prediabetes and T2DM and reported lower levels in T2DM compared to prediabetes, even though both were significanlty lower than in healthy controls.It is important to note that a number of miRNAs including novel ones with potential to distinguish between hyperglycaemia and normal glucose tolerance were uncovered in the current study.For example, miR-hsa-miR-1299 had the highest fold change in IGT versus controls and was not detected in individuals with DM, whilst mir-novel-chr2_55842 was amongst the 10 th most differentially expressed in IGT only.In hepato-hepatocellular carcinoma, miR-1299 inhibits cell proliferation by targeting cyclin-dependent kinase 6, [41] however there is limited information about miR-1299 in diabetes.Therefore, further studies are needed to elucidate the molecular mechanisms of miR-1299 and other novel miRNAs identified in this study.\t\n\nSome of the dysregulated miRNAs found in our study corroborate findings of many other studies that have aimed to characterize miRNAs in different tissue types of individuals with DM and/or prediabetes.A recent systematic study of dysregulated miRNAs in T2DM identified a total of 158 dysregulated miRNAs in adipose, islet, skeletal muscle, whole blood, PBMC, plasma and serum [26].Similarly we found 36 (23%) of these miRNAs dysregulated in T2DM and IGT (Supplementary Table 4).Furthermore, three additional miRNAs (miR-27b, miR-98, and miR-21) previously reported to be dysregulated in mixed ethnic ancestry women with IGT or T2DM [27] were also differentially expressed in screen-detected DM in our sample.The miRNAs found in the current study and others have been shown to play a direct role in insulin production and secretion [21][22][23][24][25]28].This was confirmed by bioinformatics techniques we applied to identify the potential biological functions affected by the miRNA signatures.p53 signaling, PI3K/ Akt, p53 signaling and MAPK were respectively the 2 nd , 3 rd and 6 th targeted significant pathways in enrichment analysis by KEGG.The PI3K/Akt/ and MAPK pathways plays a major signaling role in the cellular response to extracellular stimuli, including glucose homeostasis, cell proliferation and survival [29].In glucose homeostasis,   the activation of these pathways is directly under the control of insulin receptors upon insulin stimulation [30].\t\nEarly identification of individuals with elevated risk of developing diabetes mellitus, followed by the implementation of effective prevention interventions can delay the onset of the disease and related complications.In this regard, recent studies have shown that miRNAs are useful as early markers of certain disease types, including diabetes.We used high throughput sequencing to assess miRNA expression profiles from whole blood of 12 individuals with screen-detected diabetes, 12 with prediabetes and 12 with normal glucose tolerance, matched for age, blood pressure, smoking and body mass index.We identified a total of 261 (57 novel) differentially expressed miRNA profiles between the study groups.Comparison of the miRNA expression profiles between prediabetess and diabetes revealed 25 common miRNA, but highlighted some interesting differences.For instance, three miRNAs (miR-126-3p, miR-28-3p miR-486-5p) were dysregulated in prediabetes compared to screen-detected diabetes.Target gene analysis showed thousands of potential genes and KEGG pathway analysis revealed 107 significant pathways of which some are involved signal transduction, cell-cell communications, cell growth and death, immune response, endocrine system and metabolic diseases.This first detailed African study has shown both known and novel differentially expressed miRNAs in relation to glucose tolerance.\t\n\nEarly identification of individuals with elevated risk of developing diabetes mellitus, followed by the implementation of effective prevention interventions can delay the onset of the disease and related complications.In this regard, recent studies have shown that miRNAs are useful as early markers of certain disease types, including diabetes.We used high throughput sequencing to assess miRNA expression profiles from whole blood of 12 individuals with screen-detected diabetes, 12 with prediabetes and 12 with normal glucose tolerance, matched for age, blood pressure, smoking and body mass index.We identified a total of 261 (57 novel) differentially expressed miRNA profiles between the study groups.Comparison of the miRNA expression profiles between prediabetess and diabetes revealed 25 common miRNA, but highlighted some interesting differences.For instance, three miRNAs (miR-126-3p, miR-28-3p miR-486-5p) were dysregulated in prediabetes compared to screen-detected diabetes.Target gene analysis showed thousands of potential genes and KEGG pathway analysis revealed 107 significant pathways of which some are involved signal transduction, cell-cell communications, cell growth and death, immune response, endocrine system and metabolic diseases.This first detailed African study has shown both known and novel differentially expressed miRNAs in relation to glucose tolerance.\t\n\nOverall, in addition to complementing earlier studies on miRNAs in prediabetes and diabetes, our findings provide evidence of known and novel differentially expressed miRNAs in African mixed ancestry individuals with IGT and screen-detected DM.We further observed that the aberrant expression profiles of miRNAs were linked to several biological processes, such as signal transduction, cell-cell communications, cell growth and death, immune response, endocrine system and metabolic diseases.Larger prospective studies in this and other racial populations from Africa are needed to characterize the molecular mechanisms of African-specific differentially expressed miRNAs, as well as assess their potential to predict worsening of glucose tolerance status.\t\n\nDespite the growing evidence of the important role and potential diagnostic value of miRNAs in dysglycaemia, such properties are yet to be demonstrated in the African setting.Therefore, in the present study we aimed to identify dysregulated miRNA in a South African mixed ancestry population previously reported to be at high risk of diabetes [18].To avoid potential bias from treatment induced alterations in miRNA expression, we focused on individuals with normal glucose tolerance (NGT), prediabetes individuals with IGT only and those with screen-detected diabetes who had not initiated glucose lowering drug treatment.",
+      "\t\n\nSome recently-identified miRNAs have been associated with insulin secretion, insulin resistance, and inflammation, and differences have emerged in some circulating miRNA levels between individuals with and without type 2 diabetes (40).Zhao and others (41) examined some miRNAs in pregnant women at 16-19 weeks of gestation (WG), finding a significantly lower expression of 3 miRNAs (miR-29a, miR-132 and miR222) in women who went on to develop GDM at 24-28 WG than in those who did not develop GDM.MiR-29 plays a part in glucose homeostasis: its overexpression inhibits insulinstimulated glucose uptake and downregulates gluconeogenesis (42).MiR-132 targets the insulin-mediated regulation of cytochrome P450 (which is involved in hepatic metabolism), and it has a role in trophoblast expansion (its reduced expression impairs normal trophoblast development) (42,43).MiR-222 is involved in regulating the cell cycle (controlling the cyclindependent kinase inhibitor).",
+      "\t\n\nUpon further epigenetic regulatory elements in diabetes, micro-RNAs, such as miR-15a and miR-29b, were found to be downregulated in type 2 diabetes, whereas miR-27a and miR-320a were upregulated and might open the possibility for new diagnostic markers [187, [231][232][233].",
+      "\t\n\nIn addition to predicting targets of the differentially expressed miRNAs in T2DMED based on a literature review, IGF-1, as one of the target genes of miR-18a or miR-206, was confirmed via luciferase assay.T2DMED rats with downregulation of IGF-1 in their CCs have been reported (El-Sakka et al. 1999).In experiments with human diabetic erectile tissue, researchers also found a decreased expression of IGF-1, which was mainly located in the layers of smooth muscle cells (Castela et al. 2012).In this study, we also verified this reduction via ELISA.IGF-1 is essential to the regeneration of NOS-containing nerve fibres in the dorsal and intracavernosal nerves (Jung et al. 1999).Intervention of IGF-1 expression in the penis could ameliorate ED in T2DMED rats (Pu et al. 2007).Thus, miR-18a and/or miR-206 suppression of IGF-1 may be an interesting research direction for T2DMED.\t\n\nThe genes regulated by the four miRNAs relate to several KEGG pathways which might be involved in the mechanisms of T2DMED\t\n\nexpression of miR-18a, miR-206, miR-122, and miR-133   were confirmed by qRT-PCR (p < 0.05 and FDR <5 %).According to bioinformatic analysis, the four miRNAs were speculated to play potential roles in the mechanisms of T2DMED via regulating 28 different genes and several pathways, including apoptosis, fibrosis, eNOS/cGMP/ PKG, and vascular smooth muscle contraction processes, which mainly focused on influencing the functions of the endothelium and smooth muscle in the CC.IGF-1, as one of the target genes, was verified to decrease in the CCs of T2DMED animals via ELISA and was confirmed as the target of miR-18a or miR-206 via luciferase assay.Finally, these four miRNAs deserve further confirmation as biomarkers of T2DMED in larger studies.Additionally, miR-18a and/or miR-206 may provide new preventive/therapeutic targets for ED management by targeting IGF-1.\t\nexpression of miR-18a, miR-206, miR-122, and miR-133   were confirmed by qRT-PCR (p < 0.05 and FDR <5 %).According to bioinformatic analysis, the four miRNAs were speculated to play potential roles in the mechanisms of T2DMED via regulating 28 different genes and several pathways, including apoptosis, fibrosis, eNOS/cGMP/ PKG, and vascular smooth muscle contraction processes, which mainly focused on influencing the functions of the endothelium and smooth muscle in the CC.IGF-1, as one of the target genes, was verified to decrease in the CCs of T2DMED animals via ELISA and was confirmed as the target of miR-18a or miR-206 via luciferase assay.Finally, these four miRNAs deserve further confirmation as biomarkers of T2DMED in larger studies.Additionally, miR-18a and/or miR-206 may provide new preventive/therapeutic targets for ED management by targeting IGF-1.\t\n\nIn conclusion, for the first time, we reported the differentially expressed miRNAs in a classical murine model of T2DMED.Four differentially expressed miRNAs (miR-18a, miR-206, miR-122 and miR-133) were confirmed by qRT-PCR and are speculated to play crucial roles in influencing the functions of the endothelium and smooth muscle via regulating 28 different genes and several pathways, including apoptosis, fibrosis, eNOS/cGMP/PKG, and vascular smooth muscle contraction processes.IGF-1, as one of the target genes, was verified to decrease in the CCs of T2DMED animals and was confirmed as the target of miR-18a or miR-206 via luciferase assay.These four miRNAs deserve further confirmation as biomarkers of T2DMED in larger studies and may provide new perspectives for understanding the molecular aetiology of T2DMED in the future.Particularly, miR-18a and/or miR-206 may provide new preventive/therapeutic targets for ED management by targeting IGF-1.",
+      "\t\n\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\t\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.",
+      "\t\n\nFigure 4. Candidate miRNA regulatory hubs in a type 2 diabetes gene network. (A) Each data point represents a 59-reference miRNA or a 59-shifted isomiR from primary human beta cells, and the y-axis shows the negative Log2 of the p-value of the predicted miRNA targeting score among genes in a type 2 diabetes (T2D) network.The dashed red line denotes the significance threshold (empirical P = 0.05). (B) Effects of miR-29 mimic and inhibitor in MIN6 cells on the mRNA levels of four T2D genes are shown.The x-axis lists the gene symbols for each of four predicted miR-29 target genes and the y-axis depicts the relative quantitative value (RQV; expression determined by RT-qPCR and normalized to Rps9) in response to the miR-29 mimic (blue) or the miR-29 inhibitor (red) relative to mock transfection.The data shown represent at least two independent experiments, each conducted in triplicate.P-values were calculated based on Student's t-tests. *, P,0.05; **, P,0.01.doi:10.1371/journal.pone.0073240.g004\tCandidate 59-shifted isomiR Regulatory Hubs in Type 2 Diabetes\n\nGenome-wide association studies for type 2 diabetes (T2D) have primarily (though not exclusively) implicated genes with critical function in the pancreatic beta cell [45,46].Therefore, we sought to determine if any of the highly expressed human beta cell miRNAs, including 59-shifted isomiRs, serve as regulatory hubs in T2D.We first assembled a list of genes (n = 92) implicated in T2D and related conditions including maturing onset diabetes of the young (MODY) (Methods).We then implemented a Monte Carlo simulation strategy (Methods) to determine for each miRNA whether the predicted regulatory impact on T2D genes is significantly (uncorrected P,0.05) greater than expected by chance (such miRNAs are termed ''candidate regulatory hubs'').We identified 10 candidate miRNA regulatory hubs (Fig. 4A; Table S3 in File S2).The top two were the 59-reference miRNAs miR-29 and let-7, both of which have been implicated in beta cell function and glucose homeostasis [47][48][49].Though miR-29 has been shown to regulate glucose-stimulated insulin secretion, its target genes in the beta cell are largely unknown.To validate the in silico approach, we selected several predicted targets (Camk1d, Glis3, and Jazf1), and one previously validated target (Slc16a1 [48]), of miR-29 from among the T2D gene list for evaluation in MIN6 cells.Specifically, we transiently transfected MIN6 cells with a miR-29 mimic or inhibitor (antagomiR) and measured the mRNA levels of each of the four genes by real-time quantitative PCR (RT-qPCR).Three of the four genes were significantly (p,0.05) down regulated by the over-expression of miR-29 and three genes were significantly (p,0.05) up regulated by the antagomiR-mediated inhibition of miR-29 (Fig. 4B).These findings are consistent with previous reports that miR-29 is involved in the regulation of beta cell function [48,50], and they serve as a validation of the in silico regulatory hub analysis.",
+      "\t\n\nFigure 2. miRNA expression profile changes in T2D compared with control subjects using the Exiqon chip platform and TaqMan confirmation (FDR <10%). (a) Data are plotted to show the pattern of change of these significantly up-/down-regulated miRNA.Black lines represent those miRNA that increase/decrease progressively with IGT and T2D (DM), green lines represent miRNAs that are increased/decreased with IGT and then revert with T2D, while orange lines show miRNAs increased/decreased only in the T2D state. (b) miRNAs that show the expression profile during myocyte differentiation (cell data derived from Chen et al. [55]) is the opposite pattern to that observed in the muscle of patients with T2D (green = down-regulated probe sets, red = up-regulated probe sets; the color range is from -3-fold to +3-fold change).MG refers to the data produced by Chen et al. during myogenesis. (c) Expression level of miR-1, miR-133a, miR-133b and miR-206 in muscle biopsies from healthy individuals (NGT, n = 10, white bars), individuals with impaired glucose tolerance (IGT, n = 10, grey bars) and individuals with type 2 diabetes (T2D, n = 10, black bars).miR-133a (P < 0.001) and miR-206 (P = 0.04) were significantly reduced in T2D patients when compared with expression levels in healthy controls.Data are expressed as fold change from NGT and shown as mean  standard error. **P < 0.001, *P < 0.05. (d) Expression level of miR-133a in muscle versus indices of glucose homeostasis in subjects with and without T2D.Expression of miR-133a is positively correlated with fasting glucose, R 2 = 0.41 (P < 0.001, n = 30).Data are shown as Ct levels normalized to RNU48 and plotted versus fasting glucose levels (mmol/L).",
+      "\t\n\nT2D loci were also identified at clusters of noncoding RNAs with roles in islet  cell function.One locus includes a set of microRNAs specifically expressed in islet  cells, the maternally expressed noncoding RNA MEG3, and the paternally expressed gene DLK1.Targets of these microRNAs increase  cell apoptosis 40 , and reduced Meg3 expression impairs insulin secretion 41 .DLK1 inhibits adipocyte differentiation, thereby protecting against obesity 3 , and promotes pancreatic ductal cell differentiation into  cells, increasing insulin secretion 42,43 .Other variants near MEG3 have been associated with type 1 diabetes 44 (EAS and EUR LD r 2 = 0 with EAS lead variant).The other noncoding RNA locus is the MIR17HG cluster of miRNAs, which regulate glucose-stimulated insulin secretion and pancreatic  cell proliferation stress 45 ; one of these microRNAs, miR-19a, affects hepatic gluconeogenesis 46 .Yet another T2D locus is located near TRAF3, which is a direct target of the MIR17HG microRNA cluster and promotes hyperglycaemia by increasing hepatic glucose production 47,48 .The T2D association results suggest that these noncoding RNAs influence disease susceptibility."
+    ],
+    [
+      "\tConclusion\n\nIn our sequencing study involving 6888 individuals, 2.2% of individuals with early onset diabetes and 0.7% of individuals with late onset diabetes harbored a likely pathogenic mutation in monogenic diabetes genes.Our results confirm previous reports that MODY is under-diagnosed [19,75], particularly in individuals presenting with early onset diabetes and clinically labeled as T2D and, in such cases, genetic testing can provide an etiological diagnosis.With the continuing reduction in costs of DNA sequencing, genetic screening of all known monogenic diabetes genes in individuals with early onset diabetes should be routinely considered since it can identify individuals with undiagnosed MODY as well as atypical forms of monogenic diabetes.Knowledge of mutations in monogenic diabetes genes has the potential to influence diagnosis and therapy for individuals with diabetes as well as to enable the genetic testing of relatives.",
+      "\tConclusions\n\nGenomics research in monogenic diabetes and the implementation of NGS-based approaches for precision diagnosis of MODY subtypes undoubtedly move the physicians and patients towards the era of precision genomic medicine that takes into account the individual genetic data.Specific issues are emerging such as the right estimate of variant pathogenicity and age-dependent penetrance, the multi-genic causality, and the composite phenotypes.Lessons learned from MD with recent findings in common T2D genetic architecture support a continuum of diabetes phenotypes from rare monogenic to common adult-onset diabetes which impacts the strategies for both diagnosis and longitudinal investigation of diverse clinical subtypes along the life course.Beyond facing youngonset diabetes, practitioners should systematically promote a comprehensive genetic testing of MD-MODY subtypes, with benefits of optimal patient care and of strong reduction of global medical costs.\t\nPurpose of Review Non-autoimmune monogenic diabetes (MD) in young people shows a broad spectrum of clinical presentations, which is largely explained by multiple genetic etiologies.This review discusses how the application of state-of-the-art genomics research to precision diagnosis of MD, particularly the various subtypes of maturity-onset diabetes of the young (MODY), has increasingly informed diabetes precision medicine and patient care throughout life.Recent Findings Due to extended genetic and clinical heterogeneity of MODY, diagnosis approaches based on next-generation sequencing have been worthwhile to better ascribe a specific subtype to each patient with young-onset diabetes.This guides the best appropriate treatment and clinical follow-up.Summary Early etiological diagnosis of MD and individualized treatment are essential for achieving metabolic targets and avoiding long-term diabetes complications, as well as for drastically decreasing the financial and societal burden of diabetesrelated healthcare.Genomic medicine-based practices help to optimize long-term clinical follow-up and patient care management.\t\n\nPurpose of Review Non-autoimmune monogenic diabetes (MD) in young people shows a broad spectrum of clinical presentations, which is largely explained by multiple genetic etiologies.This review discusses how the application of state-of-the-art genomics research to precision diagnosis of MD, particularly the various subtypes of maturity-onset diabetes of the young (MODY), has increasingly informed diabetes precision medicine and patient care throughout life.Recent Findings Due to extended genetic and clinical heterogeneity of MODY, diagnosis approaches based on next-generation sequencing have been worthwhile to better ascribe a specific subtype to each patient with young-onset diabetes.This guides the best appropriate treatment and clinical follow-up.Summary Early etiological diagnosis of MD and individualized treatment are essential for achieving metabolic targets and avoiding long-term diabetes complications, as well as for drastically decreasing the financial and societal burden of diabetesrelated healthcare.Genomic medicine-based practices help to optimize long-term clinical follow-up and patient care management.\tIntroduction\n\nMaturity-onset diabetes of the young (MODY), a dominantly inherited familial form of diabetes typically diagnosed before 25 years of age in non-obese subjects, represents the most frequent subgroup of early-onset non-autoimmune diabetes [1,2].MODY is a monogenic disease but with a high clinical and genetic heterogeneity, although always caused by a primary inherited or de novo genetically induced defect in insulin secretion responsible for chronic hyperglycemia.This pathophysiological feature common to all MODY cases arises from a functional impairment of one of the diverse pancreatic -cell expressed key regulators of insulin biosynthesis and secretion [2,3].More than fifteen MODY genetic subtypes have been characterized raising the issue of an accurate etiological genetic diagnosis at an early age enabling a genuine personalized medicine of diabetes.MODY patients are usually diagnosed under the age of 25-30 years, but overt diabetes or moderate chronic hyperglycemia can happen at any age from childhood to young adulthood or at later age.The broad range of phenotypic features and variability in the clinical presentations are largely dependent on the underlying genetic defect that actually determines both pathophysiology and long-term progression of diabetes.\t\n\nIn this review, we highlight the recent advances in the field of genomics of monogenic diabetes (MD) with the current challenges of accurately defining and recognizing the various MODY subtypes and of translating molecular diagnosis into personalized care over the lifetime.\t\n\nThe known genetic causes of MODY have pointed out major pancreatic -cell expressed genes regulating insulin secretion, such as alterations in GCK and a network of transcription factors important for the control of -cell function.Recent works have further provided new clues for better understanding specific functional mechanisms related to MODY genetic defects.\tA Global View on MODY Genetics\n\nClinical Heterogeneity and Genetic Subtypes of MODY More than 25 years of comprehensive investigation of MODY genetic components, through the study of patient cohorts and multiplex families, have provided great advances in the knowledge and functional characterization of major MODY genes with mostly various protein-coding changes.So far, at least 15 genes causing MODY, involving different mutation types, have been formally identified (details on these genes are given in Table 1).In these genes, a single, mostly highly penetrant, rare mutation is sufficient to cause a MODY phenotype.The major MODY genes encode pancreatic -cell expressed proteins involved in developmental processes, in the maturation and maintenance of cell function (through transcription factors regulating the transcriptional network of pancreatic -cells), in the control of -cell glucose sensing (through the glucokinase enzyme), in -cell signaling, and in insulin production and secretion [2].From our current knowledge of the underlying pathogenic mechanisms, it is well substantiated that MODY-causing mutations cluster into key genes and interconnected biological pathways that represent core regulatory networks for pancreatic -cell identity and function (as for -cell transcriptional network, or regulatory proteins of reticulum endoplasmic homeostasis) [14].Along the same line, -cell dysfunction is the main driver of MODY, together with decreased -cell mass and cellular death.",
+      "\tU N C O R R E C T E D A C C E P T E D A R T I C L E BACKGROUND\n\nMaturity-onset diabetes of the young (MODY) is a monogenic form of diabetes mellitus characterised by autosomal dominant inheritance, a young age of onset (often diagnosed before 25 years of age) and pancreatic -cell dysfunction (MODY; MIM# 606391) (Fajans and Bell, 2011;Hattersley, 1998;Molven and Njolstad, 2011;Tattersall, 1974).Heterozygous mutations in the genes encoding the glycolytic enzyme glucokinase (Froguel, et al., 1992;Hattersley, et al., 1992) and the transcription factors, hepatocyte nuclear factor (HNF)-1 alpha (HNF1A; MIM# 142410) (HNF1A MODY, formerly MODY3) (Yamagata, et al., 1996a), HNF-4 alpha (HNF4A; MIM# 600281) (HNF4A MODY, formerly MODY1) (Yamagata, et al., 1996b) and HNF1B (formerly MODY5) (Horikawa, et al., 1997) have been shown to cause MODY.A distinct clinical phenotype is associated with each genetic aetiology (Edghill, et al., 2006;Stride and Hattersley, 2002).Mutations in the genes pancreatic and duodenal homeobox 1 (PDX1) (Stoffers, et al., 1997), NEUROD1 (Malecki, et al., 1999), CEL (Torsvik, et al., 2010), KCNJ11 (Yorifuji, et al., 2005) INS (Edghill, et al., 2008), and ABCC8 (Bowman, et al., 2012) are rare causes of autosomal dominant diabetes.Other potential forms of MODY include mutations in the transcription factor genes KLF11 (Neve, et al., 2005), PAX4 (Plengvidhya, et al., 2007) and BLK (Borowiec, et al., 2009), but the identification of additional families showing co-segregation of mutations with diabetes is required to confirm these as \"MODY genes\".",
+      "\tIntroduction\n\nMaturity onset diabetes of the young (MODY) is the most common monogenic subtype of diabetes that is characterized by an early-onset of diabetes, no requirement for insulin at diagnosis, and no signs of autoimmunity or insulin resistance [1] .MODY is inherited in an autosomal dominant manner.It is a clinically heterogeneous group of disorders caused by -cell dysfunction.It is estimated that MODY accounts for up to 1.8% of patients with diabetes [2] .Mutations in 13 genes are known to cause MODY; the most prevalent are HNF1A , GCK and HNF4A [3,4] .The MODY subtypes differ in age of onset of diabetes, the pattern of hyperglycemia, response to treatment, and associated extrapancreatic manifestations [5] .As compared to type 2 diabetes, the clinical symptoms present often at a relatively young age in patients without overweight, who have a positive family history.As compared to type 1 diabetes, progression may be less severe, and the required dosage of insulin low.",
+      "\tCANDIDATE GENES IDENTIFIED IN HUMAN AND RODENT MODELS OF T2D\n\nMaturity onset diabetes of the young Foremost among the monogenic forms of T2D is MODY.The early age of onset and autosomal dominant pattern of inheritance have facilitated gene identication in the majority of MODY families through classical Mendelian positional cloning approaches, as described in Chapter 4.",
+      "\tMaturity Onset Diabetes of the Young (MODY)\n\nIn 1960, Fajans & Conn (50) first described maturity-onset diabetes of the young (MODY).MODY is characterized clinically by autosomal dominant transmission, early onset (usually before the age of 25 years), the correction of fasting hyperglycemia without insulin for at least two years following diagnosis, and nonketotic disease (49).Thus, the main distinguishing features compared to more typical cases of T2D include a strong family history (typically spanning several generations), a younger age of onset, and the absence of obesity.The familial pattern of inheritance and lack of requirement for insulin therapy to prevent ketosis distinguish MODY clinically from T1D. MODY usually presents as asymptomatic hyperglycemia in young adults and often has a mild course.Some patients, however, progress rapidly and require insulin therapy, and microvascular and renal complications can ensue.",
+      "\t\n\n1 Genetic causes of maturity-onset diabetes of the young A BLK, PAX4 and KLF11, although classified as MODY genes (#11, #9, and #7 respectively) in OMIM, are not listed as MODY-causing because of recently disputed or refuted gene-disease relationships (see section \"Rare types of MODY\").APPL1 was proposed as MODY14 based on two families reported in 201533, but evidence is otherwise limited.RFX6 does not have a MODY number in OMIM, but is included here as multiple loss-of-function variants were recently implicated in a phenotype very similar to that of other MODY genes but with lower penetrance 11 .OHA: Oral Hypoglycemia Agents",
+      "\tMaturity\n\n-onset diabetes of the young (MODY) is a heterogeneous single gene disorder characterized by non-insulin-dependent diabetes, an early onset and autosomal dominant inheritance.Mutations in six genes have been shown to cause MODY.Approximately 15-20% of families fitting MODY criteria do not have mutations in any of the known genes.These families provide a rich resource for the identification of new MODY genes.This will potentially enable further dissection of clinical heterogeneity and bring new insights into mechanisms of -cell dysfunction.To facilitate the identification of novel MODY loci, we combined the results from three genome-wide scans on a total of 23 families fitting MODY criteria.We used both a strict parametric model of inheritance with heterogeneity and a model-free analysis.We did not identify any single novel locus but provided putative evidence for linkage to chromosomes 6 (nonparametric linkage [NPL]score 2.12 at 71 cM) and 10 (NPL score 1.88 at 169 -175 cM), and to chromosomes 3 (heterogeneity LOD [HLOD] score 1.27 at 124 cM) and 5 (HLOD score 1.22 at 175 cM) in 14 more strictly defined families.Our results provide evidence for further heterogeneity in MODY.Diabetes 52:872-881, 2003 M aturity-onset diabetes of the young (MODY) is characterized by -cell dysfunction, no requirement for insulin in the first years of the disease, an autosomal dominant mode of inheritance, and an early age at onset of diabetes (25 years) ( 1).The identification of MODY genes has helped explain the phenotypic heterogeneity associated with the disorder.MODY is a genetically diverse subgroup of diabetes, and to date six distinct MODY genes have been identified: these encode the glycolytic enzyme glucokinase (GCK) (2,3), hepatocyte nuclear factor (HNF)-1 (4), HNF-1 (5), HNF-4 (6), insulin promoter factor (IPF)-1 (7), and NeuroD1/BETA2 (8).The relative distribution of MODY1-6 depends on the population investigated, although in all studies mutations in GCK and HNF1 are the two most prevalent forms (9 -11).Mutations in each gene result in distinct clinical and physiological characteristics (12).Glucokinase mutations present with stable mild fasting hyperglycemia throughout life as a result of reduced glucose sensing in the -cell (13).In contrast, mutations in the transcription factors (HNF-1, HNF-4, HNF-1, and IPF-1) cause a progressive -cell failure that may become severe (14).",
+      "\tTypes of monogenic diabetes\n\nMaturity-onset diabetes of the young MODY comprises most monogenic diabetes cases, with classical characteristics of young diagnosis age, family history of diabetes in an autosomal dominant pattern of transmission, and insulin independence, with some types having additional features (Table 1).While 14 genes have now been designated as MODY genes in OMIM and/or the literature, three of these (BLK, PAX4, and KLF11) have been proposed for elimination based on a recent study (10) (see Table 1 for the remaining 11 along with RFX6, recently proposed as an additional MODY gene; ref . 11).Variants in GCK, HNF1A, and HNF4A are responsible for most MODY cases, followed by HNF1B (12).Given the known genetic etiology of  (42), but evidence is otherwise limited.RFX6 does not have a MODY number in OMIM, but is included here as multiple loss-of-function variants were recently implicated in a phenotype very similar to that of other MODY genes but with lower penetrance (11).OHA, oral hypoglycemia agents.",
+      "\t\n\nThere is now clear evidence of a strong genetic component to the disease due to prevalence differences between racial groups, a higher concordance rate among monozygotic than dizygotic twins and a sibling risk ratio of approximately 3.5 [119].Maturity-onset diabetes of the young (MODY) is the autosomal dominantly inherited form of diabetes without insulin dependency, characterized by -cell dysfunction and is diagnosed at a relatively young age (<25 years) [120,121].MODY is made up of subtypes defined on the basis of genetic etiology.These genetic subtypes have aided the identification of patients who will respond to a given therapy from those who are unlikely to respond.As such, this opens the possibility of tailored drug therapy both at the individual level for MODY and for the general treatment of T1D and T2D as a whole.Identifying further forms of this monogenic diabetes will provide crucial insights into patterns of -cell dysfunction and the associated therapeutic response.Of the seven MODY genes identified to date, the most common forms present as a consequence of mutations in the genes encoding the glycolytic enzyme, glucokinase, and the transcription factor, hepatic nuclear factor-1 (HNF1) [122,123].",
+      "\t\n\nMaturity-onset diabetes of the young (MODY) is a rare, autosomal dominant form of diabetes.There are six primary forms of MODY, each a consequence of mutations in six different genes [37].In addition to the autosomal dominant inheritance, MODY is characterized by onset before the age of 25 and -cell dysfunction typically in the absence of insulin resistance or obesity.MODY3 arises from mutations in the hepatocyte nuclear factor 1 homeobox A gene (HNF1A), and patients with this disease are hyper-sensitive to the hypoglycemic effects of sulfonylureas [38].In an early case study, Pearson et al. [39] identified three MODY3 patients with HNF1A mutations, in whom cessation and reintroduction of sulfonylureas caused dramatic changes in HbA1c levels, or severe hypoglycemia, in response to introduction of sulfonylureas into the treatment regimen.A subsequent study found that MODY3 patients had a 5.2-fold or 3.9-fold greater response to gliclazide compared to metformin or patients with T2D, respectively [40].These patients also had a stronger insulin secretory response to tolbutamide and were more insulin-sensitive compared to individuals with common T2D [40].",
+      "\t\n\nBoth genetic susceptibility and environmental drivers, notably obesity and sedentary lifestyles, determine the overall risk of T2D (4)(5)(6).Supporting a genetic component, rare monogenic forms of the disease exist with Mendelian inheritance (7,8).Thus, maturity onset of diabetes of the young (MODY) is a rare form of diabetes with mutations often residing in exons encoding the functional domains of transcription factors such as hepatocyte nuclear factor hepatocyte nuclear factor 1 homeobox A (HNF1A) (9) and HNF4A (10), or of proteins involved in b cell glucose metabolism such as glucokinase (GCK) (11) (Table 1).",
+      "\tIntroduction\n\nThe maturity onset diabetes of the young (MODY) is a monogenic form of diabetes characterized by an autosomal dominant inheritance; the onset usually happens before the 25 years of age and is characterized by an impaired insulin secretion with minimal or no defect of the insulin action (Fajans and Bell 2001).Some studies suggest that 1-2% of patients with type 2 diabetes (T2D) may in fact have MODY (Shields et al. 2010).Data available suggest that people carrying one mutated allele are born with completely normal physiological and biochemical functions of the pancreatic b-cells, and diabetes will occur at some stage during adolescence (Bell and Polonsky 2001;Fajans and Bell 2001).Penetrance of diabetes in patients with mutations in MODY is quite high (more than 95% by the age of 55 years) (Frayling et al. 2001;Murphy et al. 2008).Recent studies have demonstrated heterozygous mutations in genes encoding 11 forms of MODY, including the hepatocyte nuclear factor-4a encoding the gene (HNF4A)(MODY 1), the glucokinase gene or GCK (MODY 2), the hepatocyte nuclear factor-1a that encodes HNF1A (MODY 3), the pancreas/duodenum homeobox protein 1 (PDX1, also known as IPF-1) (MODY 4), the hepatocyte nuclear factor-1b encoding the gene HNF1B (MODY 5), the neurogenic differentiation 1 that encodes the gene (NEUROD1)(MODY 6), the Kruppel-like factor 11 (KLF11) (MODY 7), the carboxylester lipase encoding the gene (CEL) (MODY 8), the paired box gene 4 (PAX4) (MODY 9), insulin gene (INS) (MODY 10), the tyrosine kinase B-lymphocyte specific gene (BLK) (MODY 11), the potassium voltage-gated channel subfamily J member 11 (KCNJ11 gene) (MODY13), and the adapter protein containing PH domain, PTB domain and leucine zipper motif 1, also known as DCC-interacting protein 13-a encoded by the APPL1 gene (MODY14).Those cases of as yet unknown genetic derangement have been classified as MODYX (Online Mendelian Inheritance in Man [OMIM], MIM entry 606391).",
+      "\t\n\nIn contrast, maturity-onset diabetes of the young (MODY) is a rare monogenic form of type 2 diabetes that has an autosomal dominant mode of inheritance.At least five different genes, located on chromosomes 20, 7, 12, 13, and 17, independently cause MODY within single pedigrees (5)(6)(7)(8)(9).MODY genes may also play a minor role in the common form of type 2 diabetes (10)."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "E240519BE7D595118C1489579F47EA95"
+    },
+    {
+      "task_id": "F03565FC1DE138132AB1F4CB52D248F7"
+    },
+    {
+      "task_id": "E36FE156B8571A149192268FE357FAF5"
+    },
+    {
+      "task_id": "5329674E4693E27C6109ACCA28EBBF2F"
+    },
+    {
+      "task_id": "80A67B6A36E27EC64F7C664F8E972C68"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_3.json
new file mode 100644
index 0000000..a01447e
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_3.json
@@ -0,0 +1,124 @@
+{
+  "question": [
+    "What genes are most commonly associated with an increased risk of developing diabetes?",
+    "How can genetic testing help predict a person's risk for diabetes?",
+    "What role do family genetics play in the likelihood of getting diabetes?",
+    "Can lifestyle changes affect genetic risk factors for diabetes?",
+    "What recent breakthroughs have been made in understanding the genetic causes of diabetes?"
+  ],
+  "answer": [
+    "The genes most commonly associated with an increased risk of developing diabetes include TCF7L2, PPARG, FTO, KCNJ11, NOTCH2, WFS1, CDKAL1, IGF2BP2, SLC30A8, JAZF1, and HHEX.",
+    "Genetic testing can help predict a person's risk for diabetes by identifying specific genetic variants or risk alleles associated with the disease. These genetic markers, when combined into a polygenic score, can provide information on individual patterns of disease predisposition. This can be particularly useful if measured early in life, as it can enable early interventions for preventing diabetes. However, the predictive value of these genetic factors is currently considered to be small compared to traditional risk factors like obesity and fasting glucose levels.",
+    "Family genetics play a significant role in the likelihood of getting diabetes. Studies have shown that siblings of individuals with diabetes have a significantly higher risk of developing the disease compared to the general population. Genetic factors account for a substantial fraction of susceptibility to type 1 diabetes. In type 2 diabetes, the risk is higher if one or both parents have the disease. However, the presence of certain genetic factors does not guarantee the development of diabetes, as environmental factors also play a significant role.",
+    "Yes, lifestyle changes can affect genetic risk factors for diabetes. Studies suggest that a healthy lifestyle or lifestyle modification can partially or totally control genetic predisposition to obesity and Type 2 Diabetes Mellitus (T2DM). However, the effectiveness of these changes can vary among individuals due to genetic influences.",
+    "Recent breakthroughs in understanding the genetic causes of diabetes include the identification of many genes that predispose to both major types of diabetes, thanks to advances in genetics. Genome-wide association studies have been particularly effective in uncovering genetic determinants of complex diseases like diabetes. More recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes. These methods have led to the identification of novel variants and loci contributing to trait variation and disease risk."
+  ],
+  "contexts": [
+    [
+      "\t\n\nIn the past 10 years, geneticists have devoted a large amount of effort to finding type 2 diabetes genes.These efforts have included many candidate-gene studies, extensive efforts to fine map linkage signals 3 , and an international linkage consortium that was perhaps the best example of a multi-centre collaboration in common-disease genetics.Of these efforts, only the candidate-gene studies produced unequivocal evidence for common variants involved in type 2 diabetes.These are the E23K variant in the potassium inwardly-rectifying channel, subfamily J, member 11 (KCNJ11) gene [4][5][6] , the P12A variant in the peroxisome proliferatoractivated receptor- (PPARG) gene 7 , and common variation in the transcription factor 2, hepatic (TCF2) 8,9 and the Wolfram syndrome 1 (WFS1) 10 genes.All of these genes encode proteins that have strong biological links to diabetes.Rare, severe mutations in all four cause monogenic forms of diabetes [11][12][13][14] , and two are targets of anti-diabetic therapies: KCNJ11 encodes a component of a potassium channel with a Genome-wide association studies provide new insights into type 2 diabetes aetiology Timothy M. Frayling Abstract | Human geneticists are currently in the middle of a race.Thanks to a new technology in the form of 'genome-wide chips', investigators can potentially find many novel disease genes in one large experiment.Type 2 diabetes has been hot out of the blocks with six recent publications that together provide convincing evidence for six new gene regions involved in the condition.Together with candidate approaches, these studies have identified 11 confirmed genomic regions that alter the risk of type 2 diabetes in the European population.One of these regions, the fat mass and obesity associated gene (FTO), represents by far the best example of an association between common variation and fat mass in the general population.key role in -cell physiology that is a target for the sulphonylurea class of drugs, and PPARG encodes a transcription factor involved in adipocyte differentiation that is a target for the thiazolodinedione class of drugs.\tSix new gene regions identified\n\nTogether, the six recent GWAS papers provide convincing evidence for six new gene regions involved in type 2 diabetes [16][17][18][19][20][21] ; a seventh publication describes how one of these variants alters BMI and represents by far the best example of an association between common genetic variation and obesity 22 .There are now 11 gene regions in which common variation alters type 2 diabetes risk with the levels of statistical confidence that are required by genetic association studies (FIGS 2,3).This progress is all the more remarkable in view of the weak genetic component to type 2 diabetes risk, as compared with many other common diseases that are currently being studied using GWAS.The sibling relative risk is 3-4 at the most for type 2 diabetes, in contrast with 5-10 for rheumatoid arthritis, 15 for type 1 diabetes, 7-10 for bipolar disorder, 17-35 for Crohn disease, 2-7 for early myocardial infarction and 2.5-3.5 for hypertension 21 .",
+      "\t\n\nGenes whose variants are commonly associated with both type 2 diabetes mellitus and cardiovascular disease.",
+      "\tGenomic Analyses for Diabetes Risk\n\nGenes signifying increased risk for both type 1 and type 2 diabetes have been identified.Genomewide association studies have identified over 50 loci associated with an increased genetic risk of type 1 diabetes.Several T1D candidate genes for increased risk of developing type 1 diabetes have been suggested or identified within these regions, but the molecular basis by which they contribute to islet cell inflammation and beta cell destruction is not fully understood. 12Also, several candidate genes for increased risk of developing type 2 diabetes have been identified, including peroxisome proliferatoractivated receptor gamma (PPAR2), angiotensin converting enzyme (ACE), methylene tetrahydrofolate reductase (MTHR), fatty acid binding protein-2 (FABP2), and fat mass and obesity associated gene (FTO). 13he conclusions of a \"Workshop on Metformin Pharmacogenomics,\" sponsored by the National Institute of Diabetes and Digestive and Kidney Diseases, were published in 2014. 14The meeting was intended to review metformin pharmacogenomics and identify both novel targets and more effective agents for diabetes.The idea behind the meeting was that understanding the genes and pathways that determine the response to metformin has the potential to reveal new drug targets for the treatment of diabetes.The group noted that there have been few genes associated with glycemic control by metformin, and the most reproducible associations have been in metformin transporter genes.They acknowledged that nongenetic factors also contribute to response to metformin and that broader system biology approaches will be required to model the combined effects of multiple gene variants and their interaction with nongenetic factors.They concluded that the overall challenge to the field of precision medicine as it relates to antidiabetes treatment is to identify the individualized factors that can lead to improved glycemic control.",
+      "\tIntroduction\n\nIt is well recognized that type II diabetes mellitus has a substantial genetic component (Barnett et al. 1981;Knowler et al. 1981;Hanson et al. 1995a).Genes that predispose to some types of diabetes have been identi-fied; these include several loci for type I diabetes (Davies et al. 1994) and for maturity-onset diabetes of the young (Froguel et al. 1992;Yamagata et al. 1996aYamagata et al. , 1996b;;Stoffers et al. 1997).However, the genes that cause the most common forms of diabetes remain unknown, and it is, therefore, likely that additional important diabetessusceptibility loci remain to be identified.Moreover, the specific risk factors through which such genes influence the development of type II diabetes are also unknown.Obesity, as quantified by body-mass index (BMI) (kg/ m 2 ), is a strong risk factor for type II diabetes (Knowler et al. 1981) and is also likely to have genetic determinants (Price et al. 1994).The present study represents a genomewide search for loci linked to diabetes and BMI in Pima Indians, a Native American population with a high prevalence of type II diabetes and obesity (Bennett et al. 1971;Knowler et al. 1978Knowler et al. , 1991)).",
+      "\tGENETIC SUSCEPTIBILITY AND GENE-ENVIRONMENT INTERACTIONS-\n\nThe recent advent of genome-wide association studies (GWAS) has led to major advances in the identification of common genetic variants contributing to diabetes susceptibility (40).To date, at least 40 genetic loci have been convincingly associated with type 2 diabetes, but these loci confer only a modest effect size and do not add to the clinical prediction of diabetes beyond traditional risk factors, such as obesity, physical inactivity, unhealthy diet, and family history of diabetes.Many diabetes genes recently discovered through GWAS in Caucasian populations have been replicated in Asians; however, there were significant interethnic differences in the location and frequency of these risk alleles.For example, common variants of the TCF7L2 gene that are significantly associated with diabetes risk are present in 20-30% of Caucasian populations but only 3-5% of Asians (41,42).Conversely, a variant in the KCNQ1 gene associated with a 20-30% increased risk of diabetes in several Asian populations (43,44) is common in East Asians, but rare in Caucasians.It is intriguing that most diabetes susceptibility loci that have been identified are related to impaired b-cell function, whereas only a few (e.g., peroxisome proliferator-activated receptor-g, insulin receptor substrate 1, IGF-1, and GCKR) are associated with insulin resistance or fasting insulin, which points toward b-cell dysfunction as a primary defect for diabetes pathogenesis.It should be noted that most of the single nucleotide polymorphisms uncovered may not be the actual causal variants, which need to be pinpointed through fine-mapping, sequencing, and functional studies.",
+      "\t\n\nInitial linkage studies in affected families indentified CAPN10 and TCF7L2 as risk-conferring genes in T2D [27].Association studies using candidate gene approach identified additional risk genes -PPARG and KCNJ11 (the targets of many current diabetes medications), IRS1, WFS1, HNF1A, HNF1B and HNF4A, among others [28].The more recent GWAS have added a plethora of genetic risk variants, but with small indifuture science group Genetics, genomics & personalized medicine in Type 2 diabetes: a perspective on the Arab region Review vidual effect size.To date, GWAS for T2D have identified over 50 genetic risk variants, but their causal relationship in the etiology of the disease remains elusive.However, it is important to note that most loci harboring disease-causing variants have been found to be associated with defective functioning of the -cells of the pancreatic islets, thus implicating this pathway as a major factor in the pathology of T2D [29].So far, the strongest association signal for T2D has been found for the TCF7L2 gene, which has been replicated across GWAS of different ethnic groups.Other important genes which have been replicated across GWAS of different populations include HHEX, SLC30A8, CDKN2A/B, IGF2BP2, HMGA2, KCNQ11 and NOTCH2-ADAM30 [28].",
+      "\t\n\nGenetic determinants of diabetes and metabolic syndromes.",
+      "\t\n\nAmong type 2 diabetes susceptibility genes few, if any, individual loci are expected to carry alleles of major effect explaining a substantial proportion of cases, although a few genes could have a substantial population effect but not give a strong genetic signal if the causal alleles were common and the increase in risk were modest [6,7].Such genes have proven hard to detect using linkage-based approaches, although recent rapid advances in genetic association methodologies have led to some successes.The P12A polymorphism in the gene encoding the peroxisome proliferator-activated receptor-g (PPARG) [7], the E23K polymorphism in the gene encoding the islet ATPdependent potassium channel Kir6.2 (ABCC8-KCNJ11) [8][9][10] and common variants in the gene encoding the transcription factor 7-like 2 gene (TCF7L2) [11,12] were all found using well-powered association mapping, and all have been reproducibly associated with diabetes in diverse samples at highly significant p-values.",
+      "\t\n\nIn support of our focus on developmental genes, pathway analysis of recent genome-wide association studies, which so far have yielded few T2D candidate genes, provided an integrated interpretation of the highest ranked risk genes for T2D [97].This analysis found that lipid metabolism and developmental genes were significantly over-represented in the upper ranked genes of the T2D genome-wide association studies, an observation based on thousands of samples, and one strongly consistent with the present independent analysis.Combined, we believe this presents strong evidence that developmental genes may play a role in setting or regulating the long-term responses of skeletal muscle to diabetes.",
+      "\tResults\n\nStrong predictors of diabetes were a family history of the disease, an increased body-mass index, elevated liver-enzyme levels, current smoking status, and reduced measures of insulin secretion and action.Variants in 11 genes (TCF7L2, PPARG, FTO, KCNJ11, NOTCH2, WFS1, CDKAL1, IGF2BP2, SLC30A8, JAZF1, and HHEX) were significantly associated with the risk of type 2 diabetes independently of clinical risk factors; variants in 8 of these genes were associated with impaired beta-cell function.",
+      "\t\n\nRecently, spectacular advance was made in identifying susceptible genes involved in T2D through genome-wide association strategy (GWAS) [10,11].Consequently, a number of novel genetic variants (PPARG, KCNJ11, IGF2BP2, KCNQ1, TCF7L2, CDKAL1, and MTNR1B) were shown to increase the risk of T2D in reproducible studies.Therefore, several studies have examined the association of these newly identified loci using a candidate gene approach for GDM.It has been reported that the pathophysiological changes of GDM are similar to those observed in T2D, which is characterized by peripheral insulin resistance accompanied by an insulin secretory defect [12,13].Functional studies showed that these new diabetogenic genes took part in many steps of the process, for instance, impaired b-cell function (CDKAL1, IGF2BP2, KCNQ1, KCNJ11, MTNR1B), insulin resistance (PPARG, TCF7L2), and abnormal utilization of glucose (GCK) [14][15][16][17][18][19][20][21][22][23].",
+      "\t\n\nGenome-wide association studies (GWAS) have discovered germline genetic variation associated with type 2 diabetes risk (1)(2)(3)(4).One of the largest GWAS, involving DNA taken from individuals of European descent and conducted by the DIAGRAM (DIAbetes Genetics Replication And Meta-analysis) consortium, identified 65 loci associated with type 2 diabetes risk (1).However, for most of these loci, the precise identity of the affected gene and the molecular mechanisms underpinning the altered risk are not known.",
+      "\t\n\nGenetic factors appear to play a role in determining an individual's risk of developing diabetes.It is hoped that genetic studies will ultimately identify key genetic elements that help determine susceptibility to diabetes, disease progression, and responsiveness to specific therapies, as well as help identify novel targets for future intervention.A substantial number of genetic loci, gene polymorphisms, and mutations have already been reported as having variable degrees of association with one or other type of diabetes (type 1, type 2, maturity onset diabetes of the young [MODY]), while others appear to be involved in response to antihyperglycemic agents.We have compiled the following glossary of genetic and genomic terms relating to diabetes, which we hope will prove a useful reference to researchers and clinicians with an interest in this disease.This is by no means an exhaustive list, but includes many of the genetic loci and variants that have been studied in association with diabetes.Gene encoding insulin-like growth factor 2 mRNA binding protein 2 (also known as IMP-2).SNPs in the gene have been associated with type 2 diabetes IFIH1",
+      "\t\n\nNearly all of the recent discoveries have used genome wide association study (GWAS) techniques to identify single nucleotide polymorphisms (SNPs) that exist at higher frequency in DNA from people with established T2DM (''cases'') than in non-diabetic individuals (''controls'').Where the physiological roles of these variants have so far been determined, the majority encode proteins linked with the b-cell.For example, of 19 validated T2DM genes, 14 have been shown to influence glucose or incretin stimulated insulin secretion (reviewed in [6]).In addition, these variants have relatively large effects on diabetes risk compared with other variants, with the seven variants with the greatest association with diabetes risk (TCF7L2, CDKAL1, HHEX, CDKNA/2B, IGF2BP2, SLC30A8, JAZF1) all affecting b-cell insulin secretion.The rapid rise in prevalence of type 2 diabetes mellitus (T2DM) has been driven by changes in environmental factors -primarily increased caloric intake and reduced energy expenditure -resulting in reduced whole body insulin sensitivity (often termed insulin resistance).Insulin resistance has been proposed to be a major driver of progression to T2DM.However, of 38 individual susceptibility loci for T2DM recently identified by genome wide association studies, by far the majority code for proteins involved in b-cell function.In this review, we discuss the possible reasons for the paucity of insulin resistance genes and ask whether the new genetic susceptibility data should focus attention on b-cell targets in the development of therapies for T2DM.",
+      "\t\n\nMore than 65 loci, encoding up to 500 different genes, have been implicated by genome-wide association studies (GWAS) as conferring an increased risk of developing type 2 diabetes (T2D).Whilst mouse models have in the past been central to understanding the mechanisms through which more penetrant risk genes for T2D, for example, those responsible for neonatal or maturity-onset diabetes of the young, only a few of those identified by GWAS, notably TCF7L2 and ZnT8/SLC30A8, have to date been examined in mouse models.We discuss here the animal models available for the latter genes and provide perspectives for future, higher throughput approaches towards efficiently mining the information provided by human genetics.\t\nMore than 65 loci, encoding up to 500 different genes, have been implicated by genome-wide association studies (GWAS) as conferring an increased risk of developing type 2 diabetes (T2D).Whilst mouse models have in the past been central to understanding the mechanisms through which more penetrant risk genes for T2D, for example, those responsible for neonatal or maturity-onset diabetes of the young, only a few of those identified by GWAS, notably TCF7L2 and ZnT8/SLC30A8, have to date been examined in mouse models.We discuss here the animal models available for the latter genes and provide perspectives for future, higher throughput approaches towards efficiently mining the information provided by human genetics.",
+      "\t\n\nGenomic information associated with Type 2 diabetes.",
+      "\tBackground\n\nMultiple genetic loci have been convincingly associated with the risk of type 2 diabetes mellitus.We tested the hypothesis that knowledge of these loci allows better prediction of risk than knowledge of common phenotypic risk factors alone.",
+      "\t\n\nAs 80% of type 2 diabetes patients are obese, a further research focus is the identification of genes encoding 'diabesity', predisposing the carrier to both pathological conditions.Philippe Froguel (Lille, France) found in a French population with a BMI of 40, as well in Germans with early onset obesity, a linkage with markers on chromosome 2p, 8 and around D10S1781.Leptin gene polymorphisms on chromosome 7 were only associated with blood leptin levels and diet success in the extremely obese.Stephen Rich (Winston-Salem, NC) showed how quantitative trait linkage (QTL) can greatly increase the accuracy of genetic studies.Rich found a clustering for type 2 diabetes candidate genes in families with diabetic nephropathy (Caucasians s 52.7 and African Americans s 58.1) as well as a correlation with arterial-wall width.Takashi Kadowaki (Tokyo, Japan) illustrated the important role of animal models in the understanding of diabetes.Using glucokinase-, IRS2-and PPAR-knockout mice, he was able to measure the effect of different dietary fats on insulin resistance, -cell hyperplasia, overt diabetes and arterial hypertension."
+    ],
+    [
+      "\t\n\nResearchers are expanding our understanding of genetic risk factors for diabetes through ongoing discoveries.Genetic variants associated with increased susceptibility to type 2 diabetes, a disease that affects more than 200 million people worldwide, have been identified (NHGRI & NIDDK, 2007).Such discoveries accelerate efforts to understand genetic contributions to chronic illness, as well as facilitate greater investigation of how these genetic factors interact with each other and with lifestyle factors.Ultimately, once the association of these variants with diabetes are confirmed, genetic tests may be utilized to identify (even before escalating blood sugars) those individuals, like Vanessa, who may be able to delay or prevent diabetes with healthy lifestyle decisions and behaviors.Information to assist nurses in this challenge is available in a toolkit \"Your Game Plan for Preventing Type 2 Diabetes\" (Your Game Plan, n.d.).Would you have known whether or not genetic testing was available for Vanessa?If you had said no to this question but could have explained the progress currently being made in understanding diabetes, Vanessa would have had access to the best care possible today.",
+      "\t\n\nProgress toward wider use of genetic testing in the prediction of type 2 diabetes and its complications will require three developments.The first involves identification of a growing number of risk variants that, collectively, deliver greater predictive and discriminative performance than the subset thus far known.The second involves understanding how genetic information can be combined with other conventional risk factors (and possibly with non-DNA-based biomarkers, as these emerge) to provide a more accurate assessment of individual risk.It should be kept in mind that susceptibility genotype information will not be orthogonal to those traditional factors, since several of them (such as ethnicity, family history, and BMI) capture overlapping genetic information.The third development will be evidence that imparting such information results in clinically meaningful differences in individual behavior or provides a more rational basis for therapeutic or preventative interventions.\t\n\nOf course, individual small effects can amount to more when considered collectively, and it is true that genetic testing (for the 17 known genes, for example) can identify subsets of individuals who have inherited particularly high or low numbers of risk alleles and therefore have marked differences in individual risk (87).However, the numbers of individuals in these \"extreme\" high-and low-risk groups are comparatively small, and for many, their risk will already be obvious through conventional factors (family history, BMI, and previous gestational diabetes, for example).When the information from the known type 2 diabetes-susceptibility variants is examined using approaches such as receiver-operating curve analysis, which are better suited for evaluating the performance of diagnostic tests at the population level, the results look far less spectacular (72,87).",
+      "\tClinical Utility of Genetic Information: Prediction of Type 2 Diabetes\n\nOne of most important clinical utilities of genetic information is to predict the risk of developing T2D among nondiabetic individuals.This will facilitate the early interventional strategies to prevent or delay the onset of the disease.A vast number of recent studies have constructed genetic risk score models by summing up numerous independently inherited susceptible variants for T2D to evaluate the predictive ability from the current genetic information.For example, the area under the receiver operating characteristic (ROC) curves (AUCs) is used to assess discriminative accuracy of this approach.The AUC value can range from 0.5 to 1.0, where the AUC of 0.5 stands for the lack of discrimination and AUC of 1 stands for perfect discrimination.An AUC value of greater than 0.75 is considered to be clinically useful [140].\t\nWith rapidly increasing prevalence, diabetes has become one of the major causes of mortality worldwide.According to the latest studies, genetic information makes substantial contributions towards the prediction of diabetes risk and individualized antidiabetic treatment.To date, approximately 70 susceptibility genes have been identified as being associated with type 2 diabetes (T2D) at a genome-wide significant level ( < 510 8 ).However, all the genetic loci identified so far account for only about 10% of the overall heritability of T2D.In addition, how these novel susceptibility loci correlate with the pathophysiology of the disease remains largely unknown.This review covers the major genetic studies on the risk of T2D based on ethnicity and briefly discusses the potential mechanisms and clinical utility of the genetic information underlying T2D.",
+      "\tGENOMICS IN THE PREDICTION, PREVENTION, AND DIAGNOSIS OF DIABETES\n\nThe incidence and prevalence of diabetes have doubled over the past two decades (13), and there are now about 30 million adults in the U.S. living with this condition, 95% of whom have type 2 diabetes (14).Genome-wide association (GWA) studies test hundreds of thousands or even millions of common (minor allele frequency [MAF] .5%)and lowfrequency (MAF 1-5%) variants across both protein coding (exonic) and noncoding (intronic) regions of the genome.Large GWA studies have identified more than 50 genetic loci associated with various glycemic traits and at least 90 loci associated with type 2 diabetes (15)(16)(17)(18).These genetic variants, which may explain as much as 10% of the variance in disease susceptibility, have advanced our understanding of the biology of diabetes, but each genetic locus confers only a small increase in risk.For example, the common variant from these GWA studies most strongly associated with type 2 diabetes, an intronic variant in TCF7L2 (rs7903146), is associated with a 37% increased relative risk per copy of the variant allele (19).Rare variants (MAF ,1%) and variants that are common only in specific ancestral populations have been associated with a greater increase in diabetes risk, but they account for less of the overall burden of diabetes (20)(21)(22).",
+      "\t\n\nThe promise of genetic risk scoring for diabetes can be evaluated in the framework of three perspectives.First is the potential for robust prediction of diabetes risk.Second is the prospect of designing targeted preventive and therapeutic interventions (personalized medicine).Thirdly, increased knowledge could provide genomic clues to ethnic disparities in diabetes.Regarding robustness of prediction, results from the Framingham Offspring Study showed that clinical risk assessment (using age, sex, family history, BMI, fasting glucose level, systolic blood pressure, high-density lipoprotein cholesterol level, and triglyceride level) performed as well as cumulative genotype score at 18 loci in predicting incident type 2 diabetes during 28 years of follow-up of initially normoglycemic subjects (14).Also, cumulative genotype score at 34 loci did not add significantly to clinical risk factors in predicting progression from impaired glucose tolerance to type 2 diabetes among the multiethnic cohort enrolled in the Diabetes Prevention Program (15).One current limitation is the incomplete framework from which GRS is constructed.For example, the 17 SNPs studied in the present report (17) represent just about half of the .30diabe-toSNPs identified to date.Even the latter do not represent all possible risk loci, and important information on structural variants that might increase diabetes risk is often lacking.Thus, current experience renders the promise of robust genetic prediction and personalized diabetes intervention a distant hope.",
+      "\t\n\nRegardless, one expects many of the important susceptibility genes for type 2 diabetes will be uncovered in the next 10 years.Once that occurs, intense effort will be focused on developing targeted therapies.Also, medical care will shift to genetic testing of persons with type 2 diabetes, followed by giving them the most effective proven therapy for that genetic form of the disease.Also, their family members will undergo genetic testing while still normally glucose tolerant to determine if they carry a genetic predisposition.If so, specific treatment plans will be developed for prevention of the disease, again based on proven efficacy for each genetic defect.",
+      "\t\n\nTwo more recent population -based studies using a longitudinal design with prospectively investigated cohorts have examined the predictive value of a genotype score in addition to common risk factors for prediction of T2DM [194,195] .Meigs et al. [194] reported that a genotype score based on 18 risk alleles predicted new cases of diabetes in the community but provided only a slightly better prediction of risk than knowledge of common clinical risk factors alone [195] .A similar conclusion was drawn in the paper by Lyssenko et al. [196] , along with an improved value of genetic factors with an increasing duration of follow -up, suggesting that assessment of genetic risk factors is clinically more meaningful the earlier in life they are measured.They also showed that  -cell function adjusted for insulin resistance (using the disposition index) was the strongest predictor of future diabetes, although subjects in the prediabetic stage presented with many features of insulin resistance.It is also noteworthy that many of the variants that were genotyped appear to infl uence  -cell function.The addition of DNA data to the clinical model improved not only the discriminatory power, but also the reclassifi cation of the subjects into different risk strategies.Identifying subgroups of the population at substantially different risk of disease is important to target these subgroups of individuals with more effective preventative measures.As more genetic variants are now identifi ed, tests with better predictive performance should become available with a valuable addition to clinical practice.",
+      "\t\n\nPredicting T2DM in healthy individuals has been attempted using a diabetes risk score that is derived from common clinical information, such as adiposity, blood pressure, and family history of T2DM.However, using the risk score is inevitably limited in predicting T2DM because T2DM has a strong genetic basis; concordance of T2DM is about 70% for monozygotic twins, compared to about 20-30% for dizygotic twins. 2 Limitations in predicting T2DM have driven researchers to employ genetic risk assessments.Moreover, unlike clinical markers, genetic markers do not change with time, so they possess the advantage of identifying high-risk individuals long before disease onset, which could enable early interventions for preventing T2DM.Conventionally, family-based linkage studies have played an important role in identifying genes having a large effect in monogenic disorders, such as maturity-onset diabetes of the young. 3However, linkage studies have low power for polygenic diseases that are influenced by multiple genes, as is the case with the majority of those with T2DM.Therefore, using monogenic mutations would have very limited value for predicting risk of disease in the general population because of their low frequency.",
+      "\tDiscussion\n\nOur study provides insight into the relative importance of clinical risk factors and those that are related to a panel of DNA variants associated with type 2 diabetes.Obesity was a strong risk factor for future diabetes, a risk that almost doubled in subjects with a family history of diabetes.However, the addition of data from genotyping of the known DNA variants to clinical risk factors (including a family history of diabetes) had a minimal, albeit statistically significant, effect on the prediction of future type 2 diabetes.Notably, the ability of genetic risk factors to predict future type 2 diabetes improved with an increasing duration of follow-up, suggesting that assessment of genetic risk factors is clinically more meaningful the earlier in life they are measured.\t\n\nIn conclusion, the inclusion of common genetic variants that are associated with type 2 diabetes very slightly improved the prediction of future type 2 diabetes, as compared with the inclusion of clinical risk factors alone.Although this effect might be too small to allow for individual risk prediction, it could be useful in reducing the number of subjects who would need to be included in intervention studies aimed at the prevention of type 2 diabetes.Supported by grants from the Swedish Research Council (including Linn grant 31475113580), the Heart and Lung Foundation, the Swedish Diabetes Research Society, a Nordic Center of Excellence Grant in Disease Genetics, the Diabetes Program at the Lund University, the Finnish Diabetes Research Society, the Sigrid Juselius Foundation, the Phlsson Foundation, the Crafoord Foundation, the Folkhlsan Research Foundation, the Novo Nordisk Foundation, the European Network of Genomic and Genetic Epidemiology, the Wallenberg Foundation, and the European Foundation for the Study of Diabetes.\t\nA bs tr ac t\nBackgroundType 2 diabetes mellitus is thought to develop from an interaction between environmental and genetic factors.We examined whether clinical or genetic factors or both could predict progression to diabetes in two prospective cohorts. MethodsWe genotyped 16 single-nucleotide polymorphisms (SNPs) and examined clinical factors in 16,061 Swedish and 2770 Finnish subjects.Type 2 diabetes developed in 2201 (11.7%) of these subjects during a median follow-up period of 23.5 years.We also studied the effect of genetic variants on changes in insulin secretion and action over time. ResultsStrong predictors of diabetes were a family history of the disease, an increased body-mass index, elevated liver-enzyme levels, current smoking status, and reduced measures of insulin secretion and action.Variants in 11 genes (TCF7L2, PPARG, FTO, KCNJ11, NOTCH2, WFS1, CDKAL1, IGF2BP2, SLC30A8, JAZF1, and HHEX) were significantly associated with the risk of type 2 diabetes independently of clinical risk factors; variants in 8 of these genes were associated with impaired beta-cell function.The addition of specific genetic information to clinical factors slightly improved the prediction of future diabetes, with a slight increase in the area under the receiveroperating-characteristic curve from 0.74 to 0.75; however, the magnitude of the increase was significant (P = 1.010 4 ).The discriminative power of genetic risk factors improved with an increasing duration of follow-up, whereas that of clinical risk factors decreased. ConclusionsAs compared with clinical risk factors alone, common genetic variants associated with the risk of diabetes had a small effect on the ability to predict the future development of type 2 diabetes.The value of genetic factors increased with an increasing duration of follow-up.",
+      "\t\n\nGenetic variants can also identify patients at higher risk, predict rates of C-peptide decline, and predict response to various therapies (41).With a better understanding of inheritance profiles, it may become possible to realize new targets for individualized intervention.",
+      "\t\n\nGenetic factors appear to play a role in determining an individual's risk of developing diabetes.It is hoped that genetic studies will ultimately identify key genetic elements that help determine susceptibility to diabetes, disease progression, and responsiveness to specific therapies, as well as help identify novel targets for future intervention.A substantial number of genetic loci, gene polymorphisms, and mutations have already been reported as having variable degrees of association with one or other type of diabetes (type 1, type 2, maturity onset diabetes of the young [MODY]), while others appear to be involved in response to antihyperglycemic agents.We have compiled the following glossary of genetic and genomic terms relating to diabetes, which we hope will prove a useful reference to researchers and clinicians with an interest in this disease.This is by no means an exhaustive list, but includes many of the genetic loci and variants that have been studied in association with diabetes.Gene encoding insulin-like growth factor 2 mRNA binding protein 2 (also known as IMP-2).SNPs in the gene have been associated with type 2 diabetes IFIH1",
+      "\t\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.\t\n\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.",
+      "\t\n\nTwo trials in the field of T2D have assessed weight change in response to genetic testing.In the Genetic Counseling and Lifestyle Change for Diabetes Prevention Study (107), 177 patients with metabolic syndrome were randomized to receive genetic testing for T2D susceptibility based on 36 T2D-associated SNPs plus brief genetic counseling versus no genetic testing.Diabetes risk for genotyped  participants was summarized with a risk score categorizing their genetic risk as low, average, high.All patients were then enrolled in a 12-week lifestyle medication program modeled on the evidencebased DPP (108).The lifestyle intervention was effective: the group overall lost a mean of 8.5 6 10.1 pounds, with 31% losing at least 5% of their body weight.Communicating genetic risk did not change this effectiveness, however.The genotyped and control arms did not differ with respect to weight loss, attendance at the 12 DPP sessions, or motivation or confidence to make health behavior changes (107).In a second randomized trial, 601 patients with obesity or overweight received T2D risk estimates based on family history, BMI, and fasting plasma glucose, followed by either T2D genetic susceptibility results from four T2D-associated SNPs or eye disease counseling as a control (109).All participants received brief lifestyle counseling but were not otherwise enrolled in a weight loss program.Although the group receiving genetic risk information reported lower calorie and fat intake after 3 months, the two groups did not differ in these behaviors or in physical activity, weight loss, insulin resistance, or perceived risk after 6 months.",
+      "\t\n\nConclusions and Future Directions GWAS and GWAS meta-analyses have by far been the most efficient way to identify new T2D genes (Figure 2), but their predictive value for future occurrence of T2D has been very limited compared to classic risk factors such as obesity and fasting glucose levels (Walford et al., 2014).Although it might be good news that our genome does not fully dictate our future, the knowledge of its specificities may help us to improve our health.Early genetic studies showed that the higher risk for T2D conferred by TCF7L2 variant can be reversed by lifestyle intervention (Florez et al., 2006), opening avenues for strategies targeted on genetically selected individuals with pre-diabetes.TCF7L2 has also been shown to be associated with a lower efficiency of oral sulfonylureas in newly diagnosed T2D patients (Pearson et al., 2007), but a more recent Danish study suggested that in contrast to clinical markers, all known T2D-associated variants do not significantly affect the time to prescription of the first drug after disease onset (Hornbak et al., 2014).In other words, frequent SNPs are not helpful to predict patients' futures, though the good use of genetic data may contribute to provide better care to newly diagnosed T2D patients who are currently all treated the same (with metformin).",
+      "\tBackground\n\nMultiple genetic loci have been convincingly associated with the risk of type 2 diabetes mellitus.We tested the hypothesis that knowledge of these loci allows better prediction of risk than knowledge of common phenotypic risk factors alone."
+    ],
+    [
+      "\tA. Genetic Screening\n\nWe have discussed above the genetic component of T1D.The genetic susceptibility to T1D is determined by genes related to immune function with the potential exception of the insulin gene (434).The genetic susceptibility component of T1D allows some targeting of primary preventive care to family members of diagnosed T1D patients, but there is no complete inheritance of the disease.Nevertheless, the risk for developing T1D compared with people with no family history is 10 -15 times greater.Although 70% of individuals with T1D carry defined risk-associated genotypes at the HLA locus, only 3-7% of the carriers of such genetic risk markers develop diabetes (3).",
+      "\tGenes\n\n2][43][44][45][46][47] Twin studies need to be considered carefully, however, as the intrauterine environments of dizygotic-twin (separate placentas), monozygotic-twin (60-70% share one placenta), and singleton pregnancies (one placenta without competition for maternal nutrients) will all be diff erent, and this can be a confounder in the inter pretation of eff ects. 44A large study from Sweden on familial risk of type 2 diabetes showed that the relative risks were highest in individuals with at least two aff ected siblings, irrespective of parental diabetes status. 42This fi nding suggests that a recessive pattern of inheritance from uncommon genetic defects, the sharing of similar intrauterine, postnatal, or both environments by siblings (eg, breastfeeding or bottle feeding or childhood nutrition), or a combination of these factors is important.9][50] A greater number of these loci are associated with impaired -cell function (KCNJ11, TCF7L2, WFS1, HNF1B, SLC30A8, CDKAL1, IGF2BP2, CDKN2A, CDKN2B, NOTCH2, CAMK1D, THADA, KCNQ1, MTNR1B, GCKR, GCK, PROX1, SLC2A2, G6PC2, GLIS3, ADRA2A, and GIPR) than impaired insulin sensitivity (PPARG, IRS1, IGF1, FTO, and KLF14) or obesity (FTO). 38,48,50Of these, TCF7L2 is the strongest susceptibility locus for type 2 diabetes, being associated with -cell dysfunction. 48Most patients with monogenic forms of diabetes also have gene defects that aff ect islet -cell function. 51,52Nevertheless, only around 10% of the heritability of type 2 diabetes can be explained by susceptibility loci identifi ed so far, with each locus having a low eff ect size. 36The remaining heritability might be related to a large number of less common variants (allele frequency <5%) that are diffi cult to fi nd with current approaches of genome-wide association studies, and/or epigenetic phenomena.",
+      "\t\n\nObserved increased risk in African Americans is likely to result from a combination of shared environmental and genetic factors.Although there are few published studies specifically investigating familial aggregation of type 2 diabetes in African-American families, Rotimi et al. (10) found that relatives of African-American probands with type 2 diabetes had a 2.95-fold (95% CI 1.55-5.62)higher prevalence of diabetes when compared with relatives of unaffected individuals.In the GENNID (Genetics of Noninsulin Dependent Diabetes Mellitus) African-American families, the majority of first-degree relatives of African-American individuals with type 2 diabetes had abnormal glucose tolerance (11), with 27% found to have undiagnosed diabetes and 31% impaired fasting glucose and/or impaired glucose tolerance.",
+      "\t\n\nmore frequently than by chance alone among siblings who share the phenotype of type 1 diabetes.Nuclear families, or even just the affected sibling pairs themselves, are genotyped with panels of markers spanning the genome at a modest density.Linkage between a marker and a susceptibility locus for type 1 diabetes is determined by accumulating evidence across families.Since affected sibling pairs are relatively rare in type 1 diabetes, data from linkage studies are collected from a rather unique subgroup of families with type 1 diabetes.In general, linkage studies are the method of choice when the risk factors being sought have large effect sizes but are relatively rare.As risk factors become more common and have smaller effect sizes, association methods emerge as a potentially more powerful approach (Fig. 1).Since the genetic basis of type 1 diabetes is probably a complex mixture of small, moderate, and large genetic effects, multiple strategies are needed and vary according to the population being studied and their exposure to unknown environmental factors.",
+      "\tEvidence from family and twin studies\n\nThe obvious familial aggregation of T2D is clearly consistent with a genetic component to disease susceptibility, although a shared environment may also contribute.The extent of familial aggregation is often summarised in terms of the sibling relative risk (l s , the ratio of disease prevalence in the siblings of aected individuals compared with that in the general population).l s for T2D in European populations is approximately 3.5 (35% versus 10%) 4 , a modest value compared with the equivalent gure of around 15 for type 1 diabetes.The patterns of segregation in families with T2D are (with rare exceptions, such as maturity onset diabetes of the young  MODY  see below) consistent with a complex, multifactorial inheritance. 5orts to estimate the heritability of T2D by a comparison of the concordance rates in mono-and dizygotic twins have varied greatly as a result of dierences in ascertainment scheme, diagnostic criteria and follow-up duration.69 Concordance for diabetes is generally higher in identical twins (supporting a genetic basis for disease), although the extremely high concordance rates in some early studies 6 were undoubtedly inated by ascertainment bias.",
+      "\tThe genetics of type 1 diabetes\n\nThere is a strong genetic risk to T1D.This is exemplified by (Redondo et al., 2001) who demonstrated a strong concordance of genetic inheritance (65%) and T1D susceptibility in monozygotic twin pairs.That is, when one sibling is afflicted, there is a high probability that the other twin will develop T1D by the age of 60 years.Additionally, autoantibody positivity and islet destruction was observed after a prospective long-term follow-up of monozygotic twins of patients with T1D, despite initial disease-discordance among the twins (Redondo et al., 2008).",
+      "\tHeritability\n\nFamily history is an important risk factor for the development of T1D and T2D.In rare cases, there are families in which diabetes is inherited as a monogenic disease.More generally, the sibling of a patient with T1D has a 15-fold higher risk of developing the disease (6%) than does an unrelated individual (0.4%) (53).In T2D, the absolute risk to siblings is 30%-40%, as compared to a population prevalence of 7%, providing a relative risk to siblings of four to sixfold.In T1D and T2D, rates of concordance are much higher for monozygotic twins as compared to dizygotic twins.Specifically, in T1D, the concordance rate for monozygotic twins is estimated to range from 21%-70%, higher than the 0%-13% range reported for dizygotic twins (145).For T2D, Barnett et al. (8) found that 48 of 53 identical twin pairs were concordant for T2D if followed for long enough, and Poulsen et al. (141) described a concordance rate of 43% in Danish dizygotic twins as compared to 63% in monozygotic twins.Interestingly, while the relative risk to a sibling ( S , which tracks with power in a linkage study) is higher in T1D than T2D, the absolute risk and concordance in monozygotic twins are higher in T2D than in T1D.",
+      "\tType 1 diabetes is a genetic disease\n\nFamily studies have indicated that genetic factors are important determinants of type 1 diabetes risk.First, the risk to a sibling of an affected individual is approximately 6%, as compared with an average risk of 0.4% (depending on the population), or a relative increased risk of 15-fold (17).The increased risk to siblings is referred to as l s (18) and is one measure of the degree of familial clustering of the disease.\t\nFamily and twin studies indicate that a substantial fraction of susceptibility to type 1 diabetes is attributable to genetic factors.These and other epidemiologic studies also implicate environmental factors as important triggers.Although the specific environmental factors that contribute to immune-mediated diabetes remain unknown, several of the relevant genetic factors have been identified using two main approaches: genome-wide linkage analysis and candidate gene association studies.This article reviews the epidemiology of type 1 diabetes, the relative merits of linkage and association studies, and the results achieved so far using these two approaches.Prospects for the future of type 1 diabetes genetics research are considered.\t\n\nFamily and twin studies indicate that a substantial fraction of susceptibility to type 1 diabetes is attributable to genetic factors.These and other epidemiologic studies also implicate environmental factors as important triggers.Although the specific environmental factors that contribute to immune-mediated diabetes remain unknown, several of the relevant genetic factors have been identified using two main approaches: genome-wide linkage analysis and candidate gene association studies.This article reviews the epidemiology of type 1 diabetes, the relative merits of linkage and association studies, and the results achieved so far using these two approaches.Prospects for the future of type 1 diabetes genetics research are considered.\tType 1 diabetes has unusual epidemiological features related to gender\n\nType 1 diabetes also displays unusual patterns of inheritance that may yield insights into etiology and provide clues to the best methods for analyzing genetic studies.The risk to the offspring is generally greater from a mother or father who was diagnosed at an early age (again suggesting that early-onset cases are more heavily genetically 'loaded').However, the risk of diabetes is approximately two to four times higher for a child whose father has type 1 diabetes than one whose mother is affected [see (52,53) and references therein].This parental difference is largely due to a low risk for offspring of mothers who were diagnosed at a later age (53).The difference could be explained by at least three different factors.First, the risk alleles could only be active when transmitted by the father (such as is seen in imprinting, where only one of the parental alleles is expressed).Alternatively, a maternal environmental factor during pregnancy could be protective.However, it is difficult to see how this protective effect would be restricted to mothers diagnosed at a later age, especially since the protective effect was unrelated to the mother's duration of diabetes or even diabetic status at delivery (53).Finally, mothers who are diagnosed at a later age could represent more 'environmental' cases of diabetes, and thus be less likely to pass on risk genes to their offspring.",
+      "\t\n\nCopyright  2008 Massachusetts Medical Society.All rights reserved.Panel A shows the incidence of type 2 diabetes in four quartiles (Q) of body-mass index (BMI) among Malm subjects who had a family history of diabetes and those without such a history.An increase in the quartile of the BMI gradually increased the risk of diabetes, as compared with the lowest quartile, with an odds ratio of 1.50 for the second quartile (95% confidence interval [CI], 1.26 to 1.78; P = 6.710 6 ), of 2.36 for the third quartile (95% CI, 2.00 to 2.78; P = 1.510 24 ), and of 4.96 for the fourth quartile (95% CI, 4.25 to 5.79; P = 1.110 90 ).Panel B shows the incidence of type 2 diabetes in relation to insulin secretion (disposition index) among subjects with a family history of diabetes and those without such a history.Subjects with a disposition index below the median of 23,393 (26.1% of highrisk subjects and 9.4% of low-risk subjects) had an increase in the risk of type 2 diabetes by a factor of 3.23 (95% CI, 2.41 to 4.34; P = 5.810 15 ), as compared with those above the median.A family history of diabetes significantly increased the risk of diabetes in subjects with impaired insulin secretion (35.5% vs. 9.9%), with an odds ratio of 4.86 (3.12 to 7.56, P = 2.310 12 ).Panel C shows the incidence of type 2 diabetes in carriers of an increasing number of risk alleles in 11 genes, which individually predicted future risk of type 2 diabetes, in relation to quartiles of BMI.There was a stepwise increase in diabetes risk with an increasing number of risk alleles and increasing quartiles of BMI so that participants carrying more than 12 risk alleles showed a doubling of the risk conferred by BMI alone.In the highest quartile of BMI (31.8% vs. 5.1%), this yielded an odds ratio of 8.0 (95% CI, 5.71 to 11.19; P = 9.110 34 ).Panel D shows the incidence of type 2 diabetes in carriers of an increasing number of risk alleles in the 11 genes, which individually predicted future risk of type 2 diabetes, in relation to low insulin secretion.Carriers of more than 12 risk alleles and a low disposition index (37.9%vs. 10.1%) had an odds ratio of 5.81 (95% CI, 3.18 to 10.61; P = 1.110 8 ).",
+      "\tEvidence for a genetic basis: family and twin studies of Type I diabetes\n\nWhat is the evidence that Type I diabetes has a genetic basis?The simplest evidence comes from the fact that the frequency of the disorder is higher in close relatives of diabetic patients than in the general population (note: the reference population in the discussion which follows are people of European ancestry, who have the highest prevalence of Type I diabetes).For example, the frequency of Type I diabetes in siblings of diabetics is about 6 % by age 30 [1], while the frequency in the general population is about 0.4 % by age 30 [2].Thus, Type I diabetes is about 6/0.4,i. e. 15 times more common in siblings of diabetic patients than in the general population.This ratio between frequency in siblings compared with the general population is referred to as l sib [3].",
+      "\tType 1 Diabetes\n\nThe higher type 1 diabetes prevalence observed in relatives implies a genetic risk, and the degree of genetic identity with the proband correlates with risk (22)(23)(24)(25)(26). Gene variants in one major locus, human leukocyte antigen (HLA) (27), confer 50-60% of the genetic risk by affecting HLA protein binding to antigenic peptides and antigen presentation to T cells (28).Approximately 50 additional genes individually contribute smaller effects (25,29).These contributors include gene variants that modulate immune regulation and tolerance (30)(31)(32)(33), variants that modify viral responses (34,35), and variants that influence responses to environmental signals and endocrine function (36), as well as some that are expressed in pancreatic b-cells (37).Genetic influences on the triggering of islet autoimmunity and disease progression are being defined in relatives (38,39).Together, these gene variants explain ;80% of type 1 diabetes heritability.Epigenetic (40), gene expression, and regulatory RNA profiles (36) may vary over time and reflect disease activity, providing a dynamic readout of risk.\tGenetics\n\nBoth type 1 and type 2 diabetes are polygenic diseases where many common variants, largely with small effect size, contribute to overall disease risk.Disease heritability (h 2 ), defined as sibling-relative risk, is 3 for type 2 diabetes and 15 for type 1 diabetes (17).The lifetime risk of developing type 2 diabetes is ;40% if one parent has type 2 diabetes and higher if the mother has the disease (18).The risk for type 1 diabetes is ;5% if a parent has type 1 diabetes and higher if the father has the disease (19).Maturity-onset diabetes of the young (MODY) is a monogenic disease and has a high h 2 of ;50 (20).Mutations in any 1 of 13 different individual genes have been identified to cause MODY (21), and a genetic diagnosis can be critical for selecting the most appropriate therapy.For example, children with mutations in KCJN11 causing MODY should be treated with sulfonylureas rather than insulin.",
+      "\t\n\nGenetic factors have an important role in the development of diabetes, with some forms of the disease resulting from mutations in a single gene.Others are multifactorial in origin.The monogenic forms of diabetes account for approximately 5% of cases and are caused by mutations in genes encoding insulin 3 , the insulin receptor 4 , the glycolytic enzyme glucokinase 5 , and the transcription factors hepatocyte nuclear factor-1 (HNF-1), HNF-1, HNF-4, insulin promoter factor-1 and NeuroD1/BETA2 (refs  6-10).Mutations in maternally inherited mitochondrial genes can also cause diabetes, often in association with hearing loss 11 .",
+      "\t\n\nStudies [71][72][73][74] in Mexican and Asian populations have identified several mutations associated with type 2 diabetes in young people.The high prevalence of type 2 diabetes in the parents of young people diagnosed with type 2 diabetes could reflect a stronger genetic predisposition, even when monogenic diabetes is excluded.This hypothesis suggests that efforts to define genes that cause type 2 diabetes by linkage might be more powerful if focused on young adults with diabetes, raising the question of whether type 2 diabetes in older populations has a relatively smaller genetic contribution and a stronger environmental contribution. 66",
+      "\tFamily studies\n\nThe 29 index patients had 130 first-degree relatives (58 parents, 63 siblings, and nine children).Ten families were negative for fasting hyperglycaemia except for one sibling with juvenile-onset diabetes mellitus only.However, a family history of maturity-onset diabetes was present in seven families in members other than first-degree relatives.No relative had a history of psychiatric illness on direct questioning.There was no maternal history of diabetes or deafness.The parents of three index patients were consanguineous: one family was English, one Pakistani, and one of mixed Arabic/African descent.All the other index patients were caucasians.",
+      "\t\n\nWe found that the presence or absence of parental diabetes and the genotype score were independently associated with the risk of diabetes.This suggests that family history as a risk factor for diabetes conveys more than heritable genetic information; it probably includes nongenetic familial behaviors and norms.The lower relative risks for diabetes associated with observed parental diabetes as compared with those associated with self-reported family history (approximately 1.8 vs. approximately 2.2) support the contention that family history contains more risk information than is implied by inheritance of the diabetes phenotype alone.One of the limitations of our study is that the 18 SNPs we included are probably insufficient to account for the familial risk of diabetes.They account for a minority of diabetes heritability, and the SNP array platforms from which they were chosen capture only approximately 80% of common variants in Europeans.In addition, we have not considered structural variants that might confer a risk of diabetes.It is possible that the addition of rare risk alleles with large effects, or a much larger number of common risk alleles with small individual effects, could improve discrimination. 36Indeed, as many as 500 loci may underlie the genetic risk of type 2 diabetes. 16Also, we did not study interactions among genes or between genes and the environment that might alter the genetic risk in exposed persons.As more diabetes risk variants become known, their incorporation into the genotype score may explain more of the genetic risk implied by parental diabetes.",
+      "\t\n\nGenetics is one example of the 'other risk factors' involved in the pathogenesis of DR.Twin and epidemiological studies have strongly suggested a genetic component in the etiology of DR (6 -10), with heritability scores ranging from 27 to 52% in both type 1 and type 2 diabetes (7 -10).There is an increased risk of severe DR among family members of DR subjects (8,9) and in siblings of affected subjects (8,9).Furthermore, several studies have also shown a discrepant rate of the prevalence of DR among different racial ethnic groups in the US population, with a significantly higher prevalence observed among Hispanic, African-American and Chinese-American when compared with Caucasian populations (11).While these differences may partially be attributed to lifestyle factors, evidence from familial aggregation, ethnic differences and heritability clearly supports a genetic contribution in the etiology of DR."
+    ],
+    [
+      "\t\n\nIn addition to lifestyle factors, it is known that type 2 diabetes has a strong genetic component.Recent genomewide association studies have identified >60 genetic variants that are associated with type 2 diabetes but individual effects of genetic variants are considered to be small [139,140].",
+      "\t\n\nAn individual's risk of developing T2D is influenced by a combination of lifestyle, environmental, and genetic factors.Uncovering the genetic contributors to diabetes holds promise for clinical impact by revealing new therapeutic targets aimed at the molecular and cellular mechanisms that lead to disease.Genome-wide association studies performed during the past decade have uncovered more than 100 regions associated with T2D (5)(6)(7)(8)(9)(10)(11)(12).Although these studies have provided a better understanding of T2D genetics, the majority of identified variants fall outside protein-coding regions, leaving the molecular mechanism by which these variants confer altered disease risk obscure.Consequently, T2D genome-wide association studies have identified few loci with clear therapeutic potential.",
+      "\t\n\nThe notion that lifestyle modifi cation can eliminate the increased risk for development of T2DM in subjects with genetic susceptibility is also supported by fi ndings of Barwell et al. (2008) who reported that women with family history of T2DM experience greater improvement in insulin sensitivity following an exercise intervention than women with no family history.Although lifestyle modifi cation has been found effi cient in obesity and T2DM prevention even among genetically susceptible individuals, considerable heterogeneity in intervention responses has been observed.Genetic infl uences have been suggested to contribute to this heterogeneity.Risk allele carriers in several obesity-and T2DM-associated genes, for instance, have been found to experience suppressed weight reduction and improvement in various metabolic parameters in response to exercise or combined lifestyle interventions ( Franks et   preference for foods of high energy density ( Haupt et al., 2009b ;Speakman et al., 2008 ;Timpson et al., 2008 ).In summary, healthy lifestyle or lifestyle modifi cation may keep genetic predisposition to obesity and T2DM under control.Genetics has, however, been suggested to infl uence the outcome of a lifestyle intervention or even to determine individual PA level, food intake, and motivation for lifestyle change.\tLifestyle and Genetics in Obesity and Type 2 Diabetes \n\nRecent advancement in human genetics has led to the identifi cation of a relatively big number of obesity-and T2DM-associated loci.Their contribution to disease risk has, however, been shown to be small and their predictive value low, suggesting that lifestyle plays crucial role in obesity and T2DM development ( Vimaleswaran and Loos, 2010 ).Indeed, studies investigating the gene-lifestyle interactions in obesity and T2DM have suggested that the biological eff ect of genetic predisposition may be partially or totally abolished by healthy lifestyle or lifestyle modifi cation and vice versa.Epidemiological studies have reported that the negative eff ect of several obesity-and T2DM-associated genes may be attenuated in individuals with higher PA levels or healthy lifestyle, whereas low PA and western dietary pattern have been found to accentuate it. ( 1 ).\t\n\nGene-lifestyle interaction studies supporting the protective role of diet, exercise or combined lifestyle interventions in individuals genetically susceptible to obesity and type 2 diabetes.This document was downloaded for personal use only.Unauthorized distribution is strictly prohibited.\tConclusions \n\nObesity and T2DM are clearly the results of a complex interplay between inherited factors and the environment.Recent advancements made through the GWA approach have substantially contributed to our understanding of obesity and T2DM genetics, however, most of the loci identifi ed to date have modest eff ect on disease risk.Hence, lifestyle factors, namely physical inactivity and food overconsumption seem to have major importance for the development of both diseases.Healthy lifestyle and lifestyle modifi cation, on the other hand, appear to be the most effi cient tools for obesity and T2DM prevention.In addition, gene-lifestyle interaction studies suggest that lifestyle determines whether an individual is likely to develop the disease and that genetic susceptibility may be partially or totally kept under control by lifestyle modifi cation.Since genetics seems to infl uence individual response to a lifestyle intervention and even the motivation for lifestyle change, personalized interventions according to genotype may be considered in the future.By then lifestyle modifi cation targeting dietary change and increased physical activity may be recommended for successful obesity and T2DM prevention irrespectively of genetic susceptibility.\tLifestyle and Genetics in Obesity and type 2 Diabetes\n\nvaluable insights into the interactions between genetic predisposition and lifestyle factors, namely physical activity (PA) and food consumption.This current progress may have essential contribution to our understanding of the pathophysiology of both diseases, as well as, to the development and implementation of future treatment and prevention strategies.It is, therefore, the aim of the present review to summarize the available literature on the eff ect of the interactions between lifestyle and genetics on obesity and T2DM.",
+      "\t\n\nLifestyle behaviors and genetic loci have clear and distinguishable effects on T2D risk; however, the pattern of disease occurrence within and between populations that differ in their genetic and environmental underpinnings suggests T2D is caused in part by the interaction between adverse lifestyle behaviors and the genetic profile of an individual.For many, this seems a reasonable assumption, but there is little robust empirical evidence supporting the presence of such interactions.\t\n\nNotwithstanding the important role lifestyle factors play in the etiology of T2D, persons living similar lifestyles can vary considerably in their susceptibility to the disease, with the variance being least among biologically related individuals, suggesting a genetic basis to the disease.In the past 4 years, major advances have been made in unraveling the genetic architecture of T2D.This search has cumulated in the discovery and confirmation of more than 30 common predisposing loci [10], but the variance in disease risk explained by these variants is much lower than predicted from heritability studies [11].Thus, the genetic associations discovered to date are likely to represent no more than the tip of the iceberg with respect to the genetic landscape of T2D.\t\n\nThe availability of detailed information on gene  environment interactions may enhance our understanding of the molecular basis of T2D, elucidate the mechanisms through which lifestyle exposures influence diabetes risk, and possibly help to refine strategies for diabetes prevention or treatment.The ultimate hope is genetics might one day be used in primary care to inform the targeting of interventions that comprise exercise regimes and other lifestyle therapies for individuals most likely to respond well to them.",
+      "\t\n\nAt 1-week follow-up, 44% of participants indicated that the primary risk factor for them was genes/family history, followed by diet (26%) and lifestyle (19%).There was not a significant difference in the proportion of participants at increased genomic risk who indicated genes/ family history as the primary cause (p = 0.5144).In addition, no statistically significant difference in IPQ-R subscales and risk perception between those at increased and nonincreased genomic risk for T2DM or between those with and without a family history for other factors related to illness perception was observed.",
+      "\tDiscussion\n\nOur study provides insight into the relative importance of clinical risk factors and those that are related to a panel of DNA variants associated with type 2 diabetes.Obesity was a strong risk factor for future diabetes, a risk that almost doubled in subjects with a family history of diabetes.However, the addition of data from genotyping of the known DNA variants to clinical risk factors (including a family history of diabetes) had a minimal, albeit statistically significant, effect on the prediction of future type 2 diabetes.Notably, the ability of genetic risk factors to predict future type 2 diabetes improved with an increasing duration of follow-up, suggesting that assessment of genetic risk factors is clinically more meaningful the earlier in life they are measured.",
+      "\t\n\nAlthough the expected range of effects that are realistic for gene-lifestyle interactions in type 2 diabetes remains unclear, a doubling of the genetic risk estimate in the group exposed to adverse lifestyle factors compared with those who are unexposed (b GE = 2) is at the upper end of the interaction effect estimate ranges reported for common variants and common exposures (10).It is reasonable to conclude, therefore, that most of the interaction studies published to date report \"lucky\" true-positive results or false-positive results that may be underpinned by analytical and reporting biases.The replication of few examples of genelifestyle interactions in type 2 diabetes suggests that the literature is composed largely of the latter.Despite this, recent developments in the ways genetic association studies are performed, such as adoption of hypothesis-free approaches, the availability of comprehensive genotype arrays in large sample collections, global collaborations, and more rigorous analysis and reporting of data, have led to the emergence of many reproducible genetic association signals for type 2 diabetes and related glycemic traits, which has spurred a number of large-scale studies of gene-lifestyle interactions.",
+      "\t\n\nGenetic and epigenetic factors determine cell fate and function.Recent breakthroughs in genotyping technology have led to the identification of more than 20 loci associated with the risk of type 2 diabetes (Sambuy 2007;Zhao et al. 2009).However, all together these loci explain <5% of the genetic risk for diabetes.Epigenetic events have been implicated as contributing factors for metabolic diseases (Barker 1988;Kaput et al. 2007).Unhealthy diet and a sedentary lifestyle likely lead to epigenetic changes that can, in turn, contribute to the onset of diabetes (Kaput et al. 2007).At present, the underlying molecular mechanisms for disease progression remain to be elucidated.",
+      "\t\n\nThird, there is the issue as to whether early diagnosis can be shown to result in beneficial outcomes, for example by motivating improvements in lifestyle or treatments that reduce the risk of disease.In the case of TD, the potential for lifestyle modification and/or pharmaceutical intervention (e.g., with metformin) to reduce diabetes progression is clear (, ), and these benefits seem to accrue irrespective of genetic risk.In the Diabetes Prevention Program, for example, lifestyle intervention was effective at reducing diabetes incidence compared with placebo even among those with the highest quartile of TD rsPS ().However, there is limited evidence to date that the communication of genetic risk is sufficient to motivate most individuals to undertake the kind of long-term behavioral modification required for sustained benefit (-).There is also some (at least theoretical) risk of harm if the communication of risk information is mishandled.This could arise through failure to use ethnically appropriate scores, or to incorporate other relevant health information.For example, an overweight person with a low TD polygenic score may be at far greater risk of disease than the polygenic score alone would suggest.Some individuals may be liable to interpret high genetic risk in a deterministic and fatalistic way, failing to appreciate that remediation of risk through lifestyle modification is no less likely to be effective in their case.",
+      "\t\n\nTwo trials in the field of T2D have assessed weight change in response to genetic testing.In the Genetic Counseling and Lifestyle Change for Diabetes Prevention Study (107), 177 patients with metabolic syndrome were randomized to receive genetic testing for T2D susceptibility based on 36 T2D-associated SNPs plus brief genetic counseling versus no genetic testing.Diabetes risk for genotyped  participants was summarized with a risk score categorizing their genetic risk as low, average, high.All patients were then enrolled in a 12-week lifestyle medication program modeled on the evidencebased DPP (108).The lifestyle intervention was effective: the group overall lost a mean of 8.5 6 10.1 pounds, with 31% losing at least 5% of their body weight.Communicating genetic risk did not change this effectiveness, however.The genotyped and control arms did not differ with respect to weight loss, attendance at the 12 DPP sessions, or motivation or confidence to make health behavior changes (107).In a second randomized trial, 601 patients with obesity or overweight received T2D risk estimates based on family history, BMI, and fasting plasma glucose, followed by either T2D genetic susceptibility results from four T2D-associated SNPs or eye disease counseling as a control (109).All participants received brief lifestyle counseling but were not otherwise enrolled in a weight loss program.Although the group receiving genetic risk information reported lower calorie and fat intake after 3 months, the two groups did not differ in these behaviors or in physical activity, weight loss, insulin resistance, or perceived risk after 6 months.",
+      "\t\n\nThe missing heritability of T2DM could be accounted for by the interactions between susceptibility loci and various environmental determinants, whereby the impact of a given genetic variant is modified by the environmental milieu (and vice versa).Evidence that lifestyle factors modify the genetic effects on T2DM risk has been generated from both observational studies and clinical trials 82 .However, genetic background might also affect the individual's response to lifestyle interventions 83 .In addition, replication data are sparse, and comprehensive, large-scale studies have failed to provide a compelling basis for the significant interaction effect 84,85 .This failure might have occurred because the interaction effects are of small magnitude or might be due to the limited statistical power and multiple sources of bias and confounding factors in the current research methods 86 .\tGenomics and gene-environment interactions\n\nEven though many cases of T2DM could be prevented by maintaining a healthy body weight and adhering to a healthy lifestyle, some individuals with prediabetes mellitus are more susceptible to T2DM than others, which suggests that individual differences in response to lifestyle interventions exist 76 .Substantial evidence from twin and family studies has suggested a genetic basis of T2DM 77 .Over the past decade, successive waves of T2DM genome-wide association studies have identified >100 robust association signals, demonstrating the complex polygenic nature of T2DM 5 .Most of these loci affect T2DM risk through primary effects on insulin secretion, and a minority act through reducing insulin action 78 .Individually, the common variants (minor allele frequency >5%) identified in these studies have only a modest effect on T2DM risk and collectively explain only a small portion (~20%) of observed T2DM heritability 5 .It has been hypothesized that lower-frequency variants could explain much of the remaining heritability 79 .However, results of a large-scale sequencing study from the GoT2D and T2D-GENES consortia, published in 2016, do not support such a hypothesis 5 .Genetic variants might help reveal possible aetiological mechanisms underlying T2DM development; however, the variants identified thus far have not enabled clinical prediction beyond that achieved with common clinical measurements, including age, BMI, fasting levels of glucose and dyslipidaemia.A study published in 2014 linked susceptibility variants to quantitative glycaemic traits and grouped these variants on the basis of their potential intermediate mechanisms in T2DM pathophysiology: four variants fitted a clear insulin resistance pattern; two reduced insulin secretion with fasting hyperglycaemia; nine reduced insulin secretion with normal fasting glycaemia; and one altered insulin processing 80 .Considering such evidence, the genetic architecture of T2DM is highly polygenic, and thus, substantially larger association studies are needed to identify most T2DM loci, which typically have small to modest effect sizes 81 .",
+      "\t\n\nAlthough precision diabetes medicine is much more than genetics, the majority of relevant research has focused on evaluating the role of genetic variants in precision prevention.Large epidemiological studies (75) and intervention trials (76,77) strongly suggest that standard approaches for lifestyle modification are equally efficacious in preventing diabetes regardless of the underlying genetic risk.This contrasts with the extensive epidemiological evidence suggesting that the relationship of lifestyle with obesity is dependent on genetic risk (78-81); however, with few exceptions (e.g., [74]), analyses in large randomized controlled trials have failed to show that these same genetic variants modify weight loss in response to lifestyle intervention (82).It is also important to recognize that knowledge of increased genetic risk for diabetes may not motivate improvements in lifestyle behaviors.Indeed, knowledge of increased genetic risk for diabetes may decrease motivation to modify behavior in genetic fatalists (83).",
+      "\t\n\nOther aspects that have been overlooked in large GWAS on T2DM relate to environmental effects such as diet, physical activity, and stresses, which may affect gene expression.For example, fish oil may stimulate PPARG in much the same fashion as the thiazolidinedione class of drugs; however, studies on the interaction of the PPARG variant with dietary components have not been performed.The spectacular rise in the incidence of diabetes among Pima Indians and other populations as they adopt Western diets and lifestyles dramatically demonstrates the key role of the environment [12].Consequently, it could be expected that the effect of a common gene variant among populations that have very different diets and exercise habits might be totally different, thus explaining some instances of lack of replication. [4].Another variable that influences the statistical and real association of an SNP with a disease or response to a diet is epigenetic interaction.Epigenesis is the study of heritable changes in gene function that occur without a change in the DNA sequence, such as DNA methylation and chromatin remodeling.Both mechanisms can affect gene expression by altering the accessibility of DNA to regulatory proteins or complexes such as transcription factors, and they can be influenced by certain nutrients and by overall caloric intake.Thus, it can be expected that long-term exposure to certain diets could produce permanent epigenetic changes in the genome [7]."
+    ],
+    [
+      "\tConcluding remarks\n\nFor the past two decades, genetics has been widely advocated as a tool for unravelling the pathogenesis of common forms of diabetes, but the complexity of the problem defied easy solutions.Recent advances have made it possible to find many of the genes that predispose to both major types of diabetes.Much work is still needed to translate knowledge of these genes into benefits for patients.The greatest benefit is likely to come from new\tIntroduction\n\nWe are all witnesses to a period of astonishing progress in our understanding of the genetic basis of diabetes, and the advances of recent months are arguably the most important made since the role of the HLA region was recognised in type 1 diabetes.The number of genetic regions causally implicated is now 11 each for type 1 and type 2 diabetes [1][2][3][4][5][6][7][8][9], and is set to rise further.The bewildering pace of new discovery stands in stark contrast to the slow progress that characterised the previous two decades, with a total combined output of three confirmed genes for type 2 diabetes and six for type 1 (Fig. 1).At last, it seems, our understanding of the genetic basis of complex, multifactorial forms of diabetes is catching up with that of rarer, single-gene disorders.",
+      "\t\n\nThis technology recently facilitated rapid progress in type 2 diabetes genetic research.This is all the more remarkable because type 2 diabetes does not have a strong genetic component compared with some other common traits, and was previously described as 'a geneticist's nightmare' 1,2 .Nevertheless, early results have been excellent, yielding six new replicating gene regions.",
+      "\tFuture directions\n\nDelays in identifying genetic variants that are robustly associated with differences in individual predisposition to the complications of diabetes, have constrained progress towards a mechanistic understanding of these conditions.Some approaches to overcome these limitations are outlined in Figure 4.",
+      "\t\n\nRecent advances in GWAS have substantially improved our understanding of the pathophysiology of diabetes, but the currently identified genetic susceptibility loci are insufficient to explain differences in diabetes risk across different ethnic groups or the rapid rise in diabetes prevalence over the past several decades.Clinical utility of these loci in predicting future risk of diabetes is also limited.",
+      "\t\n\nGenetic factors are known to play a role in T2D and an understanding of the genetic basis of T2D could lead to the development of new treatments (Frayling, 2007a,b;Frayling & Mccarthy, 2007;Frayling, 2008).With the increased prevalence of diabetes worldwide, the need for intensive research is of high priority.Sequencing of the human genome and development of a set of powerful tools has made it possible to find the genetic contributions to common complex diseases (Donnelly, 2011).Genome-wide association studies (GWAS) have been used to search for genetic risk factors for complex disease (Hindorff, Junkins et al., 2009;Hindorff, Sethupathy et al., 2009).Used in combination with the scaffold data of the human genome courtesy of the HUGO Project (2003) and the International HapMap Project (Thorisson et al., 2005), it is now possible to analyse the whole genome to identify genetic variants that contribute to common disease in a fast and efficient manner.",
+      "\t\n\nAll of these genetic research efforts of the last decade have led to the identification of at least 27 (confirmed and potential) type 2 diabetes susceptibility genes, and their time-course of discovery or initial publication is depicted in Fig. 1.",
+      "\t\n\nUnfortunately, these questions are not yet answered.The early 1990s was the beginning of the era of molecular biol- ogy, and it was generally assumed that within a few years this powerful new technology would identify the genetic defects in type 2 diabetes.Indeed, the genetic basis for many monogenic forms of diabetes has been discovered such as mitochondrial genome defects and the association with diabetes and deafness, Wolfram's syndrome, several rare syndromes of extreme insulin resistance and obesity, and many of the MODY syndromes (maturity onset diabetes of youth).Still, these account for only a small proportion of diabetes.",
+      "\tNew d iscoveries in the g enetic e tiology of T 2 DM\n\nImportant advances in T2DM genetics have been made with the completion of GWA studies based on HapMap -selected common SNPs.This has become reality with the outstanding breakthroughs made in the knowledge and assessment of human genome variations, their mapping and their links with the genetic background of common diseases [167] , and in the development and accessibility to very high throughput genotyping techniques based on microarray technology and to biostatistical tools for large cohort data analyses.",
+      "\t\n\nOver the past two years, there has been a spectacular change in the capacity to identify common genetic variants that contribute to predisposition to complex multifactorial phenotypes such as type 2 diabetes (T2D).The principal advance has been the ability to undertake surveys of genome-wide association in large study samples.Through these and related efforts, $20 common variants are now robustly implicated in T2D susceptibility.Current developments, for example in high-throughput resequencing, should help to provide a more comprehensive view of T2D susceptibility in the near future.Although additional investigation is needed to define the causal variants within these novel T2Dsusceptibility regions, to understand disease mechanisms and to effect clinical translation, these findings are already highlighting the predominant contribution of defects in pancreatic b-cell function to the development of T2D.",
+      "\t\n\nTo date, studies of diabetes have played a major role in shaping thinking about the genetic analysis of complex diseases.Based on trends in genomic information and technology, combined with the growing public health importance of diabetes, diabetes will likely continue to be an important arena in which methods will be pioneered and lessons learned.It is with great enthusiasm that we look forward to this effort, and with avid curiosity we await to see whether the lessons of today will be supported by the data of tomorrow.",
+      "\t\n\nIn recent years tremendous changes had occurred in the field of molecular genetics and personalized medicine especially on exploring novel genetic factors associated with complex diseases like T2D with the advancement of new and improved genetic techniques including the next generation sequencing (NGS).In this review, we summarize recent developments from studies on the genetic factors associated with the development of T2D in the Arab world published between 2015 and 2018, which were based on the latest available genetic technologies.Few such studies have been conducted in this region of the world.Therefore, our study will provide valuable contributions to advanced genetic research and a personalized approach to diabetes management.",
+      "\t\nIt has proven to be challenging to isolate the genes underlying the genetic components conferring susceptibility to type 1 and type 2 diabetes.Unlike previous approaches, 'genome-wide association studies' have extensively delivered on the promise of uncovering genetic determinants of complex diseases, with a number of novel disease-associated variants being largely replicated by independent groups.This review provides an overview of these recent breakthroughs in the context of type 1 and type 2 diabetes, and outlines strategies on how these findings will be applied to impact clinical care for these two highly prevalent disorders.\t\n\nIt has proven to be challenging to isolate the genes underlying the genetic components conferring susceptibility to type 1 and type 2 diabetes.Unlike previous approaches, 'genome-wide association studies' have extensively delivered on the promise of uncovering genetic determinants of complex diseases, with a number of novel disease-associated variants being largely replicated by independent groups.This review provides an overview of these recent breakthroughs in the context of type 1 and type 2 diabetes, and outlines strategies on how these findings will be applied to impact clinical care for these two highly prevalent disorders.",
+      "\t\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.",
+      "\t\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.\t\n\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.",
+      "\t\n\nMuch has been made over the past decade of the potential for genetics to advance our understanding of the pathogenesis of type 2 diabetes and to 'revolutionise' management of this condition [1].Others have argued that these claims are premature [2]; indeed, some have questioned the contribution of genetic predisposition to the pathogenesis of common forms of type 2 diabetes [3].",
+      "\t\n\n During the last decade, there have been major advances in our understanding of the genetic basis of the most common subtypes of type 1 (T1D) and type 2 diabetes (T2D), with .500robust associations identified  Although individual variants typically have only a modest effect on risk, when combined into a polygenic score, they offer increasing power to capture information on individual patterns of disease predisposition with the potential to influence clinical management",
+      "\tTHE GENETICS OF TYPE 1 DIABETES\n\nThe study of the genome to map disease-susceptibility regions for T1D and other multifactorial diseases has been facilitated by recent advances in next generation DNA sequencing methods."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "B36C57B013A41A55687021F0B0381728"
+    },
+    {
+      "task_id": "E2DB78EE98507BDA17501CDAC1C32074"
+    },
+    {
+      "task_id": "2D8A4643C25BA9AEECDF9422D43C0EDE"
+    },
+    {
+      "task_id": "3F639DE5D9A1A9BE45168C06A00C571F"
+    },
+    {
+      "task_id": "A34A4714BF78D63988FD46A4FA033340"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_4.json
new file mode 100644
index 0000000..a579777
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_diabetes_4.json
@@ -0,0 +1,114 @@
+{
+  "question": [
+    "How do genes influence how our bodies respond to sugar and insulin?",
+    "Are there specific genetic markers that can indicate a higher risk for Type 1 versus Type 2 diabetes?",
+    "How can new gene therapies potentially cure or treat diabetes?",
+    "What is the difference between monogenic and polygenic diabetes?",
+    "How does studying the DNA of people with diabetes help scientists find better treatments or cures?"
+  ],
+  "answer": [
+    "Genes play a crucial role in how our bodies respond to sugar and insulin. Certain gene variants can impair insulin sensitivity and affect glucose, fatty acid, and energy metabolism at both cellular and whole-body levels. For instance, abnormalities in the genes encoding for proteins involved in the insulin-signaling network can cause insulin resistance and related traits. This can lead to metabolic diseases like type 2 diabetes, obesity, and cardiovascular diseases. Additionally, genetic mutations can severely alter insulin sensitivity. Some genes also play a role in insulin secretion by pancreatic -cells, which is crucial for maintaining normal glucose levels.",
+    "Yes, there are specific genetic markers that can indicate a higher risk for Type 1 versus Type 2 diabetes. For Type 1 diabetes, the greatest genetic risk is conferred by specific alleles, genotypes, and haplotypes of the HLA class II (and class I) genes. There are also about 50 non-HLA region loci that affect the Type 1 diabetes risk. For Type 2 diabetes, the risk is higher if one parent has the disease, particularly if the mother has it. The disease is polygenic, with many common variants contributing to overall disease risk.",
+    "New gene therapies can potentially treat diabetes by targeting specific genetic variations that affect the response to certain drugs. For example, genetic variation in the organic cation transporter 1 (OCT1) has been found to affect the response to the diabetes drug metformin. Understanding these gene-drug interactions can lead to more personalized and effective treatment strategies. Additionally, therapies that slow the loss of -cell function, which is a characteristic of type 2 diabetes, could provide more durable glucose control. Incretin-based therapies, which improve -cell health, could potentially slow disease progression. Furthermore, the use of nanotechnology in gene therapies could introduce novel strategies for glucose measurement and insulin delivery.",
+    "Monogenic diabetes is a form of the disease that results from mutations in a single gene. It is characterized by high phenotypic penetrance, meaning the presence of the mutation almost certainly leads to the development of the disease. On the other hand, polygenic diabetes is a form of the disease that results from the combined effect of mutations in multiple genes. Each of these mutations contributes a small amount of risk, and the disease typically also requires a permissive environment to develop.",
+    "Studying the DNA of people with diabetes helps scientists identify key biological processes and genes involved in the disease's pathogenesis. This can lead to the discovery of novel drug targets for the disease. Additionally, understanding genetic variants can influence an individual's response to therapy, paving the way for personalized medicine. Furthermore, advancements in genomics and genetic testing can help identify individuals at risk of developing diabetes, enabling early intervention and prevention strategies."
+  ],
+  "contexts": [
+    [
+      "\t\n\nElucidating the potential mechanisms involved in the detrimental effect of excess body weight on insulin action is an important priority in counteracting obesityassociated diseases.The present study aimed to disentangle the epigenetic basis of insulin resistance by performing a genome-wide epigenetic analysis in visceral adipose tissue (VAT) from morbidly obese patients depending on the insulin sensitivity evaluated by the clamp technique.The global human methylome screening performed in VAT from 7 insulin-resistant (IR) and 5 insulin-sensitive (IS) morbidly obese patients (discovery cohort) analyzed using the Infinium HumanMethyla-tion450 BeadChip array identified 982 CpG sites able to perfectly separate the IR and IS samples.The identified sites represented 538 unique genes, 10% of which were diabetes-associated genes.The current work identified novel IR-related genes epigenetically regulated in VAT, such as COL9A1, COL11A2, CD44, MUC4, ADAM2, IGF2BP1, GATA4, TET1, ZNF714, ADCY9, TBX5, and HDACM.The gene with the largest methylation fold-change and mapped by 5 differentially methylated CpG sites located in island/shore and promoter region was ZNF714.This gene presented lower methylation levels in IR than in IS patients in association with increased transcription levels, as further reflected in a validation cohort (n 5 24; 11 IR and 13 IS).This study reveals, for the first time, a potential epigenetic regulation involved in the dysregulation of VAT that could predispose patients to insulin resistance and future type 2 dia-1 Both authors equally contributed to this work.\t\nElucidating the potential mechanisms involved in the detrimental effect of excess body weight on insulin action is an important priority in counteracting obesityassociated diseases.The present study aimed to disentangle the epigenetic basis of insulin resistance by performing a genome-wide epigenetic analysis in visceral adipose tissue (VAT) from morbidly obese patients depending on the insulin sensitivity evaluated by the clamp technique.The global human methylome screening performed in VAT from 7 insulin-resistant (IR) and 5 insulin-sensitive (IS) morbidly obese patients (discovery cohort) analyzed using the Infinium HumanMethyla-tion450 BeadChip array identified 982 CpG sites able to perfectly separate the IR and IS samples.The identified sites represented 538 unique genes, 10% of which were diabetes-associated genes.The current work identified novel IR-related genes epigenetically regulated in VAT, such as COL9A1, COL11A2, CD44, MUC4, ADAM2, IGF2BP1, GATA4, TET1, ZNF714, ADCY9, TBX5, and HDACM.The gene with the largest methylation fold-change and mapped by 5 differentially methylated CpG sites located in island/shore and promoter region was ZNF714.This gene presented lower methylation levels in IR than in IS patients in association with increased transcription levels, as further reflected in a validation cohort (n 5 24; 11 IR and 13 IS).This study reveals, for the first time, a potential epigenetic regulation involved in the dysregulation of VAT that could predispose patients to insulin resistance and future type 2 dia-1 Both authors equally contributed to this work.",
+      "\tElucidate the pathogenesis linking obesity and type 2 diabetes\n\nA better understanding of mechanisms linking obesity, insulin resistance, and type 2 diabetes may ultimately facilitate more individualized treatment.One future research priority is to clarifty how identified gene variants affect glucose, fatty acid, and energy metabolism at both cellular and whole-body levels.Rather than searching for a single factor or theory explaining the predisposition to -cell decompensation in obese individuals, a multifactorial, synergistic explanation seems more compatible with current knowledge.Multiple mechanisms may link -cell dysfunction to systemic insulin resistance, including differing cellular responses to nutrient excess and impaired brain neurocircuits governing energy homeostasis.One way to approach this complex pathophysiology is to examine glucose-tolerant obese patients and study the association with and progression to -cell decompensation.",
+      "\t\n\nWe began the investigation by focusing on insulin-signaling genes, a natural and well-established candidate for finding a signature set of genes associated with insulin resistance or diabetes [9].In particular, by examining microarray data, we attempted to detect a statistically significant, transcriptional alteration in a set of insulin-signaling genes in diabetic tissue compared to normal.Surprisingly, using existing analytical methods, we were unable to detect such alterations in microarray data produced in several human studies.Using sophisticated and remarkably sensitive techniques, previous studies identified the oxidative phosphorylation pathway as transcriptionally down-regulated in diabetic muscle tissue compared to normal [10,11].However, insulin-signaling gene sets were not detected to be transcriptionally altered, using state of the art analyses, more than expected by chance.\tAuthor Summary\n\nType 2 diabetes mellitus currently affects millions of people.It is clinically characterized by insulin resistance in addition to an impaired glucose response and associated with numerous complications including heart disease, stroke, neuropathy, and kidney failure, among others.Accurate identification of the underlying molecular mechanisms of the disease or its complications is an important research problem that could lead to novel diagnostics and therapy.The main challenge stems from the fact that insulin resistance is a complex disorder and affects a multitude of biological processes, metabolic networks, and signaling pathways.In this report, the authors develop a network-based methodology that appears to be more sensitive than previous approaches in detecting deregulated molecular processes in a disease state.The methodology revealed that both insulin signaling and nuclear receptor networks are consistently and differentially expressed in many models of insulin resistance.The positive results suggest such network-based diagnostic technologies hold promise as potentially useful clinical and research tools in the future.affected in the disease state. (3) Evaluate the hypothesis that genes in a given gene set are observed in a higher proportion (i.e., enriched) than expected by chance in the HSN and repeat for each gene set in the assembly.Repeat (2) and (3) for every insulin resistant or diabetic condition compared to normal in the dataset. (4) Order the gene sets of interest based on the number of different HSNs where they appear enriched. (5) For each gene set, assign a p-value to the number of conditions where it is enriched.The gene sets with a significant p-value are taken as transcriptionally affected across a broad set of diabetes-related models.Consistent with the stated goal of GNEA, gene sets enriched in a few conditions, while potentially interesting in their own right, will not generally be assigned a significant p-value (Figure 1).",
+      "\tIn addition, we have\ndetermined the effects of these modifications on the pattern of gene expression\nin each tissue, and how insulin signaling might interact with nuclear receptor\nsignaling in insulin resistance. Tissues of particular importance in development\nof type 2 diabetes and the metabolic syndrome include the liver, brain and fat. In liver, for example, insulin action through IRS-1 and Akt is involved in control\nof glucose production, while insulin action through IRS-2 and atypical PKCs is\nmore involved in hepatic lipogenesis.",
+      "\tExercise training and the Ala allele must act either independently or in synergy\nto modify glucose homeostasis through increasing glucose uptake or by decreasing\nhepatic glucose output. At the whole body level, exercise training has been shown\nto increase insulin sensitivity (Borghouts & Keizer 2000, Short et al 2003, Duncan\net al 2003) and has also been shown to decrease basal hepatic glucose production\nin patients with type 2 diabetes (Segal et al 1991).",
+      "\tIV. Gene Variants Affecting Insulin Sensitivity\n\nInsulin resistance provokes a critical challenge for the pancreatic -cell that has to be compensated for by increments in insulin secretion to maintain normoglycemia.Thus, genetically determined -cell defects may only become apparent in the presence of insulin resistance (9,247).Insulin resistance is therefore considered an early and crucial step in the pathogenesis of type 2 diabetes.Undoubtedly, insulin resistance is strongly associated with obesity.Although the cause-effect relationship is far from being clear, insulin resistance is often suggested to result from obesity and to be predominantly caused by environmental factors, such as high-caloric diet and/or physical inactivity (248,249).However, the genetic investigations of the last 10 yr revealed that certain gene variants impair insulin sensitivity without influencing the overall fat mass.Recent advances in the field, mainly based on candidate gene approaches, also strengthen the role of genetics in the establishment of insulin resistance.",
+      "\t\n\nKey components of the insulin signaling pathways have also been tested.They were at fi rst thought to be important players in the context of the insulin resistance of T2DM.Several of these genes are also expressed in pancreatic  -cells, and several studies from knockout animals have demonstrated that they may also have an important role in the mechanisms of insulin secretion [23,24] .More than 50 different mutations have been found in the coding regions of the insulin receptor gene on chromosome 19p (see Chapter 15 ) [67] ; patients with these mutations seldom present with the common form of T2DM [68] , but rather with a syndrome of severe insulin resistance associated with leprechaunism, or with acanthosis nigricans, hirsutism and major hyperinsulinemia [69] .Missense variants in the gene encoding the fi rst substrate for the insulin receptor kinase ( IRS1 ) on chromosome 2q have been detected in several populations [70 -73] but an association of these variants with diabetes was not observed in all studies [74,75] .",
+      "\t\n\nFigure 2: Role of genes and the environment in development of obesity and type 2 diabetes Interaction of genes that aff ect body adiposity with environmental factors results in development of obesity and associated insulin resistance.However, only when genes for abnormal -cell function are present along with those for body adiposity does interaction with the environment result in development of type 2 diabetes.\t\n\nGlucose metabolism is normally regulated by a feedback loop including islet  cells and insulin-sensitive tissues, in which tissue sensitivity to insulin aff ects magnitude of -cell response.If insulin resistance is present,  cells maintain normal glucose tolerance by increasing insulin output.Only when  cells cannot release suffi cient insulin in the presence of insulin resistance do glucose concentrations rise.Although -cell dysfunction has a clear genetic component, environmental changes play an essential part.Modern research approaches have helped to establish the important role that hexoses, aminoacids, and fatty acids have in insulin resistance and -cell dysfunction, and the potential role of changes in the microbiome.Several new approaches for treatment have been developed, but more eff ective therapies to slow progressive loss of -cell function are needed.Recent fi ndings from clinical trials provide important information about methods to prevent and treat type 2 diabetes and some of the adverse eff ects of these interventions.However, additional long-term studies of drugs and bariatric surgery are needed to identify new ways to prevent and treat type 2 diabetes and thereby reduce the harmful eff ects of this disease.",
+      "\t\n\nGenetic studies of IL6 and IL6R in type 2 diabetes and insulin resistance",
+      "\t\n\nInsulin resistance has a central role in the pathogenesis of several metabolic diseases, including type 2 diabetes, obesity, glucose intolerance, metabolic syndrome, atherosclerosis, and cardiovascular diseases.Insulin resistance and related traits are likely to be caused by abnormalities in the genes encoding for proteins involved in the composite network of insulin-signaling; in this review we have focused our attention on genetic variants of insulin-signaling inhibitor molecules.These proteins interfere with different steps in insulin-signaling: ENPP1/PC-1 and the phosphatases PTP1B and PTPRF/LAR inhibit the insulin receptor activation; INPPL1/SHIP-2 hydrolyzes PI3-kinase products, hampering the phosphoinositide-mediated downstream signaling; and TRIB3 binds the serine-threonine kinase Akt, reducing its phosphorylation levels.While several variants have been described over the years for all these genes, solid evidence of an association with type 2 diabetes and related diseases seems to exist only for rs1044498 of the ENPP1 gene and for rs2295490 of the TRIB3 gene.However, overall the data recapitulated in this Review article may supply useful elements to interpret the results of novel, more technically advanced genetic studies; indeed it is becoming increasingly evident that genetic information on metabolic diseases should be interpreted taking into account the complex biological pathways underlying their pathogenesis.\t\nInsulin resistance has a central role in the pathogenesis of several metabolic diseases, including type 2 diabetes, obesity, glucose intolerance, metabolic syndrome, atherosclerosis, and cardiovascular diseases.Insulin resistance and related traits are likely to be caused by abnormalities in the genes encoding for proteins involved in the composite network of insulin-signaling; in this review we have focused our attention on genetic variants of insulin-signaling inhibitor molecules.These proteins interfere with different steps in insulin-signaling: ENPP1/PC-1 and the phosphatases PTP1B and PTPRF/LAR inhibit the insulin receptor activation; INPPL1/SHIP-2 hydrolyzes PI3-kinase products, hampering the phosphoinositide-mediated downstream signaling; and TRIB3 binds the serine-threonine kinase Akt, reducing its phosphorylation levels.While several variants have been described over the years for all these genes, solid evidence of an association with type 2 diabetes and related diseases seems to exist only for rs1044498 of the ENPP1 gene and for rs2295490 of the TRIB3 gene.However, overall the data recapitulated in this Review article may supply useful elements to interpret the results of novel, more technically advanced genetic studies; indeed it is becoming increasingly evident that genetic information on metabolic diseases should be interpreted taking into account the complex biological pathways underlying their pathogenesis.",
+      "\tConclusion\n\nWe would propose that it is highly probable that more insulin resistance than b-cell dysfunction T2DM susceptibility genes remain undiscovered at the present time, most likely due to problems associated with study design and the complex nature of physiological responses to nutrients and insulin.In addition, it must be understood that even with 38 genes identified relevant to T2DM pathophysiology, the risk conferred by these combined genes accounts for only a small proportion of overall risk.It must be remembered that the rapid changes in T2DM incidence and prevalence observed in recent decades are a result of the interaction of a stable genetic background with a rapidlychanging environment.Future intervention at newly-discovered insulin secretion controlling loci should improve b-cell function allowing a more robust defence against environmental insult.Targeting oxidative stress, metabolic stress and low grade inflammation may provide fruitful avenues.However, novel therapeutic approaches, whether pharmacological or nonpharmacological, which can target the effects of diet-induced obesity on tissue-specific insulin resistance in the early pathogenesis of T2DM remain a central and invaluable goal of research aiming to halt the rapidly-increasing prevalence of T2DM and its complications worldwide.\tWhy the paucity of genes involved in insulin resistance\n\nrelative to b-cell function?\t\n\nHowever, these cases provide evidence for the existence of genetic mutations that can severely alter insulin sensitivity.It remains possible therefore that the paucity of insulin resistance genes found by GWAS may be at least in part explained by the relative difficulty of accurately measuring small variations in insulin sensitivity compared to measuring small changes in insulin secretion in large populations.",
+      "\t\n\nBaboons also show patterns similar to humans with respect to insulin resistance.Insulin resistance-related phenotypes were significantly heritable in baboons (Cai et al. 2004;Tejero, Freeland-Graves et al. 2004).We showed that one set of genes contributing to insulin resistance also appeared to influence adiposity-related phenotypes, which revealed a common genetic basis for development of insulin resistance and obesity (Cai et al. 2004).Variation in glucose transporter 4 (GLUT4) mRNAwas found to be under significant genetic influence and was genetically correlated with plasma insulin and body weight, supporting their regulation by a common set of genes (Tejero, Proffitt et al. 2004).",
+      "\t\n\nI nsulin resistance precedes and predicts the development of type 2 diabetes mellitus (DM) (1,2).Defects in insulin signal transduction, gene expression, and muscle glycogen synthesis, and accumulation of intramyocellular triglycerides have all been identified as potential mediators of insulin resistance in high-risk individuals (1,(3)(4)(5)(6)(7).However, the molecular pathogenesis of DM remains unknown.Mouse data highlight the importance of glucose uptake into muscle but suggest a role for novel mechanisms, distinct from insulin signaling pathways (8).The importance of genetic risk factors is exemplified by the high concordance of DM in identical twins, the strong influence of family history and ethnicity on risk, and the identification of DNA sequence alterations in both rare and common forms of DM (9).Environmental factors, including obesity, inactivity, and aging, also play critical roles in DM risk.Because both genotype and environment converge to influence cellular function via gene and protein expression, we hypothesize that alterations in expression define a phenotype that parallels the metabolic evolution of DM and provides potential clues to pathogenesis.We used high-density oligonucleotide arrays to identify genes differentially expressed in skeletal muscle from nondiabetic and type 2 diabetic subjects.Because hyperglycemia per se can modulate expression, we also evaluated gene expression in insulin-resistant subjects at high risk for DM (''prediabetes'') on the basis of family history of DM and Mexican-American ethnicity (10).We demonstrate that prediabetic and diabetic muscle is characterized by decreased expression of oxidative phosphorylation genes, many of which are regulated by nuclear respiratory factor (NRF)-dependent transcription.Further-more, expression of peroxisomal proliferator activator receptor  coactivator (PGC1) and - (PPARGC1 and PERC), coactivators of both PPARG and NRF-dependent transcription, is significantly reduced in both prediabetic and diabetic subjects.Taken together, these data indicate that decreased PGC1 expression may be responsible for decreased expression of NRFdependent metabolic and mitochondrial genes and may contribute to the metabolic disturbances characteristic of insulin resistance and DM.",
+      "\t\n\nStudies carried out to identify genetic and nongenetic components participating in homeostatic regulation of glucose and in T2D physiopathology have identified insulin resistance as a postreceptor defect that ultimately affects translocation of the glucose transporter GLUT4 toward the cell surface [9,10].The transduction of insulin signals is mediated by a series of phosphorylation cascades linked to the initial activation of the tyrosine kinase receptor of insulin and its action on the substrates of the insulin receptors (insulin receptor substrate IRS1, IRS-2, IRS-3, and IRS-4) [11].Tyrosine phosphorylation of IRS1 and its binding to phosphatidylinositol 3-kinase are critical events in the insulin signaling cascade leading to insulin-stimulated glucose transport. [12].The importance of IRS1 in insulin signaling has been confirmed in studies showing that this gene plays a very important role not only in peripheral insulin sensitivity, but also in the regulation of insulin secretion by pancreatic -cells [12,13].In addition, IRS1 knockout mice adipocytes showed considerable decrease in glucose transport and in the translocation of GLUT4 to the plasma membrane as a response to insulin [14].Insulin receptor substrate-1, whose gene is located in chromosome 2q36, has 21 sites for tyrosine kinase phosphorylation, which are responsible for most of its enzymatic function."
+    ],
+    [
+      "\tA. Genetic Screening\n\nWe have discussed above the genetic component of T1D.The genetic susceptibility to T1D is determined by genes related to immune function with the potential exception of the insulin gene (434).The genetic susceptibility component of T1D allows some targeting of primary preventive care to family members of diagnosed T1D patients, but there is no complete inheritance of the disease.Nevertheless, the risk for developing T1D compared with people with no family history is 10 -15 times greater.Although 70% of individuals with T1D carry defined risk-associated genotypes at the HLA locus, only 3-7% of the carriers of such genetic risk markers develop diabetes (3).",
+      "\t\n\nPrevious reports show that in the Japanese population, the frequency of a positive family history of diabetes in Japanese diabetic patients is particularly higher in parents of young-onset type 2 diabetic patients and lower in patients who have maximal BMI 35 kg/m 2 compared with those with maximal BMI 30 kg/m 2 (17).Therefore, we considered BMI and age at onset as possible covariates and/or confounding factors.We designed two subset populations, the first one is the subset termed Young-Onset45, in which both siblings were 45 years of age at diagnosis, and which includes the younger-diagnosed 20% families.The other is the subset termed Lean30, in which both siblings have a maximal BMI 30 kg/m 2 (Table 3).Genotyping of microsatellite markers.Genomic DNA was isolated from whole blood using the phenol-chloroform method.Genotyping was performed using a fluorescence-labeled human linkage mapping set (PE-LMSV2) comprising 400 highly informative microsatellite markers with an average intermarker spacing of 9.7 cM.Multiplex PCR conditions were set up for each of the 28 panels to amplify the 400 markers in 87 PCRs.PCR (95C for 12 min, then 40 cycles at 94C for 15 min, 55C for 15 min, 72C for 30 min, and 72C for 10 min) was performed with a 384-well plate on a GeneAmp PCR system (9700 Biblock; Perkin-Elmer, Foster City, CA) using the following (in 10-l reactions): 20 -40 ng genomic DNA, 2.5 mmol/l MgCl 2 , 0.25 mmol/l dNTPs (Pharmacia), variable amounts (0.2-1.5 pmol) of 5 and 3 primers, and 0.4 units AmpliTaq Gold DNA polymerase (Perkin-Elmer) in 1 PCR buffer II (Perkin-Elmer). (Multiplex PCR conditions are available from the authors on request. )An automated 96-channel pipettor Multimek 96 (Beckman) was used for the pipetting steps.Pooled amplification products were electrophoresed through 5% polyacrylamide gels (Long Ranger Singel Pack; Perkin Elmer) for 1.5 h at 2,000 V on 24-cm plates on an ABI 377 DNA sequencer.Semiautomated fragment sizing was performed by using Genescan 3.0 software (ABI), followed by allele calling with Genotyper 2.1 software (ABI).Some panels were electrophoresed on a multicapillary ABI 3700 sequencer and analyzed by Genescan-2.1 software (Perkin-Elmer).Among 400 markers in PE-LMSV2, eight markers (D1S214, D1S252, D3S2338, D3S1285, D4S1534, D7S640, D15S153, and D19S221) were not included because of technical problems.",
+      "\t\nType 1 diabetes (T1D) tends to cluster in families, suggesting there may be a genetic component predisposing to disease.However, a recent large-scale genome-wide association study concluded that identified genetic factors, single nucleotide polymorphisms, do not account for overall familiality.Another class of genetic variation is the amplification or deletion of .1 kilobase segments of the genome, also termed copy number variations (CNVs).We performed genome-wide CNV analysis on a cohort of 20 unrelated adults with T1D and a control (Ctrl) cohort of 20 subjects using the Affymetrix SNP Array 6.0 in combination with the Birdsuite copy number calling software.We identified 39 CNVs as enriched or depleted in T1D versus Ctrl.Additionally, we performed CNV analysis in a group of 10 monozygotic twin pairs discordant for T1D.Eleven of these 39 CNVs were also respectively enriched or depleted in the Twin cohort, suggesting that these variants may be involved in the development of islet autoimmunity, as the presently unaffected twin is at high risk for developing islet autoimmunity and T1D in his or her lifetime.These CNVs include a deletion on chromosome 6p21, near an HLA-DQ allele.CNVs were found that were both enriched or depleted in patients with or at high risk for developing T1D.These regions may represent genetic variants contributing to development of islet autoimmunity in T1D.",
+      "\t\n\nmore frequently than by chance alone among siblings who share the phenotype of type 1 diabetes.Nuclear families, or even just the affected sibling pairs themselves, are genotyped with panels of markers spanning the genome at a modest density.Linkage between a marker and a susceptibility locus for type 1 diabetes is determined by accumulating evidence across families.Since affected sibling pairs are relatively rare in type 1 diabetes, data from linkage studies are collected from a rather unique subgroup of families with type 1 diabetes.In general, linkage studies are the method of choice when the risk factors being sought have large effect sizes but are relatively rare.As risk factors become more common and have smaller effect sizes, association methods emerge as a potentially more powerful approach (Fig. 1).Since the genetic basis of type 1 diabetes is probably a complex mixture of small, moderate, and large genetic effects, multiple strategies are needed and vary according to the population being studied and their exposure to unknown environmental factors.\tDise a se Pr edic tion\n\nCurrent approaches for the prediction of type 1 diabetes take advantage of the major genetic risk factors, genotyping for HLA-DR and HLA-DQ loci (which is then combined with family history), and screening for autoantibodies directed against islet-cell antigens. 43,44The individual distribution of specific risk alleles correlates with gradations in disease penetrance, enabling a tiered staging strategy for the prediction of type 1 diabetes.For example, children who carry both of the highestrisk HLA haplotypes (DR3-DQ2 and DR4-DQ8) have a risk of approximately 1 in 20 for a diagnosis of type 1 diabetes by the age of 15 years. 45If the child has a sibling who has diabetes and the same haplotypes, the risk is even higher (approximately 55%). 46Since this haplotype combination occurs in only 2.3% of the white population, it is possible to envision universal screening strategies that pinpoint this highest-risk group.Inclusion of additional moderate HLA risk haplotypes and screening for autoantibodies would add cost and complexity to a population-screening approach but have the potential to identify the majority of all children with diabetes before the onset of the disease.If this were possible, then tests of potential preventive strategies could be performed, as outlined later in this article.The large number of new risk loci for type 1 diabetes that were recently identified from genomewide association studies could be added to these prediction schemes.These genetic factors are relatively easy, inexpensive, and noninvasive to measure and can be detected well before other features, such as autoantibodies, would typically develop.\t\nIn 1976, the noted human geneticist James Neel titled a book chapter \"Diabetes Mellitus: A Geneticist's Nightmare.\" 1 Over the past 30 years, however, the phenotypic and genetic heterogeneity of diabetes has been painstakingly teased apart to reveal a family of disorders that are all characterized by the disruption of glucose homeostasis but that have fundamentally different causes.Recently, the availability of detailed information on the structure and variation of the human genome and of new high-throughput techniques for exploiting these data has geneticists dreaming of unraveling the genetic complexity that underlies these disorders.This review focuses on type 1 diabetes mellitus and includes an update on recent progress in understanding genetic factors that contribute to the disease and how this information may contribute to new approaches for prediction and therapeutic intervention.Type 1 diabetes becomes clinically apparent after a preclinical period of varying length, during which autoimmune destruction reduces the mass of beta cells in the pancreatic islets to a level at which blood glucose levels can no longer be maintained in a physiologic range.The disease has two subtypes: 1A, which includes the common, immune-mediated forms of the disease; and 1B, which includes nonimmune forms.In this review, we focus on subtype 1A, which for simplicity will be referred to as type 1 diabetes.Although there are rare monogenic, immune-mediated forms of type 1 diabetes, 2,3 the common form is thought to be determined by the actions, and possible interactions, of multiple genetic and environmental factors.The concordance for type 1 diabetes in monozygotic twins is less than 100%, and although type 1 diabetes aggregates in some families, it does not segregate with any clear mode of inheritance. 4-7Despite these complexities, knowledge of genetic factors that modify the risk of type 1 diabetes offers the potential for improved prediction, stratification of patients according to risk, and selection of possible therapeutic targets.As germ-line factors, genetic risk variants are present and amenable to study at all times -before, during, and after the development of diabetes.Thus, genetic information can serve as a potential predictive tool and provide insights into pathogenetic factors occurring during the preclinical phase of the disease, when preventive measures might be applied. Gene tic S t udiesBecause of the uncertainty regarding the number and action of genes involved in type 1 diabetes, genetic studies have tended to focus on approaches that require few assumptions about the underlying model of disease risk.The two primary approaches have been linkage studies (using pairs of affected relatives, typically siblings) and association studies (using either case-control or family-based designs).Linkage studies using affected sibling pairs seek to identify regions of the genome that are shared",
+      "\t\n\nMore than 60 susceptibility loci have been identified (Table 1).The greatest genetic risk (50%) for T1D is conferred by alterations to immune genes, especially those encoding the classical HLAs (Ounissi-Benkalha and Polychronakos, 2008).Other genetic loci (Table 1) are believed to influence population-level risk for T1D, although it is poorly understood how these non-HLA loci contribute to disease susceptibility (Ram et al., 2016a).\tThe genetics of type 1 diabetes\n\nThere is a strong genetic risk to T1D.This is exemplified by (Redondo et al., 2001) who demonstrated a strong concordance of genetic inheritance (65%) and T1D susceptibility in monozygotic twin pairs.That is, when one sibling is afflicted, there is a high probability that the other twin will develop T1D by the age of 60 years.Additionally, autoantibody positivity and islet destruction was observed after a prospective long-term follow-up of monozygotic twins of patients with T1D, despite initial disease-discordance among the twins (Redondo et al., 2008).",
+      "\tType 1 diabetes is a genetic disease\n\nFamily studies have indicated that genetic factors are important determinants of type 1 diabetes risk.First, the risk to a sibling of an affected individual is approximately 6%, as compared with an average risk of 0.4% (depending on the population), or a relative increased risk of 15-fold (17).The increased risk to siblings is referred to as l s (18) and is one measure of the degree of familial clustering of the disease.\t\nFamily and twin studies indicate that a substantial fraction of susceptibility to type 1 diabetes is attributable to genetic factors.These and other epidemiologic studies also implicate environmental factors as important triggers.Although the specific environmental factors that contribute to immune-mediated diabetes remain unknown, several of the relevant genetic factors have been identified using two main approaches: genome-wide linkage analysis and candidate gene association studies.This article reviews the epidemiology of type 1 diabetes, the relative merits of linkage and association studies, and the results achieved so far using these two approaches.Prospects for the future of type 1 diabetes genetics research are considered.",
+      "\tCONCLUSION\n\nThe greatest genetic risk (both increased risk, susceptible, and decreased risk, protective) for type 1 diabetes is conferred by specific alleles, genotypes, and haplotypes of the HLA class II (and class I) genes.There are currently about 50 non-HLA region loci that also affect the type 1 diabetes risk.Many of the assumed functions of the non-HLA genes of interest suggest that variants at these loci act in concert on the adaptive and innate immune systems to initiate, magnify, and perpetuate -cell destruction.The clues that genetic studies provide will eventually help lead us to identify how -cell destruction is influenced by environmental factors.While there is extensive overlap between type 1 diabetes and other immune-mediated diseases, it appears that type 1 and type 2 diabetes are genetically distinct entities.These observations may suggest ways to help identify causal gene(s) and, ultimately, a set of disease-associated variants defined on specific haplotypes.Unlike other complex human diseases, relatively little familial clustering remains to be explained for type 1 diabetes.The remaining missing heritability for type 1 diabetes is likely to be explained by as yet unmapped common variants, rare variants, structural polymorphisms, and gene-gene and/or gene-environmental interactions, in which we can expect epigenetic effects to play a role.The examination of the type 1 diabetes genes and their pathways may reveal the earliest pathogenic mechanisms that result in the engagement of the innate and adaptive immune systems to produce massive -cell destruction and clinical disease.The resources established by the international T1DGC are available to the research community and provide a basis for future discovery of genes that regulate the earliest events in type 1 diabetes etiology-potential targets for intervention or biomarkers for monitoring the effects and outcomes of potential therapeutic agents.",
+      "\t\n\nGenome-wide search for genes affecting the age at diagnosis of type 1 diabetes.\t\nGenome-wide search for genes affecting the age at diagnosis of type 1 diabetes.\t\n\nGenes affecting type 1 diabetes diagnosis age / A. Syreeni et al.\tIntroduction\n\nOver 60 loci in the genome contribute to genetic predisposition to type 1 diabetes (T1D) [1][2][3][4][5] in which insulin deficiency results from an autoimmune attack against insulin-producing beta cells of the pancreatic islets.Heterogeneity in the disease aetiology is recently acknowledged and immunological processes leading to T1D in individuals diagnosed later in life appear different from the processes in individuals having disease onset in early childhood, in which B cells are involved in the pathological process in the pancreas [5].Different genes and genetic variants may thus affect disease course at varying ages, also suggested by the high diagnosis age correlation (r 2 = 0.95) in Finnish monozygotic twins concordant for T1D [6].Of the known T1D risk loci, however, only the HLA locus and a few non-HLA loci, have been associated with age at diagnosis [7][8][9][10].Genetic risk score combines risk-increasing alleles into a single score and the genetic risk score for T1D has already been suggested for clinical use for screening of infants at highest T1D risk [11].All disease-susceptibility variants are included in the score, but only a few known T1D variants have stronger effects in individuals with early-onset disease [10].",
+      "\tGenetics\n\nBoth type 1 and type 2 diabetes are polygenic diseases where many common variants, largely with small effect size, contribute to overall disease risk.Disease heritability (h 2 ), defined as sibling-relative risk, is 3 for type 2 diabetes and 15 for type 1 diabetes (17).The lifetime risk of developing type 2 diabetes is ;40% if one parent has type 2 diabetes and higher if the mother has the disease (18).The risk for type 1 diabetes is ;5% if a parent has type 1 diabetes and higher if the father has the disease (19).Maturity-onset diabetes of the young (MODY) is a monogenic disease and has a high h 2 of ;50 (20).Mutations in any 1 of 13 different individual genes have been identified to cause MODY (21), and a genetic diagnosis can be critical for selecting the most appropriate therapy.For example, children with mutations in KCJN11 causing MODY should be treated with sulfonylureas rather than insulin.\tType 1 Diabetes\n\nThe higher type 1 diabetes prevalence observed in relatives implies a genetic risk, and the degree of genetic identity with the proband correlates with risk (22)(23)(24)(25)(26). Gene variants in one major locus, human leukocyte antigen (HLA) (27), confer 50-60% of the genetic risk by affecting HLA protein binding to antigenic peptides and antigen presentation to T cells (28).Approximately 50 additional genes individually contribute smaller effects (25,29).These contributors include gene variants that modulate immune regulation and tolerance (30)(31)(32)(33), variants that modify viral responses (34,35), and variants that influence responses to environmental signals and endocrine function (36), as well as some that are expressed in pancreatic b-cells (37).Genetic influences on the triggering of islet autoimmunity and disease progression are being defined in relatives (38,39).Together, these gene variants explain ;80% of type 1 diabetes heritability.Epigenetic (40), gene expression, and regulatory RNA profiles (36) may vary over time and reflect disease activity, providing a dynamic readout of risk.",
+      "\t\n\nType 1 diabetes as well as type 2 diabetes shows a genetic predisposition, although only type 1 diabetes is HLA dependent [32,33,36,40].",
+      "\t\n\nType 1 diabetes risk stratification by T1D family history and HLA genotyping",
+      "\t\n\nStudies [71][72][73][74] in Mexican and Asian populations have identified several mutations associated with type 2 diabetes in young people.The high prevalence of type 2 diabetes in the parents of young people diagnosed with type 2 diabetes could reflect a stronger genetic predisposition, even when monogenic diabetes is excluded.This hypothesis suggests that efforts to define genes that cause type 2 diabetes by linkage might be more powerful if focused on young adults with diabetes, raising the question of whether type 2 diabetes in older populations has a relatively smaller genetic contribution and a stronger environmental contribution. 66"
+    ],
+    [
+      "\t\n\nType 2 diabetes mellitus affects 9.6% of the adults in the United States and more than 200 million people worldwide.Diabetes can be a devastating disease, but it can now be treated with nine classes of approved drugs (insulins, sulfonylureas, glinides, biguanides, -glucosidase inhibitors, thiazolidinediones, glucagon-like peptide 1 mimetics, amylin mimetics, and dipeptidyl peptidase 4 inhibitors), in addition to diet and exercise regimens.Choosing which drug to give a patient is based on efficacy and also availability, cost, safety, tolerability, and convenience.Personalized medicine promises a path for individually optimized treatment choices, but realizing this promise will require a more comprehensive characterization of disease and drug response.In this issue of the JCI, Shu et al. make significant progress by integrating diverse data supporting the hypothesis that genetic variation in organic cation transporter 1 (OCT1) affects the response to the widely used biguanide metformin (see the related article beginning on page 1422).We discuss metformin, OCT1, pharmacogenetics, and how the integrative genomics revolution is likely to change our understanding and treatment of diabetes.\t\n\nType 2 diabetes mellitus affects 9.6% of the adults in the United States and more than 200 million people worldwide.Diabetes can be a devastating disease, but it can now be treated with nine classes of approved drugs (insulins, sulfonylureas, glinides, biguanides, -glucosidase inhibitors, thiazolidinediones, glucagon-like peptide 1 mimetics, amylin mimetics, and dipeptidyl peptidase 4 inhibitors), in addition to diet and exercise regimens.Choosing which drug to give a patient is based on efficacy and also availability, cost, safety, tolerability, and convenience.Personalized medicine promises a path for individually optimized treatment choices, but realizing this promise will require a more comprehensive characterization of disease and drug response.In this issue of the JCI, Shu et al. make significant progress by integrating diverse data supporting the hypothesis that genetic variation in organic cation transporter 1 (OCT1) affects the response to the widely used biguanide metformin (see the related article beginning on page 1422).We discuss metformin, OCT1, pharmacogenetics, and how the integrative genomics revolution is likely to change our understanding and treatment of diabetes.\t\nType 2 diabetes mellitus affects 9.6% of the adults in the United States and more than 200 million people worldwide.Diabetes can be a devastating disease, but it can now be treated with nine classes of approved drugs (insulins, sulfonylureas, glinides, biguanides, -glucosidase inhibitors, thiazolidinediones, glucagon-like peptide 1 mimetics, amylin mimetics, and dipeptidyl peptidase 4 inhibitors), in addition to diet and exercise regimens.Choosing which drug to give a patient is based on efficacy and also availability, cost, safety, tolerability, and convenience.Personalized medicine promises a path for individually optimized treatment choices, but realizing this promise will require a more comprehensive characterization of disease and drug response.In this issue of the JCI, Shu et al. make significant progress by integrating diverse data supporting the hypothesis that genetic variation in organic cation transporter 1 (OCT1) affects the response to the widely used biguanide metformin (see the related article beginning on page 1422).We discuss metformin, OCT1, pharmacogenetics, and how the integrative genomics revolution is likely to change our understanding and treatment of diabetes.",
+      "\tA small number of medications\nthat are currently approved for the treatment of T2DM, including metformin, GLP1 receptor\nagonists and SGLT2 inhibitors, have been or are being evaluated as adjuncts to insulin\ntherapy in patients with T1DM275. For instance, the addition of metformin to insulin therapy\ndid not significantly improve glycaemic control in children276 or adults with T1DM277 but\nprovided a modest reduction in total daily insulin dose and body mass index.",
+      "\t\n\nThe best example of pharmacogenetics has been in the treatment of patients with PNDM resulting from mutations in the Kir6.2 and SUR1 subunits of the K ATP channel.These patients frequently present with ketoacidosis and no detectable endogenous insulin secretion, and therefore insulin injections are the only treatment option.Insulin treatment is difficult in a young child, and outstanding glycemic control is rarely achieved.Finding that one-third of the patients with PNDM had mutations in the Kir6.2 channel that reduced channel closure in response to ATP led to the possibility of treating these patients with sulfonylureas that close the channel by an ATP-independent route (4,42).It was then possible to replace insulin injections with high-dose oral sulfonylureas in 90% of patients and also to achieve improved glycemic control without an increase in hypoglycemia (43,44).Insulin secretion is regulated despite the -cell having a limited response to ATP; this is predominantly mediated through nonclassical pathways for insulin secretion, particularly GLP1 (43).Excellent glycemic control is also seen in the majority of patients with SUR1 mutations treated with sulfonylureas (45).Therefore, 50% of patients diagnosed before 6 months with permanent diabetes can benefit greatly from a molecular diagnosis.To date, patients with K ATP channel mutations have maintained near normoglycemia for over 4 years (A.T.H., unpublished data).Doses tend to reduce over time, suggesting that the effectiveness of this treatment will be long lasting.",
+      "\tDevelop innovative approaches to pharmacological and surgical management\n\nInnovative approaches to managing obesity may lower certain barriers undermining treatment of both obesity and type 2 diabetes.For example, modulating the incretin axis may benefit both energy balance and glycemia.Novel pharmacological development may depend on information gained from more efficient use of genomic, proteomic, and metabolomic approaches and from information learned from studying weight-loss mechanisms in bariatric surgery.In addition, co-opting less traditional organs such as the brain and gut into the core pathophysiology of type 2 diabetes may reveal new biomarkers and/or targets for therapeutic intervention.Finally, safe and effective centrally acting drugs that decrease appetite or increase satiety are urgently needed.However, as regulatory agencies increase the need for safety testing, fewer new and innovative approaches for weight loss are being developed because of the prolonged time and immense expense involved.",
+      "\t\n\nPharmacogenomic studies in case of newer therapies are few.Incretin-based therapies, which help control postmeal glucagon levels and hence blood sugar, involve the use of two types of medicine classes -DPP-4 inhibitors and GLP-1 receptor analogs.\t\n\nTable 2 summarizes some of the gene-drug interactions for a few important medicinal classes used in diabetes treatment.",
+      "\tFuture developments in mostly untested areas\n\nBecause available treatments at present do not easily achieve and maintain normal concentrations of glucose as -cell function progressively decreases, new approaches are being developed (table 1), which represent mostly untested mechanisms.\t\n\nFigure 3: Drugs to treat type 2 diabetes (A) The rate of introduction of new classes of drugs has accelerated during the past 20 years.Two classes (animal insulin and inhaled insulin; red) are essentially no longer available as therapeutics. (B) Diff erent classes of drugs act on diff erent organ systems.Insulin is a replacement for the natural product of islet  cells.Classic organ systems that have been targeted for decades comprise the pancreatic islet, liver, muscle, and adipose tissue.Non-classic targets have been focused on recently, and include the intestine, kidneys, and brain.DPP4=dipeptidyl peptidase 4. SGLT2=sodium-glucose co-transporter 2. GLP-1=glucagon-like peptide 1.\t\n\nIn view of the fact that type 2 diabetes is a progressive disease due to advancing -cell dysfunction, can new drugs slow loss of -cell function to provide durable glucose control?In the ADOPT study, 161 recently diagnosed and previously untreated patients were given 4 years of monotherapy with glibenclamide, metformin, or rosiglitazone.Glibenclamide produced the largest initial reduction in glycaemia, but provided poorest maintenance of overall glucose control.Whereas the onset of glucose lowering with the other two drugs was slower than for glibenclamide, it was most sustained with rosiglitazone, with intermediate maintenance of glucose control with metformin, which was mostly related to eff ect on -cell function. 11,161Whether recently introduced drugs will maintain glucose control over the long term remains to be established.Limited data from a few patients suggest that incretin-based therapies, which are purported to improve -cell health, could have such a benefi t. 162 Strategies to slow disease progression have also focused on people with impaired glucose tolerance or impaired fasting glucose because of their high risk of development of type 2 diabetes.Several studies have examined the ability of lifestyle modifi cation and drugs to slow progression to diabetes (table 2). ][165][166][167][168][169][170][171][172][173][174][175] Findings from prolonged follow-up showed that in some instances the benefi t of treatment was retained for 10 years or more, [176][177][178] and could reduce risk of development of severe retinopathy. 179In the DPP study, 180 restoration of individuals to normal fasting and 2 h glucose concentrations only once during the intervention phase was associated with a reduced rate of subsequent diabetes, mostly as a result of improved -cell function.A question that has largely gone unanswered is whether the interventions actually alter the natural history of the disease, or simply mask the development of diabetes as a result of earlier commencement of treatment. 181Only reports of the eff ects of troglitazone in DPP 172 and insulin glargine in ORIGIN 146 suggest a residual benefi t after prolonged withdrawal of the intervention.However, despite good rationale for approval of interventions to delay the onset of diabetes, 182 no drug has yet received offi cial sanction as a preventive treatment.\tOral and injectable drugs: present knowledge, lessons learned, and implications for the future\n\nThe increasing prevalence of type 2 diabetes has stimulated development of many new approaches to safely treat hyperglycaemia (fi gure 3).The aim of these therapies is to reduce and maintain glucose concentrations as close to normal for as long as possible after diagnosis (panels 1, 2), and thereby prevent development of complications.Although some therapies have been unsuccessful because of adverse eff ects or negligible therapeutic effi cacy, several are very well accepted and are used worldwide.The mode of action for most of these drugs has been reported (fi gure 3).However, individual responses to these drugs can diff er greatly, probably as a result of the heterogeneous nature of the pathophysiology of type 2 diabetes.The appendix provides further discussion on drugs that have been widely available for more than a decade (eg, sulfonylurea antidiabetics, biguanide antidiabetics, -glucosidase inhibitors, and peroxisome proliferatoractivated receptor  agonists).",
+      "\tPotential for treatment\n\nSuccessful glycaemic control of T2D patients often requires a combination of several of oral agents, together with subcutaneous insulin for more severe cases.The use of currently available therapeutics can often lead to side effects, including increase in body weight, risk of hypoglycaemia and gastrointestinal problems.In addition, the efficacy of these drugs is limited to the early stages of T2D, when fasting blood glucose levels are relatively low, with approximately 40% of T2D patients on oral anti-diabetics failing to control their blood glucose and having to supplement with insulin.And, of course, all T1D patients currently face a lifetime of injecting insulin.So there is room for more efficacious therapeutic agents.",
+      "\tNanotechnology and Diabetes\n\nThe interface of nanotechnology in the treatment of diabetes has introduced novel strategies for glucose measurement and insulin delivery.Researchers have demonstrated the advantages of glucose sensors and closed-loop insulin delivery approaches in facilitating the diabetes treatment to make it [34] beneficial in both type 1 and type 2 diabetes.\t\n\nFor the management of type 2 diabetes, a well monitored glycemic control is required.The need to control the progressive deterioration of  cell function is essential since it can lead to a loss of glycemic control.Conventional drugs and insulin are effective but cannot repair the associated metabolic and glucoregulatory dysfunctions.The menace of diabetes is increasing day by day and aggressive and targeted combinational therapy is the need of the hour particularly incretin based therapy and peptide analogs.This may restore and preserve  cell function and halt the progression of type 2 diabetes [87].In the present era, the effectiveness and the success of the new drug will depend on its ability to treat/relieve one or more of the metabolic disturbances whether increased production of insulin or enhancement in glucose uptake and utilization by the peripheral tissues particularly skeletal muscle.Besides new generations of therapeutics, several other classes have also been reported as alternative strategies alone or in combinations to provide an effective treatment for diabetes.",
+      "\tTherapeutics\n\nAside from insulin and insulin analogs, therapies for diabetes include those that enhance insulin secretion, those that stimulate insulin action, those that reduce hepatic and endogenous glucose production, and those that impact glycemia through other mechanisms.By better understanding the pathophysiology and natural history of various subtypes of diabetes and applying what we know about the modes of action and pharmacogenomics of existing therapies, we can better apply a personalized approach to diabetes management.There is a growing body of evidence regarding which phenotypic and genotypic subsets of patients with diabetes respond best, or are resistant to, specific therapies (113), including sulfonylureas (114,115), metformin (116,117), thiazolidinediones (118,119), incretin therapies (120), and inhibitors of sodium-glucose cotransporter 2 (SGLT2) (121,122).",
+      "\t\n\nA variety of treatment modalities exist for individuals with type 2 diabetes mellitus (T2D).In addition to dietary and physical activity interventions, T2D is also treated pharmacologically with nine major classes of approved drugs.These medications include insulin and its analogues, sulfonylureas, biguanides, thiazolidinediones (TZDs), meglitinides, -glucosidase inhibitors, amylin analogues, incretin hormone mimetics, and dipeptidyl peptidase 4 (DPP4) inhibitors.Pharmacological treatment strategies for T2D are typically based on efficacy, yet favorable responses to such therapeutics are oftentimes variable and difficult to predict.Characterization of drug response is expected to substantially enhance our ability to provide patients with the most effective treatment strategy given their individual backgrounds, yet pharmacogenetic study of diabetes medications is still in its infancy.To date, major pharmacogenetic studies have focused on response to sulfonylureas, biguanides, and TZDs.Here, we provide a comprehensive review of pharmacogenetics investigations of these specific anti-diabetes medications.We focus not only on the results of these studies, but also on how experimental design, study sample issues, and definition of 'response' can significantly impact our interpretation of findings.Understanding the pharmacogenetics of anti-diabetes medications will provide critical baseline information for the development and implementation of genetic screening into therapeutic decision making, and lay the foundation for \"individualized medicine\" for patients with T2D.\t\nA variety of treatment modalities exist for individuals with type 2 diabetes mellitus (T2D).In addition to dietary and physical activity interventions, T2D is also treated pharmacologically with nine major classes of approved drugs.These medications include insulin and its analogues, sulfonylureas, biguanides, thiazolidinediones (TZDs), meglitinides, -glucosidase inhibitors, amylin analogues, incretin hormone mimetics, and dipeptidyl peptidase 4 (DPP4) inhibitors.Pharmacological treatment strategies for T2D are typically based on efficacy, yet favorable responses to such therapeutics are oftentimes variable and difficult to predict.Characterization of drug response is expected to substantially enhance our ability to provide patients with the most effective treatment strategy given their individual backgrounds, yet pharmacogenetic study of diabetes medications is still in its infancy.To date, major pharmacogenetic studies have focused on response to sulfonylureas, biguanides, and TZDs.Here, we provide a comprehensive review of pharmacogenetics investigations of these specific anti-diabetes medications.We focus not only on the results of these studies, but also on how experimental design, study sample issues, and definition of 'response' can significantly impact our interpretation of findings.Understanding the pharmacogenetics of anti-diabetes medications will provide critical baseline information for the development and implementation of genetic screening into therapeutic decision making, and lay the foundation for \"individualized medicine\" for patients with T2D.",
+      "\t\n\ntherapeutic target for the development of agents to improve glucose regulation and to prevent or treat type 2 diabetes.",
+      "\t\n\nThe only existing therapy is insulin for T1D.Developments in long-acting and glucose-sensitive insulins are improving the health and well-being of people with T1D, as are technological advances in continuous glucose monitoring devices, insulin pumps, closed-loop systems, and the artificial pancreas."
+    ],
+    [
+      "\tGenetics and pharmacogenomics\n\nWe are at the dawn of the age of pharmacogenomics and personalized medicine and ever closer to achieving the \"$1,000 genome. \"What does this mean for diabetes?Forward genetic approaches (i.e., starting from phenotype and identifying the genetic cause) to dissecting mendelian forms of diabetes have been hugely successful in identifying a small subset of diabetic patients in whom rare, highly penetrant mutations of a single gene cause their diabetes (13).While common variants of these genes that make a small contribution to polygenic diabetes may also exist (13), the variants causing monogenic diabetes have limited utility in pharmacogenetics due to their low allele frequency.The vast majority of type 2 diabetes patients have polygenetic forms of the disease that typically also require a permissive environment (e.g., obesity, sedentary lifestyle, advancing age, etc.) to be penetrant.Each locus contributes a small amount of risk (odds ratios typically ranging from 1.1- to 1.5-fold), so large cohorts are needed to identify the at-risk alleles.Some of the loci identified to date include transcription factor 7-like 2 (TCF7L2) (14), calpain 10 (CAPN10) (15), peroxisome proliferator-activated receptor  (PPARG) (16), and potassium inwardly rectifying channel, subfamily J, member 11 (KCNJ11) (17).However, the pace of gene identification is increasing due to the availability of large-scale databases of genetic variation and advances in genotyping technology.A recent genome-wide study identified solute carrier family 30, member 8 (SLC30A8), a  cell Zn transporter, and two other genomic regions as additional diabetes risk loci (18).",
+      "\tLESSONS LEARNED FOR MULTIFACTORIAL DISEASE\n\nMonogenic and syndromic forms account for only a small, though highly informative, proportion of cases of nonautoimmune diabetes.The challenge for medical science lies in bringing equivalent mechanistic insights and translational benefits to the hundreds of millions of people already affected by, or at risk of, more common, typical forms of diabetes.For type 2 diabetes, there is abundant evidence that individual susceptibility is influenced by both the combination of genetic variation at multiple sites and a series of environmental exposures encountered during life (52).Tracking down the specific genetic variants involved has been tougher than for monogenic forms of disease, since the correlations between genotype and phenotype are far weaker (53,54).However, recent efforts have now identified at least 17 confirmed type 2 diabetessusceptibility variants (  (69), and development and exploitation of this methodology has had the greatest impact on susceptibility gene discovery.Even so, many of these discoveries have been hard-won.One reason for this is that the \"candidate\" gene-based approach has proved, with notable exceptions (55,56), to be an inefficient route to susceptibility gene discovery; it is only with the advent of functionally agnostic genome-wide approaches that the floodgates have opened (70).Another reason is that detection of the variants of modest effect that appear to be responsible for much of type 2 diabetes susceptibility (per-allele odds ratios [ORs] 1.10 -1.40, for risk-allele frequencies 10 -90%) has required association studies conducted in extremely large sample sizes (thousands of individuals) (54).Variants within TCF7L2 have the largest effects seen so far, with a per-allele OR of 1.4 (57): the 15% of Europeans carrying two copies of the risk allele are at approximately twice the lifetime risk of type 2 diabetes as the 40% who have none.",
+      "\tGenes and T2DM -from \"susceptibility\" to \"determination\"\n\nAs far as genetic bacground of T2DM is concerned, the disease may be divided into two large groups: monogenic and polygenic forms [71,73] (Tab.1).Monogenic forms are a consequence of rare mutations in a single gene [73].Mutations may affect the structure and subsequently the function of a protein or tRNA.In some cases they may be localised in regulatory parts of genes and alter gene expression.Monogenic forms are characterised by high phenotypic penetrance, which means that the presence of the mutation practically determines the development of the disease.They are also characterised by early age of diagnosis, and frequently, but not always, a severe clinical picture, and occasionally the presence of extra-pancreatic features.Genetic background plays a critical role in their pathogenesis, while the environment only slightly modifies the clinical picture.The known forms of monogenic T2DM are characterized either by severe defect in insulin secretion or profound decrease in insulin sensitivity.Like in other Mendelian traits, in spite of their huge influence on the health of some individuals and families, their role in entire populations is very limited.\t\nThe development of type 2 diabetes (T2DM) is determined by two factors: genetics and environment.The genetic background of T2DM is undoubtedly heterogeneous.Most patients with T2DM exhibit two different defects: the impairment of insulin secretion and decreased insulin sensitivity.This means that there are at least two pathophysiological pathways and at least two groups of genes that may be involved in the pathogenesis of T2DM.As far as genetic bacground of T2DM is concerned, the disease may be divided into two large groups: monogenic and polygenic forms.In this review, we present genes known to cause rare monogenic forms of diabetes with predominant insulin deficiency (MODY -maturity-onset diabetes of the young, MIDD -maternally inherited diabetes with deafness) and uncommon syndromes of severe insulin resistance.We also describe some of the main approaches used to identify genes involved in the more common forms of T2D and the reasons for the lack of spectacular success in this field.Although major genes for T2DM still await to be discovered, we have probably established a \"road map\" that we should follow.\t\n\nIn polygenic forms of T2DM, the susceptibility genetic variants have very modest consequence at the individual level, however, their population effects are significant [71,73,78].In case of polygenic diseases, we search for common variants that are present in the group of patients and in healthy controls.Those polymorphisms generate just a small increase in individual risk.For common diabetes forms caused by many genes and the environment the same strategies as described above were generally used however, with much less success.This fact is a result of fundamental differences in the character of the genetic background of both monogenic and complex forms.Many susceptibility genes for T2DM have been suggested but in majority of cases it is difficult to replicate the findings in other populations.One of the major problems in the search for genes responsible for common forms of diabetes is the genetic heterogeneity of the disease with different genes responsible for the development of T2DM in different populations.Furthermore, even within the same ethnic group, different genes may be responsible for different subtypes of diabetes (for instance with predominating failure in insulin secretion or insulin resistance).This is why several genome scans that have been completed so far are in general not fully reproducible [17,40,72].In addition to that, there are multiple methodological problems.Researchers were studying various populations differing in age of onset of diabetes, severity of clinical picture of the disease, and way of treatment of diabetes.In general, for the purpose of genome scans the researchers have to collect a large number of families (rather small in size-for example sibs) [47,71,73,76,78,89,119].In addition to that, analysis had different, often weak, statistical power and at the level of interpretation different criteria of significance were used.Some studies were based on the very strict criteria proposed by scientists from Massachusetts Institute of Technology while others were analysed with the usage of more liberal rules [57].This is why drawing more general conclusions based on these studies should be very careful.\t\n\nThe development of type 2 diabetes (T2DM) is determined by two factors: genetics and environment.The genetic background of T2DM is undoubtedly heterogeneous.Most patients with T2DM exhibit two different defects: the impairment of insulin secretion and decreased insulin sensitivity.This means that there are at least two pathophysiological pathways and at least two groups of genes that may be involved in the pathogenesis of T2DM.As far as genetic bacground of T2DM is concerned, the disease may be divided into two large groups: monogenic and polygenic forms.In this review, we present genes known to cause rare monogenic forms of diabetes with predominant insulin deficiency (MODY -maturity-onset diabetes of the young, MIDD -maternally inherited diabetes with deafness) and uncommon syndromes of severe insulin resistance.We also describe some of the main approaches used to identify genes involved in the more common forms of T2D and the reasons for the lack of spectacular success in this field.Although major genes for T2DM still await to be discovered, we have probably established a \"road map\" that we should follow.",
+      "\tII. Genetics of Type 2 Diabetes\n\nType 2 diabetes clearly represents a multifactorial disease, and several findings indicate that genetics is an important contributing factor.First, certain ethnic minorities and indigenous groups with low population admixture (e.g., Pima Indians, Micronesians and other Pacific Islanders, Australian Aborigines, and Mexican-Americans) show exceptionally high type 2 diabetes prevalence (up to 21% in Pima Indians) (10 -12).Second, type 2 diabetes clusters within families and first-degree relatives have, compared with the general population, an up to 3.5-fold higher risk to develop the disease (13,14).Finally, twin studies demonstrated a markedly higher concordance for type 2 diabetes in monozygotic compared with dizygotic twins (70 vs. 10%) (15).Type 2 diabetes does not follow simple Mendelian inheritance and, therefore, is considered a polygenic disease.According to the generally accepted common variant-common disease hypothesis (16), complex diseases, such as type 2 diabetes, are caused by the simultaneous occurrence of common DNA sequence variations (minor allele frequencies 5%) in many genes.Each of these DNA alterations is supposed to exert only moderate effects on the affected genes' function and/or expression, but in their sum, these variations confer an increased susceptibility toward the adverse environmental factors mentioned above.Single nucleotide polymorphisms (SNPs), exchanges of single base pairs, cover approximately 90% of the sequence variation within the human genome (SNP Fact Sheet of the Human Genome Project; available at http://www.ornl.gov/sci/techresources/Human_Genome/faq/snps.shtml) and are therefore regarded as the major determinants of the individual predisposition to complex diseases.Thus, strong efforts are currently ongoing to map and catalog these sequence variations (The International HapMap Project at http://www.hapmap.org/index.html.en).However, the less frequent copy number variations (due to deletion and/or duplication of DNA segments one kilobase to several megabases in size) and smaller DNA insertions, deletions, duplications, and inversions may also play a role.All of these findings initiated an intensive search for the genes, or better gene variants, responsible for the genetic predisposition to type 2 diabetes.",
+      "\tDISCUSSION\n\nType 2 diabetes is a highly polygenic trait, and hundreds of loci associated with the disease have been identified, mostly via large GWAS meta-analyses conducted under additive genetic models (2,3).This prior work has produced useful results, identifying potential therapeutic targets and also enabling the creation of polygenic scores capable of quantifying one's genetic risk (34).A sizeable fraction of the heritability of type 2 diabetes, however, remains unexplained by loci identified using additive models.Recessive modeling offers a way to identify new associations, creating opportunities for discovery and improved genetic risk stratification.",
+      "\tINTRODUCTION\n\nDiabetes is a common, chronic disease that profoundly impacts health and longevity.Susceptibility is influenced by inheritance, and there has been substantial progress in identifying genes which, when mutated, influence individual risk of disease.Through study of common and rare forms, both polygenic and monogenic, diabetes genetics encompasses many pressing issues in human genetic research.",
+      "\t\n\nThe different types of heterogeneity at the phenotypic level are mirrored by potential different types of genetic heterogeneity.Thus, type 2 diabetes could be 'polygenic' as illustrated in Figure 1C, or it could be 'oligogenic' as illustrated in Figure 1D.Although there is no way to be certain about which pattern is correct, the many reports of linkages with substantial LOD scores (the ratio of the odds favoring vs the odds against linkage) between various chromosomal regions and type 2 diabetes (to be discussed below) are encouraging and favor the oligogenic pattern (Figure 1D).The uncertainties surrounding the issue of phenotypic and genetic heterogeneity are highly salient, since the strategies for gene discovery, the likelihood of success, and the public health relevance of the search for type 2 diabetes susceptibility genes are all profoundly dependent upon which of these types of heterogeneity turns out to be correct.\tThe Search for Diabetes Genes 111\n\n'polygenic', but rather 'oligogenic', i.e. that at least some diabetes susceptibility genes had relatively large effects.",
+      "\tVariant classification\n\nKey to diagnosing monogenic diabetes and other genetic conditions is not only identifying the variant but also distinguishing The Journal of Clinical Investigation of occurrences leads to a higher level of evidence supporting pathogenicity.However, the uncommonness of monogenic diabetes often makes it difficult for individual laboratories to acquire enough cases.By pooling case data, expert panels can achieve levels of case-based evidence for pathogenicity not possible for any single laboratory or clinic.",
+      "\t\n\nIn the past decade, genome-wide association (GWAS) and sequencing studies have identified genetic loci that help explain the inherited basis of T2D and glycemic traits.These studies are providing insights into the genetic architecture of T2D, including the number, frequency and effect sizes of risk variants in populations around the world.The polygenic nature of T2D is now well established, and multiple risk variants are being identified at some loci, suggesting allelic heterogeneity.Concurrently, increasing numbers of genes and variants have been implicated in monogenic forms of diabetes, including maturity onset diabetes of the young (MODY) and neonatal diabetes (7), and at least five genes have been implicated in both monogenic and polygenic diabetes (8).A recent simulation study evaluated genetic architectures for consistency with results from T2D genetic studies and found that many different disease models were still possible with respect to the number of loci, allele frequencies and level of selective pressure (9).Ongoing studies should more substantially narrow the bounds on feasible architectures (9).",
+      "\t\n\nIn the case of relatively uncommon monogenic and syndromic forms of diabetes, such as maturity onset diabetes of the young (MODY) and neonatal diabetes, identification of rare causal mutations has delivered both knowledge and clinical translation [4,5].In contrast, progress in unravelling the genetic architecture of more typical, common, multifactorial type 2 diabetes has been painfully slow [6].The reasons have been well-rehearsed [7].The complex web of susceptibility factors-genetic, environmental, social-that contributes to individual risk of developing type 2 diabetes means that most predisposing genetic variants will have only a modest marginal impact on disease risk.The majority of genetic studies performed to date have simply had insufficient power to uncover these reliably [7].The few type 2 diabetes-susceptibility variants convincingly demonstrated-notably the P12A variant in PPARG and E23K in KCNJ11 [8,9]-have only modest effects on disease risk (odds ratios ~1.2), far too small to offer (either individually or in combination) clinically useful predictive testing.Since these variants lie within genes whose products are already known to be therapeutic targets, these particular discoveries have also had limited capacity to deliver novel pathophysiological insights.Among those working on the genetics of type 2 diabetes, there was growing apprehension that these two genes might be providing a representative view of the genetic architecture of type 2 diabetes.",
+      "\tA\n\nnumber of studies have implicated a genetic basis for type 2 diabetes (1).The discovery of monogenic forms of the disease underscored the phenotypic and genotypic heterogeneity, although monogenic forms account for only a few percent of the disease (1).Defining the genetic basis of the far more common polygenic form of the disease presents more difficulties (2,3).Nevertheless, some interesting results have recently emerged.A genome scan of Hispanic-American families (330 affected sib-pairs [ASPs]) found linkage to chromosome 2q37 (logarithm of odds [LOD] 4.15) (4), and the causative gene has been recently reported (5).A number of other genome scans in various racial groups have identified other putative susceptibility loci (6 -8).The largest genome-wide scan for type 2 diabetes loci reported to date studied 477 Finnish families (716 ASPs) and found evidence for linkage to chromosome 20q12-13.1(LOD 2.06 at D20S107) (9).Interestingly, similar results have been reported by at least three other groups (10 -12).",
+      "\t\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.\t\n\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.\t\n\nIn this review, however, we focus on a different route from human genetics to translation, one that derives estimates of an individual's predisposition to diabetes and its subtypes (in the form of polygenic scores) from the patterns of individual geneticvariation at sites known to influence diabetes predisposition.\t\n\n During the last decade, there have been major advances in our understanding of the genetic basis of the most common subtypes of type 1 (T1D) and type 2 diabetes (T2D), with .500robust associations identified  Although individual variants typically have only a modest effect on risk, when combined into a polygenic score, they offer increasing power to capture information on individual patterns of disease predisposition with the potential to influence clinical management",
+      "\t\nType 2 diabetes (T2D) had long been referred to as the ''geneticist's nightmare. ''Genome-wide association studies have fully confirmed the polygenic nature of T2D, demonstrating the role of many genes in T2D risk.The increasingly busier picture of T2D genetics is quite difficult to understand for the diabetes research community, which can create misunderstandings with geneticists, and can eventually limit both basic research and translational outcomes of these genetic discoveries.The present review wishes to lift the fog around genetics of T2D with the hope that it will foster integrated diabetes modeling approaches from genetic defects to personalized medicine."
+    ],
+    [
+      "\t\n\nResearchers are expanding our understanding of genetic risk factors for diabetes through ongoing discoveries.Genetic variants associated with increased susceptibility to type 2 diabetes, a disease that affects more than 200 million people worldwide, have been identified (NHGRI & NIDDK, 2007).Such discoveries accelerate efforts to understand genetic contributions to chronic illness, as well as facilitate greater investigation of how these genetic factors interact with each other and with lifestyle factors.Ultimately, once the association of these variants with diabetes are confirmed, genetic tests may be utilized to identify (even before escalating blood sugars) those individuals, like Vanessa, who may be able to delay or prevent diabetes with healthy lifestyle decisions and behaviors.Information to assist nurses in this challenge is available in a toolkit \"Your Game Plan for Preventing Type 2 Diabetes\" (Your Game Plan, n.d.).Would you have known whether or not genetic testing was available for Vanessa?If you had said no to this question but could have explained the progress currently being made in understanding diabetes, Vanessa would have had access to the best care possible today.",
+      "\t\n\nWith further progress in unravelling the pathogenic roles of genes and epigenomic phenomena in type 2 diabetes, pharmacogenomic and pharmacoepigenomic studies might eventually yield treatment choices that can be personalised for individual patients.",
+      "\t\n\nIn addition, the mechanisms whereby a given DNA change leads to an increased risk of diabetes need to be reconstructed.In type 1 diabetes we need to understand how the susceptibility variants influence immune response and tolerance.In type 2, we need to know whether they influence disease predisposition through primary effects on beta cell function, through insulin action, or by some other mechanism.",
+      "\t\nGenomics has contributed to a better understanding of many disorders including diabetes.The following article looks at the ethical, social and legal consequences of genomic medicine and predictive genetic testing for diabetes.This is currently a field in its nascent stage and developing rapidly all over the world.The various ethical facets of genomic medicine in diabetes like its effects on patient physician relationship, risk communication, genetic counseling and familial factors are explored and elucidated from a clinical, ethical, social and legal perspective.\t\n\nGenomics has contributed to a better understanding of many disorders including diabetes.The following article looks at the ethical, social and legal consequences of genomic medicine and predictive genetic testing for diabetes.This is currently a field in its nascent stage and developing rapidly all over the world.The various ethical facets of genomic medicine in diabetes like its effects on patient physician relationship, risk communication, genetic counseling and familial factors are explored and elucidated from a clinical, ethical, social and legal perspective.",
+      "\t\n\nBy identifying key biological processes and genes involved in the pathogenesis of diabetes, novel drug targets for the disease and related metabolic disorders such as obesity and metabolic syndrome may be determined.",
+      "\t\n\nGenetic factors are known to play a role in T2D and an understanding of the genetic basis of T2D could lead to the development of new treatments (Frayling, 2007a,b;Frayling & Mccarthy, 2007;Frayling, 2008).With the increased prevalence of diabetes worldwide, the need for intensive research is of high priority.Sequencing of the human genome and development of a set of powerful tools has made it possible to find the genetic contributions to common complex diseases (Donnelly, 2011).Genome-wide association studies (GWAS) have been used to search for genetic risk factors for complex disease (Hindorff, Junkins et al., 2009;Hindorff, Sethupathy et al., 2009).Used in combination with the scaffold data of the human genome courtesy of the HUGO Project (2003) and the International HapMap Project (Thorisson et al., 2005), it is now possible to analyse the whole genome to identify genetic variants that contribute to common disease in a fast and efficient manner.",
+      "\tGenomics of T2D\n\nDiet, lifestyle, environment, and even genetic variation influence an individual's response to disease therapy.Like GWAS which identify genetic variants conferring risk for a disease, studies have been carried out for identifying genetic variants responsible for patient differences in drug response.Pharmacogenomics in diabetes focuses on the study of gene polymorphisms which influence an individual's response to antidiabetic drugs.Such genetic variants influence the pharmacodynamics and/or pharmacokinetics of the drug, thus affecting its efficacy or toxicity in an individual.The difference in response to treatments and therapies across individuals on account of these factors strengthens the case for personalized medicine in diabetes.",
+      "\t\n\nRegardless, one expects many of the important susceptibility genes for type 2 diabetes will be uncovered in the next 10 years.Once that occurs, intense effort will be focused on developing targeted therapies.Also, medical care will shift to genetic testing of persons with type 2 diabetes, followed by giving them the most effective proven therapy for that genetic form of the disease.Also, their family members will undergo genetic testing while still normally glucose tolerant to determine if they carry a genetic predisposition.If so, specific treatment plans will be developed for prevention of the disease, again based on proven efficacy for each genetic defect.",
+      "\t\n\nFailure to understand the pathophysiology of diseases such as type 2 diabetes and obesity frustrates efforts to develop improved therapeutic and preventive strategies.The identification of DNA variants influencing disease predisposition will, it is hoped, deliver clues to the processes involved in disease pathogenesis.This would not only spur translational innovation but also provide opportunities for personalized medicine through stratification according to an individual person's risk and more precise classification of the disease subtype.In this article, I consider the extent to which these objectives have been realized.",
+      "\t\n\nTo date, studies of diabetes have played a major role in shaping thinking about the genetic analysis of complex diseases.Based on trends in genomic information and technology, combined with the growing public health importance of diabetes, diabetes will likely continue to be an important arena in which methods will be pioneered and lessons learned.It is with great enthusiasm that we look forward to this effort, and with avid curiosity we await to see whether the lessons of today will be supported by the data of tomorrow.",
+      "\t\n\nThe availability of detailed information on gene  environment interactions may enhance our understanding of the molecular basis of T2D, elucidate the mechanisms through which lifestyle exposures influence diabetes risk, and possibly help to refine strategies for diabetes prevention or treatment.The ultimate hope is genetics might one day be used in primary care to inform the targeting of interventions that comprise exercise regimes and other lifestyle therapies for individuals most likely to respond well to them.",
+      "\t\n\nGreat strides have been made clinically in the prevention, development, and treatment of the disease but no therapeutic method have been completely successful till date.With new technologies revolutionizing the treatment possibilities, the search for an effective medication is not far ahead.The extensive research leading to the discovery of the pathway genes contributing to the development of the disease and the sequencing of complete genomes have revolutionized the diabetes research.The development of the techniques like the PCRs, DNA microarray, and gene knockouts with silencing has opened up a new area in the identification of the defective genes/mutations in the genome of the organism.The increasing prevalence of diabetes globally is creating a financial burden on the economy of the respective country.Unlike some other diseases, treatment exists for diabetes, and if managed correctly, it is very effective in reducing complications such as heart attacks, amputations, blindness, and kidney failure.With the ongoing research, a right therapeutic for the treatment of diabetes is not unachievable.",
+      "\t\n\nThe future will see intensified research and improvement in such methodologies to identify and characterise the multiple genes underlying complex diseases.One of the most important goals of genetic studies of diabetes is to determine which multilocus genotypes (across all susceptibility loci) create the highest risk for development of diabetes.Individuals with those genotypes would be targeted for treatment to prevent diabetes when safe and effective prophylactic therapies become available.It is possible that several prophylactic options could be available, with effectiveness depending on the exact set of predisposing genes carried by the at-risk person.Thus, the next generation of genetic studies of Type I diabetes (and other complex disorders) will involve dissection of gene-gene interactions in order to clarify which persons, by virtue of their multilocus genotype, are most susceptible to diabetes.This research will be accompanied by studies of gene-environment interaction, when the relevant non-genetic factors are more clearly understood (eg.do differences in diabetes susceptibility via antiviral defence genes relate primarily to certain types of virus? ).",
+      "\tConclusions\n\nHow will sequencing genomes influence the health of people at risk for or affected with diabetes?The more complete understanding of the biological mechanisms underlying diabetes derived from these studies may lead to identification of novel drug targets.Individuals with variants in genes responsible for MODY or neonatal diabetes respond better to specific drugs [50,51], and sequencing may identify small numbers of individuals with combinations of rarer, more highly penetrant variants that respond better to specific therapeutic options.Although sets of known variants for type 2 diabetes do not add substantially to prediction of type 2 diabetes development in the overall population [52,53], identification of individuals at greater or lower genetic risk for diabetes within the overall population or in specific subgroups, such as younger onset or leaner individuals [54,55], could lead to better targeted health information and also allow identification of higher risk individuals leading to more efficient design of clinical trials for disease prevention.\t\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.",
+      "\t\n\nAll very well, you may say, that must be great for the geneticists, but what does all of this mean for our understanding of diabetes?And what difference will this make to the clinical management of this condition?In truth, it is far too early to offer an authoritative answer to such questions, but here are three immediate lessons.",
+      "\tFUTURE PROSPECTIVES\n\nRecent technological developments around CRISPR-Cas9 and its derivative technologies, combined with advances in human cellular models, should accelerate our understanding of the interplay between diabetes risk-associated genetic variants and their functional roles in disease pathogenesis.These approaches may also find use in clinical applications and in drug screens (Figure 2), enhancing the development of precision medicines for personalized treatment.",
+      "\t\n\nT2D human genetics has other potentials; for instance, NGS large screen for mutations in new putative drug targets can be very helpful in validating them (for example, if causing insulin secretion defects in beta cells) and in determining drugs side effect in humans carrying loss-or gain-of-function mutations.T2D genetics has shown biologists the results of the experiments of nature that have mutated genes and non-coding regions, with direct effects on T2D risk.It revealed in human the role of key pathways involved in glucose homeostasis, opening novel therapeutic avenues.As modern genomics is not biased by prior researchers' hypotheses, but aims to assess all genome influences comprehensively, it brings unique integrated information that deserves to be tested by experimental biologists in animal models and cell lines.Biologists ought not to fear the plethora of T2D genes.On the contrary, together with geneticists, they should formulate innovative strategies for exploiting genetic discoveries in order to answer the following question in humans: among the numerous described metabolic pathways, what is essential to glucose control?What is causing early diabetic abnormalities?And what should be targeted to prevent or even cure T2D?",
+      "\tTHE GENETICS OF TYPE 1 DIABETES\n\nThe study of the genome to map disease-susceptibility regions for T1D and other multifactorial diseases has been facilitated by recent advances in next generation DNA sequencing methods."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "4EE84E22AA592E8150F75B2C3540A23C"
+    },
+    {
+      "task_id": "0B617CD2F3796318CCFF8D220E037B5A"
+    },
+    {
+      "task_id": "D616F7F573665700708E48DD48AA4683"
+    },
+    {
+      "task_id": "D4DBF70BD6F78E8A5C515706F4892B1E"
+    },
+    {
+      "task_id": "0EB12EE3B8B38A98C5E6ACA63D55A150"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_1.json
new file mode 100644
index 0000000..540702f
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_1.json
@@ -0,0 +1,61 @@
+{
+  "question": [
+    "What is GeneNetwork.org, and how does it help scientists understand genetics?",
+    "How do researchers use GeneNetwork.org to study diseases?",
+    "What can GeneNetwork.org tell us about how genes interact with each other?",
+    "How does GeneNetwork.org help in finding the genetic causes of common diseases?",
+    "Can GeneNetwork.org predict my risk of developing certain health conditions based on my genes?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "GeneNetwork.org provides a platform for studying gene interactions and exploring genetic correlates to various phenotypes. It uses co-regulation patterns from tens of thousands of samples to construct networks that link DNA differences to traits. It also offers tools for assessing associations among multiple genes and QTLs. The platform can visualize the relative positions and numbers of possible interacting partners, their interaction type (positive or negative correlation), and in some cases, suggest the directionality of the interaction. It also allows users to study relationships between genes, pathways, and phenotypes in an easy-to-use format.",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [],
+    [],
+    [
+      "GeneNetwork: A Toolbox for Systems GeneticsMegan K. Mulligan1, Khyobeni Mozhui2, Pjotr Prins1,2, Robert W. Williams11.Departmentof Genetics, Genomics, and Informatics, University of Tennessee Health ScienceCenter, Memphis, USA2.PreventiveMedicine, University of Tennessee Health Science Center, Memphis, USAAuthor ManuscriptAbstractThe goal of systems genetics is to understand the impact of genetic variation across all levels ofbiological organization, from mRNAs, proteins, and metabolites, to higher-order physiological andbehavioral traits.",
+      "Until highly accurate genomics networks can beconstructed from more complete data, inferences drawnfrom biological networks should be considered as hypothesis that need to be further tested with experimental method, where the results can then illuminatethe representation of the biological system. The predictive power of the genomics networks could be enhancedby more systematically integrating interactions of informational molecules, such as protein-protein interactions, protein-DNA interactions, protein-RNA interactions, RNA-RNA interactions, protein state information, methylation state, and interactions with metabolites, as these types of data have become available(Schadt et al. 2009).",
+      "GeneNetwork is an interactive software (Geisert et al. , 2009), which enables usersreadily to reconstruct genetic network based on microarraydata without being intimately involved in complicatedmathematical computation. Materials and methodsMiceOne pair of heterozygous (lew/ ) mice was purchasedfrom the Mouse Mutant Stock Resource colonies at TheJackson Laboratory (TJL). A breeding colony was thenestablished by mating them at the University of TennesseeHealth Science Center (UTHSC).",
+      "Until highly accurate genomics networks can beconstructed from more complete data, inferences drawnfrom biological networks should be considered as hypothesis that need to be further tested with experimental method, where the results can then illuminatethe representation of the biological system. The predictive power of the genomics networks could be enhancedby more systematically integrating interactions of informational molecules, such as protein-protein interactions, protein-DNA interactions, protein-RNA interactions, RNA-RNA interactions, protein state information, methylation state, and interactions with metabolites, as these types of data have become available(Schadt et al. 2009).",
+      "GeneNetwork can allow users to study relationships between genes, pathways, andphenotypes in an easy to use format. 28bioRxiv preprint doi: https://doi.org/10.1101/2020.12.23.424047; this version posted December 24, 2020. The copyright holder for this preprint(which was not certified by peer review) is the author/funder. All rights reserved. No reuse allowed without permission.",
+      "GeneNetwork: A Toolbox for Systems GeneticsMegan K. Mulligan1, Khyobeni Mozhui2, Pjotr Prins1,2, Robert W. Williams11.Departmentof Genetics, Genomics, and Informatics, University of Tennessee Health ScienceCenter, Memphis, USA2.PreventiveMedicine, University of Tennessee Health Science Center, Memphis, USAAuthor ManuscriptAbstractThe goal of systems genetics is to understand the impact of genetic variation across all levels ofbiological organization, from mRNAs, proteins, and metabolites, to higher-order physiological andbehavioral traits.",
+      "Those prior knowledge driven geneticsystem-level approaches do not necessarily overlap withgene network analyses which are used to find modulesof highly co-expressed genes with a gene of interest. Thegenerally held view is that genes which are associated orinteracting are more likely to share function and therebybuild up a network. However, this view seems to be theexception rather than the rule in gene networks (Gillisand Pavlidis 2012) since functional information withingene networks is typically concentrated in only a very fewinteractions whose properties cannot be reliably relatedto the rest of the network.",
+      "Peidis et al. BMC Systems Biology 2010, 4:14http://www.biomedcentral.com/1752-0509/4/14In 2005, we published the first report documentingthe ability of the systems genetics tool GeneNetwork topredict interactions between molecules that could bethen confirmed by molecular analysis [3]. The P2P-Rgene, coding for a hnRNP-related protein [4] that bindsboth the p53 [5] and Rb1 [4] tumor suppressor proteinswas used as a test molecule. P2P-R was entered intoGeneNetwork to search for a co-variant that was mosthighly co-expressed in three tissues of the BXD mousegenetic reference panel, ie,, cerebellum, hematopoieticstem cells and whole brain specimens.",
+      "GeneNetwork can allow users to study relationships between genes, pathways, andphenotypes in an easy to use format. 28bioRxiv preprint doi: https://doi.org/10.1101/2020.12.23.424047; this version posted December 24, 2020. The copyright holder for this preprint(which was not certified by peer review) is the author/funder. All rights reserved. No reuse allowed without permission.",
+      "Taking this approach a step further, GeneNetwork[99] is constructedfrom co-regulation patterns found within tens of thousands of samplesfor which gene expression was measured. GeneNetwork provides unprecedented resolution and predictive power across multiple cell typesand tissues. Analogous to discovering patterns in expression data, thenetwork of protein-protein interactions can also be computationally predicted using various methods[381]. The combined current knowledge of how cells control functionssuch as growth, movement, dierentiation, metabolism, communication, and response to stress or pathogens is captured in high-level pathway databases such as WikiPathways[188], Reactome[97] or KEGG[180].",
+      "GeneNetwork is an interactive software (Geisert et al. , 2009), which enables usersreadily to reconstruct genetic network based on microarraydata without being intimately involved in complicatedmathematical computation. Materials and methodsMiceOne pair of heterozygous (lew/ ) mice was purchasedfrom the Mouse Mutant Stock Resource colonies at TheJackson Laboratory (TJL). A breeding colony was thenestablished by mating them at the University of TennesseeHealth Science Center (UTHSC).",
+      "Network based methods of co-expression analysis haveproven useful in identifying evolutionarily conserved gene and protein interactions (Stuart,Segal, Koller, & Kim, 2003), revealing highly connected hub genes that are crucial forsurvival (Carter, Brechbuhler, Griffin, & Bond, 2004), and detecting cell-type specificnetworks, even amongst heterogeneous populations such as the nervous system (Oldham etal. , 2008).",
+      "Next to direct protein-protein interactions, geneticinteractions from model organisms, and interactions withinwww.frontiersin.orgNeuroinformatics of major neuropsychiatric disorderspathways can be valuable information for a functional relationbetween seemingly unrelated genes. Spatiotemporal analysis ofgene expression correlation in human brain (using BrainSpandevelopmental transcriptome data; Kang et al. , 2011) has identified three co-expression modules. Although GO enrichment ofthe whole list (180 genes) did not highlight any functional categories, analysis of the co-expressed genes resulted in enrichmentof the modules. This suggests that co-expression is a meaningful factor in exploring disease gene specificity.",
+      "A new functional gene network for human genesIn order to test the general ability of a gene network to prioritize disease genes, particularly in conjunction with GWAS studies, we constructed a genome-scale functional network of human genes, incorporating diverse expression, protein interaction, genetic interaction, sequence, literature, and comparative genomics data, including both data collected directly from human genes, as well as that from orthologous genes of yeast, worm, and fly.The resulting HumanNet gene network can be accessed through a web interface (http://www.functionalnet.org/humannet).Using this interface, researchers can easily search the network using a set of ''seed'' Network-guided genome-wide association mining genes of interest.The interface returns a list of genes ranked according to their connections to the seed genes, together with the evidence used to identify each coupling.The interactions and evidence can be downloaded, and a network visualization tool has been incorporated.All linkages can also be downloaded for independent analysis.",
+      "As mentioned previously, GeneNetwork(www.genenetwork.org) is a collaborative Web-based resource equipped with tools andfeatures for studying gene/gene and exploring genetic correlates to neurobehavioralphenotypes (Chesler et al. , 2003, 2004). The Web site is home to a growing collection ofgene expression and phenotypic data from a variety of species and brain regions, with a hostof links to external resources for tracing the interrelationships of a gene among multipleWeb-based resources. GeneNetwork also offers a number of correlation and mappingstrategies for assessing associations among multiple genes and QTLs.",
+      "It is possible for agene to play an important role in relevant networks, although geneticvariation, specifically, may not contribute to the genes association withthe network. Protein-protein interactions and expression correlationchanges might be more important drivers for inclusion of such a gene in agiven network. Furthermore, the genetic variation in other genesassociated with the same pathway may confer the relevance of the overallnetwork.",
+      "GeneNetwork has a function that constructs such association networks using either phenotype or transcript abundance, or indeed both simultaneously. It provides avisualization of the relative positions and numbers of possible interacting partners, how they interact (positive ornegative correlation) and in some situations, based onprior knowledge, it may suggest the directionality of theinteraction. An association network using principal component scorescalculated using a selected set of malting quality andyield-related trait data as variables provides an overview ofthe key barley traits that segregate in the St/Mx population(Figure 3, Additional File 3).",
+      "Network-Based ApproachesBased on these large-scale molecular interactions data, such as protein-protein interactions (PPIs), genetic interactions, TF-target interactions, and miRNA-target interactions, molecular networks can be used to visualize the relationships among a gene set, with genes represented as nodes and their molecular interactions as edges.Topological features of a network can often reveal the most critical regulators as hubs, or nodes with the most links, and the functional units/neighborhood among genes as the network modules, within which nodes are densely connected and in between which the nodes are relatively loosely connected.",
+      "GeneNetwork.org also offers a powerful statistical platform foronline network analyses and mapping, enabling numerous molecular questions to be probed in one centralized location(Chesler et al. , 2003, 2005; Li et al. , 2010; Mulligan et al. , 2012,2017, 2019). Most data are from groups of animals or humanswho have been fully genotyped or even sequenced. As a result, itcan be used to model causal networks that link DNA differencesto traits such as differences in expression, cell number, volumes,and behavior using real-time computation and graphing.",
+      "These different sources of interactiondata can be collated into network models (see Note 1) whichallow analysis using techniques borrowed from graph theory. Klaus Schughart and Robert W. Williams (eds. ), Systems Genetics: Methods and Protocols, Methods in Molecular Biology, vol. 1488,DOI 10.1007/978-1-4939-6427-7_10,  Springer Science+Business Media New York 2017239240Rupert W. OverallAn important advantage of a network representation over a simplelisting of genes correlating to a phenotype is that the interactionsbetween the genes are also taken into account."
+    ],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "EE2897F8FCF3BE2C8C19B4F50FF98A0A"
+    },
+    {
+      "task_id": "AB28308963A7CA23CC34A71540C39D6D"
+    },
+    {
+      "task_id": "7BB057A9D03590E415C6BBB5067F5511"
+    },
+    {
+      "task_id": "89A02CE1A9BC0B7E6604478BD9024B13"
+    },
+    {
+      "task_id": "F869432C96A0C9D74FF98A7900FA0F05"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_2.json
new file mode 100644
index 0000000..fecb6cc
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_2.json
@@ -0,0 +1,40 @@
+{
+  "question": [
+    "How does GeneNetwork.org make use of data from different populations around the world?",
+    "What kinds of genetic data are available on GeneNetwork.org?",
+    "How do scientists use GeneNetwork.org to study differences in gene expression?",
+    "Can GeneNetwork.org be used to learn about genetic influences on behavior?",
+    "What role does GeneNetwork.org play in personalized medicine?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [],
+    [],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "72D16BB14C6B8C59DB45C46B0D070E0E"
+    },
+    {
+      "task_id": "422190722E532AC62CBC822E7822EA18"
+    },
+    {
+      "task_id": "277F800382DCBE27854EA848370B5B3E"
+    },
+    {
+      "task_id": "D1DCDB999C8056628C62B7EEB0412369"
+    },
+    {
+      "task_id": "F920B6CB94883D4F1514C45CA524BDC3"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_3.json
new file mode 100644
index 0000000..f7a35a2
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_3.json
@@ -0,0 +1,88 @@
+{
+  "question": [
+    "How does the information on GeneNetwork.org help in developing new treatments for diseases?",
+    "What is a gene network, and why is it important for understanding genetics?",
+    "How do researchers identify which genes are important for certain traits using GeneNetwork.org?",
+    "How can GeneNetwork.org help in understanding complex traits like height or intelligence?",
+    "Are there any known genetic mutations that cause premature aging?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Researchers can identify important genes for certain traits using GeneNetwork.org by utilizing its various features. They can use the global search bar to search for genes, mRNAs, or proteins across all datasets. They can also use the Calculate Correlations tab to assess genetic correlations of the trait of interest with all other records in the database. The platform also allows for the construction of association networks using phenotype or transcript abundance. Additionally, GeneNetwork.org provides background information about genes of interest, including the trait identifier, gene symbol, chromosomal location, and megabase position of the gene. It also allows for data mining in genomic regions containing candidates for quantitative trait genes.",
+    "GeneNetwork.org can help in understanding complex traits like height or intelligence by using both routine and advanced statistical methods to explore and test relations between these phenotypes and underlying genetic variation. It enables complex queries in real time, including very fast QTL mapping. The platform allows for the correlation and comparison across traits, and the identification of common genetic determinants of correlated phenotypes. It also facilitates the construction of molecular networks that drive these traits, providing a comprehensive view of the trait and aiding in the identification of key genes underlying these processes.",
+    "Yes, there are several known genetic mutations that cause premature aging. These include mutations in genes involved in DNA metabolism or regulation, such as those seen in Werner syndrome (WS), Bloom syndrome (BLM), Cockayne syndrome (CS), ataxia-telangiectasia (AT), Hutchinson-Gilford progeria syndrome (HGPS), and restrictive dermopathy (RD). Other examples include mutations in the LMNA gene causing Hutchinson-Gilford progeria syndrome, and mutations in RecQ genes causing Werner syndrome, Bloom syndrome, and Rothmund-Thomson syndrome."
+  ],
+  "contexts": [
+    [],
+    [],
+    [
+      "The GeneNetwork is an open resource and consists of a set of linked resources for systemsgenetics. It has been designed for integration of networks of genes, transcripts, and traits suchas toxicity, cancer susceptibility, and behavior for several species. Phenotypic QTLs using theroo lines were identified in numerous other QTL mapping studies [46,47,60,69,75,89,114,115]. For sets of phenotypes, particularly those in Gene Network's databases (Drosophilaphenotypes are not yet in this database), a variety of correlation analyses can be performedwith the gene expression data.",
+      "Author ManuscriptGeneNetwork main search page and organization. Most analyses in GeneNetwork willfollow the steps shown in panels A through D. In this workfl ow, a data set is selected (A)and mined for traits of interest based on user search queries (B). Traits are then selectedfrom the search (C) and placed in a collection for further inspection and quantitative analysis(D). The banner menu contains additional search options and helpful resources under theSearch and Help tab, respectively (E)Author ManuscriptMethods Mol Biol. Author manuscript; available in PMC 2020 September 17. Mulligan et al.",
+      "GeneNetwork.org is a tool for quantitative genetics that started in 2001 as WebQTL [38].It evolved from analyses of forward genetics in the BXD mouse family, to phenome-wide association studies and reverse genetics in a variety of species.Although GeneNetwork.orgcontains data for many species and populations, it most prominently contains data for the BXD family.Over 10,000 \"classical\" phenotypes, measured under a variety of environmental conditions and over 100 'omics datasets, are available on GeneNetwork.orgfor the BXD family.GeneNetwork.organd the BXD RI population are therefore a powerful tool for systems genetics and experimental precision medicine.The great advantage of inbred lines, with stable genometypes that can be resampled is that data can be reused and reanalysed over time, as tools improve.From the very start of the genome sequencing revolution, when loci were first mapped to causative genes, new tools and a greater understanding of the genome have allowed us to go back to old data and gain new insight.",
+      "Exploring genes, molecules, and phenotypes is easily accomplished using GeneNetwork. In thismanuscript we will outline some simple use cases, and show how a small number of plausiblecandidate genes can be identified for an immune phenotype. 1. DataOnce you have navigated to genenetwork.org, there are two ways to search for data in GN. Thefirst is to use the global search bar located at the top of the page (Figure 1). This is a newfeature in GN that allows researchers to search for genes, mRNAs, or proteins across all of thedatasets.Alternatively, with the handful of candidatesidentified, it is practical to move to wet lab assays, for example seeing if over- or underexpression of our candidate genes in vitro leads to changes in CCL5 levels. ConclusionGeneNetwork is an excellent tool for exploring complex phenotypes with systems genetics. Here we have used GeneNetwork to explore an inflammatory phenotype, and identified a smallnumber of plausible candidate genes. A similar workflow can be used for any trait onGeneNetwork, or for any phenotype collected by an investigator in a genetically diversepopulation.Similarly, by using the dropdown menu on the left (Figure 1), a user can switch to phenotypes,and search for any phenotype of interest in the same way. Figure 1: The global search bar, also called the Search All function, is a good area to start exploringgenes, mRNA, and proteins within GeneNetwork. To best use this new tool, use standard gene symbolscontaining more than two characters in the name. Another area to acquire data is the Select and search pull-down menus (Figure 2). To getstarted, the user has to choose a population of interest.",
+      "Author ManuscriptGeneNetwork main search page and organization. Most analyses in GeneNetwork willfollow the steps shown in panels A through D. In this workfl ow, a data set is selected (A)and mined for traits of interest based on user search queries (B). Traits are then selectedfrom the search (C) and placed in a collection for further inspection and quantitative analysis(D). The banner menu contains additional search options and helpful resources under theSearch and Help tab, respectively (E)Author ManuscriptMethods Mol Biol. Author manuscript; available in PMC 2020 September 17. Mulligan et al.",
+      "Using the GeneNetwork database, we performedthe analysis in a two-step fashion: (1) we ranked correlationsusing Spearman rank test with n-numbers larger than 15 overlapping strains, and with P-values < 0.01; and (2) we performeda trait overrepresentation test using key word searches, in whichsignificantly correlated traits should be overrepresented in theGeneNetwork database. This approach should prevent finding ofa correlation by pure chance, albeit that there still could be abias toward studies with more in depth phenotyping. In total,we selected 34 traits (Table 1, Figure 1).",
+      ", (Chesler et al. , 2005; Galperin and Cochrane,2009; Gentleman et al. , 2004; Mailman et al. , 2007; Saal et al. , 2002; Swertz et al. , 2010)). One relatively well-known database is GeneNetwork (www.genenetwork.org) (Chesler etal. , 2005). GeneNetwork is designed primarily as a web service for exploratory andstatistical analysis of large published phenotype and genome datasets, and includes datafrom several species (see Supplementary Discussion). GeneNetwork includes extensivephenotype data extracted from the literature and submitted by users, which makes itpractical to compare data on drug responses with gene expression patterns.",
+      "Exploring genes, molecules, and phenotypes is easily accomplished using GeneNetwork. In thismanuscript we will outline some simple use cases, and show how a small number of plausiblecandidate genes can be identified for an immune phenotype. 1. DataOnce you have navigated to genenetwork.org, there are two ways to search for data in GN. Thefirst is to use the global search bar located at the top of the page (Figure 1). This is a newfeature in GN that allows researchers to search for genes, mRNAs, or proteins across all of thedatasets.Alternatively, with the handful of candidatesidentified, it is practical to move to wet lab assays, for example seeing if over- or underexpression of our candidate genes in vitro leads to changes in CCL5 levels. ConclusionGeneNetwork is an excellent tool for exploring complex phenotypes with systems genetics. Here we have used GeneNetwork to explore an inflammatory phenotype, and identified a smallnumber of plausible candidate genes. A similar workflow can be used for any trait onGeneNetwork, or for any phenotype collected by an investigator in a genetically diversepopulation.",
+      "GeneNetwork provides users withuseful background information regarding their gene or genes of interest including the traitidentifier, gene symbol, chromosomal location, and megabase position of the gene. Inaddition to this, GeneNetwork can be used to study correlations between traits and toperform data mining in genomic regions containing candidates for quantitative trait genes(Hoffman et al. , 2011). All datasets in GeneNetwork are linked to a materials and methodsinformation page that summarizes experimental details relating to the dataset.",
+      "As mentioned previously, GeneNetwork(www.genenetwork.org) is a collaborative Web-based resource equipped with tools andfeatures for studying gene/gene and exploring genetic correlates to neurobehavioralphenotypes (Chesler et al. , 2003, 2004). The Web site is home to a growing collection ofgene expression and phenotypic data from a variety of species and brain regions, with a hostof links to external resources for tracing the interrelationships of a gene among multipleWeb-based resources. GeneNetwork also offers a number of correlation and mappingstrategies for assessing associations among multiple genes and QTLs.",
+      "Here we provide open access and availability tothese data by integrating them into the GeneNetwork, aweb-based analytical tool that has been designed for multiscale integration of networks of genes, transcripts andtraits and optimized for on-line analysis of traits controlled by a combination of allelic variants and environmental factors. GeneNetwork with its central module WebQTLfacilitates the exploitation of permanent genetic referencepopulations that are accompanied by genotypic, phenotypic and mRNA abundance datasets.GeneNetwork has a function that constructs such association networks using either phenotype or transcript abundance, or indeed both simultaneously. It provides avisualization of the relative positions and numbers of possible interacting partners, how they interact (positive ornegative correlation) and in some situations, based onprior knowledge, it may suggest the directionality of theinteraction. An association network using principal component scorescalculated using a selected set of malting quality andyield-related trait data as variables provides an overview ofthe key barley traits that segregate in the St/Mx population(Figure 3, Additional File 3).DiscussionUsing GeneNetwork for barleyThe framework for analysis using GeneNetwork for barleyis shown in Figure 1A. Associations between transcriptabundance, phenotypic traits and genotype can be established either using correlation or genetic linkage mappingfunctions [29,30]. The main page of GeneNetwork athttp://www.genenetwork.org provides access to subsets ofdata through pull-down menus that allow specific datasets to be queried. The datasets can be further restrictedusing a single text box for specific database entries toquery probe set or trait ID, or annotations associated withthe database entries.",
+      "GeneNetwork.org also offers a powerful statistical platform foronline network analyses and mapping, enabling numerous molecular questions to be probed in one centralized location(Chesler et al. , 2003, 2005; Li et al. , 2010; Mulligan et al. , 2012,2017, 2019). Most data are from groups of animals or humanswho have been fully genotyped or even sequenced. As a result, itcan be used to model causal networks that link DNA differencesto traits such as differences in expression, cell number, volumes,and behavior using real-time computation and graphing.Forexample, given the intense current interest in opiate addiction, it is important toremap decade-old data using new linearmixed-model mapping algorithms available in GeneNetwork.org. There is agreat amount of amassed data on opiateinduced changes in locomotion, and hundreds of other drug-related traits (Philip etal. , 2010) for .60 strains of recombinantinbred mice that have all been fully genotyped. This analysis can identify thegene variants that influence responsesto these drugs-of-abuse. Figure 5. Example workflow in GeneNetwork.org.",
+      "Using GeneNetwork, click on the Calculate Correlations tab to assessgenetic correlations of the trait of interest with all other records in thedatabase, including BXD published phenotypes, BXD genotypes, andmRNA from various brain regions as well as other tissues. To begin,select BXD Published Phenotypes from the Database pull-down menuand click Compute. The default option returns the top 500 phenotypesassociated with the trait of interest, but the Return pull-down barallows researchers to choose how many results to display. Researcherscan also choose between selecting Pearson or Spearman Rankcorrelations.",
+      "However, prioritizingthe long lists of genes produced bycomparative microarray studies conducted in either species has provenexceedingly difficult. As the costs associated with validating a given genesrole in driving a complex trait are considerable, an effective strategy for prioritizing candidate genes is crucial. Investigators therefore have used moresystems-level approaches that combinegenetic, genomic, and pharmacologicalmethods to better delineate gene networks causally related to ethanolbehaviors. Networks allow us to inferrelationships between genes and determine which are most important."
+    ],
+    [
+      "Using the relationships between genotype,gene expression, and behavior in three databases created in the same recombinant inbredstrain set, advances in genome analysis technology have been applied to the reanalysis oftraits that have been historically importantfoundations in neuroscientific research. Directly building on these early achievementsis possible by using bioinformatics approaches to pull together newly developed resourcesand tools with the wide body of previousresults in the field. As complete genomesequences in both of these strains become available, the exact locations of SNPs, which maybe responsible for these phenotypic differences,will be determined.",
+      "Forexample, while the structure learned for this example dataset showsthat the Genotype in the dataset directly impacts Gene1 andGene3, the network structure alone is not able to fully describe thisimpact (e.g. , Does having Genotype = 1 tend to increase or decreasethe value of Gene1 and Gene3?). To more fully investigate thequantitative relationships between variables, users can click on aparticular node of the network and enter a value for the variable aseither evidence or an intervention (see Subheading 2.3.3).",
+      "These lines have been used for three decades to map thegenetic basis of complex phenotypes, and allow detection ofcausative genetic loci even for traits with modest heritability(Belknap 1998). The population also serves as a geneticreference population, allowing correlation and comparisonacross traits, both within and among different laboratoriesto evaluate common genetic determinants of correlatedphenotypes (Crabbe et al . 1996). This approach has beenfacilitated through the development of GeneNetwork(www.genenetwork.org), an Internet resource for the multivariate genetic analysis of complex traits in genetic referencepopulations (Chesler et al .",
+      "These networks may be exploited to identifyrelationships among complex phenotypes, polymorphic and non-polymorphic therapeutic targets, and sources of genetic variability in drug response or disease. Understanding these networks will also allow us to understand how different individualscan use highly polymorphic networks to achieve very similar phenotypic states inmany cases, and highly variable phenotypic states in others. Such analyses will necessarily require special adaptations of QTL analysis for gene expression, though, inBioinformatics for Geneticists, Second Edition.",
+      "It is of great interest to unravel the inner workings of how genotypes influence molecular networks to affect a phenotype such as agility, seizures, and even drug addiction, toname a few. Geneticists have already achieved great success in associating a genotype andphenotype for a trait determined by one gene (i.e. monogenic traits), but much presentattention is now focused on traits that are determined by many genes (i.e. complex traits). These traits are continuously distributed random variables and thus referred to as quantitative traits. Linear modeling is used to identify genotypes that predict phenotype values.",
+      "This strategy required a considerable eort, but also expanded the range of studies and possibleforms of analysis. In many cases, however, per subject phenotype datawere not available. GeneNetwork uses both routine and advanced statistical methods to extract, explore, and test relations among phenotypes and underlying genetic variation. It enables complex queries inreal time, including very fast QTL mapping.",
+      "As an example, Figure 1figure supplement 1A illustrates a sample networkand Figure 1figure supplement 1B depicts a group of correlated traits in this network. Relyingentirely on trait information, however, makes it difficult to identify the shared mechanisms and todistinguish shared molecular mechanisms from shared environmental influences. Alternatively,a common way to improve predictions is by integrating relationships between genes and traits,using genetrait correlations, associations, or causal mutations (Rzhetsky et al. , 2007; Cotsapaset al. , 2011; Baker et al. , 2012; Hwang et al. , 2012; Gat-Viks et al. , 2013).",
+      "When applied to the field of neuroscience, this can revealbiologically relevant meaning and render novel insights into the molecular mechanisms thatgovern behavior. Focusing on these interactions and the gene networks that emergecapitalize on the unbiased investigational methods imparted in whole-genome analysis. Moreover, due to the complexity of neurobehavioral traits, it may be more relevant andinformative to correlate the function of a network of genes with a phenotype, rather than anindividual gene. NIH-PA Author Manuscript4.1.",
+      "Using the relationships between genotype,gene expression, and behavior in three databases created in the same recombinant inbredstrain set, advances in genome analysis technology have been applied to the reanalysis oftraits that have been historically importantfoundations in neuroscientific research. Directly building on these early achievementsis possible by using bioinformatics approaches to pull together newly developed resourcesand tools with the wide body of previousresults in the field. As complete genomesequences in both of these strains become available, the exact locations of SNPs, which maybe responsible for these phenotypic differences,will be determined.",
+      "The combinationof expression genetics with classical linkage analysis, however,allows the in silico identification of candidate genes controllingpolygenic phenotypes as complex as adult neurogenesis and, at thesame time, reveals insights into regulatory transcriptional networksunderlying such phenotypes (18). Genetic polymorphisms influence systems-level phenotypesthrough a network of genes. The small molecular variation is anaturally occurring perturbation of this network that can reveal thegenes that comprise it. Discovering this network and the consequences of this variation are facilitated by the use of geneticreference populations.",
+      "These networks may be exploited to identifyrelationships among complex phenotypes, polymorphic and non-polymorphic therapeutic targets, and sources of genetic variability in drug response or disease. Understanding these networks will also allow us to understand how different individualscan use highly polymorphic networks to achieve very similar phenotypic states inmany cases, and highly variable phenotypic states in others. Such analyses will necessarily require special adaptations of QTL analysis for gene expression, though, inBioinformatics for Geneticists, Second Edition.",
+      "Theinformation that defines how variations in DNA lead to variations in complex traitsof interest flows through molecular networks that actually define the complex traits. Therefore, characterizing the molecular networks that underlie complex traits likedisease can provide a more comprehensive view of disease, and this in turn can leadto the direct identification of key genes underlying disease processes, as well as providing a rich biological context within which to infer the functional roles played bythese key genes.An alternative to the forward genetics approach to dissecting complex traits likedisease is the construction of molecular networks that drive disease, where suchnetworks are constructed from molecular phenotype data scored in populations thatmanifest disease. The information that defines how variations in DNA lead to variations in complex traits of interest flows through molecular networks that actuallydefine the complex traits.Therefore, characterizing the molecular networks thatunderlie complex traits like disease can provide a more comprehensive view of disease, and this in turn can lead to the direct identification of key genes underlyingdisease processes, as well as providing a rich biological context within which toinfer the functional roles played by these key genes.",
+      "The great thing about having accessto the data in Table 1 in GeneNetwork is that we can let these numbers speak forthemselves. Do the traits map strongly to any chromosomal location? If so, what fraction ofthe variance in the trait can be causally linked to the location(s)? Does performance on thistask, whatever it may be measuring, covary with hippocampal size or body weight? To whatextent does the speed of finding the platform during the learning phase of the studycorrespond to the persistence with which the strains search for the missing platform?",
+      "Detection of putative genetic networks underlyingcomplex traitsComplementary epistasis may be of especially greatimportanceDetecting and characterizing genetic networks underlying acomplex trait involves determining the number, genetic relationships, and hierarchy of segregating FGUs (or loci) associated withthe trait in a biparental population. Two general approaches arereadily available - the quantitative genetics approach and thepopulation genetics approach. The power to detect a geneticnetwork is largely dependent on its complexity, which isdetermined largely by the number of segregating loci, r, withineach of the signaling pathways underlying the trait.While gene networks controlling biological processes presumably include the genetic determinants of complex trait variation,these two important areas of study have remained largelyindependent. For example, gene networks consisting of multiplehierarchical signaling pathways might explain high-order epistasis,but only digenic epistasis affecting complex traits has been possibleto map [24,25]. Recent modeling efforts have suggested thatepistasis might be better explained by functional relationships inIntroductionGreat progress has been made in genetic dissection of quantitativetrait variation during the past two decades, but a few puzzling resultshave recurred in many QTL mapping studies.",
+      "Using the relationships between genotype,gene expression, and behavior in three databases created in the same recombinant inbredstrain set, advances in genome analysis technology have been applied to the reanalysis oftraits that have been historically importantfoundations in neuroscientific research. Directly building on these early achievementsis possible by using bioinformatics approaches to pull together newly developed resourcesand tools with the wide body of previousresults in the field. As complete genomesequences in both of these strains become available, the exact locations of SNPs, which maybe responsible for these phenotypic differences,will be determined.",
+      "These networks may be exploited to identifyrelationships among complex phenotypes, polymorphic and non-polymorphic therapeutic targets, and sources of genetic variability in drug response or disease. Understanding these networks will also allow us to understand how different individualscan use highly polymorphic networks to achieve very similar phenotypic states inmany cases, and highly variable phenotypic states in others. Such analyses will necessarily require special adaptations of QTL analysis for gene expression, though, inBioinformatics for Geneticists, Second Edition.",
+      "These networks may be exploited to identifyrelationships among complex phenotypes, polymorphic and non-polymorphic therapeutic targets, and sources of genetic variability in drug response or disease. Understanding these networks will also allow us to understand how different individualscan use highly polymorphic networks to achieve very similar phenotypic states inmany cases, and highly variable phenotypic states in others. Such analyses will necessarily require special adaptations of QTL analysis for gene expression, though, inBioinformatics for Geneticists, Second Edition."
+    ],
+    [
+      "Studies of genes and molecular processes that are associated with segmental progeroid disorders, such as Hutchinson-Gilford progeria syndrome (HGPS, progeria, OMIM#176670), could be of importance when studying the genetic mechanisms of aging (Martin, 2005;Baker et al., 1981).For example, most cases of HGPS are caused by a de novo point mutation in the LMNA gene (LMNA c.1824C>T; p.G608G).This mutation activates a cryptic splice site that results in aberrant splicing of the lamin A transcript (Eriksson et al., 2003).Interestingly, it has been shown that the products of this aberrant splicing, the truncated transcript and resultant protein (named progerin), increase in number with aging in HGPS (Goldman et al., 2004;Cao et al., 2007;Rodriguez et al., 2009).In addition, several reports have found progerin, and increasing levels of progerin, in normal cells over the course of normal aging (Scaffidi & Misteli, 2006;McClintock et al., 2007;Cao et al., 2007;Rodriguez et al., 2009), which suggests a similar genetic mechanism in HGPS and normal aging.Moreover, genome-scale expression profiling in cells from HGPS patients, as well as in physiological aging, has revealed widespread transcriptional misregulation in multiple mammalian tissues (Ly et al., 2000;Csoka et al., 2004;Zahn et al., 2007;Scaffidi & Misteli, 2008;Cao et al., 2011;McCord et al., 2013).",
+      "DNA Repair and Accelerated Aging SyndromesThe association of human syndromes of accelerated aging with inherited mutations in DNA repair genes strongly implicates DNA damage in the human aging process.These disorders, known as segmental progeroid syndromes, are characterized by accelerated onset of a subset of human aging phenotypes that frequently include neurodegeneration (50).Mutations in genes involved in singleor double-strand DNA break repair result in cerebellar degenerative syndromes known as ataxias, which are manifested by movement disorders.The continued proliferation of cerebellar granule cells during postnatal development may underlie the vulnerability of the cerebellum to inherited deficits in genome stability.In contrast, inherited mutations in DNA helicases, such as Werner and Rothmund-Thomson syndromes, give rise to features of accelerated aging that often do not include nervous system dysfunction.This may reflect the role of RecQ-like helicases in recombinant events in replicating cells.Inherited mutations in enzymes involved in nucleotide and base excision repair, including xeroderma pigmentosum and Cockayne syndrome, are characterized by accelerated aging phenotypes that include neurodegeneration, mental retardation, and delayed psychomotor development (50).A new human progeroid syndrome that is caused by a loss of function mutation in the XPF-ERCC1 endonuclease that repairs helix-distorting DNA lesions was recently described.Mice deficient in ERCC1 recapitulate the progeroid features and exhibit a gene expression profile in the liver that overlaps with that of normal aging mice (correlation coefficient 0.32), suggesting that this type of DNA damage may contribute to the aging process (51).Segmental progerias typically have a short life span of less than 20 years, which may account for the absence of Alzheimer-type neuropathological Double-strand break (DSB): a severe form of DNA damage involving scission of both DNA strands, usually induced by ionizing radiation or ROS NHEJ: nonhomologous end joining changes.However, individuals with Werner syndrome, a longer-lived progeroid syndrome, can have variable neuropathology, with one 57-year-old case reportedly showing unusually high levels of amyloid -protein deposition in the brain (52).",
+      "Hutchinson-Gilford progeria syndrome (HGPS) and Werner syndrome are rare human genetic disorders characterized by premature aging phenotypes with a shortened life span.This group of diseases resembles physiological aging to a certain extent, serving as excellent models to gain insight into the biology of aging in humans (24,25).These diseases are due to either a mutation in genes encoding the DNA repair machinery or the A-type lamin, leading to disorganized chromatin structures.The causative mutations behind these progeria syndromes indicate that genomic instability and chromatin deterioration are causes of human aging.Furthermore, the knowledge we gain from understanding the molecular pathology of these human premature aging diseases provides us with useful information to understand the complex aging process.Individuals with HGPS do not recapitulate all aging phenotypes because they usually show segmental progeria affecting multiple tissues.By recapitulating some molecular and cellular changes that are characteristics of the natural aging process, these models provide us with a unique opportunity to understand the aging process in a human model (24,25).",
+      "Researchers in recent studies have focused on gene mutations accompanying known progeroid syndromes, such as Hutchinson-Gilford progeria, Werner syndrome, Rothmund-Thomson syndrome, Cockayne syndrome, ataxia telangiectasia, and Down syndrome. 143The most common skin disorders of these syndromes, which are characterized by an acceleration of the aging phenotype, are alopecia, skin atrophy and sclerosis, telangiectasia, poikiloderma, thinning and graying of hair, and several malignancies.Most of these syndromes are inherited in an autosomal recessive way and mostly display defects in DNA replication, recombination, repair, and transcription.Expression gene patterns of skin cells derived from old and young donors with Werner syndrome, 144 show that 91% of the analyzed genes have similar expression changes in Werner syndrome and in normal aging, implying transcription alterations common to Werner syndrome and normal aging represent general events in the aging process.",
+      "DNA Repair-Related Progeroid SyndromesAs mentioned previously, premature aging syndromes are often caused by mutations in genes whose function is to preserve genomic integrity.In this respect, the RecQ family of DNA helicases has been found to function in DNA damage repair, including base excision repair and in DNA double-strand break (DBS) repair, as well as in DNA replication subjected to a normal or stressed state [36].Mutations in three RecQ genes (WRN, BLM, and RECQL4) give rise to the Werner syndrome (WS), Bloom syndrome (BS), and Rothmund-Thomson syndrome (RTS), respectively [37].Additional genetic defects in the DNA damage repair system also cause the following disorders: Cockayne syndrome (CS), xeroderma pigmentosum (XP), and trichothiodystrophy (TTD).An alternative strategy to the investigation of aging using the humans themselves is the study of progeroid syndromes, a group of very rare genetic disorders characterized by accelerated aging and the presence of clinical features that resemble physiological aging, including osteoarthritis and osteoporosis, loss of muscle mass, hair loss, short stature, skin tightness, and cardiovascular diseases [4].In addition to the genuine medical interest in improving the quality of life of these patients, the study of progeroid syndromes has attracted great interest in the past 10 years, in that they constitute an invaluable source of information for understanding the molecular basis of human aging.ConclusionsRecent advances in the study of progeroid syndromes, especially HGPS, have provided novel insights into our understanding of the aging process in humans.The main progeroid syndromes revised in this chapter are caused by mutations in genes encoding for DNA repair enzymes or the nuclear lamina protein lamin A, which reinforces the notion that genome instability is a critical determinant of aging.The study models that recapitulate progeroid syndromes have dramatically stimulated aging research; while cellular models have allowed the dissection of basic cellular and molecular processes linked to aging, mice models have facilitated screening of therapeutic drugs.It is expected that upcoming technologies and the design of novel optimized animal models will help to accomplish a translational medicine approach in aging research, with HGPS being the ideal model for such a goal.",
+      "Progeroid syndromesPatients suffering from progeroid syndromes, or accelerated aging phenotypes, display an array of physical and biological features that vary widely between tissues and diseases and among individuals.Some of the main characteristics for the specific disorders of interest to this review are cited below (for further review of molecules involved and clinical presentation, see Ref. 96).A general dilemma in studies on the role of telomeres in progeroid syndromes (and aging) is that telomere involvement could be direct as well as indirect.For example, the increased cell death resulting from defective DNA repair could result in telomere shortening via increased compensatory (stem) cell turnover or via direct effects on (repair of) telomeric DNA.For many segmental aging disorders, it has proven to be very difficult to distinguish between direct and indirect effects on telomere length.Perhaps phenotypically the most striking segmental aging genetic disorder in humans, Hutchinson-Gilford Progeria syndrome (HGPS), is caused by point mutations in lamin A, a key component of nuclear scaffolding (34,72).Lamin A deficiency results in absence of hair, craniofacial deformities (\"pinched\" facial features), emaciated and wrinkled appearance, as well as cardiovascular defects that eventually lead to stroke or heart attack at a very young age.The disease is characterized by specific defects in FIG. 8. Defects in human telomerase.The human telomerase complex is minimally composed of two proteins, telomerase reverse transcriptase (hTERT, green) and dyskerin (or DKC1, blue), that both bind specifically to a folded RNA molecule (or hTERC, black) containing a telomere repeat anchoring sequence and a template (red box).Known mutations in each component have now been linked to autosomal dominant dyskeratosis congenita (AD DC), bone marrow failure (BMF), and idiopathic pulmonary fibrosis (IPF) (6,63,127,134,151,217,231,234).The telomerase complex is thought to dimerize, bind to the single-strand G-rich telomere end, and catalyze the addition of new repeats (see also Figs. 3 and 4).The complex translocates along (newly added) telomere tracts for further elongation.Mutations affecting telomerase function lead to failure to assemble a functional complex.In the majority of cases, the level of telomerase activity is reduced by 50%.Such a reduction in telomerase activity compromises telomere length maintenance and increases apoptosis and senescence in proliferating cells (see Fig. 4).nuclear shape (183).Because expression of (defective) lamin A is limited to certain cell types, some cells and tissues are more affected than others.While there is evidence that DNA damage responses in cells expressing mutant lamin A are abnormal (133), the role of telomeres in this disorders (if any) remains to be clarified.A number of other segmental aging disorders have been more directly linked to telomere (dys)function.Among these, Fanconi anemia (FA) and ataxia telangiectasia (AT) are generally autosomal recessive diseases caused by mutations in, respectively, Fanconi genes (encoding any of 12 Fanconi anemia complementation group proteins) and the ataxia telangiectasia mutated gene (encoding the ATM protein).These proteins are implicated in DNA damage and repair pathways; in addition, ATM is known to phosphorylate FANCD2 (for reviews, see Refs.64,118,190).Both diseases are associated with accelerated telomere shortening (29,121,123,146), and abnormalities in telomere replication or repair are thought to play a role in the pathogenesis, particularly in the progression of the disease to immunodeficiency and bone marrow failure, as well as in the increased predisposition to malignancy in young adults.Other syndromes related to the Fanconi DNA damage response pathway include Nijmegen breakage syndrome (NBS) and Seckel syndrome.Other \"progeroid\" genes that have been implicated in DNA replication and repair are the family of genes encoding the RecQ DNA helicases.One of the functions of these enzymes is to assist in the resolution and repair of broken or stalled replication forks.Telomeric DNA is known to readily form higher order DNA structures such as G quadruplex structures in vitro (159), and it seems plausible, based on work in C. elegans (42), that specialized helicases are required to resolve structures of G-rich DNA arising sporadically during lagging strand DNA synthesis (62).Helicases that could be involved include RecQ protein-like 2 (RecQL2), RecQL3, and RecQL4 with known mutations that give rise to Werner (WRN), Bloom (BLM), and Rothmund Thompson syndromes, respectively.Accelerated telomere shortening is observed in Werner's syndrome (51), and pathology in animal model systems is accentuated in the context of telomerase deficiency (40,156).",
+      "The relationship between DNA damage accumulation and aging has gained maximum credibility through studies conducted on various human progeria syndromes, which are genetic disorders where patients precociously develop features resembling natural aging.Most of the reported progeria syndromes, including Werner syndrome (WS), Bloom's syndrome (BS), Rothmund-Thomson syndrome (RTS), Cockayne syndrome type A and type B (CSA and CSB), Xeroderma pigmentosum (XP), Trichothiodystrophy (TTD) and Hutchinson-Gilford progeria syndrome (HGPS) are caused by mutations of genes that are directly or indirectly involved in DNA repair.Of these, WS, BS and RTS are associated with defects in RecQ helicases, i.e.RECQL2 (WRN), RECQL3 (BLM) and RECQL4 respectively, whereas CS, XP and TTD shared similar defects in NER pathway.RecQ helicases are a group of highly conserved proteins from bacteria to humans.The roles of RecQ helicases in DNA metabolism, including DNA replication, transcription, repair and recombination, have been extensively investigated and are demonstrated to be the underlying pathological basis of WS, BS and RTS [139][140][141][142].Most recently, delayed DNA damage checkpoint response and defective DNA repair were found to contribute to the progeria phenotypes in HGPS as well [143].",
+      "They arise from mutations in one or several genes involved in DNA metabolism or in its regulation.Accelerated aging also may result from partial genome imbalances as seen in the chromosomal disorders of Down, Klinefelter and Turner syndromes.These defects result in part from accumulated damage to DNA.Such damage may result inability to maintain replicative fidelity of the genome [2][3][4].Thus, organisms with mutations to genes directly involved in basic genome structure, maintenance and replicative fidelity would understandably have an accelerated aging phenotype and/or shortened life spans.Individuals with a progeroid syndrome have a premature aging phenotype and, depending on the specific mutations involved, the effects on lifespan may range from moderate to severe.Examples include Werner syndrome (WS), Bloom syndrome (BLM), Cockayne syndrome (CS), ataxia-telangiectasia (AT), Hutchinson-Gilford progeria syndrome (HGPS), and restrictive dermopathy (RD).",
+      "The identification of these diseases spurred the creation of numerous animal models, and the characterization of engineered laboratory mutants led to the identification of many new human diseases of systemic and segmental accelerated aging.The animal models are useful for discovering how, when, and where (in what tissues) DNA damage contributes to aging, an area in which much work is still needed.The models, because of their accelerated aging, are useful for rapid hypothesis and drug testing.The models for the large part faithfully recapitulate the human genetic diseases; however, it is notable that mice tend to display a milder phenotype than humans.This might arise from the environmental contribution to human disease, which is not well reproduced in experimental model systems.Collectively, however, these human diseases and their conservation in multiple animal model systems strongly support the role of DNA damage as a proximal contributor to aging.",
+      "The number of identified genes associated with progeroid syndromes has increased in recent years, possibly shedding light as well on mechanisms underlying ageing in general.Several heritable premature aging syndromes have for a long time been linked to defects in genome maintenance, due to altered DNA repair mechanisms.These mainly include the following autosomal recessive syndromes: (i) Werner syndrome, due to mutations in RecQL2 DNA helicase; (ii) Cockayne syndrome (CS) type A and B, due to mutations in the genes encoding the group 8 or 6 excision-repair cross-complementing proteins (ERCC8 and ERCC6), respectively; (iii) Rothmund-Thomson syndrome (RTS), due to RecQL4 mutations; (iv) trichothiodystrophy (TTD), due to mutations in the genes ERCC2/XPD and ERCC3/XPB, encoding the two helicase subunits of the transcription/repair factor TFIIH, as well as in TFB5, encoding the tenth subunit of TFIIH (Giglia-Mari et al., 2004); (v) ataxia-telangiectasia, due to mutations in the ataxia-telangiectasia mutated gene (ATM); (vi) xeroderma pigmentosum (XP), a genetically heterogeneous autosomal recessive disorder in which can be distinguished at least seven complementation groups, due to mutations of different DNA excisionrepair proteins (Hasty et al., 2003;Kipling et al., 2004).All these progeroid diseases, involving heritable defects in DNA repair, suggest a central role of genome integrity maintenance in the aging process.ConclusionFrom a pathophysiological point of view, the known Progeroid syndromes are caused either by mutations in genes encoding DNA repair proteins, such as in WS, Bloom syndrome (BS), Rothmund-Thomson syndrome, Cockayne syndrome, xeroderma pigmentosum or trichothiodystrophy (Hasty et al., 2003;Wood et al., 2005), or by mutations in genes encoding Lamins A/C or partners involved in their biological pathway, such as HGPS or RD (De Sandre-Giovannoli et al., 2003;Eriksson et al., 2003;Navarro et al., 2004Navarro et al., , 2005)).Progeroid syndromes are heritable human disorders displaying features that recall premature ageing.In these syndromes, premature aging is defined as ''segmental'' since only some of its features are accelerated.A number of cellular biological pathways have been linked to aging, including regulation of the insulin/growth hormone axis, pathways involving ROS metabolism, caloric restriction, and DNA repair.Different animal models, ranging from yeast, to nematodes, to mice, have been instrumental in obtaining evidence for these connections (Hasty et al., 2003).Several heritable premature aging syndromes have for a long time been linked to defects in genome maintenance, due to altered DNA repair mechanisms.These mainly include the following autosomal recessive syndromes: (i) Werner syndrome, due to mutations in RecQL2 DNA helicase; (ii) Cockayne syndrome (CS) type A and B, due to mutations in the genes encoding the group 8 or 6 excision-repair cross-complementing proteins (ERCC8 and ERCC6), respectively; (iii) Rothmund-Thomson syndrome (RTS), due to RecQL4 mutations; (iv) trichothiodystrophy (TTD), due to mutations in the genes ERCC2/XPD and ERCC3/XPB, encoding the two helicase subunits of the transcription/repair factor TFIIH, as well as in TFB5, encoding the tenth subunit of TFIIH (Giglia-Mari et al., 2004); (v) ataxia-telangiectasia, due to mutations in the ataxia-telangiectasia mutated gene (ATM); (vi) xeroderma pigmentosum (XP), a genetically heterogeneous autosomal recessive disorder in which can be distinguished at least seven complementation groups, due to mutations of different DNA excisionrepair proteins (Hasty et al., 2003;Kipling et al., 2004).All these progeroid diseases, involving heritable defects in DNA repair, suggest a central role of genome integrity maintenance in the aging process.The number of identified genes associated with progeroid syndromes has increased in recent years, possibly shedding light as well on mechanisms underlying ageing in general.Among these, premature aging syndromes related to alterations of the LMNA gene have recently been identified.LMNA encodes Lamins A/C, ubiquitous nuclear proteins belonging to the intermediate filament superfamily.These premature aging disorders have thus been classified as ''Laminopathies'', the large group of diseases associated to Lamin A/C defects.This group of heterogeneous disorders includes three main subgroups: (1) neuromuscular disorders (Emery-Dreifuss muscular dystrophy, limb-girdle",
+      "However, only those genetic disorders that exhibit premature aging, neurodegeneration (mental defects), and some form of chromosomal/DNA damage all together will be empha-sized here.Perhaps the most appropriate disorder under this category is Down's syndrome.It has several features of premature aging and the genetic defect is trisomy of the distal part of the long arm of chromosome 21.The critical segment of chromosome 21 is shown to have three genes coding for copper-and zinc-dependent superoxide dismutase, oncogene ets-2, and cystathione ~-synthase (Delabar et al., 1987).Since elevated levels of superoxide dismutase are found in various tissues of these individuals, it is postulated that the accelerated aging of these patients may be caused by overproduction of superoxide dismutase, which is responsible for the production of H20 2 while scavenging the oxygen-free radicals.The brains of Down's syndrome individuals are particularly vulnerable to oxidative DNA damage because the high levels of superoxide dismutase found in this tissue are not accompanied by an elevation in the glutathione peroxidase and catalase (Balazs and Brookshank, 1985) that would have normally helped in removing the overproduced H202.Other genetic syndromes characterized by signs of nervous debility, premature aging, and DNA damage/ decreased DNA-repair capacity, are Ataxia Telangiectasia (AT) and Cockayne syndrome (CS).",
+      "Rare genetic disorders of agingProgeria, also known as Hutchinson-Gilford progeria syndrome, affects one in four million births worldwide with equal distribution between sex and race, causing a child's body to age more rapidly (Genetics Home Reference, 2019a).Symptoms typically occur within the first year of life, and most children do not live past 13 years.Mutation in the LMNA gene (not an adduct or telomere factor) contributes to abnormal lamin A protein, called progerin, causing cell instability and cells to easily breakdown (Genetics Home Reference, 2019a).There is no current cure for progeria but farnesyltransferase inhibitors, a cancer drug, has shown promise in reversing cell damage (Genetics Home Reference, 2019a).Other supportive treatments include cardiovascular diseaserelated issues, growth hormones, and bone/joint health.Adalia Rose has taken to social media, with multiple YouTube and Facebook postings, to help others understand her case of progeria.",
+      "Mitochondrial DNA (mtDNA) mutations are thought to have a causal role in many age-related pathologies.Here we identify mtDNA deletions as a driving force behind the premature aging phenotype of mitochondrial mutator mice, and provide evidence for a homology-directed DNA repair mechanism in mitochondria that is directly linked to the formation of mtDNA deletions.In addition, our results demonstrate that the rate at which mtDNA mutations reach phenotypic expression differs markedly among tissues, which may be an important factor in determining the tolerance of a tissue to random mitochondrial mutagenesis.",
+      "INTRODUCTIONIn genetics, identification of genotype-phenotype relationships relies on generated or selected mutants, which highlight underlying mechanisms.For the biology of aging, mutants that display delayed or accelerated aging have been invaluable.Rare heritable syndromes have been identified in the human population that exhibit multiple features of premature aging.A search in the Online Mendelian Inheritance in Man database (OMIM version February 25, 2015) using the keywords \"premature aging,\" \"progeria,\" or \"progeroid\" yielded 20 syndromes with at least one known mutated gene.Certainly this list is far from complete; for example, ataxia telangiectasia, fanconi anemia, and maternally transmitted mitochondrial syndromes such as maternally inherited diabetes and deafness and mitochondrial encephalomyopathy (MIDD/MELAS) are missing.Additionally, many more conditions await identification as unrecognized progeroid syndrome.The application of powerful exome and whole genome sequencing technologies will dramatically accelerate molecular resolution of genetic defects in rare patients with features of accelerated aging, and through this process, many new genes underlying these conditions will be identified.However, when we assign a primary function to each of the causally mutated genes in the known syndromes, it appears that the majority is linked to perturbed genome integrity, a second class represents metabolism, and one syndrome appears connected with cell adhesion (Figure 1).Recently, evidence has emerged for bidirectional interactions between the main aging-related processes: For instance, most DNA damage is derived from endogenous metabolic sources, and compromised genome function indirectly affects many cellular processes including metabolism (1, 2).This suggests the existence of a tightly interwoven network that underlies aging, which is the focus of this review.Progeria-associated syndromes classified by primary function of the causal genetic defect.These 20 human syndromes, listed outside of the circle, were selected from the OMIM database using the keywords \"premature aging,\" \"progeria,\" and \"progeroid. \"Related primary functions were combined in the categories genome integrity, metabolism, and adhesion (inner circle).Abbreviations: DSB, DNA double-strand break; MDPL, mandibular hypoplasia, deafness, progeroid features, and lipodystrophy; PI3K, phosphoinositide-3-kinase; PS, phosphatidylserine; XFE, XpF-Ercc1.GAPO indicates growth retardation, alopecia, pseudoanodontia, and optic atrophy.SHORT indicates short stature, hyperextensibility, hernia, ocular depression, Rieger anomaly, and teething delay."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "25114E7E0872CA766015799208B593EF"
+    },
+    {
+      "task_id": "E72B05930CFE17F0F8781A3F85380920"
+    },
+    {
+      "task_id": "9296083F6746C5627B41C544450F0EF2"
+    },
+    {
+      "task_id": "0EE082035FC7C6545DEDFD74266E8E43"
+    },
+    {
+      "task_id": "DB6A2E2E3506A39B4CF3362C0B22A471"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_4.json
new file mode 100644
index 0000000..74e5ce8
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_4.json
@@ -0,0 +1,59 @@
+{
+  "question": [
+    "What are the practical applications of the research done through GeneNetwork.org?",
+    "How can I access and use the data available on GeneNetwork.org?",
+    "What are some recent discoveries made using GeneNetwork.org?",
+    "How do scientists ensure the accuracy of the data on GeneNetwork.org?",
+    "What\u2019s the difference between looking at one gene and studying a whole gene network?"
+  ],
+  "answer": [
+    "GeneNetwork.org is used for exploratory and statistical analysis of large published phenotype and genome datasets. It allows researchers to model causal networks linking DNA differences to traits such as differences in expression, cell number, volumes, and behavior. It can also be used to identify plausible candidate genes for specific phenotypes, predict the behavior of a system following perturbations, and identify genes directly interacting with a compound of interest. Furthermore, it can be used to investigate the co-expression of genes with distinct functional sets, and generate networks of genes based on their connectivity.",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [
+      "Nonetheless,influence networks do have practical utility for (1) identifyingfunctional modules, that is, identify the subset of genes thatregulate each other with multiple (indirect) interactions, buthave few regulations to other genes outside the subset;(2) predicting the behaviour of the system following perturbations, that is, gene network models can be used to predictthe response of a network to an external perturbation andto identify the genes directly hit by the perturbation (diBernardo et al, 2005), a situation often encountered in the drugdiscovery process, where one needs to identify the genes thatare directly interacting with a compound of interest; (3)identifying real physical interactions by integrating the genenetwork with additional information from sequence data andother experimental data (i.e.",
+      "These programs have the capability to integrate large datasets ofgenetic and expression data from humans and animalstudies. Notably, the GeneNetwork program (www.genenetwork.org) can combine expression data gathered fromdifferent brain regions and tissues and map these withdescribed traits as a way to build gene networks [65]. Evolving developments in bioinformatics promise muchmore; it is now feasible to adopt a new modular approach,known as systems biology. Systems biology is a mathematical modeling technique applied to complex biologicalorganizations or processes for the purposes of generatingpredictive models that are more representative of biological situations [66,67].",
+      "This approach requires the accumulation and integration of many types of data,and also requires the use of many types of statistical tools to extract relevant patterns ofcovariation and causal relations as a function of genetics, environment, stage, and treatment. Inthis protocol we explain how to use the GeneNetwork web service, a powerful and free onlineresource for systems genetics. We provide workflows and methods to navigate massive multiscalardata sets and we explain how to use an extensive systems genetics toolkit for analysis andsynthesis.",
+      "GeneNetwork is one ofeither generate or test ideas by reusing data that oftenan interlinked trio of sites built up by NIAAA (GeneWeaverhave been rescued from the classic literature. Below is a short list of both well-known and more esoteric and WebGestalt are the other two) to house extensiveresources, many of which have been supported by NIAAA, data for human, monkey, rat, mouse, and fruit fly.",
+      "Thus, a simple WebQTL session generates hypotheses that caninitiate investigations into genes previously unsuspected of havingany functional involvement with the original reference gene, letalone with thymocyte development. These examples give an indication of only some of the functionsavailable within GeneNetwork. Currently, systems genetics isa powerful technology for dening clusters of co-regulated genes. Its use is centred upon user-specied genes and can identify novelpotential master regulatory genes for further investigation. We areworking to increase the functionality and power of the GeneNetwork and systems genetics further in a number of areas.",
+      "Each data set containing gene identifierswas uploaded into the online application, and each gene was overlaid onto a molecularnetwork developed from information contained in the ingenuity pathways database. Networks of genes were then generated based on their connectivity, and we chose the top50 significant networks.",
+      "Exploring genes, molecules, and phenotypes is easily accomplished using GeneNetwork. In thismanuscript we will outline some simple use cases, and show how a small number of plausiblecandidate genes can be identified for an immune phenotype. 1. DataOnce you have navigated to genenetwork.org, there are two ways to search for data in GN. Thefirst is to use the global search bar located at the top of the page (Figure 1). This is a newfeature in GN that allows researchers to search for genes, mRNAs, or proteins across all of thedatasets.Recent improvements toGeneNetwork have reinvigorated it, including the addition of data from 10 species, multi-omicsanalysis, updated code, and new tools. The new GeneNetwork is now an exciting resource forpredictive medicine and systems genetics, which is constantly being maintained and improved. Here, we give a brief overview of the process for carrying out some of the most commonfunctions on GeneNetwork, as a gateway to deeper analyses, demonstrating how a smallnumber of plausible candidate genes can be found for a typical immune phenotype.",
+      "This approach requires the accumulation and integration of many types of data,and also requires the use of many types of statistical tools to extract relevant patterns ofcovariation and causal relations as a function of genetics, environment, stage, and treatment. Inthis protocol we explain how to use the GeneNetwork web service, a powerful and free onlineresource for systems genetics. We provide workflows and methods to navigate massive multiscalardata sets and we explain how to use an extensive systems genetics toolkit for analysis andsynthesis.",
+      ", (Chesler et al. , 2005; Galperin and Cochrane,2009; Gentleman et al. , 2004; Mailman et al. , 2007; Saal et al. , 2002; Swertz et al. , 2010)). One relatively well-known database is GeneNetwork (www.genenetwork.org) (Chesler etal. , 2005). GeneNetwork is designed primarily as a web service for exploratory andstatistical analysis of large published phenotype and genome datasets, and includes datafrom several species (see Supplementary Discussion). GeneNetwork includes extensivephenotype data extracted from the literature and submitted by users, which makes itpractical to compare data on drug responses with gene expression patterns.",
+      "In the currentstudies, the online GeneNetwork system was employed to further probe P2P-R biological functions. Molecularstudies were then performed to confirm the GeneNetwork evaluations. Results: GeneNetwork and associated gene ontology links were used to investigate the coexpression of P2P-R withdistinct functional sets of genes in an adipocyte genetic reference panel of HXB/BXH recombinant strains of ratsand an eye genetic reference panel of BXD recombinant inbred strains of mice.",
+      "Exploring genes, molecules, and phenotypes is easily accomplished using GeneNetwork. In thismanuscript we will outline some simple use cases, and show how a small number of plausiblecandidate genes can be identified for an immune phenotype. 1. DataOnce you have navigated to genenetwork.org, there are two ways to search for data in GN. Thefirst is to use the global search bar located at the top of the page (Figure 1). This is a newfeature in GN that allows researchers to search for genes, mRNAs, or proteins across all of thedatasets.Recent improvements toGeneNetwork have reinvigorated it, including the addition of data from 10 species, multi-omicsanalysis, updated code, and new tools. The new GeneNetwork is now an exciting resource forpredictive medicine and systems genetics, which is constantly being maintained and improved. Here, we give a brief overview of the process for carrying out some of the most commonfunctions on GeneNetwork, as a gateway to deeper analyses, demonstrating how a smallnumber of plausible candidate genes can be found for a typical immune phenotype.",
+      "Taking this approach a step further, GeneNetwork[99] is constructedfrom co-regulation patterns found within tens of thousands of samplesfor which gene expression was measured. GeneNetwork provides unprecedented resolution and predictive power across multiple cell typesand tissues. Analogous to discovering patterns in expression data, thenetwork of protein-protein interactions can also be computationally predicted using various methods[381]. The combined current knowledge of how cells control functionssuch as growth, movement, dierentiation, metabolism, communication, and response to stress or pathogens is captured in high-level pathway databases such as WikiPathways[188], Reactome[97] or KEGG[180].",
+      "However, the accurate derivation of such high-throughput data andtheir analysis in terms of biological function has been critical to truly leveraging the postgenomicrevolution. This chapter will describe an approach that focuses on the use of gene networks to bothorganize and interpret genomic expression data. Such networks, derived from statistical analysisof large genomic datasets and the application of multiple bioinformatics data resources, potentially allow the identification of key control elements for networks associated with human disease,and thus may lead to derivation of novel therapeutic approaches.",
+      "To test this hypothesis, we used the Web-basedGeneNetwork databases that have been recently introducedto the scientific community and proved to be a powerful toolfor hypothesis-driven investigations (Chesler et al. 2003,2004; Wang et al. 2003). Researchers can take advantageof genetic diversity in panels of recombinant inbred mousestrains to use these databases for studies of the regulation ofgene expression and genetic mechanisms of complex traits. Our in silico investigation provided evidence for potentialfunctional relationships among the 21 DAT-associated proteins detected by mass spectrometry in this study.",
+      "As mentioned previously, GeneNetwork(www.genenetwork.org) is a collaborative Web-based resource equipped with tools andfeatures for studying gene/gene and exploring genetic correlates to neurobehavioralphenotypes (Chesler et al. , 2003, 2004). The Web site is home to a growing collection ofgene expression and phenotypic data from a variety of species and brain regions, with a hostof links to external resources for tracing the interrelationships of a gene among multipleWeb-based resources. GeneNetwork also offers a number of correlation and mappingstrategies for assessing associations among multiple genes and QTLs.",
+      "Here we provide open access and availability tothese data by integrating them into the GeneNetwork, aweb-based analytical tool that has been designed for multiscale integration of networks of genes, transcripts andtraits and optimized for on-line analysis of traits controlled by a combination of allelic variants and environmental factors. GeneNetwork with its central module WebQTLfacilitates the exploitation of permanent genetic referencepopulations that are accompanied by genotypic, phenotypic and mRNA abundance datasets.",
+      "GeneNetwork.org also offers a powerful statistical platform foronline network analyses and mapping, enabling numerous molecular questions to be probed in one centralized location(Chesler et al. , 2003, 2005; Li et al. , 2010; Mulligan et al. , 2012,2017, 2019). Most data are from groups of animals or humanswho have been fully genotyped or even sequenced. As a result, itcan be used to model causal networks that link DNA differencesto traits such as differences in expression, cell number, volumes,and behavior using real-time computation and graphing.",
+      "While the improvement of gene rankings upon application of GeneRank is already significant in the examplespresented, it may become even more so once comprehensive high-quality biological network informationbecomes available. Of particular interest in that respectwill be transcriptional regulatory networks, such as arenow being generated by technologies like ChIP-chip (see[19-21] for early examples using yeast as a model organism). As discussed above, the information encoded insuch regulatory networks will be intuitively amenable toGeneRank analysis. It will also re-introduce an element ofdirectedness into the network, moving it even closer to theoriginal PageRank application."
+    ],
+    [],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "1AE8A08B2F0E63DC504738485B576741"
+    },
+    {
+      "task_id": "BB02D281C914C63292C0AE91D32CE476"
+    },
+    {
+      "task_id": "852E48D775CF521A5BA7FFF4F42E87C2"
+    },
+    {
+      "task_id": "FC617AC44D108DA97F5988E63DF6C0E6"
+    },
+    {
+      "task_id": "D40628404D48DA90F3E2B0F93FB6640E"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_5.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_5.json
new file mode 100644
index 0000000..7f19b57
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_citizenscientist_gn_5.json
@@ -0,0 +1,16 @@
+{
+  "question": [
+    "How can GeneNetwork.org contribute to advancements in genetic engineering?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "3B79463FDBC2A8CA0EB1B2887A903D9A"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_1.json
new file mode 100644
index 0000000..d24987a
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_1.json
@@ -0,0 +1,99 @@
+{
+  "question": [
+    "How do age-dependent changes in the immune system, such as immunosenescence, contribute to increased susceptibility to diseases?",
+    "How do advancements in machine learning and artificial intelligence aid in the identification of biomarkers for biological aging?",
+    "What recent discoveries have been made regarding the impact of systemic factors, such as circulating microvesicles, on aging phenotypes?",
+    "How do changes in the gut microbiome composition correlate with aging and longevity?",
+    "What are the key molecular mechanisms through which caloric restriction exerts its lifespan-extending effects across different species?"
+  ],
+  "answer": [
+    "Immunosenescence, the age-related decline in immune efficacy, affects both the innate and adaptive immune systems. This decline compromises the body's defense against pathogens, leading to increased susceptibility to infections and diseases. Additionally, aging is associated with 'inflamm-aging,' a state of chronic sterile inflammation that can promote age-related diseases and functional decline. Changes in the immune system also include a decrease in the expression of genes associated with key immune functions, such as phagocytosis in macrophages, which can lead to dysfunction of innate immune cells. Furthermore, the accumulation of apoptosis-resistant cells in the elderly can lead to dysfunctional immune responses.",
+    "Advancements in machine learning and artificial intelligence aid in the identification of biomarkers for biological aging by integrating and analyzing large and diverse datasets generated from genomic, functional, phenotypic, and lifestyle data. These technologies can predict age, forecast potential diseases in aging, and contribute to personalized medical treatment. Machine learning algorithms can also be used to assess the importance of specific factors in aging, predict future outcomes, and identify potential biomarkers for age-related diseases. Furthermore, they can help in the interpretation of complex omics data sets, which contain vast measurements of potential candidate markers.",
+    "Recent discoveries have shown that systemic factors, including circulating microvesicles, play a significant role in aging phenotypes. For instance, age-related alterations in vasoprotective endocrine factors, such as growth hormone, IGF-1, and estrogens, have been found to regulate multiple aspects of vascular aging processes. Studies using heterochronic parabiosis in mice have demonstrated the impact of circulating factors on aging phenotypes. Additionally, there is initial evidence that antigeronic factors present in young mice can rejuvenate microvascular network architecture in aged mice. However, the exact nature of these antigeronic circulating factors remains unknown. Progeronic circulating factors, which increase with age and impair tissue homeostasis, have also been identified. Further studies are needed to identify additional progeronic and antigeronic factors and their impact on aging.",
+    "Changes in the gut microbiome composition correlate with aging and longevity in several ways. Studies on centenarians and supercentenarians have shown that the microbiota adapts to the physiological changes of the long aging process, promoting health and survival. The concentration of certain bacteria, like Bacteroidetes, increases with age, while others like Actinobacteria decrease. Age-related decrease in microbiota diversity can lead to larger populations of certain microbial species, potentially increasing the chances for the evolution of novel, potentially pathogenic strains. These changes can contribute to increased frailty and development of diseases during the late stages of life. However, a healthy microbiota, characterized by the presence of bacterial compounds like Christensenellaceae, Akkermansia, and Bifidobacterium, has been linked to longevity.",
+    "The key molecular mechanisms through which caloric restriction extends lifespan across different species include signaling through the insulin-like growth factor pathway, chromatin regulation by sir2, and oxidative damage. Caloric restriction also increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes, which directly intervenes in the repair of DNA damage. Additionally, it affects nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling and target of rapamycin (TOR) signalling."
+  ],
+  "contexts": [
+    [
+      "\t\n\nOn the other hand, a direct relationship exists between physiological aging and increasing incidence of chronic inflammatory diseases.In its acute form, inflammation acts as a protective mechanism in response to pathogen invasion or tissue damage and helps to restore physiological integrity and function.However, in its chronic form, inflammation can exert detrimental effects on the cellular as well as the organismic level.Chronically inflamed tissue is characterized by infiltration of immune cells, neovascularization, fibrosis, and often tissue damage and necrosis [3].The innate immune system, especially the mononuclear phagocyte system, is the most important mediator of chronic inflammation.Monocytes originate from the myeloid hematopoietic cell lineage in bone marrow.In the blood stream, monocytes are recruited by specific stimuli into different tissues, where they differentiate into phagocytic Oxidative Medicine and Cellular Longevity macrophages.Macrophages participate in the killing of invading microorganisms and emerging tumor cells through the production of reactive oxygen or nitrogen species (ROS and RNS).In addition, macrophages secrete cytokines, which play a key role in the regulation of multiple immune functions, especially inflammatory responses [3].During aging, the continuous pressure on the immune system caused by repeated antigen stimulation, such as infections, food antigens, allergens, and self antigens, leads to an increase in activated cells and secretion of proinflammatory cytokines, such as TNF [4].These circulating proinflammatory factors may keep the immune system in a state of chronic lowlevel activation, a phenomenon described as \"inflammaging\" [5,6].Eventually, this causes \"immunosenescence,\" that is, an age-related decline in the capacity of adaptive immunity, consisting of more specific responses carried out by B and T cells [7].Thus, with advanced age, the immune system undergoes a gradual remodeling in the attempt to reestablish a new balance that assures survival, however, favoring the development of chronic inflammatory conditions [5,6,8,9].",
+      "\tThe Neuroimmune System Upon Aging\n\nThe age-associated synaptic dysfunction can also be a consequence of alterations in astrocytes and microglia, as the aging process has also been described as inflammaging, a status of chronic inflammation that contributes to the pathogenesis of neurodegenerative diseases [174].Recent data further suggest an important role of the immune system in regulating the progression of brain aging and neurodegenerative disease.This can be seen as a cause-or-consequence dilemma: do immune and inflammatory pathways become hyperactivated with age and promote degeneration or, instead, immune responses fail to cope with age-related stress and may contribute to disease [175]?",
+      "\tAging is one of the inevitably dominant risk associated with many diseases. Several biological factors contribute to this etiology which include loss of telomeres, stem cells activity and metabolism, escalation of environmental and biological stress, dysfunctioning of various micro-and macromolecules, and cell cycle and weakening of immune system (Franceschi et al., 2018).In case of cellular and molecular damage before elderly age, injury is healed to maintain the hemostasis.Nonetheless, with aging, repair mechanism is slowed or completely halted, leading to number of pathologies (Cortopassi, Gurung, & Pinto-Plata, 2017).",
+      "\t\n\nimmunity can become hyperactivated, exacerbating the age-related damage caused by innate immune responses [33].The risk of collateral damage by the adaptive immune system also potentially increases with age via autoimmunity factors, but this is believed to be counteracted by a parallel rise in self-protective mechanisms [42].Overall, the collateral damage inflicted by the innate immune system over the course of a long life is likely to be greater than that caused by adaptive immunity.\t\n\nThe damage caused by the ageing adaptive and innate immune systems gives us insights into how these different arms of the immune system may influence longevity.In general, adaptive immune function diminishes with age, whereas innate immune function is maintained [34,[43][44][45][46]. Whilst this may initially suggest that the innate immune system withstands the test of time better than the adaptive immune system, a chronic stimulation of innate immunity underpins this pattern [35].Innate immune cells become increasingly proinflammatory with age [46,47] and trained",
+      "\t\n\nThe increased expression of genes involved in immune response and inflammation observed in the colon of the 21-month-old mice points to an affected immune system in this part of the intestine of aging mice.This observation is in agreement with the fact that changes in the immune system are one of the hallmarks of the aging body.Immunosenescence is the functional decline of the adaptive immune system brought on by natural aging whereby protection against infection by pathogens and the effectiveness of vaccination decline [45,46].The second aging-induced change in the immune system is called inflammaging which is characterized by a lowgrade chronic inflammation process that contributes to the pathogenesis of many age-related diseases [47][48][49].A large variety of cells with a defense function are present especially in the lamina propria and the submucosa of the intestine accomplishing immune protection via the innate as well as by the adaptive immune response.Interestingly, our microarray and Q-PCR data clearly show that activity of both branches of the immune system is enhanced in response to aging exclusively in the colon but not in the small intestine of old mice.Expression levels of well-established pro-inflammatory cytokines like IFN, TNF, IL6 and IL1 turned out to be extremely low in the colon of both old and young mice and below the threshold of our microarray analysis.These low expression levels are probably due to the fact that these cytokines are predominantly produced by immune cells in the mucosa which is a rather low percentage of cells in relation to all cells present in the intestinal tissue.Q-PCR analysis confirmed the very low basal expression levels of these pro-inflammatory cytokines, yet a weak but significant induction of IFN TNF and IL-1 in the colon of aging mice was observed.This result suggests that low-grade inflammation might be present in the colon of the aging mice in our study, although it should be noted that no altered expression of a number of established inflammation markers like Tolllike receptors (TLRs), C-type lectin receptors (CLRs) and retinoic acid-inducible receptors (RLRs) [50] was detectable.",
+      "\tIntroduction\n\nAgeing of the immune system (immunosenescence) contributes to the increased susceptibility of the elderly to infectious disease and to the poor outcome of vaccination.Defence against pathogens is compromised mainly because of changes in adaptive immunity mediated by T and B lymphocytes; however, all components of the immune system are affected (Fig 1).Dissecting the crucial alterations responsible for dysfunctional immunity in old age will facilitate the development of rational interventions to reconstitute appropriate immune function.Given the increasing proportion of elderly people in most countries and their disproportionate consumption of health-care resources, this issue is rapidly gaining in importance.The meeting, which was dedicated solely to studies of immunosenescence, filled two days with the 'A to Z' of immunity, covering topics ranging from development to senescence, innate immunity to adaptive immunity, and genes to environments, in organisms ranging from mice to monkeys and humans.Understanding and eventually modulating immune dysfunction in the elderly now beckons.\tClinical implications of immunosenescence\n\nAs mentioned above, complications from acute infectious are likely to be more severe in the elderly owing to impaired innate immunity.However, questions remain concerning 'normal, healthy' ageing and the important clinical issue of responses to vaccinations in old age.In a mouse model of the highly relevant human pathogen influenza, the virus is cleared from the lungs more slowly in old animals, correlating with a delayed and decreased peak of cytotoxic T-cell production (D.Murasko, Philadelphia, PA, USA).Therefore, cellular responses are crucial for controlling the virus, but do not function adequately in old animals.Although there is an accumulation of memory cells (the clonal expansion referred to above), they are not solely responsible for this decrease in the virus-specific response.Both memory and naive T cells in old, but not young, mice are resistant to apoptosis, and do not 'make space' for new responses.In the mouse model, cell-transfer experiments showed that both the old environment and the old cells contributed to the problem-young cells did not deplete when transferred to an old environment and old cells did not deplete when transferred to a young environment.The factors inducing apoptosis resistance have not yet been identified; however, it is clearly important to do so and to search for them in humans.\tConclusions\n\nAll components of the immune system are altered as ageing proceeds (Fig 1 ); however, the T-cell and B-cell compartments seem to be particularly susceptible.The most severe clinical impact is probably a result of the loss of diversity in the TCR and B-cell-receptor repertoire, owing to the accumulation of dysfunctional cells, and decreased thymic and bone-marrow output.Several interventions discussed at the meeting could conceivably contribute to the restoration of appropriate immune function in the near future.\tLymphocyte development and ageing\n\nThe cells of the immune system turn over rapidly and therefore need constant replacement from the pool of haematopoietic stem cells (HSCs).If the HSCs themselves aged, it would compromise all downstream events that depend on their integrity, including production of immune cells and subsequent immune responsiveness (Rando, 2006).Evidence for age-associated alterations in the ability of HSCs to reconstitute the haematopoietic system of an animal derives from findings of increased self-renewal with age, resulting in an expansion of the HSC pool size even when transplanted into young animals (D.Rossi, Stanford, CA, USA).However, purified HSCs from old mice showed less activity on a per-cell basis and tended to generate more myeloid cells-for example, macrophages-than lymphocytes.Expression profiling of young and old HSCs revealed that genes mediating lymphoid fate and function were systematically downregulated, whereas myeloid-specification genes were upregulated, with age.The concerted nature of these changes suggests epigenetic involvement as a mechanism that contributes to HSC functional decline with age.There is also a gradual decline in the ability of murine HSCs to progress through the various stages of B-cell-differentiation (K.Dorshkind, Los Angeles, CA, USA).This reflects, in part, the microenvironmental changes involving altered production of interleukin 7 (IL-7) by stromal cells as they age (M.Cancro, Philadelphia, PA).B cells must also compete for the cytokine BLys (or B-cell activating factor (BAFF)), the receptor levels of which determine survival.Declining B-cell production in aged animals results in selective accumulation of marginal zone and memory B cells at the expense of the follicular pool of B cells.The follicular pool is responsible for producing protective immune responses to newly encountered pathogens, such as influenza H5N1.Loss of the declining stem-cell function, and the resultant decline of the follicular B-cell compartment, leads to enhanced infectious disease-related morbidity with ageing (J.Cambier, Denver, CO, USA).Hence, age affects both HSCs and the environment that determines their fate.\tInnate immunity\n\nSo, what are the age-associated changes that can be directly measured in macrophages, dendritic cells, neutrophils, natural killer (NK) cells and so on?These might be at least as important, if not more so, than the changes to adaptive immunity discussed above (Solana et al, 2006).The number and proliferation of a particular subset of 'natural' T cells with NK-cell and regulatory functions, bearing invariant V14J18 receptors (iNKT cells), is decreased in the elderly; however, whether these changes have any clinical impact is not yet known (R. Solana, Crdoba, Spain).Neutrophils from old people retain normal chemotaxis and superoxide-generation capacity, but are compromised in phagocytosis in the healthy elderly and more so in the traumatized elderly ( J. Lord, Birmingham, UK); these findings have important implications for infection in the elderly.Trauma, in the form of burn injury in mice, resulted in the death of old animals from infections that young animals were able to resist.This susceptibility of old mice correlated with higher levels of pro-inflammatory IL-6 and decreased T-cell function, and could be in part reversed by oestrogen treatment (E.J. Kovacs, Maywood, IL, USA).Dendritic cells-the essential bridge between innate and adaptive immunity-are similar in young and old people in terms of their response to cytokines (although those from the elderly secrete more IL-6 and tumour necrosis factor- (TNF)), surface phenotypes and morphology, whereas chemotaxis and, as with neutrophils, phagocytosis are impaired (S.Gupta, Irvine, CA, USA).Gene arrays indicate only a small number of differences between young and old dendritic cells, far fewer than in T cells.Nonetheless, functional impairment in antigen presentation was found, such that dendritic cells from young or old people stimulated naive CD8 cells equally well, but those from the elderly failed to stimulate CD4 cells appropriately.\t\n\nApoptosis-resistant cells that accumulate in old mice and humans-and fill the 'immunological space'-might be dysfunctional in several ways.In young mice, the number of T cells staining with soluble major histocompatibility complex (MHC)-peptide multimers carrying influenza epitopes was similar to the number of cells producing the antiviral and pro-inflammatory cytokine interferon- (IFN) on antigen stimulation.However, in old mice, the number of tetramer-positive cells exceeded the number of IFNproducers, indicating that some cells bearing antigen-specific receptors failed to respond appropriately to receptor ligation (H.Ertl, Philadelphia, PA, USA).This is similar to the situation in elderly humans, who have been found to accumulate large clonal expansions, primarily-and for unknown reasons-of cytomegalovirus (CMV)-specific CD8 cells (Pawelec et al, 2005).In the mice, this lack of reactivity was not due to poor antigen presentation by dendritic cells (Ertl).The reason for poor reactivity remains unknown; however, responses could be restored, in part, by vaccination using an adenovirus vector AdC68 that naturally infects chimpanzees rather than mice, as a way of improving immunizations by modifying the vaccine product.This might also be possible in humans by using better adjuvants for vaccination (E.Nagy, Vienna, Austria).Deciphering the mechanisms by which adjuvants enhance responses in order to design 'elderly-specific' vaccines will become increasingly important.This applies not only to infectious diseases but also possibly to vaccinating against cancer, as illustrated by differences in responses to anticancer immunizations in young and old mice.In a breast cancer model, preventive vaccination using DNA encoding certain cancer antigens was successful in protecting 90% of the young mice, but only 60% of the old mice, from developing metastases.This correlated with lower levels of IFN and IL-2 in old mice (C.Gravekamp, San Francisco, CA, USA).The production of IL-6, which is a potential inhibitor of vaccine-induced T-cell responses, was high in both young and old mice.Increasing IFN and IL-2, and depressing IL-6 production in the elderly, would therefore seem to be desirable.",
+      "\tAging and variability among immune cells\n\nHow and why the immune system becomes less effective with age are not well understood.Martinez-Jimenez et al. performed single-cell sequencing of CD4+ T cells in old and young mice of two species.In young mice, the gene expression program of early immune activation was tightly regulated and conserved between species.However, as mice aged, the expression of genes involved in pathways responding to immune cell stimulation was not as robust and exhibited increased cell-to-cell variability.",
+      "\t\nThe aging population is at a higher risk for age-related diseases and infections.This observation could be due to immunosenescence: the decline in immune efficacy of both the innate and the adaptive immune systems.Age-related immune decline also links to the concept of 'inf lamm-aging,' whereby aging is accompanied by sterile chronic inf lammation.Along with a decline in immune function, aging is accompanied by a widespread of 'omics' remodeling.Transcriptional landscape changes linked to key pathways of immune function have been identified across studies, such as macrophages having decreased expression of genes associated to phagocytosis, a major function of macrophages.Therefore, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.In this review, we discuss both molecular and cellular phenotypes of innate immune cells that contribute to age-related inf lammation.\t\n\nThe aging population is at a higher risk for age-related diseases and infections.This observation could be due to immunosenescence: the decline in immune efficacy of both the innate and the adaptive immune systems.Age-related immune decline also links to the concept of 'inf lamm-aging,' whereby aging is accompanied by sterile chronic inf lammation.Along with a decline in immune function, aging is accompanied by a widespread of 'omics' remodeling.Transcriptional landscape changes linked to key pathways of immune function have been identified across studies, such as macrophages having decreased expression of genes associated to phagocytosis, a major function of macrophages.Therefore, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.In this review, we discuss both molecular and cellular phenotypes of innate immune cells that contribute to age-related inf lammation.\tIntroduction\n\nThe human population is aging, which has led to the rise in prevalence of many so-called age-related diseases.Not only is the aging population much more susceptible to age-related diseases, they are also more susceptible to infections.For example, elderly individuals are at a higher risk of developing severe COVID-19 or complications from influenza infections [1,2].This increased chance of infection can be due to the decline of the function of the immune system, a phenomenon called 'immunosenescence' [3].Age-related changes in the function of the immune system are also accompanied by a chronic sterile inflammation, a mechanism dubbed 'inflamm-aging,' which is thought to promote age-related disease and functional decline [4].Inflamm-aging is associated with many different factors, most typically encompassing increases in pro-inflammatory cytokines tumor necrosis factor alpha [TNFa], interleukin 1 beta [IL1b] and interleukin 6 [IL6] [5].Although these cytokines may directly contribute to increased systemic inflammation.Age-related increase in genomic instability may itself also drive aspects of inflammaging.Indeed, re-activation of LINE-1 transposable elements during aging and in senescent cells has been proposed to drive an interferon response, thus contributing to sterile inflammation [20][21][22].In addition, chronic DNAdamage signaling itself, for instance in aged lymphocytes, may also render them more activation-prone through innate receptors even in the absence of infection [23].\t Immune decline is a hallmark of aging.  Aging associates with a state of chronic sterile inflammation.\t Aging associates with a state of chronic sterile inflammation.  Innate immune cells undergo widespread molecular and functional remodeling with aging.\t\n\nIn this review, we will focus on how innate immune cells act as key contributors to age-related inflammation (Figure 1).We will discuss both molecular and cellular phenotypes which have been described in the aging innate immune system, and how they could relate to the phenomenon of inflamm-aging and immunosenescence.\t\n\nImportantly, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.Indeed, aging is accompanied by widespread remodeling of transcriptional landscapes across tissues and cell types (reviewed in [33]).In addition, age-related inflammatory signatures at the transcriptional levels have been observed across species and tissues, suggesting that such 'omic' remodeling is a conserved aging response [34,35]."
+    ],
+    [
+      "\t\n\nKnowledge of genetic interrelationship between the biomarkers of aging may lead to the discovery of a downstream common pathway that summarizes aging processes; the list of biomarkers should be as comprehensive as possible via incorporating other well-known systems involved in aging in addition to the musculoskeletal system.Further development of the pleiotropy-based approaches will be useful for other studies of multiple related phenotypes which employ genome-wide associations to decipher genetics in the absence of disease endophenotypes, which is the case of human aging.With the advent of these approaches, new candidate genes may emerge for further pursuit.In its turn, discovery of the \"phenome of aging\" may translate into innovative diagnostic and therapeutic interventions to improve the overall health of older men and women.",
+      "\t\n\nBiomarkers of aging can be used to assess the health of individuals and to study aging and age-related diseases.We generate a large dataset of genome-wide RNA-seq profiles of human dermal fibroblasts from 133 people aged 1 to 94 years old to test whether signatures of aging are encoded within the transcriptome.We develop an ensemble machine learning method that predicts age to a median error of 4 years, outperforming previous methods used to predict age.The ensemble was further validated by testing it on ten progeria patients, and our method is the only one that predicts accelerated aging in these patients.",
+      "\t\n\nIt should be mentioned that although the objectives of those researchers sound encouraging and ambitious, the search for biomarkers of ageing for their application in the improvement of human health, and prevention of diseases related to ageing, will only increase the generation of data.The great part of the search for biomarkers has been as a result of the extensive studies of human cohorts, resulting in genomic, functional, phenotypic, and lifestyle data of the individuals studied (Table 13.1).Thus, due to the generation of these data and technological advances, possibly in the future, artificial intelligence programs will be able to reliably forecast the life of an individual, as well as the possible diseases that he may suffer in ageing; so these advances and discoveries will allow us to achieve a \"personalized medical treatment\" as a result of to the integration of biomarkers of ageing.\tMeg3\n\nDecrease in cell senescence [85] (continued) number of biomarkers that are candidates to determine human ageing.However, these biomarkers have considerable variability among different individuals because the ageing process has an intrinsic multicausal nature.So, a multisystemic integration of biomarkers to determine biological age is still reliably found.Currently, thanks to the different analyses performed using new technologies and new knowledge on the molecular basis, there are leading to the discovery of many Biomarkers classified according to their type and their modulation in ageing novel molecular markers.Some of these technologies are the omics techniques, such as metabolomics, proteomics or genomics, also induces data generation, offering an overview of new biomarkers of ageing.However, it remains to be clarified which markers can be an accurate, reliable predictor of ageing.Among the various studies carried out to solve these questions, the MARK-AGE study was a project supported by the European Commission.The main objective of this project was to carry out a population study of approximately 3200 subjects to identify a set of ageing biomarkers, which together with correctly established parameters, would measure the biology of an individual, compared to the result that would only have using a biomarker individually [72].\tIntegration of Biomarkers of Ageing\n\nBiomarkers of ageing allow estimating the biological age of an organism (Table 13.1) while providing information on their health status.Different studies are looking for the integrated use of multiple biomarkers, in order to make the estimation of health status more accurate.As we could see throughout this chapter, there are a large\t\n\nTo make significant progress in aging research, we urgently need molecular biomarkers for aging studies, particularly in humans.This chapter focuses on the inflammatory state, the markers of oxidative stress, and the hormonal profile which are the main functions that impact the development of aging and can be influenced by the gene and environmental variables in which human beings develop.",
+      "\tDiscussion\n\nMachine-learning can be applied as a systems biology approach, integrating multiple classes of biometric data to assess the importance of specific factors, while also predicting future outcomes.Whereas conventional assessments of disease identification exist, more detailed genomic and epigenomic testing is likely to reveal a comprehensive, systemic valuation of an etiology.To-date, studies have applied machine-learning algorithms in examining the physiological, biochemical, and/or genetic components of disease onset or progression [51].The advantage of our current study is through the assimilation of patient-matched data across a variety of critically impacted systems, providing an archetype for developing novel, descriptive, diagnostic measures through machine-learning algorithms that are specific for each disease type.By individually representing our datasets in Figs. 2, 3 and 4, we were able to reach more conclusive data in Fig. 5 by choosing the most predictive features for our final model.For the first time, a multi-omics, machine-learning approach was used to assess the progression and development of type 2 diabetes mellitus in a patient population, identifying potential biomarkers for cardiovascular risk and revealing the fundamental role of genetics in the pathology.\t\n\nIn the current study, machine-learning was used as a predictive tool to integrate cardiac physiological, biochemical, genomic, and epigenomic biomarker data in a patient-matched fashion and enable determination of type 2 diabetic status.In 50 patients, machine-learning algorithms revealed the interconnectedness between diabetic classification, mitochondrial function, and methylation status.Our study highlights how novel biomarkers can be used to augment existing diagnostic standards as well as provide new, and more precise, methods for identifying the development and severity of type 2 diabetes mellitus in potentially at-risk populations, such as those with prediabetes.While we examine physiological, biochemical, and molecular datasets using machine-learning algorithms, our goal was to understand which features possessed the best predictive accuracies and if these specific features could be used alone, or in conjunction, with HbA1c.The purpose for the inclusion of models that do not rise above 50% predictive accuracy was to contrast them against those models that do rise above 50% in the absence of HbA1c, to determine which biomarkers are the best overall predictors.\t\n\nThe quantity and diversity of omics-based approaches continues to expand.Convenience and increasingly inexpensive options for biometric-based valuations incite a growing demand for the incorporation and meaningful explanation of large and diverse patient datasets.The methodology outlined in this manuscript can serve as an archetype for the development and implementation of machine-learning to other disciplines seeking to evaluate disease progression.By using various health outcomes datasets, we were able to identify, and combine, the most prominent biomarkers into an accurate predictive algorithm engineered around 50 patients.While we have identified specific genetic features that are highly predictive in 50 patients, as a much larger patient population is applied to this model, the prioritization of other features is likely to occur, enhancing the diagnostic potential for the individual diabetic or prediabetic patient.Indeed, this is the advantage of using machine-learning models, in that they continue to learn and develop more accurate predictions as the number of features and sampled population grows.\tMolecular pathogenesis and machine-learning\n\nWhile clinical practice has recently experienced a surge in deep learning applications used for non-invasive imaging [52], implementing machine-learning algorithms to the fundamental biochemistry and cellular and molecular processes of the body is now only blossoming.Onset and progression of type 2 diabetes has been traditionally measured through blood glucose levels, but, the multifaceted aspects of the disease could create variability in prognosis between vastly different demographic and ethnic groups.Owusu Adjah et al. [14] recently identified BMI as a risk factor for determining ethnic group disposition to type 2 diabetes mellitus.Specifically, the relationship between BMI and increased incidence of diabetes mellitus is non-linear; some groups, such as South Asian populations, were more disposed to developing the disease even at lower BMIs.While the current Fig. 6 Overview of machine-learning pipeline implementing biological variables across a spectrum of gathered information.From the patient population undergoing coronary artery bypass graft surgery (CABG), physiological parameters (demographics, health reports, etc.) and atrial tissue were used for subsequent analyses.From cardiac tissue genomic (mitochondrial DNA), epigenomic (TFAM promoter CpG methylation), and biochemical (nuclear and mitochondrial function) were assessed.Cumulatively, the biological data was processed through tree ensembles in SHAP and validated through CART analysis with tenfold cross validation.Using these machine-learning algorithms, graphical depictions and biomarker feature importance are able to be derived, allowing for prediction of the onset and progression of diabetes.Ultimately, by using biological data at the genomic and epigenomic level, it allows for precision medicine approaches and more personalized diagnostics and prognostics.TFAM: transcription factor A, mitochondrial; mtDNA: mitochondrial DNA; CpG: cytosine nucleotide followed by a guanine nucleotide; CART: Classification and Regression Trees; SHAP: SHapley Additive exPlanations manuscript examines cardiovascular tissue, other less invasive approaches have been used to apply machinelearning algorithms.By retrieving blood from the basilica vein, circulating biomarkers were examined for their role in predicting early recurrence of atrial fibrillation following cryoballoon ablation [53].Support vector machines confirmed that decreased levels of creatine-kinase (CK-MB) and Troponin T (TnT) were associated with increased early recurrence of atrial fibrillation following cryoballoon ablation.Additionally, a unique, non-invasive approach for potentially diagnosing type 2 diabetes in patients was performed through the examination of toenails.Carter et al. [54], through a variety of machine learning algorithms, focused on 22 elements, including aluminum, cesium, nickel, vanadium, and zinc, and was able to get an AUC of 0.90 when predicting diabetic status using a random forest model.Similar to parts of the aims of this study, other groups have attempted to use machine learning to separate diabetic and non-diabetic patients without the inclusion of blood glucose or HbA1c [55].In a testing set of 13,700 patients from the Luzhou, China region, random forest machine-learning algorithms provided a 0.7225 accuracy when predicting diabetic status from physical examination data in the absence of blood glucose [55].Also using a random forest model, Tang et al. [56] revealed how CpG island methylation data, combined with microRNA expression profiles, can be instrumental in cancer pathogenesis; implementing this two-feature selection process, they were able to identify the best tissue specific features, ultimately allowing for the identification of the originating tissue where tumor progression began.In a similar fashion, the machine-learning algorithm HeteSim [57], which examines heterogeneous datasets and calculates their relatedness, was employed in ascribing how gene profiles can be related to phenotypic outcomes, specifically in the validation and prediction of genes classified within major diseases [58].",
+      "\tWhat do chemical biomarkers tell us about aging? Aging is not a homogeneous process\tThe nature of chemical biomarkers of aging\n\nCentral to the study of chemical theories of biogerontology is the definition of biomarkers of the aging process, chemical 'handles' that can be used to assess the progress of aging and the effectiveness of anti-aging strategies.As it turns out, most of the age-biomarkers measured today are products of non-enzymatic chemistry.Living organisms are complex mixtures of reactive chemicals, including dietary components, metabolic intermediates, side-products of metabolism, xenobiotics, drugs, etc.Reactions between the constituents of this mixture occur at random throughout the body, but evidence of the role of cumulative non-enzymatic chemistry in aging is most apparent in long-lived proteins, such as lens crystallins and tissue collagens.The increase in post-synthetic chemical modifications of crystallins with age results in an agedependent increase in brown color and fluorescence of lens proteins.These chemical modifications are associated with aggregation, crosslinking and insolubilization of lens proteins, leading gradually to the development of cataracts (Hoenders and Bloemendal 1983;Harding et al. 1989).Similar changes occur in collagens (Bailey et al. 1998) leading to decreased elasticity of the extracellular matrix, resulting, for example, in the age-dependent stiffening of tendons  Dilysine crosslink",
+      "\t\n\nPeople of the same chronological age have different aging states, which can be monitored using various biomarkers (Belsky et al. 2015).These markers are usually measurable indicators of a particular outcome or source of aging, such as phenotypical measures like frailty and molecular measures like DNA methylation dynamics (Schumacher et al. 2021;Lpez-Otn et al. 2023).Although informative, they are not always quantitatively predictive of an individual's true biological age, nor are they easy to obtain.The advancement of high-throughput screening platforms and extensive longitudinal studies has greatly facilitated the search for new noninvasive and quantitative biomarkers of aging.For instance, highthroughput sequencing allows unbiased multiomics profiling of DNA, RNA, and epigenetic changes during aging, providing a comprehensive view of senescence at tissue and single-cell levels (Solovev et al. 2020;Aging Atlas Consortium 2021).These omics data sets contain vast and noisy measurements of potential candidate markers and, consequently, require carefully designed computational models to identify and extract predictive signals from the data.However, construction of such models is often highly degenerate, yielding little overlap of identified biomarkers between studies and thus making results difficult to interpret (Thompson et al. 2018;Galkin et al. 2020).\t\n\nMost of the existing omics-based aging clocks have been constructed using data from bulk tissues, which neglect the variations in cell compositions and cell-to-cell aging heterogeneity.To gain a more detailed and nuanced view of cell type-specific molecular changes during aging, several studies have applied machine-learning models to single-cell transcriptomics and DNA methylation data (Trapp et al. 2021;Buckley et al. 2023).Despite their success in predicting chronological age within specific training contexts, these clocks are constrained by their applicability to a limited number of cell types and tissues.Their generalizability to other cell types and disease data, particularly in cases with ambiguous cell type identities, remains uncertain.Additionally, problems like data sparsity and batch effects are more pronounced in single-cell omics data, further complicating the identification of consensus aging markers and the interpretation of model results.Furthermore, as chronological age is often the only available measure of biological age, it becomes critical to determine whether the features learned from single-cell omics data can capture other dimensions of biological aging.",
+      "\t\n\nEach of these criteria deserves some amplification.A biomarker validation program would start with a list of candidate biomarkers, each known to be age-sensitive (by cross-sectional and/or longitudinal analyses) in adults.By hypothesis, some of these traits would reflect interindividual differences in the aging process, but each would also be sensitive to genetic and nongenetic factors that also vary among individuals, statistical \"noise\" that would interfere with the extraction of the \"signal\" attributable to aging itself.A correlation between age-sensitive immune parametersfor example, T-cell proliferation and T-cell cytokine production-would be relatively unhelpful in evaluating each of these parameters as potential biomarkers of aging, because the two assays are closely related and likely to be influenced by many factors unrelated to aging (e.g., recent infection, vaccination history, polymorphisms in immune system genes).However, a correlation between T-cell proliferation and, for example, muscle strength, or reflex speed, or lens protein cross-linking, or age at menopause, would be difficult to attribute to any obvious metabolic or pathophysiological mechanism other than linkage to some fundamental aging rate that might by hypothesis retard or accelerate changes in a wide range of age-sensitive traits.",
+      "\tMultiomics technology\n\nThe broad diversity of omics biomarkers that have been used to assess biological responses provides new opportunities to understand the impact of the environment on the risk of age-related diseases.For example, the multiomics analysis and integration method produces a priority list of multiple sets of biomarkers, which together reflect the molecular responses of the exposome.Each of these data warrants integration into a biomarker panel to aid physicians in developing age-related disease diagnoses and prognoses [78].",
+      "\t\n\nOverall, demonstrating that a particular intervention is affecting human aging, as done in model organisms, is virtually impossible.Interventions, including drugs, emerging from basic research on aging will probably target specific age-related pathological conditions and/or dysfunction.Subsequent studies of health biomarkers and multiple age-related diseases may reveal broader effects.Success in animal models or short-term human studies may be sufficient to convince potential patients of the usefulness of particular dietary supplements or approaches, as exemplified by those voluntarily undergoing CR (http://www.crsociety.org/),which can serve as basis for further studies (Soare et al., 2011).\t\n\nTo facilitate target gene prioritization, a number of additional approaches may be employed.For example, in silico studies of transcriptional regulation can allow the identification of upstream regulators (for review, see de Magalha es et al., 2010).Furthermore, an emerging approach to study the complex interactions between the multiple components of biological systems is network biology (Baraba si et al., 2011).Given the complexity of aging, network approaches may be particularly suited to identify crucial regulators of its modulation by the environment.For instance, knowing the protein-protein interaction network of candidate proteins allows the identification of hubs, proteins with a large number of interactions, which tend to be more biologically relevant (Fig. 3).Together with other biological (e.g., kinases and receptors are often seen as promising drug targets), medical, and strategic considerations already used for target selection in drug discovery (for review, see Knowles and Gromo, 2003), the integrated knowledge of aging-related pathways can help identify suitable targets for drug discovery.In addition, the advent of largescale databases of compounds and drugs, such as Drug-Bank (Wishart et al., 2008), STITCH (Kuhn et al., 2008), and the Connectivity Map (Lamb et al., 2006), paves the way to cross-linking longevity/CR-associated genes with drug databases to identify candidate molecules for effects on aging.\t\n\nWe now know of hundreds of genes that regulate aging in model organisms, dozens associated with longevity in humans, and hundreds differentially expressed with age.This vast amount of information yields increased power for personalized and stratified medicine, for identifying biomarkers of aging, and for drug development to extend lifespan and ameliorate age-related diseases.Overall, it gives us a blueprint (albeit still imperfect) of how aging is controlled that we can use to potentially manipulate the basic aging process, whatever its underlying molecular mechanisms may be.Moreover, our knowledge of nutrient-sensing pathways that mediate the effects of CR has greatly increased in recent years, opening new opportunities for drug discovery and ultimately for perhaps developing an antiaging pill that retards aging with minimal side effects.",
+      "\tIntegrating genomics and biomarker research\n\nOnce the use of established biomarkers of biological age is standardized, the biomarker information can be integrated into studies aimed at finding causal determinants of aging and longevity.An example of an integrated approach to identify lifespan regulating loci is represented by testing whether genetic variants associated with potential biomarkers also associate with longevity.To date, GWAS have identified many genetic variants that associate with age-associated traits, such as leukocyte telomere length and features from glycome and metabolome profiles [84][85][86].The joint effect of the majority of these variants on aging and longevity still needs to be determined.One study identified a haplotype in the TERT gene that was associated with increased telomere length and longevity, which indicates that genetic variants associated with telomere length regulation might also play a role in longevity [87]."
+    ],
+    [
+      "\tSeveral studies have shown\nthat the systemic milieu regulates stem cell decline during aging. Liang et al. showed\nthat HSCs have a reduced ability to home to the bone marrow and spleen after\ntransplantation into old versus young recipients (Liang et al. , 2005). Further experiments\ndemonstrated that the muscle stem cell niche adversely effects stem cell function as\nevidenced by the restoration of old stem cell regenerative potential upon exposure to a\nyoung systemic microenvironment (Conboy et al. , 2005; Conboy and Rando, 2005).\tHowever, studies do indicate that aged tissues have a diminished capacity to return to a\nhomeostatic state after exposure to stress or injury, therefore indicating a defect in stem\ncell function during the aging process. Since the HSC population provides an ideal\nmodel to study stem cell aging, it is necessary to elucidate the mechanisms of\nhematopoietic aging and expand the findings to other tissues and organ systems. Theories of Aging and Age Related Epigenomic Changes\nThere are two major theories of organismal aging: evolutionary and damage\nbased.\tHSCs as a Model for Stem Cell Aging\nWhen studying aging it is important to choose an appropriate model system. For\ninstance, cells (such as skin and blood) that undergo continuous turnover are removed\nfrom circulation long before they have time to feel the effects of aging, and certainly long\nbefore they could exert an effect on tissue function. The predominant substrates for\naging, thus it seems, would be long-lived cells in the organism, namely tissue specific\nstem cells, since this population is exposed to both intrinsic and extrinsic effectors of\naging throughout the lifespan of an individual.\tWith\nthis in mind, it has been hypothesized that the aging or functional failure of tissuespecific stem cells, which fulfill this job, may limit tissue repair and renewal, therefore\ncontributing to overall organismal aging (Krtolica, 2005; Van Zant and Liang, 2003). Because of the unprecedented experimental model systems that are available for the\nexploration of HSCs, stem cell aging research in the field of hematology has been the\nsubject of extensive studies. Indeed, the hematopoietic system has served as an important\nmodel for advancing our understanding of stem cell biology and its association with\naging.",
+      "\t\n\nThe several lines of evidence support the hypothesis that essential metabolic pathways interconnected with environmental factors and genetic background are involved in the appearance of different markers of cellular senescence.They have emerged as potential regulators of cellular senescence, particularly through those pathways involved in the maintenance and repair of stem cells and progenitor cells: mitochondrial integrity, mitotic competence, and eradication of senescent cells.The complexity of events that are under the control of the genetic programs induced in response to environmental challenges creates the need for further studies that must be performed to unravel the biological roles of the highly dynamic aging process through different tissues and different stages of cell life.The increasing research across different species has allowed the identification of conserved processes associated with the biology of aging.However, it is essential to consider that information from lower organisms cannot be generalized, since worms do not develop age-associated diseases such as osteoporosis, arthritis, or Alzheimer's disease.",
+      "\t\n\nThere is growing evidence that noncell-autonomous mechanisms play a critical role in orchestrating vascular aging processes (Figure 1).Aging-induced alterations in vasoprotective endocrine factors are of particular importance.Such changes include an age-related decline in circulating levels of growth hormone, 215 IGF-1, 216 and estrogens, all of which regulate multiple aspects of endothelium-dependent vasodilation, 217 autoregulation of blood flow, 218 vascular structural remodeling, atherogenesis, 219 and angiogenic processes. 220he impact of circulating factors on aging phenotypes was also demonstrated by studies using mice with heterochronic parabiosis, which involves surgically connecting the circulatory system of a young and an aged mouse. 221erebromicrovascular density typically declines with advanced age, 222 and there is initial evidence that circulating antigeronic factors (which reverse/prevent development of aging phenotypes) present in young mice can rejuvenate microvascular network architecture in aged heterochronic parabionts. 221he antigeronic circulating factors present in young mice are currently unknown, and the previously proposed role for GDF11 (growth differentiation factor 11) 221 remains controversial.Future studies should identify additional antigeronic factors that might be targeted by interventions to extend vascular health span.Progeronic circulating factors increase with age and impair tissue homeostasis in young animals.There is initial evidence that mediators secreted by senescent cells (eg, inflammatory cytokines, such as TNF- 35 ) may serve as progeronic circulating factors.Further studies are warranted to identify additional progeronic proteins and determine their impact on atherogenesis, endothelial function, blood-brain barrier integrity, and microvascular function in aging.\t\n\nAdditional evidence to support a central role of antigeronic circulating factors governing vascular aging processes is derived from studies on caloric restriction-a dietary regimen, which improves health and slow the aging process in evolutionarily distant organisms. 223Caloric restriction was shown to promote a youthful endothelial phenotype by upregulating and activating eNOS in aged animals [223][224][225] and perhaps humans. 226 critical role of antigeronic circulating factors in vasculoprotective phenotypic responses induced by caloric restriction was first indicated by the observations that in vitro treatment of cultured aged endothelial cells with sera derived from caloric restricted animals mimics phenotypic effects observed in vivo during caloric restriction, promoting anti-inflammatory and proangiogenic effects. 42,227Treatment with sera derived from caloric restricted animals upregulates SIRT1 228 ; however, the exact nature of the circulating factor responsible for this effect remains elusive. ][231] Human studies are needed to identify novel progeronic and antigeronic circulating factors and their cofactors, activators, or inhibitors/antagonists and to seek associations with vascular aging phenotypes.Future studies should also identify cellular origins of circulating progeronic and antigeronic factors that impact vascular aging and characterize pathological conditions that alter their levels in circulation with aging.Further, mechanistic studies describing the cellular effects of progeronic and antigeronic circulating factors in the vascular wall are warranted.",
+      "\t\n\nMitochondrial-derived peptides (MDPs) in aging-related phenotypes",
+      "\t\nBackground: Aging is believed to have a close association with cardiovascular diseases, resulting in various pathological alterations in blood vessels, including vascular cell phenotypic shifts.In aging vessels, the microRNA(miRNA)mediated mechanism regulating the vascular smooth muscle cell (VSMC) phenotype remains unclarified.MiRNA microarray was used to compare the expressions of miRNAs in VSMCs from old rats (oVSMCs) and young rats (yVSMCs).Quantitative reverse transcription real-time PCR (qRT-PCR) and small RNA transfection were used to explore the miR-542-3p expression in oVSMCs and yVSMCs in vitro.Calcification induction of yVSMCs was conducted by the treatment of -glycerophosphate (-GP).Alizarin red staining was used to detect calcium deposition.Western blot and qRT-PCR were used to investigate the expression of the smooth muscle markers, smooth muscle 22 (SM22) and calponin, and the osteogenic markers, osteopontin (OPN), and runt-related transcription factor 2 (Runx2).Lentivirus was used to overexpress miR-542-3p and bone morphogenetic protein 7 (BMP7) in yVMSCs.Luciferase reporter assay was conducted to identify the target of miR-542-3p.Results: Compared with yVSMCs, 28 downregulated and 34 upregulated miRNAs were identified in oVSMCs.It was confirmed by qRT-PCR that oVSMC expressed four times lower miR-542-3p than yVSMCs.Overexpressing miR-542-3p in yVSMCs suppressed the osteogenic differentiation induced by -GP.Moreover, miR-542-3p targets BMP7 and overexpressing BMP7 in miR-542-3p-expressing yVSMCs reverses miR-542-3p's inhibition of osteogenic differentiation.Conclusions: miR-542-3p regulates osteogenic differentiation of VSMCs through targeting BMP7, suggesting that the downregulation of miR-542-3p in oVSMCs plays a crucial role in osteogenic transition in the aging rat.\t\n\nBackground: Aging is believed to have a close association with cardiovascular diseases, resulting in various pathological alterations in blood vessels, including vascular cell phenotypic shifts.In aging vessels, the microRNA(miRNA)mediated mechanism regulating the vascular smooth muscle cell (VSMC) phenotype remains unclarified.MiRNA microarray was used to compare the expressions of miRNAs in VSMCs from old rats (oVSMCs) and young rats (yVSMCs).Quantitative reverse transcription real-time PCR (qRT-PCR) and small RNA transfection were used to explore the miR-542-3p expression in oVSMCs and yVSMCs in vitro.Calcification induction of yVSMCs was conducted by the treatment of -glycerophosphate (-GP).Alizarin red staining was used to detect calcium deposition.Western blot and qRT-PCR were used to investigate the expression of the smooth muscle markers, smooth muscle 22 (SM22) and calponin, and the osteogenic markers, osteopontin (OPN), and runt-related transcription factor 2 (Runx2).Lentivirus was used to overexpress miR-542-3p and bone morphogenetic protein 7 (BMP7) in yVMSCs.Luciferase reporter assay was conducted to identify the target of miR-542-3p.Results: Compared with yVSMCs, 28 downregulated and 34 upregulated miRNAs were identified in oVSMCs.It was confirmed by qRT-PCR that oVSMC expressed four times lower miR-542-3p than yVSMCs.Overexpressing miR-542-3p in yVSMCs suppressed the osteogenic differentiation induced by -GP.Moreover, miR-542-3p targets BMP7 and overexpressing BMP7 in miR-542-3p-expressing yVSMCs reverses miR-542-3p's inhibition of osteogenic differentiation.",
+      "\t\n\nThe major question is whether replicative senescence does play a role in human aging.Several studies have shown an inverse relationship between donor age and the replicative life span in vitro for fibroblasts or MSC [13,44,45].This effect is usually relatively small with a high variation between different donor samples [12,46].At least some of the variability was attributed to differences in donor health status, conditions for the biopsy and the initial CFU-F frequency in the bone marrow sample [47].Furthermore, the pace of senescence might be affected by the culture conditions [19,48].In MSC preparations used in this study we did not discern any age-associated effects on replicative senescence.If the number of cumulative population doublings was not significantly affected by aging it is all the more surprising, that there was a significant association between age-induced gene expression changes and replicative senescence.These results indicate that the molecular sequels of aging in vivo and replicative senescence in vitro are based on similar mechanisms.",
+      "\t\n\nFinally, we asked whether additional cellular components of the immune system also show increased transcriptional variability upon aging.",
+      "\tSystemic aging has been more formally proposed as the hormonal\n\n3\ncontrol of aging, where changes in humoral factors with age can cause system-wide\nchanges in the homeostatic condition (Wise, Krajnak et al. 1996). Support for this idea\nhas gained traction from studies of mice expressing a mutant form of the KLOTHO gene\nencoding a protein hormone that leads to phenotypic changes characteristic of accelerated\naging (Kuro-o, Matsumura et al. 1997). Conversely, when the wild-type KLOTHO gene\nis overexpressed in mice it leads to a modest yet significant increase in both male and\nfemale lifespan (Kurosu, Yamamoto et al. 2005).\tStudies of invertebrate systems such as C. elegans and D. melanogaster\nhave yielded keen insight into stem cell biology and mechanisms of aging, but it has\npredominantly been the study of the mammalian hematopoietic system that has led to the\ncurrent understanding of the physiology of hematopoiesis. The utilization of mouse\ngenetics has only recently been fully realized as a tool as it was this mammalian model\nthat yielded the breakthrough discoveries of Till and McCulloch (Till and McCulloch\n1961).",
+      "\t\n\nOur results indicate that cell identity influences multiple aspects of aging, highlighting the importance of aging studies at the single-cell level.However, it remains difficult to identify which age-related changes are causal and link molecular changes at the level of individual cell types to physiological aging phenotypes, like reduced glomerular filtration rate or decreased pulmonary regeneration.Future single-cell studies may focus on collecting additional time points and phenotypes throughout the aging process, allowing for time series-based causal inference methods (Granger 1969;Bar-Joseph et al. 2012;Finkle et al. 2018;Qiu et al. 2018;Lu et al. 2019) to reveal the relationships between the molecular players of aging.Functional challenges, such as the differentiation of stem cells during regeneration or the stimulation of immune cells during infection, would also help dissect how transcriptional aging magnitudes and differential gene expression influence tissue function.Single-cell measurements collected during functional challenges may also reveal the dynamics of perturbation and subsequent return to homeostasis necessary to evaluate \"resilience\" in a given cell type (Kirkland et al. 2016;Hadley et al. 2017).\t\n\nAt both the molecular and functional level, a host of aging phenotypes and associated mechanisms have been revealed in individual cell types (Shaw et al. 2010;Chakkalakal et al. 2012;Keyes et al. 2013;Liu et al. 2013;Flach et al. 2014;Blau et al. 2015;Brack and Muoz-Cnoves 2016;Keyes and Fuchs 2018).Although some of these studies present unique features of aging within individual cell identities, it is difficult to compare them systematically because of differences in experimental conditions and assay methodology.Using traditional molecular biology assays, it is difficult to measure high-dimensional molecular phenotypes across multiple cell identities, making large-scale comparisons of aging phenotypes across cell identities intractable.The recent development of single-cell RNA-sequencing (scRNA-seq) has ameliorated this limitation, allowing for measurement of transcriptional features across all prevalent cell identities in a tissue in a single experiment.\t\nAging is a pleiotropic process affecting many aspects of mammalian physiology.Mammals are composed of distinct cell type identities and tissue environments, but the influence of these cell identities and environments on the trajectory of aging in individual cells remains unclear.Here, we performed single-cell RNA-seq on >50,000 individual cells across three tissues in young and old mice to allow for direct comparison of aging phenotypes across cell types.We found transcriptional features of aging common across many cell types, as well as features of aging unique to each type.Leveraging matrix factorization and optimal transport methods, we found that both cell identities and tissue environments exert influence on the trajectory and magnitude of aging, with cell identity influence predominating.These results suggest that aging manifests with unique directionality and magnitude across the diverse cell identities in mammals.\t\n\nAging is a pleiotropic process affecting many aspects of mammalian physiology.Mammals are composed of distinct cell type identities and tissue environments, but the influence of these cell identities and environments on the trajectory of aging in individual cells remains unclear.Here, we performed single-cell RNA-seq on >50,000 individual cells across three tissues in young and old mice to allow for direct comparison of aging phenotypes across cell types.We found transcriptional features of aging common across many cell types, as well as features of aging unique to each type.Leveraging matrix factorization and optimal transport methods, we found that both cell identities and tissue environments exert influence on the trajectory and magnitude of aging, with cell identity influence predominating.These results suggest that aging manifests with unique directionality and magnitude across the diverse cell identities in mammals.",
+      "\tDiscussion\n\nConsequences of disease as well as age exert profound influences upon cells including alteration of gene expression, metabolism, functional competency, replicative potential, and more [10,18].Certain features of aged cells are exacerbated or mitigated by environmental conditions in host tissues such as oxidative stress, nutrient status, inflammatory / cytokine production, and pathological changes [5,7,40,42].Many of these conditions can be recapitulated in cell culture studies with treatments that mimic the aged tissue environment [6,37].Studies using established cell lines to study biological consequences of aging are of limited value for extrapolation to the complex in vivo mileau.In situ studies have provided significant insight regarding adaptations and distinct features of aged cells [9,46,55], but whether the characteristic phenotypic state of aged cells is retained following isolation and culture expansion is poorly understood.Moreover, conditions of culture expansion inherently favor cells with the highest proliferative and survival potential.Thus, it is unclear to what extent culture expansion allows hallmarks of aging to persist when harvesting cellular samples from aged tissue and subjecting them to multiple passages after initial isolation.",
+      "\tConcluding remarks and future perspectives\n\nAging research has rapidly expanded over the past two decades, with studies ranging from lifespan-extending  [68,69,71].However, when their effect on cell death and senescence leads to stem cell loss and tissue degeneration, they might contribute to aging [66,67]."
+    ],
+    [
+      "\t\n\nHowever, the simplest solution to restoring pathological disturbances in the composition of the gut microbiota may be a change in dietary habits.Diet has been shown to strongly affect the composition of the microbiome (73).When obese humans were put either on a fatrestricted or carbohydrate-restricted low-calorie diet, an increase in the abundance of Bacteroidetes and a decrease in Firmicutes was reported (12).In another study, diet-induced weight loss versus weight-stabilization interventions in obese humans increased intestinal microbial gene richness and was associated with a reduced systemic inflammation (74).These data corroborate with another controlled diet intervention study in 98 human subjects showing that certain dominant gut microbial communities, or \"enterotypes,\" correlated with specific kinds of diets (73).For example, Bacteroides was associated with a protein-rich diet, whereas Prevotella correlated with a fiber-rich diet; moreover, gut microbiota composition could be altered within 24 h whereas enterotype remained stable during the 10 days of the study.Based on this rapid and dramatic plasticity of intestinal microbiota composition, there is a specific need to determine intestinal microbiota composition in a standardized way (e.g., sequencing several fecal samples per person over a specific time point while taking dietary intake and medication use into account).",
+      "\t\n\nWe next performed partial correlation analysis to investigate whether exercise-induced compositional changes in microbiota were associated with improvements in clinical parameters independent of body weight, fat mass, and visceral fat.We found that after adjustment for body weight and adiposity, associations between alterations of microbial species and improvements in insulin sensitivity-related indexes and a cluster of other metabolic features remained significant (Figure 3).At the community level, alteration in the gut microbiota was significantly associated with the percentage reduction of HOMA-IR (p < 0.01, ADONIS).Among the 19 species significantly correlated with the improvements of glucose homeostasis and insulin sensitivity, Ruminococcus gnavus, Alistipes shahii, Streptococcus mitis group, Eubacterium hallii, and Escherichia coli showed the strongest associations (Figure 3).Consistently, most of these species were also found to be differentially altered between responders and non-responders (Figure 2E).Taken together, the above findings imply that distinct changes of these species may underlie the difference in the improvement of glycemic homeostasis in response to a standard exercise regimen.",
+      "\t\n\nOn the other hand, studies on centenarians and supercentenarians have evidenced the adaptation of the microbiota to the physiological changes of the long aging process.It has been demonstrated that the microbiota on this population maintains the health and promotes the survival.Additionally, a relationship between a healthy microbiota and longevity had been proposed [44].A possible pathway is an immunological and metabolic regulation linked to the increase of bacterial compounds like Christensenellaceae, Akkermansia, and Bifidobacterium [44,45].\t\n\nFigure 9.1 depicts a visual representation of the gut microbiota composition throughout the lifespan.Variations between individuals and within an individual throughout the lifespan can be seen.In this respect, it can be said that the concentration of Bacteroidetes grows as an individual does, from 12.6% for newborns to 57% for older adults.Conversely, Actinobacteria composition reduces with age until it reaches 0.4%, and the Firmicutes, Proteobacteria, and other microbial are maintained relatively stable throughout life in healthy adults and decay at old age [20][21][22].\t\n\nThe human holobiont (commensal microbes and their multicellular eukaryotic host) constitutes a highly integrated system, which undergoes dynamic changes through time as it integrates and responds to signals from the environment.Microbiome research and aging is flourishing as we better understand the bidirectional interactions, and its evolution with a life-course perspective for the gut microbiota undergoes dynamic changes during host aging.Changes in host intestinal cell Foreword vii composition and architecture occurring during aging are matched by a decrease in the microbiota taxonomic diversity.Age-related decrease in taxonomic diversity leads to larger population size for a few age-associated microbial species, increasing the chances for the evolution of novel potentially pathogenic microbial strains, which have been related both to neurodegeneration and frailty.This knowledge positions the microbiome as a promising element for translational research.\t\n\nAll the information given by the aging research allows knowing that the microbial composition has an essential role in the establishment of cellular and tissue homeostasis.Additionally, it is known that age-dependent changes in the microbial composition can contribute to increasing of frailty and development of diseases during the late stages of life [42,43].\t\n\nAlthough the causes that lead to changes in the composition and function of the microbiota during aging are still unknown, the evidence has established that the local microbiome plays an essential role in human health.\t\n\nTherefore, research in the field has demonstrated that aging is a potential modifier of the composition and function of the human microbiome.Figure 9.3 shows the local composition of the microbiome in an average older adult.It can be seen that Bacteroidetes and Firmicutes species are the most prevalent in this age.\tMicrobiome Research and Aging: A Clinical Perspective\n\nAging is characterized by the accumulation of damage at the molecular level (DNA and proteins) and dysfunction of the organelles [31][32][33].In addition to senescent cells and compositional changes in the extracellular compartment, these changes are determinants of the organic and systemic decline [34][35][36].The microbiota reacts dynamically to these environment changes by altering the metabolic function and composition of individual bacterial species.\tConclusions\n\nDuring the last years, significant advances in the field of microbiome and aging research have been carried out; new approaches for its study have allowed the understanding of the genomic nature of the microbiota.In this regard, the introduction of metagenomics had increased knowledge of the genes that potentially allow microbes to influence their hosts in unexpected ways.Thanks to these advances, it is well known that microbiota constitutes an essential determinant of the health and longevity of humans.\t\n\nFig. 9.1 Gut microbiota throughout lifespan\tMicrobiome and Age-Related Neurodegenerative Diseases\n\nDifferent microorganisms such as bacteria, fungi, archaea, and viruses compose the human intestinal microbiota that represents, in physiologic conditions, a perfect commensalism association with their host [51,52].In general, the human intestinal microbiota is shaped by the healthy microbiota (bacteria that normally colonize the intestine) and opportunistic bacteria (which are the agents responsible for infections).Among the billions of symbiotic microorganisms that compose the intestinal microbiome, four bacteria phyla are mainly reported in adults, i.e.Firmicutes (~51%), Bacteroidetes (~48%), Proteobacteria, and Actinobacteria, (1%) [53].Lactobacteria species stand out among the normal microbiome (Lactobacillus rhamnosus, Lactobacillus acidophilus, and Lactobacillus plantarum), Bifidobacterium (B.bifidum), Enterococci, Propionobacteria, and Peptostreptococci.In the same way, opportunistic bacteria include the Bacteriodes spp.Bacilli, Clostridia, Enterobacteria, Actinobacteria, Peptococci, Staphylococci, and Streptococcus [54].Several factors, such as diet, hygiene, antibiotic exposure, and modify the intestinal microbiota [55,56].Interestingly, age also contributes significantly to the microbiome modification; in fact a recent publication highlights the vital role that represents the host aging in the microbial evolution since as the host get aged the organism experiments molecular and functional changes that induce shifts to the microbial niche [57], nevertheless, for detailed information about changes in microbiome during aging, please refer to the Chap.9 in this book.In the following paragraphs, we discuss the recent data about the relationship between the pathogenesis of the two most prevalent ND and the microbiome, which represents a new field of research.\t\n\nDiet can be a potent gut microbiome modifier.For this reason, numerous studies have been conducted to demonstrate the impact of specific diet components on the diversity of the gut microbiota [8].The results of many of these studies have proved that probiotics and prebiotics consumption are a feasible alternative, especially for specific population groups such as older adults [59].\t\n\nMany areas of opportunity can be mentioned.However, modulation of the microbiome by extrinsic factors can be a way to apply the actual knowledge in the clinical setting.Nowadays, it is possible to ensure that lifestyle and diet play a significant role in determining the microbiome.In this respect, novel therapies, as fecal transplantation adds to the traditional dietary interventions, both demonstrated to be a potential therapeutic approach for the aging population.\t\n\nIt is well known that aging is a risk factor for neurodegeneration and dementia [58]; nevertheless, recent studies support the idea that gut microbiota may have an effect on the brain and the behaviour of patients, since the evidence suggests that some metabolites secreted by the intestinal microbiota can affect in a certain way, the cognitive capacity of patients diagnosed with ND [59][60][61][62][63].This hypothesis is not entirely new since several decades ago, the concept that bidirectional communication between the CNS and the intestinal organs plays a role in emotional regulation [64,65].Four decades later, the hypothesis that the brain has a regulation of the gastrointestinal tract arose and with the help of the murine model, the existence of the brain-gut axis was reported [66].This axis is carried out through the neuroendocrine and neuroimmune system, working together with the sympathetic and parasympathetic arms of the autonomic nervous system and the enteric nervous system.",
+      "\t\n\nChanges in the gut microbiota in terms of composition and functionality during the process of aging have previously been reported [19,20,51] and it has been postulated that these changes might contribute to the development of immunosenescence and inflammaging [18,52].To establish whether the enhanced expression of genes playing a role in the immune system are due to modifications in the microbiota we measured the total number of all bacteria and of the two most prominent phyla colonizing the colon, Bacteriodetes and Firmicutes, in the luminal content of the colon.We did not observe aging-related changes.More advanced techniques like pyrosequencing are required to determine whether total number of bacteria and changes in the composition of the microbiota might play a causal role in the observed changed expression of immune-related genes in the colon of our aging mice.Although it is difficult to assess the physiological consequences of the enhanced expression of genes involved in inflammation and immune response, it seems most likely that this effect is important for the health status of the aging colon.",
+      "\tSignatures of aging in gut\n\nFor gut or the digestive system, six clusters of age-associated genes had significant enrichment of functional annotations (Fig. 2C; Supplemental Table 10).Aging in gut was found to be associated with down-regulation of genes (Clusters 1, 2, 3, and 4) participating in oxidative phosphorylation, aromatic compound metabolism, muscle contraction, amino sugar metabolism, regulation of apoptosis, and vesicle transport.Aging was also associated with up-regulation of genes (Clusters 5 and 6) involved in regulating various physiological processes, amino acid metabolism, and regulation of transport.These results suggest that metabolic pathways, especially nutrient intake and energy production, are primarily affected during aging of gut, which are the fundamental function of the digestive system.",
+      "\t\n\nSequencing of bacteria species within our gut, collectively labeled the gut microbiome, explains individual differences in the metabolism of consumed food with potential associations with body weight (Karlsson, Tremaroli, Nielsen, & Backhed, 2013).Gut permeability to bacteria is further associated with obesity and obesity-related inflammation (Teixeira et al., 2012).Over time, these mechanisms will more fully be integrated into the overarching models of obesity.",
+      "\tThe microbiome and weight change\n\nThe human microbiome may play a significant role in the etiology of obesity in both humans and animal models (64).Hosted in the gastrointestinal tract, the gut microbiome is part of a large endocrine organ that regulates not only nutrient sensing and metabolism but also satiety and energy homeostasis.The millions of microorganisms comprising the complex intestinal \"superorganism\" perform a number of functions for host health, including food processing, breakdown and metabolism of indigestible nutrients, pathogen displacement, synthesis of vitamins, and regulation of body weight (65).They play such an important role that we now know that microbiota disruptions in early life can have long-lasting effects on body weight in adulthood (66).The host bacterial composition has been shown to adapt in response to dietary factors and in response to weight loss.Diet or surgically induced weight loss promote alterations in the gut that can impact the efficacy of the treatment strategies (67,68).Specific bacterial species can have influences by themselves.For example, the archaeon Methanobrevibacter smithii, has an enhanced ability to metabolize dietary substrates or end products of the metabolism of other bacteria, thereby increasing host energy intake and weight gain (69).",
+      "\tThis microbial\ncommunity is established early in life, influenced by maternal and environment factors and\nable to impact the health of the host [2]. For example, early studies provided evidence that\ndiet plays an important role in the composition of gastrointestinal microbiota. Specifically,\ntransition to a low-fat diet in overweight humans led to a gut microbial composition similar\nto that of healthy controls [3, 4]. Also, gnotobiotic animals displayed substantial weight gains\nfollowing exposure to a complex gastrointestinal microbiota from overweight individuals\n[5, 6]."
+    ],
+    [
+      "\tCONCLUSIONS\n\nOur purpose in this review is to outline the prospects of unifying mechanism in the genetics of aging.In case after case, from mice to worms to flies to yeast, genetic variants that modify metabolism also modify life span.These effects, collectively, are as general as that of caloric restriction, which also increases longevity and resistance to stress in many situations.The evolutionary theory of aging proposes that the life span is indirectly selected on the basis of the reproductive schedule.In turn, the reproductive schedule is coordinated by neural and endocrine mechanisms in multicellular organisms.Therefore, to consider that genes determining the life span could be expressed in neuronal and endocrine cells in diverse animals is no longer far-fetched.Consistent with this hypothesis are experiments in Drosophila and C. elegans in which life span was manipulated by the expression of genes in specific neurons.Genetic approaches may, thus, be able to identify a set of circuits that regulate longevity that were established in ancestral metazoans.",
+      "\tGenetic Programs\n\nAs stated above, the universality of aging phenotypes within a species argues for an underlying genetic program.The redistribution of the Sir complex from telomeres to the nucleolus in yeast is a specific molecular While the effects of these hormones on specific orthan rats fed ad libitum, with a consequent decline in the incidence of hepatocellular carcinoma (Muskhelishvili gans are apparent, their relation to the aging process itself, if any, is not yet clear.To our knowledge, there has occurred in the past 200 years.However, slowing the aging process may increase vitality and quality of has been no animal study in which hormone supplementation extended maximum life span.However, the recent life over the entire life span of individuals.In this regard, it is noteworthy that calorically restricted rodents have findings in C. elegans provide a basis to believe that humoral factors may turn out to play an important role an extended life span that is relatively free of disease.For society, the implications of slowing the aging pro-in at least some aspects of human aging.cess are more complex.Of course, in an increasingly overpopulated world, it would be important to offset Perspective any significant effects on longevity with a compensatory Recent advances in the study of aging indicate that this reduction in birth rates.In fact, in many industrialized process is amenable to molecular analysis and may be countries, the current birth rate is sufficiently low to relatively simple.The potential of single gene mutations afford zero or negative growth.Most importantly, if the to greatly extend life span in model systems suggests slowing of aging is associated with improved health and that relatively few limiting cellular or organismal proproductivity of long-lived individuals, there may be a cesses control the rate of aging, at least in these species.",
+      "\t\n\nThen we have those pharmaceutical strategies that are www.impactaging.combased on emulating the pathways implicated in the response of lifespan to dietary restriction, particularly sirtuin-targeting agents like resveratrol [e.g.25].Again, like hormone manipulation, these pathways are heavily bound up with the regulation of reproduction, making the curtailment of the cost of reproduction the most likely mechanism by which the beneficial effects of emulating dietary restriction are achieved [cf. 26].This is a strategy in which longevity is increased by metabolic refrigeration, pseudo-hibernation, or curtailing functions [11].From the standpoint of evolutionary biology, this is, again, not an extension of the period of adaptation.It is instead trading one set of adaptations off against another.Most people do not regard curtailing their metabolism, cognition, affective stability or reproductive functions as a useful approach to the problem of aging.Nonetheless, some are willing to trade-off some of their adaptive functions for an increased lifespan, and for them this \"anti-aging\" strategy will have its attractions.",
+      "\tMetabolism\n\nStudies show that calorie restriction is the most consistent means to prolong life expectancy and health across several experimental models [55], ranging from yeasts to primates.It not only increases life expectancy, but it also delays the onset of many features and hallmarks of ageing, including age-related diseases.Transcriptional profiles are currently being applied and investigated.One of them is a caloric restriction (CR), which increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes; this has a direct intervention in the repair of DNA damage.Data from human trials (such as CALERIE, Biosphere-2 and CRON) indicate that moderate CR accompanied by adequate nutrition has positive effects on health and dramatically reduces the multiple metabolic factors involved in the pathogenesis of disease chronicles, including type 2 diabetes, heart and cerebrovascular diseases, and cancer [56].",
+      "\t\n\nLimitations of translating the results of preclinical studies should be recognized.An important recent example is caloric restriction. 239Although caloric restriction confers significant life span extension and cardiovascular protection in laboratory rodents 5,18,42,97,223,240,241 and in certain cohorts of nonhuman primates, 227,242 its protective effects in nonhuman primates in other studies 243 and in patients with multiple cardiovascular risk factors are less evident. 244Additionally, in cross-sectional studies, the older groups may represent a selected long-lived subset of the younger population.There are existing longitudinal studies in humans (eg, InCHIANTI study) and nonhuman primates, and important information related to mechanisms of vascular aging could be derived from add-on studies to these existing cohorts.",
+      "\t\n\nOn the other hand, the beneficial effects of caloric restriction are associated with alterations in metabolism, particularly the insulin/insulin-like growth factor 1 (IGF-1) pathways, which could reflect an evolution mechanism to ensure survival of a species during period of food shortage [3].Many genetic manipulations affecting nutrient-sensing pathways including the insulin and mTOR (mammalian target of rapamycin) pathways mimic the effect of caloric restriction on lifespan in yeast, worm, flies and mice and support this hypothesis [3].This review will firstly discuss in general terms how trace elements affect ageing and then use Selenium (Se) as an example to illustrate how trace elements influence the ageing process.Furthermore, the review will also illustrate how the so-called \"Omics technologies\" can be used to unravel the modes of action of trace elements and to identify biomarkers to define the optimal intake for health at the molecular level.\t\n\nEvidence is building up showing that caloric restriction, without malnutrition, extends lifespan in species ranging from yeast to non-human primates [3], but it appears, on the contrary, that inadequate/sub-optimal intake of micronutrients contribute to the development of chronic diseases.In his \"Triage theory\", B. Ames suggested that this could reflect the need for an organism to re-allocate micronutrients according to triage priorities to favour short-term survival over long-term wellbeing [4,5].The consequences of this re-allocation may remain unnoticed in the day-to-day experience but are likely to show up late in life as cancers, Alzheimer's disease, Parkinson's disease, diabetes and cardiovascular diseases.",
+      "\t\n\nCaloric restriction (CR) is the only intervention shown to extend lifespan in mammals (5).It is also the most effective means known of reducing cancer incidence and increasing the mean age of onset of age-related diseases and tumors (6).Our studies made use of an experimental design that allowed us to clearly distinguish the effects of diet from those of age on genome-wide expression patterns.Another distinctive aspect of the study allowed us to resolve changes in gene expression induced directly by CR from those that arise over time as a consequence of the interaction between CR and aging.",
+      "\tGenDR-genomics of DR\n\nDR, of which caloric restriction is the most widely studied regimen, is the most robust non-genetic intervention shown to extend lifespan in a multitude of species, from yeast to mammals (12,14).However, the exact mechanisms of how DR extends lifespan remain unknown.To decipher the mechanisms of DR in a systematic fashion, we established GenDR (http://genomics.senescence.info/diet/), the first database of DR-associated genes.Because GenDR and related analysis of DR networks have been recently described elsewhere (15), they will only be briefly described herein.To create GenDR, we compiled from the literature a list of DR-essential genes from model organisms.DR-essential genes were defined as those which, if genetically modified, interfere with DR-mediated lifespan extension and, ideally, do not affect the lifespan of animals on an ad libitum diet (or at least do not appear to be merely causing disease).A subset of these genes act as genetic DR mimetics, as their manipulation leads to an increased lifespan for ad libitum fed animals, which is not further extended by DR.One such example is the growth hormone receptor gene in mice (16), in fact the only mouse gene currently in GenDR.In GenDR, the respective homologues of DR-essential genes are included for all the common model organisms, as well as for humans (15).A complementary data set in GenDR is a list of genes consistently differentially expressed in mammals under DR.In a recent meta-analysis, a common signature of genes differentially expressed in DR across different mammalian species, strains, tissues and experiments was derived.This signature provides a set of genes that are most robustly responding to DR (17).",
+      "\t\n\nIt seems that organisms from yeast to mammals have evolved genetic programs to cope with periods of starvation that can also postpone aging and age-related diseases, but how can we take advantage of those mechanisms to improve human health?Because assaying the longevity effects of CR in humans is practically impossible, studying its molecular mechanisms in lower life forms could be beneficial to humans through the identification of candidate genes, pathways and molecular mechanisms.Although CR will not be suitable for everyone, targeting its mechanisms and developing CR mimetics may lead to drug development for a number of age-related and metabolic diseases.\t\n\nBy far the most widely studied dietary manipulation of aging is caloric restriction (CR), also called dietary restriction.CR consists of restricting the food intake of organisms normally fed ad libitum without triggering malnutrition and is the only dietary intervention shown, to date, to increase longevity and modulate the process of aging in several model organisms (Bishop and Guarente, 2007;Fontana et al., 2010;Spindler, 2010).Even in mammals, such as mice and rats, CR can extend longevity by up to 50%, delay physiological aging, and postpone or diminish the morbidity of most age-related diseases (Masoro, 2005).Ongoing studies in rhesus monkeys suggest that CR can lower the incidence of aging-related deaths in primates (Colman et al., 2009).",
+      "\tINTRODUCTION\n\nGenomic studies into human longevity are inspired by the fact that, in animal models, healthy lifespan has proved to be remarkably plastic, and major pathways of lifespan regulation have been identified.Considerable lifespan extension has been induced in models as diverse as yeast, worms, fish, flies and rodents by applying genetic manipulation and dietary restriction (DR) (see [1] for review).Reduced activity of nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling (IIS) and target of rapamycin (TOR) signalling mediated lifespan extension, and also the extension of lifespan by DR [2].An interesting observation from the perspective of human ageing is that, in rodents and monkeys, diets restricted in glucose, fat or protein uptake reduced or delayed the risk of cancer and metabolic disease, thus extending the healthspan of the animals [2].Following the discovery of genes and pathways involved in animal lifespan extension, human research has focused on the corresponding candidate human genes with genetic, genomic and epigenetic studies into ageing and longevity.The designs of these studies differ with respect to the selection of naturally occurring phenotypes and the study populations, which include population-based, patient-based, family-based and exposure-based cohorts.",
+      "\t\n\nThe 'hormesis' hypothesis of aging is based on the observation that caloric restriction or chronic low-level exposure to any of these stresses induces cross-resistance to other stresses at the same time that it extends life span (41).Hormesis effects on aging are observed in many eukaryotes in addition to budding yeast.Although the mechanistic details of these effects remain unclear, we have argued that they include a general response to environmental stresses that blocks entry into S phase under environmentally stressful conditions that are suboptimal for replicating DNA, thus protecting cells from replication stress (30).",
+      "\tINTRODUCTION\n\nMore than 70 years ago, McCay and his colleagues demonstrated that a reduction in total food intake after weaning significantly increased both mean and maximum life spans of laboratory rats (1).Over the last seven decades, numerous laboratories have successfully repeated McCay's findings using various strains of rats and mice as well as non-mammalian species, such as fish and flies (2)(3)(4)(5)(6).Thus, food restriction has been established as a powerful experimental tool, and the anti-aging action of food restriction has become one of the most active areas of research in the realm of biogerontology (6).While life span extension by food restriction appears to be due to alterations in aging processes, the underlying mechanism(s) by which food restriction exerts its anti-aging effects remain elusive.Identification of important antiaging and anti-tumor targets of food restriction and elucidating the molecular mechanisms by which food restriction exerts its beneficial effects could eventually provide targets for intervention in humans.",
+      "\tIn comparison, caloric\nrestriction, intermittent fasting, or a ketogenic diet generally improve lifespan and health\n811 These dietary effects are not solely dependent on patterns of caloric intake, but are\nmodulated by dietary macro- and micronutrient composition, the amount of time spent in\ndifferent metabolic states, age of onset, periodicity of access to food, sex, and of greatest\nimportance to us in this studydifferences in genometype (strain) and gene-by-dietary\ninteractions 12,13. While the effects of differences in dietary composition and caloric restriction on lifespan\nhave been studied extensively, key results remain controversial 1416.\tThis again indicates that that weight gain\naccounts for only 45% of the change in lifespan. Author Manuscript\n\nOur findings can be compared to strain variation and GXE effects in response to dietary\nrestriction. Dietary restriction without malnutrition is regarded as having an almost universal\nbenefit on longevity 5355. One exception is a pair of studies on the impact of moderately\nintense restrictiona 40% reduction in caloric intakeacross a large family of LXS strains\nof mice (n of up 44 strains with 1020 replicates per strain) 17,19.",
+      "\tNutrition, phenotype and longevity\n\nNo issue so 'vividly' illustrates the power of diet to alter health as the consistent observation of the effect of caloric restriction (CR) on longevity.To date, neither drug, gene nor environmental intervention have been successfully demonstrated to prolong longevity in animals; however, the simple reduction of food calories can increase life span by 30-40% across a number of model organisms, including yeast, Drosophilia, Caenorhabditis elegans, rodents and monkeys [5][6][7].This effect of CR raises one of the most intriguing questions facing life scientists today.Despite the demonstrated positive age-related benefits of a reduction in energy intake -including decreased insulin resistance [8], increased production of glucocorticoids [9] and increased production of heat-shock proteins [10] -the mechanisms by which CR contributes to increased longevity remain unknown.How CR leads to longer life span cannot be attributed to any single factor without considering the simultaneous effects of the others.CR could alter multiple age-related processes, from energy metabolism to oxidative stress and DNA repair.Unravelling the multiparametric links of CR and aging led to the seminal genomic experiment for nutrition: the gene expression analysis of young and old tissues in normal and CR animals [11   ] is a pioneering example of the use of DNA arrays to explore the effects of CR and aging on gene expression in mouse skeletal muscle.The experiment is compelling for its simplicity and its implications, that is, the gene expression profiles for a clear phenotypic difference were compared (young versus old versus CR old mice).The power of the technique was evident by the discovery of a wide range of affected genes, including those involved in protein and energy metabolism, biosynthesis (e.g. of fatty acids), and macromolecular damage, implying immediately that the effects of aging and CR are broad, yet interrelated.More detailed experiments are now being pursued around the world following the identification of the genes that are altered during aging and protected by CR.The publication of this experiment also followed the now routine approach of supplying the raw database through an accessible internet site.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\t\n\nA key question still unresolved is to what extent the mechanisms of aging are conserved between species with vastly different lifespans.Some studies suggest that similar mechanisms are involved in aging in many species.For example, caloric restriction extends lifespan in yeast, worms, flies, mice, and primates (Weindruch 2003).Additionally, signaling through the insulin-like growth factor pathway, chromatin regulation by sir2, and oxidative damage have each been shown to affect lifespan in diverse model organisms (Tissenbaum and Guarente 2002).Other studies emphasize that changes occurring at the end of life are unlikely to be evolutionarily conserved (Kirkwood and Austad 2000).In the wild, very few animals (including humans) survive to their maximal biological lifespan.Thus, the changes in physiology that occur in very old animals have minimal effects on the fitness of individuals, and are unlikely to be evolutionarily conserved.Therefore, aging is likely to be species-specific, and studies of old age in model organisms are unlikely to be relevant to humans.",
+      "\t\n\nIn summary, we postulate that due to metabolic changes and the subsequent increase in stress response, physiological processes evoked by starvation show strong correlation with anti-aging processes (Table 2).These observations suggest that starvation may evoke the same stress response reaction as caloric restriction, which is the only treatment known to prolong lifespan in all organisms tested to date.The difference is that starvation results in a much stronger or prolonged induction.This accentuated response during starvation may facilitate the experimental identification of basic molecular mechanisms linking nutrition and health using a nutrigenomic approach."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "A1F96E809E942FD33A6C0199E338F5A9"
+    },
+    {
+      "task_id": "2075EEA93169E52BFF50C80C4ECDF0DC"
+    },
+    {
+      "task_id": "B2CABF057C243D3BEA707C861220A769"
+    },
+    {
+      "task_id": "8800709B5C665E09BB7A9FBD6E7E7359"
+    },
+    {
+      "task_id": "BFACDAF6E27C8B3594B93785B26B0AC6"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_2.json
new file mode 100644
index 0000000..dbaf184
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_2.json
@@ -0,0 +1,109 @@
+{
+  "question": [
+    "How do oxidative stress and the subsequent accumulation of damaged macromolecules contribute to cellular aging?",
+    "How are extracellular matrix remodeling and tissue stiffness implicated in the aging process?",
+    "How do recent developments in autophagy research contribute to our understanding of its role in aging and longevity?",
+    "What are the implications of age-related shifts in stem cell niche composition and function for tissue regeneration capacity?",
+    "How do cross-links and advanced glycation end-products (AGEs) accumulation affect the structural integrity and function of aging tissues?"
+  ],
+  "answer": [
+    "Oxidative stress, primarily caused by reactive oxygen species (ROS) generated from cellular metabolism, leads to damage to various cellular components, including DNA, proteins, and lipids. This damage accumulates over time, leading to functional decline in cells. In particular, damage to DNA can lead to mutations and impaired cellular functions. The balance between DNA damage and its repair is a major determinant of cell longevity. Additionally, oxidative damage to mitochondria, a major source of ROS, can impair energy production and further contribute to aging. This process is supported by the oxidative stress theory of aging and the mitochondrial theory of aging.",
+    "Extracellular matrix (ECM) remodeling plays a significant role in the aging process. Aging results in changes in ECM biosynthesis, modifications of ECM components, and alterations of cell-matrix interactions, which contribute to age-related pathologies. The synthesis of many ECM components, such as elastin, declines with age, impairing the elasticity and resilience of tissues. Age-related ECM changes also alter vascular mechanotransduction, dysregulating cell responses to alterations in the environment. Additionally, aging and cellular senescence increase the secretion of matrix metalloproteinases (MMPs), which compromises the structural integrity of tissues and promotes pathological remodeling. This can lead to increased tissue stiffness, a common feature of aging tissues. Furthermore, dysregulated collagen synthesis contributes to vascular fibrosis and arterial stiffening.",
+    "Recent developments in autophagy research have shown that autophagy, a cellular degradation process, plays a crucial role in aging and longevity. Certain compounds like rapamycin, resveratrol, and polyamines can induce autophagy, with polyamines showing results in human clinical research. Autophagy is also linked to the regulation of various processes that contribute to aging, such as protein degradation, mitochondrial metabolism, and stress response. Studies have shown a decline in autophagy in aging mammals, and increased autophagy is required for lifespan extension in certain organisms. Furthermore, the up-regulation of autophagy by certain compounds has been associated with increased lifespan in various organisms. Dysfunctional autophagy is implicated in many age-related diseases, and the activation of autophagy has been linked with increasing lifespan in animal models.",
+    "Age-related shifts in stem cell niche composition and function can lead to a decrease in tissue regeneration capacity. This is because the stem cell's ability to self-renew and produce progeny to replenish worn-out and damaged cells in aged tissues may be compromised. This could result in a depletion of stem or progenitor cell pools, promoting age-related pathologies. Additionally, the induction of stem cell senescence may affect tissue renewal. Furthermore, the balance between stem cell proliferation and tissue regeneration, which is crucial for maximizing longevity, may be disrupted, leading to an aged phenotype.",
+    "Cross-links and AGEs accumulation can lead to several detrimental effects on aging tissues. They can cause structural changes in proteins, lipids, and nucleic acids, leading to altered function and potential damage. AGEs can mediate intracellular glycation of mitochondrial proteins, increasing ROS levels and triggering oxidative stress. They can also bind with RAGEs, activating signaling pathways that upregulate inflammatory cytokines and adhesion molecules. In the vascular system, AGEs can cause endothelial dysfunction, arterial stiffness, and increased capillary permeability. In the context of diabetes, AGEs can accelerate the death of certain cells, disrupt retinal vascular integrity, and induce neural cell dysfunction and death."
+  ],
+  "contexts": [
+    [
+      "\t\n\nCell senescence, telomere shortening, and oxidative stress Attempts at synthesizing two major areas of focus in aging research, cell senescence [287,288] and free radicals, have been made since the 1970s (for a recent review see [289,290]).Early results by Packer and Smith suggested that vitamin E treatment could completely prevent cell senescence [291]; however, this result proved to be irreproducible [292].Nevertheless, it was observed that decreasing oxygen tension, from the customary 21% O 2 to more physiological levels (3% O 2, as would be found in vivo) led to an increase in cell doublings before senescence (i.e., an increase in the Hayflick limit or replicative life span [293][294][295][296]).Similar effects were also reported using antioxidants [296][297][298].In the 1990s, von Zglinicki et al. reported that a mild increase in oxygen tension (40%) triggered senescence within 3 cell divisions in human fibroblasts [299].von Zglinicki and co-workers proposed that oxidative damage to telomeres was responsible for the rapid triggering of senescence [299][300][301] and recent studies show that telomeric DNA may be particularly sensitive to oxidative damage [302].Following von Zglinicki et al. 's report, other investigators, using different oxidative stressors and different cell types, have reported very similar results.Mild oxidative stress reduces clonal life span and conversely, reduction of oxidative stress extends clonal life span [303][304][305][306][307]. Guarente's lab has provided additional evidence in this general direction, with the demonstration that RNAi knockdown of Sod1 triggered early senescence in human fibroblasts [308].This result is consistent with the earlier report by Epstein's laboratory that fibroblasts derived from Sod1 / mice failed to grow at all in culture [188].A great breakthrough in this area occurred when Campisi's lab demonstrated that senescence could be prevented completely in primary mouse cells when the cells were grown at 3% oxygen, instead of the customary 21% [309].This also resulted in a dramatic reduction of oxidative damage-signature mutations [310].In other words, these investigators demonstrated that in vitro senescence in mice cells was directly related to oxygen toxicity, i.e., oxidative damage.",
+      "\t\n\nThe free radical theory of aging, first proposed by Harman in 1956 [21], has received a lot of attention over the years as indicated by the number of scientific reviews on antioxidant interventions in different animal models and human clinical trials.The mitochondrion has been identified as a major source of reactive oxygen species (ROS) and thus oxidative stress potentially contributing to the aging process, although several plasma membrane and cystosolic enzymes may also contribute to the increased intracellular pro-oxidant status observed during aging [22].In the mitochondrial respiratory chain, electrons entering complexes I and II are transferred to complex III, then IV where they are combined with molecular oxygen and hydrogen to form H 2 O. Redox reactions at respiratory complexes I, III, and IV are coupled to the extrusion of protons from the mitochondrial matrix into the intermembrane space.The re-entry of protons into the matrix is coupled to the synthesis of ATP from ADP and P i .This oxidative phosphorylation is responsible for the vast majority of ATP production and oxygen consumption in most types of animal cells [23].Up to 2% of oxygen used in this complex reaction undergoes monoelectronic reduction and results in the formation of superoxide anion and hydrogen peroxide, which can lead to the formation of the more toxic species hydroxyl radicals [24,25].Such reactive species can attack and modify genomic DNA.An important type of oxidative DNA lesion accumulating with age is 8-oxo-deoxyguanine [26].If unrepaired, this adduct in genomic DNA may lead to a point mutation upon DNA replication.During DNA replication, 8-oxo-deoxyguanines present on either strand of DNA can mispair with adenosines and lead to G:C  T:A transversion mutations.A misincorporation of an 8-oxodeoxyguanine as a substrate nucleotide can also lead to the same type of mutational pattern [27].",
+      "\t\n\nOur results are consistent with the oxidative stress theory of aging originally proposed by Denham Harman [26], and the notion that a vicious cycle of ROS generation and oxidative damage is the ultimate driver of aging [27].Our data also indicate that endogenous nuclear DNA damage is able to trigger this cycle of escalating ROS abundance, oxidative damage, senescent cell accumulation and age-related pathology.\t\n\nTo determine if this oxidative stress is pathological, we suppressed it pharmacologically in Ercc1 -/ mice with the mitochondrial-targeted radical scavenger XJB-5-131.Chronic administration XJB-5-131 significantly reduced both oxidative DNA damage and senescence (Fig. 5).The reduced level of senescent cells corresponded to a reduction in agerelated morbidity.This is consistent with numerous recent studies demonstrating that genetic or pharmacologic elimination of senescent cells slows age-related decline [2,4,7,8,[84][85][86].The observation that suppressing oxidant production is sufficient to decreases senescence indicates that reactive species are required to ultimately cause or maintain senescence in response to genotoxic stress.",
+      "\t\n\nIntroduction as replication errors, spontaneous chemical changes to Although aging is nearly universally conserved among the DNA, programmed double-strand breaks (DSBs) (in eukaryotic organisms, the molecular mechanisms unlymphocyte development), and DNA damaging agents derlying aging are only beginning to be elucidated.A that are normally present in cells.The latter category useful conceptual framework for considering the probincludes reactive oxygen species (ROS), such as superlem of aging is the Disposable Soma model (Kirkwood oxide anion, hydroxyl radical, hydrogen peroxide, nitric and Holliday, 1979).This model proposes that organoxide, and others.Major sources of cellular ROS proisms only invest enough energy into maintenance of the duction are the mitochondria, peroxisomes, cytochrome soma to survive long enough to reproduce.Aging oc-p450 enzymes, and the antimicrobial oxidative burst of curs at least in part as a consequence of this imperfect phagocytic cells.ROS can cause lipid peroxidation, maintenance, rather than as a genetically programmed protein damage, and several types of DNA lesions: sinprocess.Although aging may involve damage to varigle-and double-strand breaks, adducts, and crossous cellular constituents, the imperfect maintenance of links.The situation in which ROS exceed cellular antinuclear DNA likely represents a critical contributor to oxidant defenses is termed oxidative stress.As normal aging.Unless precisely repaired, nuclear DNA damage byproducts of metabolism, ROS are a potential source can lead to mutation and/or other deleterious cellular of chronic, persistent DNA damage in all cells and may and organismal consequences.Damage to both nuclear contribute to aging (Sohal and Weindruch, 1996).The DNA, which encodes the vast majority of cellular RNA ROS theory of aging is discussed in depth in this issue and proteins, and mitochondrial DNA have been proof Cell by Balaban et al. (2005).In brief, longer-lived posed to contribute to aging (Karanjawala and Lieber, species generally show higher cellular oxidative stress 2004).The reader is referred to the review by Balaban resistance and lower levels of mitochondrial ROS proet al. in this issue of Cell concerning the potential role duction than shorter-lived species.Caloric restriction, of mitochondrial DNA damage in aging (Balaban et al.,",
+      "\t\n\nWe previously showed that superoxide plays a primary role in chronological age-dependent DNA damage and mutations.Our model is that the DNA damage caused by oxidative and other types of stress accumulated during aging in nondividing cells generates double-strand breaks during the fi rst round of replication after the exit from G 0 .Cells lacking SGS1 attempt to repair this damage by homologous recombination between sister chromatids but generate a large number of GCRs, especially at advanced age.",
+      "\t\n\nReactive oxygen species (ROS) have long been at the center of the debate on causes of aging and a central player in the free-radical theory of aging.One form of oxidative damage that is considered irreversible and has been correlated with age in various organisms, including replicative age in yeast, is protein carbonylation (Nystrom 2005).Protein carbonyls have been proposed as a yeast aging factor based on the observations that both protein carbonyls (Aguilaniu et al. 2003;Erjavec and Nystrom 2007) and aggregates containing heavily carbonylated proteins (Erjavec et al. 2007) are asymmetrically retained in mother cells during division.The proper asymmetric segregation of oxidatively damaged proteins appears to be dependent on a functioning actin cytoskeleton (Aguilaniu et al. 2003;Erjavec et al. 2007), which has independently been linked to ROS and life span through the actin bundling protein, Scp1 (Gourlay et al. 2004).",
+      "\t\n\nThere is some evidence that related processes occur in mammals.First, cells damaged by oxidative stress in vitro undergo stochastic transcriptional changes that parallel those in aged heart tissue (Bahar et al., 2006).Second, a deficiency in the DNA repair factor ERCC1 accelerates aging phenotypes and generates gene expression profiles reminiscent of aged animals (Niedernhofer et al., 2006).Third, cells that senesce because of replicative aging in vitro or in aged tissues in vivo exhibit alterations in heterochromatin (Herbig et al., 2006;Narita et al., 2006) and secrete growth factors that can drive tumorigenesis (Campisi, 2005).Finally, oxidative DNA damage at promoters correlates with gene repression in the aging human brain (Lu et al., 2004) and has been linked to both transcriptional and epigenetic changes that may contribute to Alzheimer's disease (Wu et al., 2008).",
+      "\t\n\nThere are many theoretical considerations on oxidative damage of mitochondria about aging.The \"free radical theory of aging,\" proposed by Harman in 1956 (138), that free radicals cause nonspecific damage to macromolecules, such as DNA, lipids, and proteins, has attracted much attention in recent years due to development in free radical biology.Harman (139) also proposed aging as consequences of mitochondrial aging that free radical reactions may contribute to changes in the mitochondrial inner membrane with age due to effects on both mtDNA and nDNA.Based on the observation of Drosophila, Miquel et al. (238) postulated that there is a distinct possibility of free radical-or lipid peroxide-induced inactivation of the mtDNA of fixed postmitotic cells with the passage of time.Fleming et al. (110) proposed that the site of irreversible injury is the mtDNA rather than the biomembranes.A two-step hypothesis on the mechanisms of in vitro cell aging, \"oxygen radical-mitochondrial injury hypothesis of cell aging,\" was proposed by Miquel and Fleming (239) that the fundamental cause of cell aging is an instability of the mitochondrial genome because of a lack of or balance between mitochondrial repair and the disorganizing effects of oxygen radicals.Thus, deprived of the ability to regenerate their mitochondrial populations, the cells will sustain an irreversible decline in their ability to synthesize ATP, with concomitant senescent degradation of physiological performance, and eventual death.Bandy and Davison (15) suggested that mitochondrial genome mutations may increase oxidative stress as implications for carcinogenesis and aging.",
+      "\tAging\n\nThe oxidative stress theory of aging proposes that accumulation of oxidative DNA damage over the life span of an organism leads to gradual decline of cellular functions and eventual death (Bohr, 2002).This model is supported by several circumstantial evidences including the observation that lower free radical production and/or antioxidant treatment protects against agerelated deterioration, and cognitive decline (Lemon et al., 2003).Further, deficit or decrease in the repair of oxidative DNA damage appears to correlate with premature aging and age-related diseases (Bohr et al., 2007).It appears likely that overall genome repair, specifically the balance between DNA damage and its repair is a major determinant of the longevity and cell viability.A specific defect in processing 5 0 dRP residue at the strand break in Sir2 (SIRT6 homolog)-deficient mice displayed age-related degenerative phenotype (Mostoslavsky et al., 2006).The activities of DGs OGG1, NTH1 and uracil DNA glycosylase (UNG) in brain mitochondria decrease significantly with age (Gredilla et al., 2010).",
+      "\tPrxs and the free radical hypothesis of aging\n\nThe evolved version of Harman's (Harman 2003) free radical theory of aging proposes that organisms age because the constituents of cells and tissues accumulate damage over time caused by reactive oxygen (and/or nitrogen) species originating from endogenous metabolism, including, among many other possible activities, mitochondrial respiration.At first glance, it appears that the data concerning Prxs and aging fit this theory like a glove, as Prxs become ''damaged'' (catalytically inactivated as a peroxidase) during aging due to a modification caused by a reactive oxygen species (ROS), specifically hydrogen peroxide (or organic hydroperoxides), and that counteracting this ''damage'' by elevating the levels of the ''repair'' enzyme Srx1 prolongs life span (Molin et al. 2011).Moreover, as the Prxs themselves act as enzymatic antioxidants and protect the genome against oxidative modifications (see below), it is possible that peroxidedependent inactivation of Prxs gives rise to a negative feedback loop with respect to the cell's capacity for ROS homeostasis.",
+      "\t\n\nAging is a dynamic and complex process defined as the time-dependent functional decline.With age, homeostasis declines and damage accumulates.One of prime candidates that induce macromolecular damage is oxidative stress from reactive oxygen species (ROS) generated from normal physiological activities.Indeed, many long-lived mutants are resistant to oxidative stress [53].Ferroptosis involves metabolic dysfunction that results in the production of both cytosolic and lipid ROS [36,38].Repression of SLC7A11 transcription by p53 results in reduction of cystine uptake.Because of less cystine uptake, the levels of intracellular glutathione (GSH) will be reduced and the cellular system for defending oxidative stress is abrogated.Thus, the sensitivity of ROS-induced ferroptosis is significantly increased in p53-activating cells.We showed that SLC7A11 is downregulated by p53 and that p53mediated ferroptosis is dramatically induced in the testis of p53 3KR/3KR Xrcc4 -/-mice.Thus, it is very likely that the combination of genomic instability and p53-mediated ferroptosis contributes significantly to the aging associated phenotypes observed in p53 3KR/3KR Xrcc4 -/-mice.",
+      "\tSources of Damage Increase with Age\n\nThe free radical theory of aging posits that aging is caused primarily by oxidative damage incurred by ROS that chemically modify critical cellular biomolecules (13).This theory has evolved over the years to become the oxidative stress theory of aging, but the principle is the same, in that the accumulation of oxidative damage drives aging.In support of this theory, a large body of literature indicates that oxidative damage to all cellular macromolecules increases with age.Furthermore, overexpression of antioxidant enzymes that detoxify ROS, such as copper-and zinc-containing superoxide dismutase (SOD), manganese-containing SOD, or catalase, increase the life span of Drosophila melanogaster by as much as 30% (14).Additionally, most long-lived mutants in D. melanogaster and Caenorhabditis elegans have increased resistance to oxidative stress.In mammals, the role of oxidative stress is less clear because overexpression of catalase, SOD1 (pancellular expression), or SOD2 (mitochondrial) does not extend the life span of mice (15).However, overexpression of catalase specifically targeted to the mitochondria does extend the life span of some mice up to 20% (16).Additionally, treatment with the antioxidant nordihydroguaiaretic acid (NDGA) and an activator of NRF2 (master regulator of antioxidant response) extends median life span in male mice (17).\t\n\nThe free radical theory of aging evolved to the mitochondrial theory of aging when mitochondria were implicated as the primary source of ROS.Electrons leaked from the electron transport chain at the inner mitochondrial membrane can react with molecular oxygen to produce a superoxide radical, which can be converted by SOD to yield hydrogen peroxide (H 2 O 2 ).In the presence of transition metal ions (e.g., Fe 2+ or Cu + ), H 2 O 2 can be further converted to the highly reactive hydroxyl radical via the Fenton-type reaction.These ROS react locally to damage genes or proteins necessary for oxidative phosphorylation, leading to further uncoupling of electron transport and increased ROS production in a feed-forward manner.Abundant evidence shows that ROS and oxidative damage increase as organisms age.But which cellular target of these damaging radicals and other reactive molecules is health and life limiting?If the answer is DNA, then one expects DNA damage to accumulate with age.",
+      "\tThe Free Radical Theory of Aging. The free radical theory of aging proposed by Denham Harman more than fifty years ago postulates that aging results from the accumulation of deleterious effects caused by free radicals, and the ability of an organism to cope with cellular damage induced by ROS plays an important role in determining organismal lifespan [3].In agreement with this theory, increased ROS production by mitochondria and increased 8-oxo-dG content in the mtDNA are frequently detected in aged tissues [40,[47][48][49][50], suggesting that progressive accumulation of oxidative DNA damage is a contributory factor to the aging process.Consistently, many studies have found that increased oxidative damage in cells is associated with aging [51][52][53].Furthermore, genetic studies in worm, fly, and mouse have linked enhanced stress resistance or reduced free radical production with increased lifespan [27].Mutant strains of C. elegans that are resistant to oxidative stress have extended lifespan, whereas those more susceptible to free radicals have shortened lifespan [54,55].Mice lacking the antioxidant enzyme superoxide dismutase 1 (SOD1) exhibit a 30% decrease in life expectancy [56].Conversely, simultaneous overexpression of SOD1 and catalase extends lifespan in Drosophila [57].Small synthetic mimetics of SOD/catalase increase lifespan in C. elegans [58], while treatment of antioxidant drugs in mice increases the median lifespan up to 25% [59,60].Further supporting this hypothesis, mice lacking Ogg1 and Myh, two enzymes of the base excision repair pathway that repairs oxidative DNA damage, show a 50% reduction in life expectancy [61].Collectively, these studies demonstrate that interplay between ROS and protective antioxidant responses is an important factor in determining aging and lifespan.\tMitochondria and Aging\n\n3.1.The Mitochondrial Theory of Aging.Because mitochondria are the major producer of ROS in mammalian cells, the close proximity to ROS places mitochondrial DNA (mtDNA) prone to oxidative damage [104].Consistently, many studies have shown that 8-oxo-dG, one of the common oxidative lesions, is detected at higher level in mtDNA than nuclear DNA, suggesting that mtDNA is more susceptible to oxidative damage [52,[105][106][107][108][109][110][111][112][113].As both the major producer and primary target of ROS, mitochondria are thought to play an important role in aging.The mitochondrial theory of aging, extended from the free radical theory, proposes that oxidative damage generated during oxidative phosphorylation of mitochondrial macromolecules such as mtDNA, proteins, or lipids is responsible for aging [114].As mtDNA encodes essential components of oxidative phosphorylation and protein synthesis machinery [115], oxidative damageinduced mtDNA mutations that impair either the assembly or the function of the respiratory chain will in turn trigger further accumulation of ROS, which results in a vicious cycle leading to energy depletion in the cell and ultimately cell death [104,114,[116][117][118].",
+      "\t\n\nThere is an emerging consensus that oxidative damage is of central importance to much of the age-related overall decline of animal cells, from yeast to humans [2][3][4][5][6][7] .Caloric restriction or environmental conditions that favour a decrease in oxidative metabolism also increase lifespan 8 , and transgenic or knockout animals with decreased oxidative metabolism have increased lifespans.For example, flies that consume oxygen at a high rate have a reduced lifespan, and low oxygen-consumption rates and cold temperatures favour a prolonged lifespan 9,10 .Lipids, proteins and DNA have all been argued to be Ageing, repetitive genomes and DNA damage Michael R. Lieber and Zarir E. Karanjawala www.nature.com/reviews/molcellbioP E R S P E C T I V E S to one another, thereby permitting a copying of information from one sister chromatid to the other.This typically restores the information content at the break site back to normal.",
+      "\t\n\nA key macromolecule at risk for ROS-mediated damage is nuclear DNA [1], which is evident from the wide range of oxidative DNA lesions that accumulate gradually in rodents and humans with advancing age [6,7].\tIntroduction\n\nA prevailing hypothesis to explain the molecular basis of ageing is Harman's ''free-radical theory of ageing'', which states that endogenous reactive oxygen species (ROS), which result from cellular metabolism, continually damage biomolecules [1].In line with this hypothesis, it has been shown that increased resistance to oxidative stress (e.g., by improved antioxidant defense) extends the lifespan of Caenorhabditis elegans, Drosophila, and rodents [2][3][4], whereas hypersensitivity to oxygen considerably reduces the lifespan of nematodes [5].",
+      "\tReplication stress, mitochondria and growth signaling\n\nIncreased oxidative damage to DNA and other cellular constituents by ROS produced in dysfunctional mitochondria is an important component of modern versions of the 'free radical theory' of aging (3,71).It is often assumed that the production of ROS in mitochondria is directly proportional to the rate of mitochondrial respiration, and that increased respiration promotes aging.A number of recent studies in budding yeast and mammals argue that these long-held assumptions are incorrect (72).For example, caloric restriction and other experimental manipulations that enhance respiration in budding yeast reduce, rather than increase levels of ROS at the same time that they enhance life span (73).Similarly, budding yeast cells cultured in medium containing glycerol or ethanol, which are metabolized via respiratory pathways, exhibit a longer chronological life span (22).Furthermore, deletion of TOR1 extends chronological life span of budding yeast by enhancing respiration, but reducing ROS (21).As might be expected based on these reports, experimental manipulations that increase the production of ROS in mitochondria shorten the chronological life span of this organism (73,74)."
+    ],
+    [
+      "\tSenescence and apoptosis are thought to contribute\nto aging and age-related disorders by decreasing the proliferative potential of progenitor\nstem cells, altering tissue regenerative capacity, decreasing tissue function and by altered\ntissue architecture and microenvironment caused by altered gene expression and secretion of\ninflammatory cytokines, growth factors, and proteases (Campisi 2003; Coppe et al. 2008;\nGarfinkel et al. 1994; Krtolica and Campisi 2002; Kuilman et al. 2008; Novakova et al. 2010; Ohtani and Hara 2013).",
+      "\t\n\nThere exists a substantial body of research addressing the tissue, cellular and molecular changes that accompany or directly contribute to aging in a range of model organisms (reviewed in [7]).However, the majority of data, generated in model organisms or in vitro (cellular senescence), has yet to be validated in human aging.Moreover the relative contribution of putative gerontogenes to human pathological agerelated processes is unknown.Age-associated impaired healing correlates with increased inflammation, increased matrix proteolysis and delayed re-epithelialization leading to chronic wound states, processes modulated by exogenous estrogen treatment [8].In a recent study we characterized estrogen-regulated changes in gene expression using a model of delayed wound healing in young mice that have been rendered hypogonadal by ovariectomization (hence removing any effects of 'intrinsic aging') [9].Thus, using comparative analysis we are now in a position to address the relative contributions of estrogen and aging to healing in elderly humans.",
+      "\t\nAging alters gene expression of growth and remodeling factors in human skeletal muscle both at rest and in response to acute resistance exercise.\t\n\nAging alters gene expression of growth and remodeling factors in human skeletal muscle both at rest and in response to acute resistance exercise.",
+      "\t\n\nStructural integrity of skeletal muscle.Some noteworthy genes that were differentially expressed only in older subjects after RL support the concept that the muscles of older subjects may have experienced a degree of stress far exceeding that in young subjects despite being exposed to the exact same stressor.For example, gene expression of MyBPH was robustly elevated (4.1-fold) in the old only, as was myosin head domain containing 1 (MYOHD1; 1.4-fold).MyBPH is an integral myosin binding partner in the A band of myofibrils that interacts with the myosin rods and titin to provide structural integrity to the contractile apparatus.Reduced MyBPH expression is associated with muscle weakness in age-related disorders (30).Interestingly, localization of MyBPH to the contractile apparatus is directed by its C terminal domain consisting of two fibronectin type III motifs (24), and our microarray analysis also revealed a 1.6-fold increase among the old in the expression of fibronectin type III domain containing 3B (FNDC3B).As shown in mice, MyBPH is upregulated in the young after more intense eccentric loading (5), again suggesting age differences in the degree of mechanical stress required to activate many of these transcriptional responses (with young muscles requiring greater stress than old).MyBPH expres-sion is modulated by the transcription factor SMARCA4 (SWI/ SNF-related, matrix-associated, actin-dependent regulator of chromatin, subfamily a, member 4), which was also significantly upregulated in the old only.Interestingly, SMARCA4 is activated by glucocorticoid receptor signaling and, in turn, regulates the expression of notable muscle-specific genes including myogenin, troponin T, and MyBPH.A strain on muscle integrity among the old was also suggested by significant downregulation (1.7-fold) of both type IV collagen 3 (COL4A3) and 4 (COL4A4) mRNA expression and 1.6-fold upregulation of TUBA8.Type IV collagen, a major constituent of basement membranes, is degraded by matrix metalloproteinases (MMP-2 and MMP-9) in response to muscle damage (49).These findings suggest that the muscles of the older subjects may have been attempting to launch a compensatory effort to maintain structural integrity-a response to this degree was apparently not sensed as necessary among the younger subjects.",
+      "\tRole of Extracellular Matrix Remodeling in Vascular Aging\n\nThe extracellular matrix (ECM) is an important contributor to health and longevity.This noncellular compartment, ubiquitous to all tissues and organs does not only provide essential mechanical scaffolding but mediates highly dynamic biomechanical and biochemical signals required for tissue homeostasis, morphogenesis, and cell differentiation.Studies on model organisms suggest that evolutionarily conserved pathways regulate ECM remodeling during aging and that promotion of ECM youthfulness by antiaging interventions is an essential signature of longevity assurance. 206Aging in mammals also results in significant changes in ECM biosynthesis, postsynthetic modifications of ECM components, and alterations of cell-matrix interactions, which contribute to the development of a spectrum of age-related pathologies. 207ge-related alterations of the ECM, including the subendothelial basement membrane, intima, media, adventitia, and interstitial matrix (which constitute more than half of the mass of the vascular tissue), play a fundamental role in impairment of both structural and regulatory homeostasis of the vasculature. 208With age, the expression of growth factors that regulate ECM biosynthesis is altered 45 and the synthesis of many ECM components (eg, elastin) declines, which impairs elasticity and resilience of the vascular wall to mechanical damage and rupture induced by bursts in wall tension because of pulsatile pressure waves. 208Age-related ECM changes also likely alter vascular mechanotransduction, dysregulating cell responses to alterations in the hemodynamic environment.Additionally, aging and cellular senescence alter the secretory phenotype of vascular endothelial and smooth muscle cells, increasing MMP secretion. 45This together with increased MMP activation 208 induced by high ROS levels compromises the structural integrity of the vasculature and promotes pathological remodeling (eg, in hypertension), resulting in increased likelihood of aneurysm formation and vessel rupture, including the development of cerebral microhemorrhages. 45The available evidence suggests that many of these age-related ECM alterations are governed by circulating factors and factors produced in the vascular wall, including the extended renin-angiotensin-aldosterone system (see above) and an age-related decline in circulating IGF-1. 209ollagen synthesis is also dysregulated with age in the vascular wall likely because of the effects of increased paracrine action of TGF- (transforming growth factor-), 123 which contributes to vascular fibrosis and arterial stiffening. 208Additional features that contribute to increased arterial stiffness include decreased elastin synthesis, elastin degradation and fragmentation, elastin calcification, alterations in cross-linking of extracellular matrix components (eg, by increased presence of advanced glycation end products). 208,210,211he pathophysiological consequences of age-related ECM remodeling and arterial stiffening have been the subject of a recent comprehensive review by AlGhatrif and Lakatta. 6In brief, as the large conduit arteries stiffen in aging, aortic pulse wave velocity, systolic pressure, and pulse pressure significantly increase, 212 whereas diastolic pressure decreases.Decreased diastolic pressure leads to a decline in coronary blood flow.Increased systolic pressure promotes left ventricular remodeling, diastolic dysfunction, and exacerbates atherogenesis.Because of the dilation of conduit arteries, wall tension significantly increases, contributing to the development of aneurysms.In addition to alterations in the biomechanical properties of large arteries, age-related ECM remodeling likely also affects microvascular transport and barrier functions. 213Age-related alteration of the ECM structure and composition are also manifested in the wall of veins, contributing to the pathogenesis of varicosities. 214\t\n\nFigure 4. Conceptual model for the pathogenic role of cellular senescence in vascular aging.The model predicts that increased presence of senescent endothelial or smooth muscle cells (SMCs) in the aged vasculature and their proinflammatory secretome (SASP [senescence-associated secretory phenotype]) contributes to impaired angiogenesis and microvascular rarefaction, pathological remodeling of the extracellular matrix (ECM), barrier disruption, chronic inflammation, and atherogenesis.MMP indicates matrix metalloproteinase.",
+      "\t\n\nAge-related transcriptional remodeling and mitochondria",
+      "\t\n\nChromatin remodeling in aging, J. G. Wood et al.",
+      "\tAging is only, in part, the result of crosslinking reactions\n\nWhile Bjorksten (1968) proposed that crosslinking was a major feature of the chemical aging of tissues, particularly of collagen, it has become apparent in recent years that many age-dependent chemical modifications of protein are monofunctional.These include oxidative modifications of phenylalanine, tyrosine and methionine residues (Table 1), carboxyalkylation of lysine (Table 4), and deamidation and racemization of amino acids.Extracellular matrix proteins accumulate higher levels of monofunctional chemical modifications, as well as crosslinks, not because they are uniquely sensitive to damage, but because they generally turnover more slowly.There are few quantitative studies on the age-dependent accumulation of biomarkers in intracellular proteins, even in proteins with long half-lives, such as contractile proteins in muscle or histones in post-mitotic cells.These proteins may be exposed to higher levels of reactive oxygen species generated in mitochondria or peroxisomes, or to higher levels of reactive carbonyl intermediates in glycolysis, but are also better protected by intracellular antioxidant and detoxification systems.",
+      "\t\n\nVarious extracellular matrix-related proteins were differentially regulated herein.Extracellular matrix proteins provide structural support, mechanical properties, and strength of tissues, including vocal folds, playing a pivotal role in phonation [62,71,72].Collagens XIV, XVIII, and Fibulin 5 were downregulated in older rabbit vocal folds compared to young tissue.To our knowledge, these specific collagen types have not been investigated in depth in vocal fold tissue; however, studies suggest that the changes in the collagen fiber density and arrangements within the lamina propria may affect phonation [73,74].Collagen type IV is exclusive to extracellular matrix basal membranes [75] and is present in the human vocal fold basal membrane providing support to epithelial and endothelial cells [76].Collagen type IV was upregulated in older rabbit vocal folds compared to young, an effect of aging observed in our study.The relationship between Collagen type IV and aging is not well established.Increased accumulation of Collagen type IV is reported in the basal lamina of cerebral microvessels in humans [77] but decreased in the skin of older adults [78].Conversely, several extracellular matrix proteins were upregulated, including Collagen type XVIII and Fibulin 5, in the presence of dehydration when observing the effect of hydration status alone.These protein changes may be related to the remodeling of the extracellular matrix [79] in response to dehydration.Moreover, the accumulation of collagens and the decrease of elastins may result in extracellular matrix stiffness in aging larynx and other organs [59,79].Finally, Lamin A was upregulated by dehydration, by a smaller magnitude, especially when observing the mean difference within the young groups.Previous data has identified that Lamin proteins A and C are important for imparting the nucleus with its stiffness, and their expression has been reported to scale with tissue stiffness [80].Thus, upregulation of this protein due to dehydration may be related to tissue stiffness in the vocal fold of rabbits.",
+      "\t\n\nRecently, collagen production and extracellular matrix remodeling were determined to be essential for longevity in C. elegans.Collagen may directly affect signaling processes associated with longevity in C. elegans, including signaling through SKN-1 [40,58].We note that HSF-1 was also recently shown to regulate cytoskeletal integrity in a process that can influence stress resistance and longevity in C. elegans [59].Thus, the linkage of both the extracellular matrix and the cytoskeleton to HSF-1 may provide a mechanism by which HSF-1 promotes longevity.\tHSF-1 regulates collagen genes which may affect the aging process\n\nIt is interesting that cuticle structure genes constitute the largest overlap with aging-related genes.In humans, mutations in collagens lead to a large number of heritable human diseases such as osteoporosis and musculoskeletal diseases [53].Collagens are long-lived proteins known to accumulate damage during aging, leading to a decline in tissue health [54].Also, type I collagens become resistant to proteolysis upon age [55,56], affecting their turnover.Interestingly, mice expressing cleavageresistant type I collagen go through an accelerated aging process [57].Thus, cellular aging can be affected by the state of the extracellular matrix in mammals.",
+      "\t\n\nAn observation that is specific for males is the global downregulation with aging of genes involved in the synthesis of the ECM and in particular of different forms of collagen (Table 2).In addition, aging males but not females showed a decrease in collagen type III.Interestingly, collagen type III decreases the size of collagen bundles and thereby increases vascular elasticity (11).Therefore, a decreased expression of collagen type III can participate in the increased stiffness that characterizes the aging aorta (23).An interesting observation from our study that directly relates to the mechanism of vascular remodeling is the upregulation in aging males of the transcript encoding collagen type VIII (Table 3).That specific collagen type, which is upregulated in response to vascular injury (24), promotes VSMC migration (1).The upregulation of this transcript together with the downregulation of other isoforms in aging males again supports the notion that this group is more susceptible to neointimal proliferation, VSMC migration, and potentially atherosclerosis.\t\n\nOur study shows that the genomic adaptation to vascular aging involves not only the genes involved in ECM composition and VSMC differentiation and migration, but also many other categories of genes participating in intracellular functions, such as cell signaling, DNA repair, metabolism, and protein synthesis.Our study also illustrates that most of the changes in gene expression with aging differ between males and females and correspond to different sets of transcription factors.Indeed, 5% of the 600 genes that were regulated by aging were observed in both old males and females.GO analysis also shows that specific subsets of genes are regulated differently between sexes, especially the genes participating in ECM composition and VSMC phenotype.We therefore propose that these transcriptional differences may underlie the different physiological properties of aging arteries between males and females, as well as their different susceptibility to vascular complications, such as hypertension or atherosclerosis.Furthermore, the analyses in young monkeys demonstrated major differences in genes regulating vascular structure, implying that the sex differences in vascular stiffness that develop with aging are programmed at an early age.",
+      "\tChronic liver diseases are characterized by aberrant matrix deposition, calling for our\nattention to the role of ECM in resolution of liver fibrosis. Tissue remodeling is regulated by MMPs,\ninvolved in the ECM degradation, and TIMPs, their endogenous inhibitors. Their subtle balance\nmaintains liver fibrogenesis. Tissue homeostasis is further regulated by proteolytic activity of the\nPLAU/PLAT/plasmin, responsible for the maintenance of the physiologic levels of ECM (40). PLAU promotes ECM degradation through activation of MMPs (MMP-2, -3 and -9; (41, 42),\nincreases the differentiation of hepatic stem cells, and HGF-dependent regeneration of hepatocytes\n(43).",
+      "\t\n\nMechanistically, the age-related increase in elastin degradation may result from augmented activity of proteases with elastinolytic activity, including certain MMPs and cysteinyl cathepsins, enzymes that, in turn, are regulated by inflammatory mediators (54,55).Collagen catabolism falls in aging arteries.\t\n\nAugmented transforming growth factor (TGF)-b activity favors the accumulation of collagen in the aortic wall.The activity of various elastases, including matrix metalloproteinases (MMPs), such as MMP-9 and MMP-12, as well as overexpression of the cysteine proteinases cathepsins S, K, and L, and the serine proteinase neutrophil elastase, elaborated by inflammatory cells, can all contribute to depletion of elastin (11).These alterations in the aorta's extracellular matrix contribute importantly to its loss of distensibility.This increased stiffness raises reflected waves and elevates systolic pressure.Yet diastolic pressure tends to decline with age.As aortic pulse wave velocity increases, pulse pressure rises (12).Indeed, pulse pressure is an independent risk factor for CV events (13).Isolated systolic hypertension accounts for the majority of uncontrolled hypertension in Americans over 50 years of age (14,15).substantially stroke and total mortality, with lesser benefit for ischemic cardiac events (16).Avoiding excessive sodium intake may provide an additional, nonpharmacological intervention for control of hypertension in older individuals (17,18).Some have raised concerns regarding the safety of aggressive lowering of blood pressure in elderly patients, particularly those with concomitant coronary artery disease (19).Indeed, a J-shaped curve relating CV outcomes to blood pressure may pertain to this In addition to reducing stroke, a major impediment to independent living and function in older patients, antihypertensive therapy may limit the development of dementing illnesses, as shown in the Syst-Eur trial (27).Decreased dementia and cognitive decline accrue with longer duration of antihypertensive treatment (28).An asymmetric loss to follow-up of individuals with impaired cognition may have biased the results of dementia in the SHEP study to the null (29).With regard to the former, vascular aging alters the function of the endothelium, the cells that line the lumen of blood vessels.Endothelial dysfunction includes reduced vasodilatory and antithrombotic properties, with an increase in oxidative stress and inflammatory cytokines (33)(34)(35) favoring atherogenesis and thrombosis, and predisposing to CVD (36).Human and experimental studies concur that diminished bioavailability of nitric oxide (NO), a key mediator of vasorelaxation and antiatherogenic processes, underlies age-dependent endothelial dysfunction (37,38).Reduced NO bioavailability can occur due to decreased synthesis or increased degradation of NO.Under normal conditions, endothelial nitric oxide synthase (eNOS) produces NO from L-arginine in the presence of the cofactor tetrahydrobiopterin (BH4) (39).Although studies differ regarding eNOS protein expression with age (34,40,41), recent data suggest an age-related alteration in eNOS function, referred to as eNOS uncoupling (42).",
+      "\tBackground\n\nTissue aging is caused by intrinsic and extrinsic factors that induce complex molecular changes and, in turn, a deterioration of cellular structures and function.These changes are major causes of age-related diseases like cancer or cardiovascular disorders [1,2].The main molecular adaptations occurring during aging are loss of genomic stability due to reduced DNA repair capacities [3], loss of proliferative potential caused by increased senescence [1,4], and age-related alterations in the DNA-methylation patterns that affect cellular plasticity [5,6].Metabolic adaptations are also considered to play a major role in aging [7][8][9][10].For instance, the metabolic function of mitochondria is progressively impaired during aging in different tissues [8,11].This can result in increased generation of reactive oxygen species that foster genomic instability [8,12].Moreover, several studies reported that caloric restrictions and diet adaptations, such as supplementation of food with branched chain amino acids [13,14], can significantly increase lifespan [15].This suggests that metabolic activity as well as nutrient sensing pathways are highly relevant for cellular aging processes (reviewed in [10]).Accordingly, interference with the insulin/IGF1 and the mammalian target of rapamycin (mTOR) pathways increased lifespan in different model organisms [7,[16][17][18].",
+      "\t\n\nWe examined the list of 447 age-regulated genes for functional groups showing a consistent change with age.One group includes genes involved in the formation of the extracellular matrix, which show a consistent increase in expression in old age.Seven age-regulated genes encode proteins known to play key roles in maintaining epithelial polarity (three types of claudins, two cadherins, occludin, and a cell adhesion molecule), all but one of which increase expression in old age (see Table S4).Forty-nine age-regulated genes encode protein components of the extracellular matrix, all but four of which increase expression in old age.In the kidney, the extracellular matrix could play a key role in governing the filtration of blood via the basement membrane, a capacity that declines with age.The observation that genes involved in forming the extracellular matrix increase expression in the kidney with age may be directly relevant to the age-related decline in glomerular filtration rate."
+    ],
+    [
+      "\tStochastic damage\n\nFigure 2. Longevity assurance, ageing and disease.New studies of the biology of ageing are revealing processes that control when and how fast ageing occurs, such as insulin-IGF-1 signalling [6], cellular senescence [4], protein refolding [43][44][45], autophagy [41] and phase 1 and 2 detoxification [36,37,52].These represent major points of intervention against ageing-related disease.As shown here, lifespan pathways control improved cellular maintenance, which leads to slowed ageing (e.g.slowed normal cognitive ageing) and protection against diseases of ageing (e.g.neurodegenerative diseases of ageing, such as Alzheimer's and Parkinson's disease, and cancer).Ageing can evolve via selection to reduce investment in energetically costly somatic maintenance processes and instead to increase early fitness traits such as growth and reproduction [50,51].Arrows denote stimulation, and T bars inhibition, of the process indicated.Red and green denote changes leading to ageing and longevity, respectively.",
+      "\t\n\nFig. 4. Schematic showing how some external interventions trigger longevity, often at least partly through stimulating autophagy.The pink writing refers to dietary, chemical, or therapeutic interventions that can extend life span, in at least some organisms (described in the text).Arrows indicate stimulating effects, and blocked lines indicate inhibitory effects.This schematic is not meant to be exhaustive but highlights the pathways that alter the epigenetic information and autophagy.",
+      "\t\n\nTORC1 regulates several downstream processes that may contribute to its role in aging, including protein degradation via autophagy, mitochondrial metabolism, stress response, and mRNA translation (Stanfel et al. 2009).Autophagy, which literally means \"self eating\", is a degradative process through which cellular components are engulfed by cytoplasmic vesicles and transported to the lysosome/vacuole for degradation (Klionsky 2007).Autophagy is repressed by TOR signaling and is induced in response to starvation or treatment with TOR inhibitors, such as rapamycin (Noda and Ohsumi 1998).A decline in the autophagic response has been reported in aging mammals (Cuervo and Dice 2000), and increased autophagy is required for life span extension in long-lived C. elegans mutants with reduced insulin/IGF-1-like signaling (Melendez et al. 2003).Several recent studies have also uncovered an important role for autophagy in the response to DR. DR induces autophagy in yeast, worms, and flies (Juhasz et al. 2007;Morck and Pilon 2006;Takeshige et al. 1992) and is reported to be required for life span extension from DR or TOR-inhibition in both worms and flies (Hansen et al. 2008;Jia and Levine 2007;Juhasz et al. 2007).Recently, up-regulation of autophagy by spermidine has also been shown to be associated with increased life span in yeast, nematodes, and flies (Eisenberg et al. 2009).",
+      "\tInductors of Autophagy and its Impact on Aging\n\nAutophagy has a role in homeostasis, which plays an essential role in the maintenance of cellular physiology and the prevention of cellular damage.Among the inducers of autophagy have been described the already-mentioned rapamycin, resveratrol, and polyamines; however, only polyamines have demonstrated results in clinical research in humans [65].It is known that these compounds can induce the canonical autophagy pathway, which includes inactivation of the mammalian objective of the rapamycin complex 1 (mTORC1), allowing phosphorylation and activation of the Unc-51 complex (Ulk1/2), where the cascade of the other members of the complex is subsequently activated, ULK as FIP200 and ATG13 [65].\t\n\nOn the other hand, interventions using chemical inducers of macroautophagy, such as rapamycin, an mTOR inhibitor, can increase the life span of middle-aged mice like that induced by spermidine or polyamine-producing gut flora supplementation [87].In an unexpected finding, aged cells showed an increased accumulation of protein aggregates, suggesting a decline in lysosome functionality during aging even though the number of lysosomes increased [72,88].This disparity could be due to changes in the pH, as suggested by the fact that the vacuolar V-type ATPase complex, which is responsible for maintaining vacuolar pH, decreased during aging, suggesting a mechanistic link between altered protein complex composition and lysosome dysfunction [72,88].The stress-induced synthesis of cytosolic and organelle-specific chaperones was also impaired in aging.Mutant mice that were deficient in a co-chaperone of the heat-shock family exhibited accelerated aging phenotypes, whereas long-lived mouse strains showed a marked upregulation of some heat-shock proteins [89].\t\n\n2016;351:173-6.81.Koga H, Kaushik S, Cuervo AM.Protein homeostasis and aging: the importance of exquisite quality control.Ageing Res Rev. 2011;10:205-15.82.Labbadia J, Morimoto RI.The biology of proteostasis in aging and disease.Annu Rev Biochem.2015;84:435-64.83.Rubinsztein DC, Mario G, Kroemer G. Autophagy and aging.Cell.2011;146:682-95.84.Tomaru U, Takahashi S, Ishizu A, Miyatake Y, Gohda A, Suzuki S, et al.Decreased proteasomal activity causes age-related phenotypes and promotes the development of metabolic abnormalities.Am J Pathol.2012;180:963-72.85.Rodriguez KA, Edrey YH, Osmulski P, Gaczynska M, Buffenstein R. Altered composition of liver proteasome assemblies contributes to enhanced proteasome activity in the exceptionally long-lived naked mole-rat.Brodsky JL, editor.PLoS One.2012.https://doi.org/10.1371/journal.pone.0035890.86.Chondrogianni N, Georgila K, Kourtis N, Tavernarakis N, Gonos ES.Enhanced proteasome degradation extends Caenorhabditis elegans lifespan and alleviates aggregationrelated pathologies.Free Radic Biol Med.2014;75:S18.https://doi.org/10.1016/j.freeradbiomed.2014.10.632.87.91.Haigis MC, Yankner BA.The aging stress response.Mol Cell.2010;40:333-44.92.Johnson SC, Rabinovitch PS, Kaeberlein M. mTOR is a key modulator of ageing and agerelated disease.Nature.2013 Jan 16;493:338-45.93.Lamming DW, Ye L, Astle CM, Baur JA, Sabatini DM, Harrison DE.Young and old genetically heterogeneous HET3 mice on a rapamycin diet are glucose intolerant but insulin sensitive.Aging Cell.2013;12:712-8.\tConserved Metabolic Pathways Offer Clues to the Factors of Aging and Longevity\n\nEvolutionarily conserved pathways, from yeast to mammals, robustly correlate with aging and longevity, and their deregulation has been implied with the development of cellular aging and include the mechanistic target of rapamycin (mTOR), insulin/ insulin growth factor 1 signaling (IIS), AMPK sensing, and sirtuin (SIRT) pathways [90].The harmonized regulation of these metabolic pathways maintains cellular and organismal homeostasis, even in the presence of external perturbations like changes in nutrient availability, temperature, oxygen level, or internal alterations, including protein misfolding and DNA damage [91].",
+      "\t\n\npivotal in this aspect providing molecular insights and having huge conceptual contributions in the field.Characterising the contribution of individual mutants in ageing is a continuously active and informative activity in the field.On top of these studies, genome-wide screens have provided insights on the role of evolutionarily conserved processes and signalling pathways in ageing such as nutrient response [17,18], protein translation, oxidative damage [19,20], mitochondrial function [21,22] and autophagy [22,23] opening new avenues for biogerontology research.Yeasts have proved informative and helped in understanding mechanisms of highly conserved pathways (from yeast to human) in physiology, health and disease such as the Target of Rapamycin (TOR) [24], glucose sensing (PKA) and stress response pathways (Sty1/p38) [25].\t\n\nA competitive ageing assay was performed in budding yeast where samples from the ageing pool were collected at specific timepoints [58].Mutants were then detected using a microarray DNA hybridization technique that quantifies abundance of the barcode tags of each mutant.Using this approach multiple short-and long-lived mutants were identified with autophagy mutants being among the short-lived and mutants coding for proteins involved in de novo purine biosynthesis pathway, which ultimately produces IMP and AMP were among the long-lived ones [58].Validation experiments targeting autophagy or purine biosynthesis has the expected lifespan outcomes.In a similar approach, deletion of genes involved in protein sorting in vacuoles, autophagy and mitochondrial function shortened life span, confirming that respiration and degradation processes are essential for long-term survival.Among the genes whose deletion significantly extended life span were genes implicated in fatty acid transport and biosynthesis, cell signalling and transfer RNA (tRNA) methylation such as ACB1, CKA2 and TRM9, respectively [59].",
+      "\t\n\nWe have recently conducted a genome-wide screen using siRNA library to identify genes regulating autophagy in human cells under normal nutritional conditions (5).In this image-based screen we took advantage of the autophagy specific GFP-LC3 reporter whose translocation from the cytosol to autophagosomes can serve as a quantitative measure of autophagy.In this study, we specifically explore the mechanisms that regulate autophagy in neural cells using the hits identified in our screen.We demonstrate that reactive oxygen species (ROS) play a general function in mediation of autophagy upstream of the type III PI3 kinase and that this pathway is essential for the up-regulation of autophagy by A.Interestingly, our data show that genes regulating autophagy are differentially expressed in normal aging and in AD patient brains.Finally, we identify candidate molecular targets that may be safely manipulated to modulate autophagy to treat neurodegenerative diseases.\t\n\nConversely, expression of the key autophagy genes, such as Atg5 and Atg7, was down-regulated in aging.This is consistent with our previous data demonstrating transcriptional down-regulation of beclin 1, in normal human brain aging (11).Together, this suggests, that unlike AD, the normal aging process may lead to transcriptional down-regulation of autophagy.\t\n\nTo further define the biological processes affected by downregulation of autophagy in aging, we used gene ontology canonical pathway analysis.It revealed a significant enrichment in the \"Axon guidance\" (P = 0.0009) and \"Regulation of actin cytoskeleton\" (P = 0.038) pathways, suggesting a connection between regulation of autophagy, axon guidance and actin dynamics.Construction of protein-protein interaction networks anchored by the hit genes belonging to these pathways (12,13) revealed two related networks encompassing, respectively, 27 (11%) and 61 (26%) of the hit genes (Fig. S6 C and D).Importantly, both networks directly connect to the known autophagy machinery through the interaction of the RIP kinase (RIPK1) and PKC (PRKCZ) with p62/sequestrosome (SQSTM1).In addition, syndecan 2 (SDC2), a part of the \"Regulation of actin cytoskeleton\" network, interacts with syntenin, a binding partner of ULK1, the human ortholog of yeast Atg1 (14).ULK1 is known to play a role in the regulation of endocytic processes involved in axon guidance (15) and to promote synapse formation in Drosophila (16).These data suggest that some of the molecular networks involved in the regulation of autophagy are closely connected to those regulating endocytosis, actin dynamics, and neuronal axon guidance, and that autophagy may play a wider role in the development and maintenance of neuronal function.\t\n\nTranscriptional Regulation of Autophagy in Normal Brain Aging.To determine whether the regulation of autophagy may have wider implications in normal aging of the human brain, we analyzed expression of the autophagy screen hit genes in a set of younger versus older human brain samples (10).We observed differential expression of a large subset of genes, including a group of 32 genes significantly (P < 0.05) up-regulated and 46 down-regulated with age (Fig. 6A and Fig. S6 A and B and Table S9).Gene ontology biological process analysis revealed that the age up-regulated group was highly enriched in genes involved in mediation and regulation of the MAP kinase pathway (P = 1.6  10 4 ).An increase in the activity of MAP kinase pathway was predicted by our previous analysis to lead to the suppression of autophagy (5).\t\n\nDifferential Expression of Autophagy Regulators in Normal Aging and in AD.Our gene expression data suggest that autophagy is also differentially regulated at the transcriptional level in normal human brain aging versus in AD.Because autophagy is known to play a protective role against onset of neurodegeneration in animal models (2,3,20,21), its down-regulation in normal aging could contribute to the observed age-dependent predisposition to development of chronic neurodegenerative diseases.In addition, the extensive overlap of the autophagy screen hits with Fig. 6.Expression of autophagy screen hit genes in normal human aging.Clustering analysis (dChip) of mRNA expression levels of select autophagy hit genes in younger (40 y old) versus older (70 y old) human brain samples, based on (i) minimum 1.2-fold change between the average expression, and (ii) P value <0.05 using unpaired t test.\tDiscussion\n\nIn this study, we demonstrate that the type III PI3 kinase plays a fundamental role in the regulation of autophagy and that ROS function as general mediators of autophagy induction upstream of this kinase.This pathway has an essential function in the initiation of autophagy in response to mitochondrial damage following exposure to A, the main pathogen of AD.At the same time, A is able to slow down autophagic processing through ROS independent inhibition of lysosomal degradation.In addition, our analysis of expression of the autophagy screen hits suggests that autophagy is differentially regulated at the transcriptional level in normal human aging and in AD, with overall levels decreased in normal aging but elevated in AD.",
+      "\t\n\nAt least two aspects need to be addressed using a system biology approach in aging research.First, although many different pathways, compartments or processes are known to be closely related to aging, such as the IIS pathway, autophagy, mitochondria, oxidative stress response and so on, it remains unclear as to how they interact, are co-regulated and balanced during aging.To provide a glimpse of this problem, we visualized the network communities among the known aging regulators based on entries in the GenAge database [62,63]  and controlling growth and proliferation (green nodes), DNA damage response for maintaining integrity of the genome (red nodes), mitochondria and oxidative stress response (yellow nodes), and ribosome and translation (blue nodes).It is obvious that the first two are intensively linked and closely entangled, while the latter two are relatively independent processes with only few links connected to the first two processes.Also, it is interesting to note that, by comparing the molecular interaction-based network with the co-citation network, the role of autophagy and protein transport in aging might be either overestimated due to study bias or under-estimated by the incompleteness of the molecular interactions among these genes.\tINTRODUCTION\n\nAging has fascinated researchers since ancient times.The hugely complicated process that has been revealed may be interpreted from different aspects, such as the accumulation of oxidative damage, shortening of telomeres, the costs of reproduction, metabolic rates, cellular senescence, etc., and these have in turn given rise to diverse theories of aging [1].However, thanks to forward and reverse genetic technologies, researchers in the recent decades have established that despite its complexity, a single or a few key genes in a few key pathways can modulate the aging rate.The most important players would appear to be those in nutrient sensing pathways or stress response pathways, such as DAF-2/IGF1R and DAF-16/FOXO in the Insulin/IGF like signaling pathway, AAK-2/AMPK in another nutrient sensing pathway, JNK in the stress response pathway, LET-363/mTOR as an inhibitor of autophagy and activator of translation and SIRT1/SIR2 in genome stability maintenance, to name a few [2,3].In addition to genetic perturbations, dietary perturbations, such as diet restriction (DR) are known to significantly extend lifespan in most organisms examined from yeasts to primates, although different pathways may act under different DR conditions, and alternative DR strategies also effect C.elegans lifespan in different ways [3,4].The main pathways revealed under different DR regimens are summarized in Fig. (1).In this small, convoluted DR response network, DAF-16 and ceTOR/LET-363 *Address correspondence to this author at the Chinese Academy of Sciences, 320 Yue Yang Road, Shanghai, 200031, China; Tel: 86-21-54920458; Fax: 86-21-54920451; E-mail: jdhan@picb.ac.cn  These authors contributed equally to this work.",
+      "\t\n\nIn vitro and animal studies have reported a decline in autophagy with age [26,36,[40][41][42][43]; however, to our knowledge, only one other publication has reported an age-associated decline in expression of autophagy genes, which was carried out in a small number of human brain tissue samples [44].Overall, these findings for major components of core autophagy machinery and upstream regulators provide evidence for a transcriptional decline in autophagy gene expression with age in human monocytes.The identification of key genes contributing to a decline in autophagy are of great interest, as pharmacologic activation of autophagy has been linked with increasing lifespan in animal models, including mice [45].Further, dysfunctional autophagy is now widely implicated in pathophysiological processes of many age-related diseases such as cancer, Alzheimer's, diabetes, and cardiovascular diseases [46].However, longitudinal studies are necessary to validate the age-related transcriptional decline of autophagy gene expression in human monocytes, and to investigate the relationship between these age-related patterns and the development of age-associated diseases.",
+      "\tThe cell-autonomous theory on the\nother hand posits that individual cells are the targets of the aging process, via a timedependent increase in homeostatic dysfunction. The potential mechanisms include\nincreases in the production of reactive oxygen species, telomere shortening and, not\nsurprisingly, genomic instability. An implication of this theory is that long-lived cells in\nthe organism, such as neurons, muscle, and importantly stem cells, would be the\npredominant substrates of aging, while those cells that undergo rapid and continuous\nturnover would be removed before they could exert an effect on tissue function.",
+      "\tConcluding remarks and future perspectives\n\nAging research has rapidly expanded over the past two decades, with studies ranging from lifespan-extending  [68,69,71].However, when their effect on cell death and senescence leads to stem cell loss and tissue degeneration, they might contribute to aging [66,67]."
+    ],
+    [
+      "\tFurther evidence of age-related changes in stem cells include the finding that a\nhigher proportion of Thy-1loSca-1+Lin-Mac-1-CD4-c-kit+ cells from old mice are in\nS/G2/M phases of the cell cycle (Morrison, 1996), and the results of Henckaerts\net al. , who showed that the proliferative response of Lin-Sca-1+c-kit+ marrow cells\nto the early-acting cytokines KL, Flt3L and TPO, decreased dramatically with age\n(Henckaerts et al. 2002). As mentioned previously, the bone marrow niche is the optimal\nmicroenvironment for the growth and functional maintenance of HSCs (Moore\n2004; Nilsson et al. 2001).\t17\nAging Effects on Hematopoietic Stem Cells and Bone Marrow Niche\nAs discussed above, HSC expansion and transplantation is clinically\nimportant to treat patients with hematological and non-hematological disorders. It\nis also well known that cancer risk increases in older people (Balducci and\nExtermann FEB 2000). Therefore, understanding aging effects on hematopoietic\nsystem, especially on HSCs and their bone marrow microenvironment (niche),\nmay not only help to prevent malignant transformation, but also to determine\nefficacy of aging stem cells for transplantation (Pinto et al. 2003; Van Zant and\nLiang 2003) .",
+      "\t\n\nMost mammalian tissues can be described as being comprised of two major cellular components: stem or progenitor cells, which are responsible for regenerative capacity or repair after injury, and differentiated somatic cells, responsible for adult stem cell support and specialized tissue/organ functions.Based on this classification, two major mechanisms can account for tissue degeneration associated with age: loss of stem cell pool division potential (loss of regenerative capacity) and loss of differentiated somatic cell function, which directly leads to loss of organ function.Loss of differentiated somatic cell function can additionally indirectly affect adult stem and progenitor cells by altering the tissue microenvironment that is essential for stem cell support (the stem cell niche).In general, loss of stem cell pool division potential can occur through multiple mechanisms including stem cell senescence, death or dysfunction of the niche.One specific mechanism that can account for the loss of both stem cell and differentiated somatic cell function is the gradual accumulation of persistent DNA damage.Persistent DNA damage and its erroneous resolution *To whom correspondence should be addressed.Tel: +1 415 209 2042; Fax: 415-209-22232; Email: dbhaumik@buckinstitute.org  2007 The Author(s) This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/ by-nc/2.0/uk/)which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.include telomeric dysfunction (9)(10)(11) and somatic mutations (12), both of which increase with age; both also have been proposed to contribute to the loss of stem and differentiated somatic cell function with age (13,14).DNA damage accumulation in stem cells has been detected in mice and clearly contributes to the attrition of stem cell division potential during aging (15).Thus, it is likely that DNA damage contributes to aging by limiting stem cell division potential and by also interfering with somatic tissue functions, including stem cell niches.",
+      "\t\n\nA diminished capacity to maintain tissue homeostasis is a central physiological characteristic of ageing.As stem cells regulate tissue homeostasis, depletion of stem cell reserves and/or diminished stem cell function have been postulated to contribute to ageing 1 .It has further been suggested that accumulated DNA damage could be a principal mechanism underlying age-dependent stem cell decline 2 .We have tested these hypotheses by examining haematopoietic stem cell reserves and function with age in mice deficient in several genomic maintenance pathways including nucleotide excision repair 3,4 , telomere maintenance 5,6 and non-homologous end-joining 7,8 .Here we show that although deficiencies in these pathways did not deplete stem cell reserves with age, stem cell functional capacity was severely affected under conditions of stress, leading to loss of reconstitution and proliferative potential, diminished self-renewal, increased apoptosis and, ultimately, functional exhaustion.Moreover, we provide evidence that endogenous DNA damage accumulates with age in wild-type stem cells.These data are consistent with DNA damage accrual being a physiological mechanism of stem cell ageing that may contribute to the diminished capacity of aged tissues to return to homeostasis after exposure to acute stress or injury.",
+      "\tSeveral studies have shown\nthat the systemic milieu regulates stem cell decline during aging. Liang et al. showed\nthat HSCs have a reduced ability to home to the bone marrow and spleen after\ntransplantation into old versus young recipients (Liang et al. , 2005). Further experiments\ndemonstrated that the muscle stem cell niche adversely effects stem cell function as\nevidenced by the restoration of old stem cell regenerative potential upon exposure to a\nyoung systemic microenvironment (Conboy et al. , 2005; Conboy and Rando, 2005).\tSince stem cells\nare capable of self-renewal and produce progeny to replenish worn-out and damaged cells\nin aged tissues, the induction of stem cell senescence may compromise tissue renewal by\ndepletion of stem or progenitor cell pools and thus promote age-related pathologies. 6\nIt is apparent that the HSC compartment undergoes considerable age-related\nchanges, however it is not yet clear whether theses changes are intrinsic to the cells\nthemselves or whether they occur due to alterations in the hematopoietic\nmicroenvironment, commonly referred to as the HSC niche.\tHowever, studies do indicate that aged tissues have a diminished capacity to return to a\nhomeostatic state after exposure to stress or injury, therefore indicating a defect in stem\ncell function during the aging process. Since the HSC population provides an ideal\nmodel to study stem cell aging, it is necessary to elucidate the mechanisms of\nhematopoietic aging and expand the findings to other tissues and organ systems. Theories of Aging and Age Related Epigenomic Changes\nThere are two major theories of organismal aging: evolutionary and damage\nbased.\tWith\nthis in mind, it has been hypothesized that the aging or functional failure of tissuespecific stem cells, which fulfill this job, may limit tissue repair and renewal, therefore\ncontributing to overall organismal aging (Krtolica, 2005; Van Zant and Liang, 2003). Because of the unprecedented experimental model systems that are available for the\nexploration of HSCs, stem cell aging research in the field of hematology has been the\nsubject of extensive studies. Indeed, the hematopoietic system has served as an important\nmodel for advancing our understanding of stem cell biology and its association with\naging.\tIn view of the importance of stem cells for maintaining\nimmune function and in a broader sense tissue homeostasis and longevity, there is a\ncritical need to better understand the mechanisms involved in HSC aging. 17\nFigure 1.1 The HSC hierarchy. The HSC compartment can be functionally divided into three populations; long-term\nHSCs, which have extensive self-renewal capacity, short-term HSCs, which have limited\nself-renewal capacity, and multipotent progenitor cells which cannot self-renew and give\nrise to common lymphoid progenitors (CLP) and common myeloid progenitors (CMP).",
+      "\tIn other words, lower HSC proliferation results in a\nmore youthful stem cell, but poorer tissue regeneration, and\nconsequently an aged phenotype; this indicates that stem cell\nproliferation and tissue regeneration are nely balanced to\nmaximize longevity, so that cell cycle disruption results in an\nuncoupling of tissue and organismal aging from the aging of\nthe resident stem cell. Finally, three lines of evidence in our work indicate broad\nchanges in epigenetic regulation with age.\tIf the rejuvenating effect of stem cells were perfect, senescing cells would be\nreplaced indenitely; but even in highly regenerative tissues\nsuch as the skin, the gut, and the hematopoietic system, agerelated decline in function is well established [1]. Still unclear\nare the effects of aging on the stem cells themselves, which\ncould contribute to inferior tissue repair. Hematopoietic stem cells (HSCs) continuously replenish\nthe blood and immune system throughout life. Data from\nmice support an age-related decline in stem cell function [1],\nsuggesting that older HSCs are inadequate to cope with the\ndemands of blood production.",
+      "\tFurthermore, the differentiation potential of the HSC compartment\nappears to become skewed toward the myeloid lineage with age\n(26 28). As HSC have been shown to cycle (29), replicative stress,\neven in the absence of detectable telomere erosion (30, 31), may\nunderlie at least some of the age-related changes in HSC (32). Many traits affecting the hemopoietic stem and progenitor cell\ncompartments also change with age in a mouse strain-dependent\nfashion (2123, 3234) and have been implicated in organismal\nlife span (21, 3234). The responsiveness of LSK cells to TGF-2\nshowed mouse strain-dependent variation in young mice.",
+      "\tFurther evidence of age-related changes in stem cells include the finding that a\nhigher proportion of Thy-1loSca-1+Lin-Mac-1-CD4-c-kit+ cells from old mice are in\nS/G2/M phases of the cell cycle (Morrison, 1996), and the results of Henckaerts\net al. , who showed that the proliferative response of Lin-Sca-1+c-kit+ marrow cells\nto the early-acting cytokines KL, Flt3L and TPO, decreased dramatically with age\n(Henckaerts et al. 2002). As mentioned previously, the bone marrow niche is the optimal\nmicroenvironment for the growth and functional maintenance of HSCs (Moore\n2004; Nilsson et al. 2001).\t17\nAging Effects on Hematopoietic Stem Cells and Bone Marrow Niche\nAs discussed above, HSC expansion and transplantation is clinically\nimportant to treat patients with hematological and non-hematological disorders. It\nis also well known that cancer risk increases in older people (Balducci and\nExtermann FEB 2000). Therefore, understanding aging effects on hematopoietic\nsystem, especially on HSCs and their bone marrow microenvironment (niche),\nmay not only help to prevent malignant transformation, but also to determine\nefficacy of aging stem cells for transplantation (Pinto et al. 2003; Van Zant and\nLiang 2003) .",
+      "\tIntroduction\n\nThe regenerative potential of our body decreases upon aging.Regenerative tissues depend on specialized adult stem cells, thus aging in these tissues can be interpreted as signs of aging in somatic stem cells [1].Adult stem cells are characterized by the dual function to differentiate into different cell lineages and to selfrenew for maintenance of the stem cell pool.It is, however, still controversial if this self-renewal also includes juvenation or if adult stem cells are doomed to undergo aging upon each cell division.It is unclear if adult stem cells undergo functional and molecular changes, if their number decreases because of aging, or if aging is due to extrinsic environmental factors without any effect on the stem cell pool [2,3].\t\n\nThere is emerging evidence that aging is not purely a cell intrinsic process, but rather regulated by interaction with the cellular microenvironment.For example, Ju and co-workers have demonstrated that telomere dysfunction induces alterations in the microenvironment that affect aging of the hematopoietic system [55].In general, adult stem cells have a slow turnover and reside in specialized niches, protected from the environment and only a few are activated at a time [33,56].By keeping adult stem cells in a quiescent state, the stem cell niche might also play a crucial role in regulating replicative senescence.Strong experimental data for this hypothesis derives form serial transplantation experiments of HSC in mice.The reconstituting ability declines continuously within 4 to 5 transfers [57,58] and this decline is thought to be telomereindependent [59], although it has been reported that telomere length decreases by serial transplantation [60].Recently, Wilson and co-workers have demonstrated that there is a dormantfraction of HSC that divides only five times during the lifetime of mice and especially these dormant HSC posses repopulating activity upon serial transplantation [61].The stem cell niche could therefore play a central role in maintaining a dormant pool of HSC to prevent replicative senescence over the lifetime of the organism [62].\t\nThe regenerative potential diminishes with age and this has been ascribed to functional impairments of adult stem cells.Cells in culture undergo senescence after a certain number of cell divisions whereby the cells enlarge and finally stop proliferation.This observation of replicative senescence has been extrapolated to somatic stem cells in vivo and might reflect the aging process of the whole organism.In this study we have analyzed the effect of aging on gene expression profiles of human mesenchymal stromal cells (MSC) and human hematopoietic progenitor cells (HPC).MSC were isolated from bone marrow of donors between 21 and 92 years old.67 genes were age-induced and 60 were age-repressed.HPC were isolated from cord blood or from mobilized peripheral blood of donors between 27 and 73 years and 432 genes were age-induced and 495 were age-repressed.The overlap of age-associated differential gene expression in HPC and MSC was moderate.However, it was striking that several age-related gene expression changes in both MSC and HPC were also differentially expressed upon replicative senescence of MSC in vitro.Especially genes involved in genomic integrity and regulation of transcription were age-repressed.Although telomerase activity and telomere length varied in HPC particularly from older donors, an age-dependent decline was not significant arguing against telomere exhaustion as being causal for the aging phenotype.These studies have demonstrated that aging causes gene expression changes in human MSC and HPC that vary between the two different cell types.Changes upon aging of MSC and HPC are related to those of replicative senescence of MSC in vitro and this indicates that our stem and progenitor cells undergo a similar process also in vivo.\t\n\nThe regenerative potential diminishes with age and this has been ascribed to functional impairments of adult stem cells.Cells in culture undergo senescence after a certain number of cell divisions whereby the cells enlarge and finally stop proliferation.This observation of replicative senescence has been extrapolated to somatic stem cells in vivo and might reflect the aging process of the whole organism.In this study we have analyzed the effect of aging on gene expression profiles of human mesenchymal stromal cells (MSC) and human hematopoietic progenitor cells (HPC).MSC were isolated from bone marrow of donors between 21 and 92 years old.67 genes were age-induced and 60 were age-repressed.HPC were isolated from cord blood or from mobilized peripheral blood of donors between 27 and 73 years and 432 genes were age-induced and 495 were age-repressed.The overlap of age-associated differential gene expression in HPC and MSC was moderate.However, it was striking that several age-related gene expression changes in both MSC and HPC were also differentially expressed upon replicative senescence of MSC in vitro.Especially genes involved in genomic integrity and regulation of transcription were age-repressed.Although telomerase activity and telomere length varied in HPC particularly from older donors, an age-dependent decline was not significant arguing against telomere exhaustion as being causal for the aging phenotype.These studies have demonstrated that aging causes gene expression changes in human MSC and HPC that vary between the two different cell types.Changes upon aging of MSC and HPC are related to those of replicative senescence of MSC in vitro and this indicates that our stem and progenitor cells undergo a similar process also in vivo.\tDiscussion\n\nThe deterioration of the regenerative potential upon aging might be due to functional changes in adult stem cells.To test this hypothesis we have investigated differential gene expression in primary, human MSC and HPC derived from different age groups.In this study, we demonstrate for the first time age-related gene expression changes in human MSC and HPC and that there is a moderate but significant concordance in the expression profiles upon aging in vivo and replicative senescence in vitro.It needs to be pointed out, that chronological age and biological age do not necessarily coincide.Multiparametric assessment of biological age might be valuable in this context.Furthermore, MSC and HPC preparations are heterogeneous and it is conceivable that they represent a mixture of different aged or senescent subsets.Further research will be necessary to address age-related changes on a single cell level to investigate the heterogeneity of aging within cell populations.activating complex, polypeptide 5 (SNAPC5) and peroxisome proliferator-activated receptor gamma (PPARG) were age-repressed.Furthermore, we have validated age associated changes in HPC for 9 genes (B): S100 calcium binding protein A10 (S100A10); vimentin (VIM); myeloid-associated differentiation marker (MYADM); pim-1 oncogene (PIM1) and annexin A2 (ANXA2) were age-induced.Timeless interacting protein (TIPIN); myosin regulatory light chain interacting protein (MYLIP); lymphocyte transmembrane adaptor 1 (LAX1) and Early growth response 1 (ERG1) were agerepressed.Protocadherin 9 (PCDH9) was not amplified in HPC from elderly donors whereas interleukine 7 receptor (IL7R) was not amplified in young samples (not presented in the figure).Differential gene expression was always calculated in relation to the mean of young samples.The mean foldratio (6SD) is demonstrated for median aged and old donor samples.RT-PCR results (red) were always in line with microarray data (blue) for all genes tested.doi:10.1371/journal.pone.0005846.g003",
+      "\tFor instance, mice null for the repair\nprotein Ercc1 show progressive marrow failure resulting in a pancytopenia, while the\nmice exhibit several symptoms of premature aging (Prasher, Lalai et al. 2005). However,\nno studies to date have demonstrated conclusively that diminished DNA repair capacity\nof HSCs with age results in their functional impairment, much less a decreased ability to\nrepair DNA lesions with age. 10\nGenetic regulation of stem cell proliferation\n\nThese many ramifications of the proliferative nature of hematopoietic stem cells\nbegs the question of what are the key molecules regulating this vital feature."
+    ],
+    [
+      "\tHowever, under diabetic conditions, AGEs generated by the exposure of proteins and lipids\nto high glucose levels crosslink ECM proteins, impair ECM degradation by MMPs and\nincrease cardiac stiffness, which together manifest as early diastolic dysfunction33,5254. AGEs can also promote the differentiation of fibroblasts into myofibroblasts, which\nproliferate and induce ECM dyshomeostasis by secreting profibrotic cytokines and matrix\nproteins. Furthermore, the altered cardiac mechanics lead to the release of other stimuli\nincluding transforming growth factor- (TGF), tumour necrosis factor (TNF), angiotensin\nII and various interleukins, which activate profibrotic responses in fibroblasts and\nmyofibroblasts55.",
+      "\t\n\nMuch work has focused on molecular features often observed with advanced age-cellular senescence, autophagy, oxidative stress, and epigenetic changes.Vascular remodeling, as a consequence of these features, is well documented leading to endothelial dysfunction and arterial stiffness.Although such features are also invoked in other conditions such as heart failure with preserved ejection fraction and valvular calcification, disentangling the key causal features suitable for therapeutic modulation remains elusive.",
+      "\t\n\nNonenzymatic glycation of proteins and lipids occurs with aging, a process that is accelerated in the setting of glucose dysregulation, such as diabetes mellitus [7].Advanced glycation end products (AGEs) formation has been implicated in a number of pathological processes associated with micro-and macrovascular diabetic complications [8][9][10].It has been demonstrated that the effects of AGEs are partially mediated through their interactions with cell surface receptor, the receptor for advanced glycation end products (RAGE) [11].The soluble form of RAGE (sRAGE) is a proteolytic cleavage product of RAGE, which has AGE-binding property but lacks the signaling cascade [12].In Caucasians without T2DM, sRAGE has been associated with decreased renal function assessed by estimated glomerular filtration rate (eGFR) or serum creatinine level [13][14][15].In Caucasian T2DM patients, sRAGE has been associated with albuminuria [16], decreased eGFR [17] and new or worsening kidney diseases and mortality [18].However, to date, only two studies reported associations of sRAGE level with renal function in Asians with T2DM [19,20].Although sRAGE is increasingly gaining importance as a biomarker in diabetic complications, it is not clear how sRAGE level is regulated and why it varies among studies.In addition, genetic studies of sRAGE remain very limited.",
+      "\t\n\nAdvanced glycation end-products (AGE) are the result of nonenzymatic glycation, which produces heterogeneous bioactive molecules, such as lipids, proteins, and nucleic acids [59].The accumulation of AGEs in aged tissues leads to several processes, such as inflammation, obesity, apoptosis, and other adverse processes related to ageing [47].These AGEs are detected by various techniques, such as gas chromatography, high-performance liquid chromatography, spectrometry, and immunochemical technique [60], which make them robust biomarkers that can be analyzed by different methodologies.",
+      "\t\n\nCritical areas of vascular aging research include the role of senescence, epigenetics, stress resilience, inflammation, macromolecular damage, proteostasis, mitochondrial and metabolic dysfunction, and impaired stem cell biology.The specific roles for cell-autonomous and noncell-autonomous mechanisms contributing to vascular aging need to be elucidated further.The role of signal transduction pathways linked to regulation of cellular energetics in the vascular aging process should be better defined.Future studies should also lead to improved understanding of the role circadian clocks to vascular aging.New studies investigating cellular heterogeneity in vascular aging are warranted.Stochastic macromolecular damage leads to regional variability in the presence of senescent cells, cells with altered metabolism, mitochondrial dysfunction, and increased ROS production.Such regional variability likely contributes to the focal development of vascular pathologies, ranging from atherosclerotic plaques to microhemorrhages.Single-cell gene expression analysis should facilitate better understanding of the pathophysiological role of functional heterogeneity.Finally, how environmental factors and lifestyle choice impact the vascular aging processes should be better understood.",
+      "\t\n\nThe characteristics of the second pathway include the formation of advanced glycation end-products (AGEs) from excessive imbibing of glucose [7].The AGEs via interaction with their receptor, RAGE, transduce a complex series of signaling events that result in cellular dysfunctions, thus generating an inflammatory response and reactive oxygen species (ROS), which in turn cause oxidative stress [7].Both in vitro and in vivo studies support the relevance of this pathway in the pathogenesis of diabetic nephropathy [7].The fact that several inhibitors of AGEs, such as pyridoxamine, LR-90 and KIOM-79, have been demonstrated to be beneficial in various murine models of diabetes emphasizes the role of AGE:RAGE interactions [8][9][10].Although these inhibitors may be effective in murine models, their efficacy certainly needs to be evaluated in diabetic nephropathy in humans.",
+      "\tAging is only, in part, the result of oxidative, free radical chemistry\n\nThe free radical theory of aging (Harman 1992) proposes that reactive oxygen is the major culprit in aging, leading to age-dependent oxidative modification, crosslinking and denaturation of proteins, with resultant loss of protein and enzyme structure and function.This theory has been expanded in recent years to include not only direct oxidation of proteins by reactive oxygen, but also the modification of proteins by Maillard reaction products, AGEs and ALEs (Thorpe and Baynes 1996).The majority of AGEs that are known to accumulate with age in tissue proteins are glycoxidation products, formed by combined glycation and oxidation reactions of precursors, such as glucose or ascorbate (Baynes 1991).In non-diabetic patients, levels of the glycoxidation products CML and pentosidine correlate with levels of methionine sulfoxide and o-tyrosine in skin collagen, indicating that these products are formed in parallel with one another (Wells-Knecht et al. 1997).Although oxidation appears to be important in the formation of AGEs and crosslinking of protein by glucose and ascorbate (Fu et al. 1994), some AGEs, such as pyrraline and crosslines, are formed non-oxidatively from glucose.The crosslines increase in lens proteins with age (Obayashi et al. 1996), so that oxidation is not essential for an age-dependent increase in crosslinking of protein by carbohydrates.In contrast to AGEs, ALEs require oxidative conditions for their formation -the first intermediate in ALE formation is a lipid peroxide, formed from a polyunsaturated fatty acid (PUFA) by an enzymatic or non-enzymatic autoxidation reaction involving molecular oxygen.The EAGLEs, CEL and MOLD, increase with age in collagen and crystallins, but cannot be classified as oxidative or nonoxidative since they may be formed either oxidatively during peroxidation of PUFA (Fu et al. 1996) or non-oxidatively from glyceraldehyde 3-phosphate or dihydroxyacetone phosphate formed during anaerobic glycolysis (Ahmed et al. 1997).Other modifications of amino acids, including deamidation, racemization and formation of hydroxykynurenine adducts are also age-dependent, non-crosslinking modifications of proteins.\tAging may be accelerated by inflammation and disease\n\nThe relationship between aging and age-related, chronic disease is complex.Healthy aging generally leads to a longer life, while chronic disease and associated inflammatory processes generally accelerate the aging process, i.e. shorten life span.The relationship between aging and chronic disease may be illustrated by diabetes, a disease in which the accumulation of AGEs in tissue proteins is accelerated by hyperglycemia.CML and pentosidine are biomarkers of normal aging of tissue collagens, and their accelerated accumulation in collagen in diabetes is de facto evidence that diabetes is a disease characterized by accelerated aging of collagen (Dyer et al. 1993).The acceleration of protein aging in diabetes is apparent, not only by the increase in AGEs, but also by increases in browning and fluorescence of collagen, and decreased solubility, decreased elasticity and increased thickness of basement membranes in diabetes (Baynes and Thorpe 1999).Notably, the rates of accumulation of other biomarkers, such as o-tyrosine and methionine sulfoxide in skin collagen, do not change significantly in diabetes (Wells-Knecht et al. 1997).Thus, the acceleration of chemical aging of collagen in diabetes is unbalanced or 'pathologic' in nature, apparently driven by the increase in circulating levels of oxidizable substrates (carbohydrates and lipids) (Baynes 1991(Baynes , 1999;;Baynes and Thorpe 1999a, b), rather than an increase in oxidative stress.Diabetes also increases the risk for cardiovascular disease, the major cause of mortality in the western world, while the increased risk for cataracts in diabetes may result from increases in both glycation and oxidative stress in the lens (Stevens 1998).",
+      "\tMG is elevated in the diabetic state and is\nthought to contribute to the development of diabetic complications, particularly through the\nformation of AGEs (60). AGE modification of vascular extracellular matrix proteins causes\n\nW\n\ncross-linking, which alters elastic properties and traps low-density lipoprotein in the vessel wall\n(60). Upon ligating RAGE, AGEs cause endothelial dysfunction, activation of NF-B, release of\n\nIE\n\npro-inflammatory molecules, and formation of vessel-damaging ROS (60). Through detoxifying\nMG, GLO1 is thought to protect against diabetic complications.",
+      "\tIt is based on the tendency of glucose to\nundergo oxydation in the presence of traces of heavy metal\nions, thus creating reactive ketoaldehydes, hydrogen peroxyde, and free radicals. It is clear now that the rearrangement of Schiff bases, Amadori products and/or AGEs is\naccompanied by generation of reactive oxygen species that\ncause conformational changes and fragmentation of the\nglycated proteins (11, 12). The proteins modified by AGEs\nare shown to be toxic, immunogenic, and capable of triggering cellular injury responses after binding to specific\nreceptors (1315).\tTaking into consideration that glycation is a slow process, it has always been regarded as typical for the longliving organisms and as affecting the long-living proteins\n(haemoglobin, crystalline, etc.)only. Surprisingly, our\nrecent studies indicated that glycation takes place also in\nE. coli and affects both the host bacterial and recombinant\nproteins (16, 17). Once started in vivo, glycation can not\nbe stopped after isolation and purification of the protein. Accumulation of AGEs continues even when pure protein preparations are stored in deep frozen solutions. A\ngreat number of studies have been dedicated to the search\nfor inhibitors of glycation.\tMullarkey CJ, Edelstein D, Brownlee M (1990) Free radical generation by early glycation products: a mechanism for accelerated atherogenesis in diabetes. Biochem Biophys Res Commun\n173:932939. Sakurai T, Tsuchiya S (1988) Superoxide production from nonenzymatically glycated protein. FEBS Lett 236:406410\nWendt T, Tanji N, Guo J, Hudson BI, Bierhaus A, Ramasamy R,\nArnold B, Nawroth PP, Yan SF, DAgati V, Schmidt AM (2003)\nGlucose, glycation, and RAGE: implications for amplification of\ncellular dysfunction in diabetic nephropathy. J Am Soc Nephrol\n14:13831395. Wautier JL, Schmidt AM (2004) Protein glycation: a firm link to\nendothelial cell dysfunction. Circ Res 95:233238.",
+      "\t\n\nFigure 15: Aspects of hyperglycemia-related vascular cell dysfunction.Hyperglycemia-induces a range of pathways in cells such as endothelium, and these include the polyol pathway, reactive oxygen species (ROS) formation, and advanced glycation endproducts (AGEs) formation.Excess glucose in endothelial cells enters polyol pathway; the electron donors like reduced nicotinamide adenine dinucleotide (NADH) and Flavin adenine dinucleotide (FADH2) accumulate in the mitochondria, thus affecting the electron transport chain; the excess electrons increase ROS in mitochondria; ROS triggers accumulation of AGEs; ROS and AGEs create mitochondrial DNA damage and mitochondrial dysfunction; protein kinase C (PKC) and AGE mediated activation of nuclear factor kappa B (NFB) activate the expression of inflammation proteins, tumor suppressor p53, and inducible nitric oxide synthase (iNOS); increased nitric oxide (NO) by iNOS is highly reactive with superoxide anions; the peroxynitrite thus generated acts as a strong oxidant and completes the vicious cycle of oxidative stress by increasing ROS production; accumulation of AGEs also increases ROS production independent of glucose levels\tM A N U S C R I P T A C C E P T E D ACCEPTED MANUSCRIPT 50\n\nglycation and lipoxidation end-products and upregulation of the receptor for AGEs (RAGE) has a key role in the hyperglycemia-induced activation of Mller glia and downstream cytokine production in the context of diabetic retinopathy (Berner et al., 2012;Curtis et al., 2011;Yong et al., 2010;Zong et al., 2010).Diabetes has also been reported to accelerate death of Mller glia (Feenstra et al., 2013;Hammes et al., 1995), an effect which has recently been linked to the disruption of retinal vascular integrity and the induction of neural cell dysfunction and death (Shen et al., 2012).A schematic diagram summarising how Mller glia changes are believed to contribute to the sight threatening complications of diabetic retinopathy is presented in Figure 11.Apart from the Mller cells, activated microglial cells adjacent to the vessels also appear to have a key role in vasoregression, the vascular hallmark of the early stages of diabetic retinopathy in both animal models (McVicar et al., 2015) and diabetic patients (Scott et al., 2014b).",
+      "\tTaking into consideration that glycation is a slow process, it has always been regarded as typical for the longliving organisms and as affecting the long-living proteins\n(haemoglobin, crystalline, etc.)only. Surprisingly, our\nrecent studies indicated that glycation takes place also in\nE. coli and affects both the host bacterial and recombinant\nproteins (16, 17). Once started in vivo, glycation can not\nbe stopped after isolation and purification of the protein. Accumulation of AGEs continues even when pure protein preparations are stored in deep frozen solutions. A\ngreat number of studies have been dedicated to the search\nfor inhibitors of glycation.\tMullarkey CJ, Edelstein D, Brownlee M (1990) Free radical generation by early glycation products: a mechanism for accelerated atherogenesis in diabetes. Biochem Biophys Res Commun\n173:932939. Sakurai T, Tsuchiya S (1988) Superoxide production from nonenzymatically glycated protein. FEBS Lett 236:406410\nWendt T, Tanji N, Guo J, Hudson BI, Bierhaus A, Ramasamy R,\nArnold B, Nawroth PP, Yan SF, DAgati V, Schmidt AM (2003)\nGlucose, glycation, and RAGE: implications for amplification of\ncellular dysfunction in diabetic nephropathy. J Am Soc Nephrol\n14:13831395. Wautier JL, Schmidt AM (2004) Protein glycation: a firm link to\nendothelial cell dysfunction. Circ Res 95:233238.\tIt is based on the tendency of glucose to\nundergo oxydation in the presence of traces of heavy metal\nions, thus creating reactive ketoaldehydes, hydrogen peroxyde, and free radicals. It is clear now that the rearrangement of Schiff bases, Amadori products and/or AGEs is\naccompanied by generation of reactive oxygen species that\ncause conformational changes and fragmentation of the\nglycated proteins (11, 12). The proteins modified by AGEs\nare shown to be toxic, immunogenic, and capable of triggering cellular injury responses after binding to specific\nreceptors (1315).",
+      "\tVascular endothelial dysfunction. In diabetes, endothelial dysfunction is linked to the accumulation of toxic lipids 90 , AGEs 91 and/or aggregated proteins 59 in the vasculature.Proteinaceous deposition on blood vessel walls damages endothelial cells 59,91 , increases the production of reactive oxygen species (ROS) 92,93 and impairs production of vasodilatory substances 92 , which results in a reduced cerebral blood flow.Stalled blood flow can lead to neurovascular uncoupling and hypoxic neuronal injury [92][93][94] .Elevated ROS production can further damage cellular structures and activate matrix metalloproteinases, inducing cytoskeletal reorganization and vascular remodelling 93 .Cytoskeletal reorganization affects the stability of tight junction proteins, resulting in increased capillary permeability, depletion of energy resources and altered neural viability 92,93 .",
+      "\t\n\nAdvanced glycation end products (AGEs) are a heterogeneous group of macromolecules that are formed by the nonenzymatic glycation of proteins, lipids, and nucleic acids.Overproduction of AGEs is considered the most important pathophysiological mechanism that induces diabetic complications (Semba et al. 2010).On one hand, AGEs mediate intracellular glycation of mitochondrial respiratory chain proteins and increase ROS levels, thus triggering oxidative stress (Coughlan et al. 2009) and endoplasmic reticulum stress (Piperi et al. 2012).On the other hand, binding of AGEs with receptors for advanced glycation end products (RAGEs) activates the AGE signalling axis to induce activation of NF-KB signalling and JAK/STAT signalling, which upregulate inflammatory cytokines and adhesion molecules (Basta 2008;Basta et al. 2004).The evidence indicates that exposure to AGEs is connected with the risk of adverse ageing-related outcomes.Akt1, Bsk, and P38b have been found to be crucial in the regulation of the AGE-RAGE-signalling pathway.Transforming growth factor beta (TGF-beta) is a major growth factor in joints that is crucial in maintaining chondrocyte homeostasis.However, the TGF-beta-signalling pathway changes with ageing, resulting in an age-related decline in the anabolic response that favours hypertrophy of chondrocytes and the development of osteoarthritis (Baug et al. 2014).In addition, Upadhyay et al. also reviewed the important role of TGF in the developmental processes of D. melanogaster and the role of TGF in regulating hormones, neurons and innate immunity (Upadhyay et al. 2017).Therefore, ageing-induced TGF-beta dysregulation is associated with deleterious effects on longevity and ageing itself.Dpp, Mad, and S6k are functionally crucial in the TGF-beta-signalling pathway.",
+      "\tIntroduction\n\nIn individuals with diabetes, nonenzymatic glycation of proteins leads to the formation of advanced glycation end products (AGE) and this process occurs at an accelerated rate in chronic hyperglycaemia 1 , and also the levels are found to be increased in complications of diabetes, such as diabetic retinopathy (DR). 2 AGE induces a variety of pathological changes, such as increased basement membrane thickening, arterial stiffness, and glomerular sclerosis. 3,4AGEs bind to a specific receptor known as receptor for advanced glycation end products (RAGE).RAGE is expressed in many of the cell types, such as the endothelial cells, monocytes, and lymphocytes, including the beta cells of the pancreas.RAGE-mediated signaling leads to the activation of transcription factors, such as NF-kB, AP-1, and STAT-1, 5,6 the adhesion molecules VCAM, ICAM, and tissue factor, 7,8 which promote a procoagulant state in the microcapillaries of the retina.This results in a hypoxic state that leads to the initiation of the angiogenic process in proliferative DR."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "A05D259409652DBA4BBB171E44BC0E4A"
+    },
+    {
+      "task_id": "92D5CE6EE0709DACC5A0B1DAFC050200"
+    },
+    {
+      "task_id": "82159196857E23B681446BAEAD1E37B8"
+    },
+    {
+      "task_id": "62833A83C24DBF2F02AB95C0D6E00814"
+    },
+    {
+      "task_id": "0BF2D6A0BF2A7B5B35D42D578BF25E9E"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_3.json
new file mode 100644
index 0000000..a9cecd0
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_3.json
@@ -0,0 +1,99 @@
+{
+  "question": [
+    "How do age-dependent changes in the immune system, such as immunosenescence, contribute to increased susceptibility to diseases?",
+    "How do advancements in machine learning and artificial intelligence aid in the identification of biomarkers for biological aging?",
+    "What recent discoveries have been made regarding the impact of systemic factors, such as circulating microvesicles, on aging phenotypes?",
+    "How do changes in the gut microbiome composition correlate with aging and longevity?",
+    "What are the key molecular mechanisms through which caloric restriction exerts its lifespan-extending effects across different species?"
+  ],
+  "answer": [
+    "Immunosenescence, the age-related decline in immune efficacy, affects both the innate and adaptive immune systems. This decline compromises the body's defense against pathogens, leading to increased susceptibility to infections and diseases. Additionally, aging is associated with 'inflamm-aging,' a state of chronic sterile inflammation that can promote age-related diseases and functional decline. Changes in the immune system also include a decrease in the expression of genes associated with key immune functions, such as phagocytosis in macrophages, which can lead to dysfunction of innate immune cells. Furthermore, the accumulation of apoptosis-resistant cells in the elderly can lead to dysfunctional immune responses.",
+    "Advancements in machine learning and artificial intelligence aid in the identification of biomarkers for biological aging by integrating and analyzing large and diverse datasets generated from genomic, functional, phenotypic, and lifestyle data. These technologies can predict age, forecast potential diseases in aging, and contribute to personalized medical treatment. Machine learning algorithms can also be used to assess the importance of specific factors in aging, predict future outcomes, and identify potential biomarkers for age-related diseases. Furthermore, they can help in the interpretation of complex omics data sets, which contain vast measurements of potential candidate markers.",
+    "Recent discoveries have shown that systemic factors, including circulating microvesicles, play a significant role in aging phenotypes. For instance, age-related alterations in vasoprotective endocrine factors, such as growth hormone, IGF-1, and estrogens, have been found to regulate multiple aspects of vascular aging processes. Studies using heterochronic parabiosis in mice have demonstrated the impact of circulating factors on aging phenotypes. Additionally, there is initial evidence that antigeronic factors present in young mice can rejuvenate microvascular network architecture in aged mice. However, the exact nature of these antigeronic circulating factors remains unknown. Progeronic circulating factors, which increase with age and impair tissue homeostasis, have also been identified. Further studies are needed to identify additional progeronic and antigeronic factors and their impact on aging.",
+    "Changes in the gut microbiome composition correlate with aging and longevity in several ways. Studies on centenarians and supercentenarians have shown that the microbiota adapts to the physiological changes of the long aging process, promoting health and survival. The concentration of certain bacteria, like Bacteroidetes, increases with age, while others like Actinobacteria decrease. Age-related decrease in microbiota diversity can lead to larger populations of certain microbial species, potentially increasing the chances for the evolution of novel, potentially pathogenic strains. These changes can contribute to increased frailty and development of diseases during the late stages of life. However, a healthy microbiota, characterized by the presence of bacterial compounds like Christensenellaceae, Akkermansia, and Bifidobacterium, has been linked to longevity.",
+    "The key molecular mechanisms through which caloric restriction extends lifespan across different species include signaling through the insulin-like growth factor pathway, chromatin regulation by sir2, and oxidative damage. Caloric restriction also increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes, which directly intervenes in the repair of DNA damage. Additionally, it affects nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling and target of rapamycin (TOR) signalling."
+  ],
+  "contexts": [
+    [
+      "\t\n\nOn the other hand, a direct relationship exists between physiological aging and increasing incidence of chronic inflammatory diseases.In its acute form, inflammation acts as a protective mechanism in response to pathogen invasion or tissue damage and helps to restore physiological integrity and function.However, in its chronic form, inflammation can exert detrimental effects on the cellular as well as the organismic level.Chronically inflamed tissue is characterized by infiltration of immune cells, neovascularization, fibrosis, and often tissue damage and necrosis [3].The innate immune system, especially the mononuclear phagocyte system, is the most important mediator of chronic inflammation.Monocytes originate from the myeloid hematopoietic cell lineage in bone marrow.In the blood stream, monocytes are recruited by specific stimuli into different tissues, where they differentiate into phagocytic Oxidative Medicine and Cellular Longevity macrophages.Macrophages participate in the killing of invading microorganisms and emerging tumor cells through the production of reactive oxygen or nitrogen species (ROS and RNS).In addition, macrophages secrete cytokines, which play a key role in the regulation of multiple immune functions, especially inflammatory responses [3].During aging, the continuous pressure on the immune system caused by repeated antigen stimulation, such as infections, food antigens, allergens, and self antigens, leads to an increase in activated cells and secretion of proinflammatory cytokines, such as TNF [4].These circulating proinflammatory factors may keep the immune system in a state of chronic lowlevel activation, a phenomenon described as \"inflammaging\" [5,6].Eventually, this causes \"immunosenescence,\" that is, an age-related decline in the capacity of adaptive immunity, consisting of more specific responses carried out by B and T cells [7].Thus, with advanced age, the immune system undergoes a gradual remodeling in the attempt to reestablish a new balance that assures survival, however, favoring the development of chronic inflammatory conditions [5,6,8,9].",
+      "\tThe Neuroimmune System Upon Aging\n\nThe age-associated synaptic dysfunction can also be a consequence of alterations in astrocytes and microglia, as the aging process has also been described as inflammaging, a status of chronic inflammation that contributes to the pathogenesis of neurodegenerative diseases [174].Recent data further suggest an important role of the immune system in regulating the progression of brain aging and neurodegenerative disease.This can be seen as a cause-or-consequence dilemma: do immune and inflammatory pathways become hyperactivated with age and promote degeneration or, instead, immune responses fail to cope with age-related stress and may contribute to disease [175]?",
+      "\tAging is one of the inevitably dominant risk associated with many diseases. Several biological factors contribute to this etiology which include loss of telomeres, stem cells activity and metabolism, escalation of environmental and biological stress, dysfunctioning of various micro-and macromolecules, and cell cycle and weakening of immune system (Franceschi et al., 2018).In case of cellular and molecular damage before elderly age, injury is healed to maintain the hemostasis.Nonetheless, with aging, repair mechanism is slowed or completely halted, leading to number of pathologies (Cortopassi, Gurung, & Pinto-Plata, 2017).",
+      "\t\n\nimmunity can become hyperactivated, exacerbating the age-related damage caused by innate immune responses [33].The risk of collateral damage by the adaptive immune system also potentially increases with age via autoimmunity factors, but this is believed to be counteracted by a parallel rise in self-protective mechanisms [42].Overall, the collateral damage inflicted by the innate immune system over the course of a long life is likely to be greater than that caused by adaptive immunity.\t\n\nThe damage caused by the ageing adaptive and innate immune systems gives us insights into how these different arms of the immune system may influence longevity.In general, adaptive immune function diminishes with age, whereas innate immune function is maintained [34,[43][44][45][46]. Whilst this may initially suggest that the innate immune system withstands the test of time better than the adaptive immune system, a chronic stimulation of innate immunity underpins this pattern [35].Innate immune cells become increasingly proinflammatory with age [46,47] and trained",
+      "\t\n\nThe increased expression of genes involved in immune response and inflammation observed in the colon of the 21-month-old mice points to an affected immune system in this part of the intestine of aging mice.This observation is in agreement with the fact that changes in the immune system are one of the hallmarks of the aging body.Immunosenescence is the functional decline of the adaptive immune system brought on by natural aging whereby protection against infection by pathogens and the effectiveness of vaccination decline [45,46].The second aging-induced change in the immune system is called inflammaging which is characterized by a lowgrade chronic inflammation process that contributes to the pathogenesis of many age-related diseases [47][48][49].A large variety of cells with a defense function are present especially in the lamina propria and the submucosa of the intestine accomplishing immune protection via the innate as well as by the adaptive immune response.Interestingly, our microarray and Q-PCR data clearly show that activity of both branches of the immune system is enhanced in response to aging exclusively in the colon but not in the small intestine of old mice.Expression levels of well-established pro-inflammatory cytokines like IFN, TNF, IL6 and IL1 turned out to be extremely low in the colon of both old and young mice and below the threshold of our microarray analysis.These low expression levels are probably due to the fact that these cytokines are predominantly produced by immune cells in the mucosa which is a rather low percentage of cells in relation to all cells present in the intestinal tissue.Q-PCR analysis confirmed the very low basal expression levels of these pro-inflammatory cytokines, yet a weak but significant induction of IFN TNF and IL-1 in the colon of aging mice was observed.This result suggests that low-grade inflammation might be present in the colon of the aging mice in our study, although it should be noted that no altered expression of a number of established inflammation markers like Tolllike receptors (TLRs), C-type lectin receptors (CLRs) and retinoic acid-inducible receptors (RLRs) [50] was detectable.",
+      "\tIntroduction\n\nAgeing of the immune system (immunosenescence) contributes to the increased susceptibility of the elderly to infectious disease and to the poor outcome of vaccination.Defence against pathogens is compromised mainly because of changes in adaptive immunity mediated by T and B lymphocytes; however, all components of the immune system are affected (Fig 1).Dissecting the crucial alterations responsible for dysfunctional immunity in old age will facilitate the development of rational interventions to reconstitute appropriate immune function.Given the increasing proportion of elderly people in most countries and their disproportionate consumption of health-care resources, this issue is rapidly gaining in importance.The meeting, which was dedicated solely to studies of immunosenescence, filled two days with the 'A to Z' of immunity, covering topics ranging from development to senescence, innate immunity to adaptive immunity, and genes to environments, in organisms ranging from mice to monkeys and humans.Understanding and eventually modulating immune dysfunction in the elderly now beckons.\tClinical implications of immunosenescence\n\nAs mentioned above, complications from acute infectious are likely to be more severe in the elderly owing to impaired innate immunity.However, questions remain concerning 'normal, healthy' ageing and the important clinical issue of responses to vaccinations in old age.In a mouse model of the highly relevant human pathogen influenza, the virus is cleared from the lungs more slowly in old animals, correlating with a delayed and decreased peak of cytotoxic T-cell production (D.Murasko, Philadelphia, PA, USA).Therefore, cellular responses are crucial for controlling the virus, but do not function adequately in old animals.Although there is an accumulation of memory cells (the clonal expansion referred to above), they are not solely responsible for this decrease in the virus-specific response.Both memory and naive T cells in old, but not young, mice are resistant to apoptosis, and do not 'make space' for new responses.In the mouse model, cell-transfer experiments showed that both the old environment and the old cells contributed to the problem-young cells did not deplete when transferred to an old environment and old cells did not deplete when transferred to a young environment.The factors inducing apoptosis resistance have not yet been identified; however, it is clearly important to do so and to search for them in humans.\tConclusions\n\nAll components of the immune system are altered as ageing proceeds (Fig 1 ); however, the T-cell and B-cell compartments seem to be particularly susceptible.The most severe clinical impact is probably a result of the loss of diversity in the TCR and B-cell-receptor repertoire, owing to the accumulation of dysfunctional cells, and decreased thymic and bone-marrow output.Several interventions discussed at the meeting could conceivably contribute to the restoration of appropriate immune function in the near future.\tLymphocyte development and ageing\n\nThe cells of the immune system turn over rapidly and therefore need constant replacement from the pool of haematopoietic stem cells (HSCs).If the HSCs themselves aged, it would compromise all downstream events that depend on their integrity, including production of immune cells and subsequent immune responsiveness (Rando, 2006).Evidence for age-associated alterations in the ability of HSCs to reconstitute the haematopoietic system of an animal derives from findings of increased self-renewal with age, resulting in an expansion of the HSC pool size even when transplanted into young animals (D.Rossi, Stanford, CA, USA).However, purified HSCs from old mice showed less activity on a per-cell basis and tended to generate more myeloid cells-for example, macrophages-than lymphocytes.Expression profiling of young and old HSCs revealed that genes mediating lymphoid fate and function were systematically downregulated, whereas myeloid-specification genes were upregulated, with age.The concerted nature of these changes suggests epigenetic involvement as a mechanism that contributes to HSC functional decline with age.There is also a gradual decline in the ability of murine HSCs to progress through the various stages of B-cell-differentiation (K.Dorshkind, Los Angeles, CA, USA).This reflects, in part, the microenvironmental changes involving altered production of interleukin 7 (IL-7) by stromal cells as they age (M.Cancro, Philadelphia, PA).B cells must also compete for the cytokine BLys (or B-cell activating factor (BAFF)), the receptor levels of which determine survival.Declining B-cell production in aged animals results in selective accumulation of marginal zone and memory B cells at the expense of the follicular pool of B cells.The follicular pool is responsible for producing protective immune responses to newly encountered pathogens, such as influenza H5N1.Loss of the declining stem-cell function, and the resultant decline of the follicular B-cell compartment, leads to enhanced infectious disease-related morbidity with ageing (J.Cambier, Denver, CO, USA).Hence, age affects both HSCs and the environment that determines their fate.\tInnate immunity\n\nSo, what are the age-associated changes that can be directly measured in macrophages, dendritic cells, neutrophils, natural killer (NK) cells and so on?These might be at least as important, if not more so, than the changes to adaptive immunity discussed above (Solana et al, 2006).The number and proliferation of a particular subset of 'natural' T cells with NK-cell and regulatory functions, bearing invariant V14J18 receptors (iNKT cells), is decreased in the elderly; however, whether these changes have any clinical impact is not yet known (R. Solana, Crdoba, Spain).Neutrophils from old people retain normal chemotaxis and superoxide-generation capacity, but are compromised in phagocytosis in the healthy elderly and more so in the traumatized elderly ( J. Lord, Birmingham, UK); these findings have important implications for infection in the elderly.Trauma, in the form of burn injury in mice, resulted in the death of old animals from infections that young animals were able to resist.This susceptibility of old mice correlated with higher levels of pro-inflammatory IL-6 and decreased T-cell function, and could be in part reversed by oestrogen treatment (E.J. Kovacs, Maywood, IL, USA).Dendritic cells-the essential bridge between innate and adaptive immunity-are similar in young and old people in terms of their response to cytokines (although those from the elderly secrete more IL-6 and tumour necrosis factor- (TNF)), surface phenotypes and morphology, whereas chemotaxis and, as with neutrophils, phagocytosis are impaired (S.Gupta, Irvine, CA, USA).Gene arrays indicate only a small number of differences between young and old dendritic cells, far fewer than in T cells.Nonetheless, functional impairment in antigen presentation was found, such that dendritic cells from young or old people stimulated naive CD8 cells equally well, but those from the elderly failed to stimulate CD4 cells appropriately.\t\n\nApoptosis-resistant cells that accumulate in old mice and humans-and fill the 'immunological space'-might be dysfunctional in several ways.In young mice, the number of T cells staining with soluble major histocompatibility complex (MHC)-peptide multimers carrying influenza epitopes was similar to the number of cells producing the antiviral and pro-inflammatory cytokine interferon- (IFN) on antigen stimulation.However, in old mice, the number of tetramer-positive cells exceeded the number of IFNproducers, indicating that some cells bearing antigen-specific receptors failed to respond appropriately to receptor ligation (H.Ertl, Philadelphia, PA, USA).This is similar to the situation in elderly humans, who have been found to accumulate large clonal expansions, primarily-and for unknown reasons-of cytomegalovirus (CMV)-specific CD8 cells (Pawelec et al, 2005).In the mice, this lack of reactivity was not due to poor antigen presentation by dendritic cells (Ertl).The reason for poor reactivity remains unknown; however, responses could be restored, in part, by vaccination using an adenovirus vector AdC68 that naturally infects chimpanzees rather than mice, as a way of improving immunizations by modifying the vaccine product.This might also be possible in humans by using better adjuvants for vaccination (E.Nagy, Vienna, Austria).Deciphering the mechanisms by which adjuvants enhance responses in order to design 'elderly-specific' vaccines will become increasingly important.This applies not only to infectious diseases but also possibly to vaccinating against cancer, as illustrated by differences in responses to anticancer immunizations in young and old mice.In a breast cancer model, preventive vaccination using DNA encoding certain cancer antigens was successful in protecting 90% of the young mice, but only 60% of the old mice, from developing metastases.This correlated with lower levels of IFN and IL-2 in old mice (C.Gravekamp, San Francisco, CA, USA).The production of IL-6, which is a potential inhibitor of vaccine-induced T-cell responses, was high in both young and old mice.Increasing IFN and IL-2, and depressing IL-6 production in the elderly, would therefore seem to be desirable.",
+      "\tAging and variability among immune cells\n\nHow and why the immune system becomes less effective with age are not well understood.Martinez-Jimenez et al. performed single-cell sequencing of CD4+ T cells in old and young mice of two species.In young mice, the gene expression program of early immune activation was tightly regulated and conserved between species.However, as mice aged, the expression of genes involved in pathways responding to immune cell stimulation was not as robust and exhibited increased cell-to-cell variability.",
+      "\t\nThe aging population is at a higher risk for age-related diseases and infections.This observation could be due to immunosenescence: the decline in immune efficacy of both the innate and the adaptive immune systems.Age-related immune decline also links to the concept of 'inf lamm-aging,' whereby aging is accompanied by sterile chronic inf lammation.Along with a decline in immune function, aging is accompanied by a widespread of 'omics' remodeling.Transcriptional landscape changes linked to key pathways of immune function have been identified across studies, such as macrophages having decreased expression of genes associated to phagocytosis, a major function of macrophages.Therefore, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.In this review, we discuss both molecular and cellular phenotypes of innate immune cells that contribute to age-related inf lammation.\t\n\nThe aging population is at a higher risk for age-related diseases and infections.This observation could be due to immunosenescence: the decline in immune efficacy of both the innate and the adaptive immune systems.Age-related immune decline also links to the concept of 'inf lamm-aging,' whereby aging is accompanied by sterile chronic inf lammation.Along with a decline in immune function, aging is accompanied by a widespread of 'omics' remodeling.Transcriptional landscape changes linked to key pathways of immune function have been identified across studies, such as macrophages having decreased expression of genes associated to phagocytosis, a major function of macrophages.Therefore, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.In this review, we discuss both molecular and cellular phenotypes of innate immune cells that contribute to age-related inf lammation.\tIntroduction\n\nThe human population is aging, which has led to the rise in prevalence of many so-called age-related diseases.Not only is the aging population much more susceptible to age-related diseases, they are also more susceptible to infections.For example, elderly individuals are at a higher risk of developing severe COVID-19 or complications from influenza infections [1,2].This increased chance of infection can be due to the decline of the function of the immune system, a phenomenon called 'immunosenescence' [3].Age-related changes in the function of the immune system are also accompanied by a chronic sterile inflammation, a mechanism dubbed 'inflamm-aging,' which is thought to promote age-related disease and functional decline [4].Inflamm-aging is associated with many different factors, most typically encompassing increases in pro-inflammatory cytokines tumor necrosis factor alpha [TNFa], interleukin 1 beta [IL1b] and interleukin 6 [IL6] [5].Although these cytokines may directly contribute to increased systemic inflammation.Age-related increase in genomic instability may itself also drive aspects of inflammaging.Indeed, re-activation of LINE-1 transposable elements during aging and in senescent cells has been proposed to drive an interferon response, thus contributing to sterile inflammation [20][21][22].In addition, chronic DNAdamage signaling itself, for instance in aged lymphocytes, may also render them more activation-prone through innate receptors even in the absence of infection [23].\t Immune decline is a hallmark of aging.  Aging associates with a state of chronic sterile inflammation.\t Aging associates with a state of chronic sterile inflammation.  Innate immune cells undergo widespread molecular and functional remodeling with aging.\t\n\nIn this review, we will focus on how innate immune cells act as key contributors to age-related inflammation (Figure 1).We will discuss both molecular and cellular phenotypes which have been described in the aging innate immune system, and how they could relate to the phenomenon of inflamm-aging and immunosenescence.\t\n\nImportantly, a key mechanism underlying innate immune cell dysfunction during aging may stem from dysregulation of youthful genomic networks.Indeed, aging is accompanied by widespread remodeling of transcriptional landscapes across tissues and cell types (reviewed in [33]).In addition, age-related inflammatory signatures at the transcriptional levels have been observed across species and tissues, suggesting that such 'omic' remodeling is a conserved aging response [34,35]."
+    ],
+    [
+      "\t\n\nKnowledge of genetic interrelationship between the biomarkers of aging may lead to the discovery of a downstream common pathway that summarizes aging processes; the list of biomarkers should be as comprehensive as possible via incorporating other well-known systems involved in aging in addition to the musculoskeletal system.Further development of the pleiotropy-based approaches will be useful for other studies of multiple related phenotypes which employ genome-wide associations to decipher genetics in the absence of disease endophenotypes, which is the case of human aging.With the advent of these approaches, new candidate genes may emerge for further pursuit.In its turn, discovery of the \"phenome of aging\" may translate into innovative diagnostic and therapeutic interventions to improve the overall health of older men and women.",
+      "\t\n\nBiomarkers of aging can be used to assess the health of individuals and to study aging and age-related diseases.We generate a large dataset of genome-wide RNA-seq profiles of human dermal fibroblasts from 133 people aged 1 to 94 years old to test whether signatures of aging are encoded within the transcriptome.We develop an ensemble machine learning method that predicts age to a median error of 4 years, outperforming previous methods used to predict age.The ensemble was further validated by testing it on ten progeria patients, and our method is the only one that predicts accelerated aging in these patients.",
+      "\t\n\nIt should be mentioned that although the objectives of those researchers sound encouraging and ambitious, the search for biomarkers of ageing for their application in the improvement of human health, and prevention of diseases related to ageing, will only increase the generation of data.The great part of the search for biomarkers has been as a result of the extensive studies of human cohorts, resulting in genomic, functional, phenotypic, and lifestyle data of the individuals studied (Table 13.1).Thus, due to the generation of these data and technological advances, possibly in the future, artificial intelligence programs will be able to reliably forecast the life of an individual, as well as the possible diseases that he may suffer in ageing; so these advances and discoveries will allow us to achieve a \"personalized medical treatment\" as a result of to the integration of biomarkers of ageing.\tMeg3\n\nDecrease in cell senescence [85] (continued) number of biomarkers that are candidates to determine human ageing.However, these biomarkers have considerable variability among different individuals because the ageing process has an intrinsic multicausal nature.So, a multisystemic integration of biomarkers to determine biological age is still reliably found.Currently, thanks to the different analyses performed using new technologies and new knowledge on the molecular basis, there are leading to the discovery of many Biomarkers classified according to their type and their modulation in ageing novel molecular markers.Some of these technologies are the omics techniques, such as metabolomics, proteomics or genomics, also induces data generation, offering an overview of new biomarkers of ageing.However, it remains to be clarified which markers can be an accurate, reliable predictor of ageing.Among the various studies carried out to solve these questions, the MARK-AGE study was a project supported by the European Commission.The main objective of this project was to carry out a population study of approximately 3200 subjects to identify a set of ageing biomarkers, which together with correctly established parameters, would measure the biology of an individual, compared to the result that would only have using a biomarker individually [72].\tIntegration of Biomarkers of Ageing\n\nBiomarkers of ageing allow estimating the biological age of an organism (Table 13.1) while providing information on their health status.Different studies are looking for the integrated use of multiple biomarkers, in order to make the estimation of health status more accurate.As we could see throughout this chapter, there are a large\t\n\nTo make significant progress in aging research, we urgently need molecular biomarkers for aging studies, particularly in humans.This chapter focuses on the inflammatory state, the markers of oxidative stress, and the hormonal profile which are the main functions that impact the development of aging and can be influenced by the gene and environmental variables in which human beings develop.",
+      "\tDiscussion\n\nMachine-learning can be applied as a systems biology approach, integrating multiple classes of biometric data to assess the importance of specific factors, while also predicting future outcomes.Whereas conventional assessments of disease identification exist, more detailed genomic and epigenomic testing is likely to reveal a comprehensive, systemic valuation of an etiology.To-date, studies have applied machine-learning algorithms in examining the physiological, biochemical, and/or genetic components of disease onset or progression [51].The advantage of our current study is through the assimilation of patient-matched data across a variety of critically impacted systems, providing an archetype for developing novel, descriptive, diagnostic measures through machine-learning algorithms that are specific for each disease type.By individually representing our datasets in Figs. 2, 3 and 4, we were able to reach more conclusive data in Fig. 5 by choosing the most predictive features for our final model.For the first time, a multi-omics, machine-learning approach was used to assess the progression and development of type 2 diabetes mellitus in a patient population, identifying potential biomarkers for cardiovascular risk and revealing the fundamental role of genetics in the pathology.\t\n\nIn the current study, machine-learning was used as a predictive tool to integrate cardiac physiological, biochemical, genomic, and epigenomic biomarker data in a patient-matched fashion and enable determination of type 2 diabetic status.In 50 patients, machine-learning algorithms revealed the interconnectedness between diabetic classification, mitochondrial function, and methylation status.Our study highlights how novel biomarkers can be used to augment existing diagnostic standards as well as provide new, and more precise, methods for identifying the development and severity of type 2 diabetes mellitus in potentially at-risk populations, such as those with prediabetes.While we examine physiological, biochemical, and molecular datasets using machine-learning algorithms, our goal was to understand which features possessed the best predictive accuracies and if these specific features could be used alone, or in conjunction, with HbA1c.The purpose for the inclusion of models that do not rise above 50% predictive accuracy was to contrast them against those models that do rise above 50% in the absence of HbA1c, to determine which biomarkers are the best overall predictors.\t\n\nThe quantity and diversity of omics-based approaches continues to expand.Convenience and increasingly inexpensive options for biometric-based valuations incite a growing demand for the incorporation and meaningful explanation of large and diverse patient datasets.The methodology outlined in this manuscript can serve as an archetype for the development and implementation of machine-learning to other disciplines seeking to evaluate disease progression.By using various health outcomes datasets, we were able to identify, and combine, the most prominent biomarkers into an accurate predictive algorithm engineered around 50 patients.While we have identified specific genetic features that are highly predictive in 50 patients, as a much larger patient population is applied to this model, the prioritization of other features is likely to occur, enhancing the diagnostic potential for the individual diabetic or prediabetic patient.Indeed, this is the advantage of using machine-learning models, in that they continue to learn and develop more accurate predictions as the number of features and sampled population grows.\tMolecular pathogenesis and machine-learning\n\nWhile clinical practice has recently experienced a surge in deep learning applications used for non-invasive imaging [52], implementing machine-learning algorithms to the fundamental biochemistry and cellular and molecular processes of the body is now only blossoming.Onset and progression of type 2 diabetes has been traditionally measured through blood glucose levels, but, the multifaceted aspects of the disease could create variability in prognosis between vastly different demographic and ethnic groups.Owusu Adjah et al. [14] recently identified BMI as a risk factor for determining ethnic group disposition to type 2 diabetes mellitus.Specifically, the relationship between BMI and increased incidence of diabetes mellitus is non-linear; some groups, such as South Asian populations, were more disposed to developing the disease even at lower BMIs.While the current Fig. 6 Overview of machine-learning pipeline implementing biological variables across a spectrum of gathered information.From the patient population undergoing coronary artery bypass graft surgery (CABG), physiological parameters (demographics, health reports, etc.) and atrial tissue were used for subsequent analyses.From cardiac tissue genomic (mitochondrial DNA), epigenomic (TFAM promoter CpG methylation), and biochemical (nuclear and mitochondrial function) were assessed.Cumulatively, the biological data was processed through tree ensembles in SHAP and validated through CART analysis with tenfold cross validation.Using these machine-learning algorithms, graphical depictions and biomarker feature importance are able to be derived, allowing for prediction of the onset and progression of diabetes.Ultimately, by using biological data at the genomic and epigenomic level, it allows for precision medicine approaches and more personalized diagnostics and prognostics.TFAM: transcription factor A, mitochondrial; mtDNA: mitochondrial DNA; CpG: cytosine nucleotide followed by a guanine nucleotide; CART: Classification and Regression Trees; SHAP: SHapley Additive exPlanations manuscript examines cardiovascular tissue, other less invasive approaches have been used to apply machinelearning algorithms.By retrieving blood from the basilica vein, circulating biomarkers were examined for their role in predicting early recurrence of atrial fibrillation following cryoballoon ablation [53].Support vector machines confirmed that decreased levels of creatine-kinase (CK-MB) and Troponin T (TnT) were associated with increased early recurrence of atrial fibrillation following cryoballoon ablation.Additionally, a unique, non-invasive approach for potentially diagnosing type 2 diabetes in patients was performed through the examination of toenails.Carter et al. [54], through a variety of machine learning algorithms, focused on 22 elements, including aluminum, cesium, nickel, vanadium, and zinc, and was able to get an AUC of 0.90 when predicting diabetic status using a random forest model.Similar to parts of the aims of this study, other groups have attempted to use machine learning to separate diabetic and non-diabetic patients without the inclusion of blood glucose or HbA1c [55].In a testing set of 13,700 patients from the Luzhou, China region, random forest machine-learning algorithms provided a 0.7225 accuracy when predicting diabetic status from physical examination data in the absence of blood glucose [55].Also using a random forest model, Tang et al. [56] revealed how CpG island methylation data, combined with microRNA expression profiles, can be instrumental in cancer pathogenesis; implementing this two-feature selection process, they were able to identify the best tissue specific features, ultimately allowing for the identification of the originating tissue where tumor progression began.In a similar fashion, the machine-learning algorithm HeteSim [57], which examines heterogeneous datasets and calculates their relatedness, was employed in ascribing how gene profiles can be related to phenotypic outcomes, specifically in the validation and prediction of genes classified within major diseases [58].",
+      "\tWhat do chemical biomarkers tell us about aging? Aging is not a homogeneous process\tThe nature of chemical biomarkers of aging\n\nCentral to the study of chemical theories of biogerontology is the definition of biomarkers of the aging process, chemical 'handles' that can be used to assess the progress of aging and the effectiveness of anti-aging strategies.As it turns out, most of the age-biomarkers measured today are products of non-enzymatic chemistry.Living organisms are complex mixtures of reactive chemicals, including dietary components, metabolic intermediates, side-products of metabolism, xenobiotics, drugs, etc.Reactions between the constituents of this mixture occur at random throughout the body, but evidence of the role of cumulative non-enzymatic chemistry in aging is most apparent in long-lived proteins, such as lens crystallins and tissue collagens.The increase in post-synthetic chemical modifications of crystallins with age results in an agedependent increase in brown color and fluorescence of lens proteins.These chemical modifications are associated with aggregation, crosslinking and insolubilization of lens proteins, leading gradually to the development of cataracts (Hoenders and Bloemendal 1983;Harding et al. 1989).Similar changes occur in collagens (Bailey et al. 1998) leading to decreased elasticity of the extracellular matrix, resulting, for example, in the age-dependent stiffening of tendons  Dilysine crosslink",
+      "\t\n\nPeople of the same chronological age have different aging states, which can be monitored using various biomarkers (Belsky et al. 2015).These markers are usually measurable indicators of a particular outcome or source of aging, such as phenotypical measures like frailty and molecular measures like DNA methylation dynamics (Schumacher et al. 2021;Lpez-Otn et al. 2023).Although informative, they are not always quantitatively predictive of an individual's true biological age, nor are they easy to obtain.The advancement of high-throughput screening platforms and extensive longitudinal studies has greatly facilitated the search for new noninvasive and quantitative biomarkers of aging.For instance, highthroughput sequencing allows unbiased multiomics profiling of DNA, RNA, and epigenetic changes during aging, providing a comprehensive view of senescence at tissue and single-cell levels (Solovev et al. 2020;Aging Atlas Consortium 2021).These omics data sets contain vast and noisy measurements of potential candidate markers and, consequently, require carefully designed computational models to identify and extract predictive signals from the data.However, construction of such models is often highly degenerate, yielding little overlap of identified biomarkers between studies and thus making results difficult to interpret (Thompson et al. 2018;Galkin et al. 2020).\t\n\nMost of the existing omics-based aging clocks have been constructed using data from bulk tissues, which neglect the variations in cell compositions and cell-to-cell aging heterogeneity.To gain a more detailed and nuanced view of cell type-specific molecular changes during aging, several studies have applied machine-learning models to single-cell transcriptomics and DNA methylation data (Trapp et al. 2021;Buckley et al. 2023).Despite their success in predicting chronological age within specific training contexts, these clocks are constrained by their applicability to a limited number of cell types and tissues.Their generalizability to other cell types and disease data, particularly in cases with ambiguous cell type identities, remains uncertain.Additionally, problems like data sparsity and batch effects are more pronounced in single-cell omics data, further complicating the identification of consensus aging markers and the interpretation of model results.Furthermore, as chronological age is often the only available measure of biological age, it becomes critical to determine whether the features learned from single-cell omics data can capture other dimensions of biological aging.",
+      "\t\n\nEach of these criteria deserves some amplification.A biomarker validation program would start with a list of candidate biomarkers, each known to be age-sensitive (by cross-sectional and/or longitudinal analyses) in adults.By hypothesis, some of these traits would reflect interindividual differences in the aging process, but each would also be sensitive to genetic and nongenetic factors that also vary among individuals, statistical \"noise\" that would interfere with the extraction of the \"signal\" attributable to aging itself.A correlation between age-sensitive immune parametersfor example, T-cell proliferation and T-cell cytokine production-would be relatively unhelpful in evaluating each of these parameters as potential biomarkers of aging, because the two assays are closely related and likely to be influenced by many factors unrelated to aging (e.g., recent infection, vaccination history, polymorphisms in immune system genes).However, a correlation between T-cell proliferation and, for example, muscle strength, or reflex speed, or lens protein cross-linking, or age at menopause, would be difficult to attribute to any obvious metabolic or pathophysiological mechanism other than linkage to some fundamental aging rate that might by hypothesis retard or accelerate changes in a wide range of age-sensitive traits.",
+      "\tMultiomics technology\n\nThe broad diversity of omics biomarkers that have been used to assess biological responses provides new opportunities to understand the impact of the environment on the risk of age-related diseases.For example, the multiomics analysis and integration method produces a priority list of multiple sets of biomarkers, which together reflect the molecular responses of the exposome.Each of these data warrants integration into a biomarker panel to aid physicians in developing age-related disease diagnoses and prognoses [78].",
+      "\t\n\nOverall, demonstrating that a particular intervention is affecting human aging, as done in model organisms, is virtually impossible.Interventions, including drugs, emerging from basic research on aging will probably target specific age-related pathological conditions and/or dysfunction.Subsequent studies of health biomarkers and multiple age-related diseases may reveal broader effects.Success in animal models or short-term human studies may be sufficient to convince potential patients of the usefulness of particular dietary supplements or approaches, as exemplified by those voluntarily undergoing CR (http://www.crsociety.org/),which can serve as basis for further studies (Soare et al., 2011).\t\n\nTo facilitate target gene prioritization, a number of additional approaches may be employed.For example, in silico studies of transcriptional regulation can allow the identification of upstream regulators (for review, see de Magalha es et al., 2010).Furthermore, an emerging approach to study the complex interactions between the multiple components of biological systems is network biology (Baraba si et al., 2011).Given the complexity of aging, network approaches may be particularly suited to identify crucial regulators of its modulation by the environment.For instance, knowing the protein-protein interaction network of candidate proteins allows the identification of hubs, proteins with a large number of interactions, which tend to be more biologically relevant (Fig. 3).Together with other biological (e.g., kinases and receptors are often seen as promising drug targets), medical, and strategic considerations already used for target selection in drug discovery (for review, see Knowles and Gromo, 2003), the integrated knowledge of aging-related pathways can help identify suitable targets for drug discovery.In addition, the advent of largescale databases of compounds and drugs, such as Drug-Bank (Wishart et al., 2008), STITCH (Kuhn et al., 2008), and the Connectivity Map (Lamb et al., 2006), paves the way to cross-linking longevity/CR-associated genes with drug databases to identify candidate molecules for effects on aging.\t\n\nWe now know of hundreds of genes that regulate aging in model organisms, dozens associated with longevity in humans, and hundreds differentially expressed with age.This vast amount of information yields increased power for personalized and stratified medicine, for identifying biomarkers of aging, and for drug development to extend lifespan and ameliorate age-related diseases.Overall, it gives us a blueprint (albeit still imperfect) of how aging is controlled that we can use to potentially manipulate the basic aging process, whatever its underlying molecular mechanisms may be.Moreover, our knowledge of nutrient-sensing pathways that mediate the effects of CR has greatly increased in recent years, opening new opportunities for drug discovery and ultimately for perhaps developing an antiaging pill that retards aging with minimal side effects.",
+      "\tIntegrating genomics and biomarker research\n\nOnce the use of established biomarkers of biological age is standardized, the biomarker information can be integrated into studies aimed at finding causal determinants of aging and longevity.An example of an integrated approach to identify lifespan regulating loci is represented by testing whether genetic variants associated with potential biomarkers also associate with longevity.To date, GWAS have identified many genetic variants that associate with age-associated traits, such as leukocyte telomere length and features from glycome and metabolome profiles [84][85][86].The joint effect of the majority of these variants on aging and longevity still needs to be determined.One study identified a haplotype in the TERT gene that was associated with increased telomere length and longevity, which indicates that genetic variants associated with telomere length regulation might also play a role in longevity [87]."
+    ],
+    [
+      "Several studies have shown\nthat the systemic milieu regulates stem cell decline during aging. Liang et al. showed\nthat HSCs have a reduced ability to home to the bone marrow and spleen after\ntransplantation into old versus young recipients (Liang et al. , 2005). Further experiments\ndemonstrated that the muscle stem cell niche adversely effects stem cell function as\nevidenced by the restoration of old stem cell regenerative potential upon exposure to a\nyoung systemic microenvironment (Conboy et al. , 2005; Conboy and Rando, 2005).\tHowever, studies do indicate that aged tissues have a diminished capacity to return to a\nhomeostatic state after exposure to stress or injury, therefore indicating a defect in stem\ncell function during the aging process. Since the HSC population provides an ideal\nmodel to study stem cell aging, it is necessary to elucidate the mechanisms of\nhematopoietic aging and expand the findings to other tissues and organ systems. Theories of Aging and Age Related Epigenomic Changes\nThere are two major theories of organismal aging: evolutionary and damage\nbased.\tHSCs as a Model for Stem Cell Aging\nWhen studying aging it is important to choose an appropriate model system. For\ninstance, cells (such as skin and blood) that undergo continuous turnover are removed\nfrom circulation long before they have time to feel the effects of aging, and certainly long\nbefore they could exert an effect on tissue function. The predominant substrates for\naging, thus it seems, would be long-lived cells in the organism, namely tissue specific\nstem cells, since this population is exposed to both intrinsic and extrinsic effectors of\naging throughout the lifespan of an individual.\tWith\nthis in mind, it has been hypothesized that the aging or functional failure of tissuespecific stem cells, which fulfill this job, may limit tissue repair and renewal, therefore\ncontributing to overall organismal aging (Krtolica, 2005; Van Zant and Liang, 2003). Because of the unprecedented experimental model systems that are available for the\nexploration of HSCs, stem cell aging research in the field of hematology has been the\nsubject of extensive studies. Indeed, the hematopoietic system has served as an important\nmodel for advancing our understanding of stem cell biology and its association with\naging.",
+      "The several lines of evidence support the hypothesis that essential metabolic pathways interconnected with environmental factors and genetic background are involved in the appearance of different markers of cellular senescence.They have emerged as potential regulators of cellular senescence, particularly through those pathways involved in the maintenance and repair of stem cells and progenitor cells: mitochondrial integrity, mitotic competence, and eradication of senescent cells.The complexity of events that are under the control of the genetic programs induced in response to environmental challenges creates the need for further studies that must be performed to unravel the biological roles of the highly dynamic aging process through different tissues and different stages of cell life.The increasing research across different species has allowed the identification of conserved processes associated with the biology of aging.However, it is essential to consider that information from lower organisms cannot be generalized, since worms do not develop age-associated diseases such as osteoporosis, arthritis, or Alzheimer's disease.",
+      "There is growing evidence that noncell-autonomous mechanisms play a critical role in orchestrating vascular aging processes (Figure 1).Aging-induced alterations in vasoprotective endocrine factors are of particular importance.Such changes include an age-related decline in circulating levels of growth hormone, 215 IGF-1, 216 and estrogens, all of which regulate multiple aspects of endothelium-dependent vasodilation, 217 autoregulation of blood flow, 218 vascular structural remodeling, atherogenesis, 219 and angiogenic processes. 220he impact of circulating factors on aging phenotypes was also demonstrated by studies using mice with heterochronic parabiosis, which involves surgically connecting the circulatory system of a young and an aged mouse. 221erebromicrovascular density typically declines with advanced age, 222 and there is initial evidence that circulating antigeronic factors (which reverse/prevent development of aging phenotypes) present in young mice can rejuvenate microvascular network architecture in aged heterochronic parabionts. 221he antigeronic circulating factors present in young mice are currently unknown, and the previously proposed role for GDF11 (growth differentiation factor 11) 221 remains controversial.Future studies should identify additional antigeronic factors that might be targeted by interventions to extend vascular health span.Progeronic circulating factors increase with age and impair tissue homeostasis in young animals.There is initial evidence that mediators secreted by senescent cells (eg, inflammatory cytokines, such as TNF- 35 ) may serve as progeronic circulating factors.Further studies are warranted to identify additional progeronic proteins and determine their impact on atherogenesis, endothelial function, blood-brain barrier integrity, and microvascular function in aging.\t\n\nAdditional evidence to support a central role of antigeronic circulating factors governing vascular aging processes is derived from studies on caloric restriction-a dietary regimen, which improves health and slow the aging process in evolutionarily distant organisms. 223Caloric restriction was shown to promote a youthful endothelial phenotype by upregulating and activating eNOS in aged animals [223][224][225] and perhaps humans. 226 critical role of antigeronic circulating factors in vasculoprotective phenotypic responses induced by caloric restriction was first indicated by the observations that in vitro treatment of cultured aged endothelial cells with sera derived from caloric restricted animals mimics phenotypic effects observed in vivo during caloric restriction, promoting anti-inflammatory and proangiogenic effects. 42,227Treatment with sera derived from caloric restricted animals upregulates SIRT1 228 ; however, the exact nature of the circulating factor responsible for this effect remains elusive. ][231] Human studies are needed to identify novel progeronic and antigeronic circulating factors and their cofactors, activators, or inhibitors/antagonists and to seek associations with vascular aging phenotypes.Future studies should also identify cellular origins of circulating progeronic and antigeronic factors that impact vascular aging and characterize pathological conditions that alter their levels in circulation with aging.Further, mechanistic studies describing the cellular effects of progeronic and antigeronic circulating factors in the vascular wall are warranted.",
+      "Mitochondrial-derived peptides (MDPs) in aging-related phenotypes",
+      "Background: Aging is believed to have a close association with cardiovascular diseases, resulting in various pathological alterations in blood vessels, including vascular cell phenotypic shifts.In aging vessels, the microRNA(miRNA)mediated mechanism regulating the vascular smooth muscle cell (VSMC) phenotype remains unclarified.MiRNA microarray was used to compare the expressions of miRNAs in VSMCs from old rats (oVSMCs) and young rats (yVSMCs).Quantitative reverse transcription real-time PCR (qRT-PCR) and small RNA transfection were used to explore the miR-542-3p expression in oVSMCs and yVSMCs in vitro.Calcification induction of yVSMCs was conducted by the treatment of -glycerophosphate (-GP).Alizarin red staining was used to detect calcium deposition.Western blot and qRT-PCR were used to investigate the expression of the smooth muscle markers, smooth muscle 22 (SM22) and calponin, and the osteogenic markers, osteopontin (OPN), and runt-related transcription factor 2 (Runx2).Lentivirus was used to overexpress miR-542-3p and bone morphogenetic protein 7 (BMP7) in yVMSCs.Luciferase reporter assay was conducted to identify the target of miR-542-3p.Results: Compared with yVSMCs, 28 downregulated and 34 upregulated miRNAs were identified in oVSMCs.It was confirmed by qRT-PCR that oVSMC expressed four times lower miR-542-3p than yVSMCs.Overexpressing miR-542-3p in yVSMCs suppressed the osteogenic differentiation induced by -GP.Moreover, miR-542-3p targets BMP7 and overexpressing BMP7 in miR-542-3p-expressing yVSMCs reverses miR-542-3p's inhibition of osteogenic differentiation.Conclusions: miR-542-3p regulates osteogenic differentiation of VSMCs through targeting BMP7, suggesting that the downregulation of miR-542-3p in oVSMCs plays a crucial role in osteogenic transition in the aging rat.\t\n\nBackground: Aging is believed to have a close association with cardiovascular diseases, resulting in various pathological alterations in blood vessels, including vascular cell phenotypic shifts.In aging vessels, the microRNA(miRNA)mediated mechanism regulating the vascular smooth muscle cell (VSMC) phenotype remains unclarified.MiRNA microarray was used to compare the expressions of miRNAs in VSMCs from old rats (oVSMCs) and young rats (yVSMCs).Quantitative reverse transcription real-time PCR (qRT-PCR) and small RNA transfection were used to explore the miR-542-3p expression in oVSMCs and yVSMCs in vitro.Calcification induction of yVSMCs was conducted by the treatment of -glycerophosphate (-GP).Alizarin red staining was used to detect calcium deposition.Western blot and qRT-PCR were used to investigate the expression of the smooth muscle markers, smooth muscle 22 (SM22) and calponin, and the osteogenic markers, osteopontin (OPN), and runt-related transcription factor 2 (Runx2).Lentivirus was used to overexpress miR-542-3p and bone morphogenetic protein 7 (BMP7) in yVMSCs.Luciferase reporter assay was conducted to identify the target of miR-542-3p.Results: Compared with yVSMCs, 28 downregulated and 34 upregulated miRNAs were identified in oVSMCs.It was confirmed by qRT-PCR that oVSMC expressed four times lower miR-542-3p than yVSMCs.Overexpressing miR-542-3p in yVSMCs suppressed the osteogenic differentiation induced by -GP.Moreover, miR-542-3p targets BMP7 and overexpressing BMP7 in miR-542-3p-expressing yVSMCs reverses miR-542-3p's inhibition of osteogenic differentiation.",
+      "The major question is whether replicative senescence does play a role in human aging.Several studies have shown an inverse relationship between donor age and the replicative life span in vitro for fibroblasts or MSC [13,44,45].This effect is usually relatively small with a high variation between different donor samples [12,46].At least some of the variability was attributed to differences in donor health status, conditions for the biopsy and the initial CFU-F frequency in the bone marrow sample [47].Furthermore, the pace of senescence might be affected by the culture conditions [19,48].In MSC preparations used in this study we did not discern any age-associated effects on replicative senescence.If the number of cumulative population doublings was not significantly affected by aging it is all the more surprising, that there was a significant association between age-induced gene expression changes and replicative senescence.These results indicate that the molecular sequels of aging in vivo and replicative senescence in vitro are based on similar mechanisms.",
+      "Finally, we asked whether additional cellular components of the immune system also show increased transcriptional variability upon aging.",
+      "Systemic aging has been more formally proposed as the hormonal\n\n3\ncontrol of aging, where changes in humoral factors with age can cause system-wide\nchanges in the homeostatic condition (Wise, Krajnak et al. 1996). Support for this idea\nhas gained traction from studies of mice expressing a mutant form of the KLOTHO gene\nencoding a protein hormone that leads to phenotypic changes characteristic of accelerated\naging (Kuro-o, Matsumura et al. 1997). Conversely, when the wild-type KLOTHO gene\nis overexpressed in mice it leads to a modest yet significant increase in both male and\nfemale lifespan (Kurosu, Yamamoto et al. 2005).\tStudies of invertebrate systems such as C. elegans and D. melanogaster\nhave yielded keen insight into stem cell biology and mechanisms of aging, but it has\npredominantly been the study of the mammalian hematopoietic system that has led to the\ncurrent understanding of the physiology of hematopoiesis. The utilization of mouse\ngenetics has only recently been fully realized as a tool as it was this mammalian model\nthat yielded the breakthrough discoveries of Till and McCulloch (Till and McCulloch\n1961).",
+      "Our results indicate that cell identity influences multiple aspects of aging, highlighting the importance of aging studies at the single-cell level.However, it remains difficult to identify which age-related changes are causal and link molecular changes at the level of individual cell types to physiological aging phenotypes, like reduced glomerular filtration rate or decreased pulmonary regeneration.Future single-cell studies may focus on collecting additional time points and phenotypes throughout the aging process, allowing for time series-based causal inference methods (Granger 1969;Bar-Joseph et al. 2012;Finkle et al. 2018;Qiu et al. 2018;Lu et al. 2019) to reveal the relationships between the molecular players of aging.Functional challenges, such as the differentiation of stem cells during regeneration or the stimulation of immune cells during infection, would also help dissect how transcriptional aging magnitudes and differential gene expression influence tissue function.Single-cell measurements collected during functional challenges may also reveal the dynamics of perturbation and subsequent return to homeostasis necessary to evaluate \"resilience\" in a given cell type (Kirkland et al. 2016;Hadley et al. 2017).\t\n\nAt both the molecular and functional level, a host of aging phenotypes and associated mechanisms have been revealed in individual cell types (Shaw et al. 2010;Chakkalakal et al. 2012;Keyes et al. 2013;Liu et al. 2013;Flach et al. 2014;Blau et al. 2015;Brack and Muoz-Cnoves 2016;Keyes and Fuchs 2018).Although some of these studies present unique features of aging within individual cell identities, it is difficult to compare them systematically because of differences in experimental conditions and assay methodology.Using traditional molecular biology assays, it is difficult to measure high-dimensional molecular phenotypes across multiple cell identities, making large-scale comparisons of aging phenotypes across cell identities intractable.The recent development of single-cell RNA-sequencing (scRNA-seq) has ameliorated this limitation, allowing for measurement of transcriptional features across all prevalent cell identities in a tissue in a single experiment.\t\nAging is a pleiotropic process affecting many aspects of mammalian physiology.Mammals are composed of distinct cell type identities and tissue environments, but the influence of these cell identities and environments on the trajectory of aging in individual cells remains unclear.Here, we performed single-cell RNA-seq on >50,000 individual cells across three tissues in young and old mice to allow for direct comparison of aging phenotypes across cell types.We found transcriptional features of aging common across many cell types, as well as features of aging unique to each type.Leveraging matrix factorization and optimal transport methods, we found that both cell identities and tissue environments exert influence on the trajectory and magnitude of aging, with cell identity influence predominating.These results suggest that aging manifests with unique directionality and magnitude across the diverse cell identities in mammals.\t\n\nAging is a pleiotropic process affecting many aspects of mammalian physiology.Mammals are composed of distinct cell type identities and tissue environments, but the influence of these cell identities and environments on the trajectory of aging in individual cells remains unclear.Here, we performed single-cell RNA-seq on >50,000 individual cells across three tissues in young and old mice to allow for direct comparison of aging phenotypes across cell types.We found transcriptional features of aging common across many cell types, as well as features of aging unique to each type.Leveraging matrix factorization and optimal transport methods, we found that both cell identities and tissue environments exert influence on the trajectory and magnitude of aging, with cell identity influence predominating.These results suggest that aging manifests with unique directionality and magnitude across the diverse cell identities in mammals.",
+      "Discussion Consequences of disease as well as age exert profound influences upon cells including alteration of gene expression, metabolism, functional competency, replicative potential, and more [10,18].Certain features of aged cells are exacerbated or mitigated by environmental conditions in host tissues such as oxidative stress, nutrient status, inflammatory / cytokine production, and pathological changes [5,7,40,42].Many of these conditions can be recapitulated in cell culture studies with treatments that mimic the aged tissue environment [6,37].Studies using established cell lines to study biological consequences of aging are of limited value for extrapolation to the complex in vivo mileau.In situ studies have provided significant insight regarding adaptations and distinct features of aged cells [9,46,55], but whether the characteristic phenotypic state of aged cells is retained following isolation and culture expansion is poorly understood.Moreover, conditions of culture expansion inherently favor cells with the highest proliferative and survival potential.Thus, it is unclear to what extent culture expansion allows hallmarks of aging to persist when harvesting cellular samples from aged tissue and subjecting them to multiple passages after initial isolation.",
+      "Concluding remarks and future perspectives\n\nAging research has rapidly expanded over the past two decades, with studies ranging from lifespan-extending  [68,69,71].However, when their effect on cell death and senescence leads to stem cell loss and tissue degeneration, they might contribute to aging [66,67]."
+    ],
+    [
+      "\t\n\nHowever, the simplest solution to restoring pathological disturbances in the composition of the gut microbiota may be a change in dietary habits.Diet has been shown to strongly affect the composition of the microbiome (73).When obese humans were put either on a fatrestricted or carbohydrate-restricted low-calorie diet, an increase in the abundance of Bacteroidetes and a decrease in Firmicutes was reported (12).In another study, diet-induced weight loss versus weight-stabilization interventions in obese humans increased intestinal microbial gene richness and was associated with a reduced systemic inflammation (74).These data corroborate with another controlled diet intervention study in 98 human subjects showing that certain dominant gut microbial communities, or \"enterotypes,\" correlated with specific kinds of diets (73).For example, Bacteroides was associated with a protein-rich diet, whereas Prevotella correlated with a fiber-rich diet; moreover, gut microbiota composition could be altered within 24 h whereas enterotype remained stable during the 10 days of the study.Based on this rapid and dramatic plasticity of intestinal microbiota composition, there is a specific need to determine intestinal microbiota composition in a standardized way (e.g., sequencing several fecal samples per person over a specific time point while taking dietary intake and medication use into account).",
+      "\t\n\nWe next performed partial correlation analysis to investigate whether exercise-induced compositional changes in microbiota were associated with improvements in clinical parameters independent of body weight, fat mass, and visceral fat.We found that after adjustment for body weight and adiposity, associations between alterations of microbial species and improvements in insulin sensitivity-related indexes and a cluster of other metabolic features remained significant (Figure 3).At the community level, alteration in the gut microbiota was significantly associated with the percentage reduction of HOMA-IR (p < 0.01, ADONIS).Among the 19 species significantly correlated with the improvements of glucose homeostasis and insulin sensitivity, Ruminococcus gnavus, Alistipes shahii, Streptococcus mitis group, Eubacterium hallii, and Escherichia coli showed the strongest associations (Figure 3).Consistently, most of these species were also found to be differentially altered between responders and non-responders (Figure 2E).Taken together, the above findings imply that distinct changes of these species may underlie the difference in the improvement of glycemic homeostasis in response to a standard exercise regimen.",
+      "\t\n\nOn the other hand, studies on centenarians and supercentenarians have evidenced the adaptation of the microbiota to the physiological changes of the long aging process.It has been demonstrated that the microbiota on this population maintains the health and promotes the survival.Additionally, a relationship between a healthy microbiota and longevity had been proposed [44].A possible pathway is an immunological and metabolic regulation linked to the increase of bacterial compounds like Christensenellaceae, Akkermansia, and Bifidobacterium [44,45].\t\n\nFigure 9.1 depicts a visual representation of the gut microbiota composition throughout the lifespan.Variations between individuals and within an individual throughout the lifespan can be seen.In this respect, it can be said that the concentration of Bacteroidetes grows as an individual does, from 12.6% for newborns to 57% for older adults.Conversely, Actinobacteria composition reduces with age until it reaches 0.4%, and the Firmicutes, Proteobacteria, and other microbial are maintained relatively stable throughout life in healthy adults and decay at old age [20][21][22].\t\n\nThe human holobiont (commensal microbes and their multicellular eukaryotic host) constitutes a highly integrated system, which undergoes dynamic changes through time as it integrates and responds to signals from the environment.Microbiome research and aging is flourishing as we better understand the bidirectional interactions, and its evolution with a life-course perspective for the gut microbiota undergoes dynamic changes during host aging.Changes in host intestinal cell Foreword vii composition and architecture occurring during aging are matched by a decrease in the microbiota taxonomic diversity.Age-related decrease in taxonomic diversity leads to larger population size for a few age-associated microbial species, increasing the chances for the evolution of novel potentially pathogenic microbial strains, which have been related both to neurodegeneration and frailty.This knowledge positions the microbiome as a promising element for translational research.\t\n\nAll the information given by the aging research allows knowing that the microbial composition has an essential role in the establishment of cellular and tissue homeostasis.Additionally, it is known that age-dependent changes in the microbial composition can contribute to increasing of frailty and development of diseases during the late stages of life [42,43].\t\n\nAlthough the causes that lead to changes in the composition and function of the microbiota during aging are still unknown, the evidence has established that the local microbiome plays an essential role in human health.\t\n\nTherefore, research in the field has demonstrated that aging is a potential modifier of the composition and function of the human microbiome.Figure 9.3 shows the local composition of the microbiome in an average older adult.It can be seen that Bacteroidetes and Firmicutes species are the most prevalent in this age.\tMicrobiome Research and Aging: A Clinical Perspective\n\nAging is characterized by the accumulation of damage at the molecular level (DNA and proteins) and dysfunction of the organelles [31][32][33].In addition to senescent cells and compositional changes in the extracellular compartment, these changes are determinants of the organic and systemic decline [34][35][36].The microbiota reacts dynamically to these environment changes by altering the metabolic function and composition of individual bacterial species.\tConclusions\n\nDuring the last years, significant advances in the field of microbiome and aging research have been carried out; new approaches for its study have allowed the understanding of the genomic nature of the microbiota.In this regard, the introduction of metagenomics had increased knowledge of the genes that potentially allow microbes to influence their hosts in unexpected ways.Thanks to these advances, it is well known that microbiota constitutes an essential determinant of the health and longevity of humans.\t\n\nFig. 9.1 Gut microbiota throughout lifespan\tMicrobiome and Age-Related Neurodegenerative Diseases\n\nDifferent microorganisms such as bacteria, fungi, archaea, and viruses compose the human intestinal microbiota that represents, in physiologic conditions, a perfect commensalism association with their host [51,52].In general, the human intestinal microbiota is shaped by the healthy microbiota (bacteria that normally colonize the intestine) and opportunistic bacteria (which are the agents responsible for infections).Among the billions of symbiotic microorganisms that compose the intestinal microbiome, four bacteria phyla are mainly reported in adults, i.e.Firmicutes (~51%), Bacteroidetes (~48%), Proteobacteria, and Actinobacteria, (1%) [53].Lactobacteria species stand out among the normal microbiome (Lactobacillus rhamnosus, Lactobacillus acidophilus, and Lactobacillus plantarum), Bifidobacterium (B.bifidum), Enterococci, Propionobacteria, and Peptostreptococci.In the same way, opportunistic bacteria include the Bacteriodes spp.Bacilli, Clostridia, Enterobacteria, Actinobacteria, Peptococci, Staphylococci, and Streptococcus [54].Several factors, such as diet, hygiene, antibiotic exposure, and modify the intestinal microbiota [55,56].Interestingly, age also contributes significantly to the microbiome modification; in fact a recent publication highlights the vital role that represents the host aging in the microbial evolution since as the host get aged the organism experiments molecular and functional changes that induce shifts to the microbial niche [57], nevertheless, for detailed information about changes in microbiome during aging, please refer to the Chap.9 in this book.In the following paragraphs, we discuss the recent data about the relationship between the pathogenesis of the two most prevalent ND and the microbiome, which represents a new field of research.\t\n\nDiet can be a potent gut microbiome modifier.For this reason, numerous studies have been conducted to demonstrate the impact of specific diet components on the diversity of the gut microbiota [8].The results of many of these studies have proved that probiotics and prebiotics consumption are a feasible alternative, especially for specific population groups such as older adults [59].\t\n\nMany areas of opportunity can be mentioned.However, modulation of the microbiome by extrinsic factors can be a way to apply the actual knowledge in the clinical setting.Nowadays, it is possible to ensure that lifestyle and diet play a significant role in determining the microbiome.In this respect, novel therapies, as fecal transplantation adds to the traditional dietary interventions, both demonstrated to be a potential therapeutic approach for the aging population.\t\n\nIt is well known that aging is a risk factor for neurodegeneration and dementia [58]; nevertheless, recent studies support the idea that gut microbiota may have an effect on the brain and the behaviour of patients, since the evidence suggests that some metabolites secreted by the intestinal microbiota can affect in a certain way, the cognitive capacity of patients diagnosed with ND [59][60][61][62][63].This hypothesis is not entirely new since several decades ago, the concept that bidirectional communication between the CNS and the intestinal organs plays a role in emotional regulation [64,65].Four decades later, the hypothesis that the brain has a regulation of the gastrointestinal tract arose and with the help of the murine model, the existence of the brain-gut axis was reported [66].This axis is carried out through the neuroendocrine and neuroimmune system, working together with the sympathetic and parasympathetic arms of the autonomic nervous system and the enteric nervous system.",
+      "\t\n\nChanges in the gut microbiota in terms of composition and functionality during the process of aging have previously been reported [19,20,51] and it has been postulated that these changes might contribute to the development of immunosenescence and inflammaging [18,52].To establish whether the enhanced expression of genes playing a role in the immune system are due to modifications in the microbiota we measured the total number of all bacteria and of the two most prominent phyla colonizing the colon, Bacteriodetes and Firmicutes, in the luminal content of the colon.We did not observe aging-related changes.More advanced techniques like pyrosequencing are required to determine whether total number of bacteria and changes in the composition of the microbiota might play a causal role in the observed changed expression of immune-related genes in the colon of our aging mice.Although it is difficult to assess the physiological consequences of the enhanced expression of genes involved in inflammation and immune response, it seems most likely that this effect is important for the health status of the aging colon.",
+      "\tSignatures of aging in gut\n\nFor gut or the digestive system, six clusters of age-associated genes had significant enrichment of functional annotations (Fig. 2C; Supplemental Table 10).Aging in gut was found to be associated with down-regulation of genes (Clusters 1, 2, 3, and 4) participating in oxidative phosphorylation, aromatic compound metabolism, muscle contraction, amino sugar metabolism, regulation of apoptosis, and vesicle transport.Aging was also associated with up-regulation of genes (Clusters 5 and 6) involved in regulating various physiological processes, amino acid metabolism, and regulation of transport.These results suggest that metabolic pathways, especially nutrient intake and energy production, are primarily affected during aging of gut, which are the fundamental function of the digestive system.",
+      "\t\n\nSequencing of bacteria species within our gut, collectively labeled the gut microbiome, explains individual differences in the metabolism of consumed food with potential associations with body weight (Karlsson, Tremaroli, Nielsen, & Backhed, 2013).Gut permeability to bacteria is further associated with obesity and obesity-related inflammation (Teixeira et al., 2012).Over time, these mechanisms will more fully be integrated into the overarching models of obesity.",
+      "\tThe microbiome and weight change\n\nThe human microbiome may play a significant role in the etiology of obesity in both humans and animal models (64).Hosted in the gastrointestinal tract, the gut microbiome is part of a large endocrine organ that regulates not only nutrient sensing and metabolism but also satiety and energy homeostasis.The millions of microorganisms comprising the complex intestinal \"superorganism\" perform a number of functions for host health, including food processing, breakdown and metabolism of indigestible nutrients, pathogen displacement, synthesis of vitamins, and regulation of body weight (65).They play such an important role that we now know that microbiota disruptions in early life can have long-lasting effects on body weight in adulthood (66).The host bacterial composition has been shown to adapt in response to dietary factors and in response to weight loss.Diet or surgically induced weight loss promote alterations in the gut that can impact the efficacy of the treatment strategies (67,68).Specific bacterial species can have influences by themselves.For example, the archaeon Methanobrevibacter smithii, has an enhanced ability to metabolize dietary substrates or end products of the metabolism of other bacteria, thereby increasing host energy intake and weight gain (69).",
+      "\tThis microbial\ncommunity is established early in life, influenced by maternal and environment factors and\nable to impact the health of the host [2]. For example, early studies provided evidence that\ndiet plays an important role in the composition of gastrointestinal microbiota. Specifically,\ntransition to a low-fat diet in overweight humans led to a gut microbial composition similar\nto that of healthy controls [3, 4]. Also, gnotobiotic animals displayed substantial weight gains\nfollowing exposure to a complex gastrointestinal microbiota from overweight individuals\n[5, 6]."
+    ],
+    [
+      "\tCONCLUSIONS\n\nOur purpose in this review is to outline the prospects of unifying mechanism in the genetics of aging.In case after case, from mice to worms to flies to yeast, genetic variants that modify metabolism also modify life span.These effects, collectively, are as general as that of caloric restriction, which also increases longevity and resistance to stress in many situations.The evolutionary theory of aging proposes that the life span is indirectly selected on the basis of the reproductive schedule.In turn, the reproductive schedule is coordinated by neural and endocrine mechanisms in multicellular organisms.Therefore, to consider that genes determining the life span could be expressed in neuronal and endocrine cells in diverse animals is no longer far-fetched.Consistent with this hypothesis are experiments in Drosophila and C. elegans in which life span was manipulated by the expression of genes in specific neurons.Genetic approaches may, thus, be able to identify a set of circuits that regulate longevity that were established in ancestral metazoans.",
+      "\tGenetic Programs\n\nAs stated above, the universality of aging phenotypes within a species argues for an underlying genetic program.The redistribution of the Sir complex from telomeres to the nucleolus in yeast is a specific molecular While the effects of these hormones on specific orthan rats fed ad libitum, with a consequent decline in the incidence of hepatocellular carcinoma (Muskhelishvili gans are apparent, their relation to the aging process itself, if any, is not yet clear.To our knowledge, there has occurred in the past 200 years.However, slowing the aging process may increase vitality and quality of has been no animal study in which hormone supplementation extended maximum life span.However, the recent life over the entire life span of individuals.In this regard, it is noteworthy that calorically restricted rodents have findings in C. elegans provide a basis to believe that humoral factors may turn out to play an important role an extended life span that is relatively free of disease.For society, the implications of slowing the aging pro-in at least some aspects of human aging.cess are more complex.Of course, in an increasingly overpopulated world, it would be important to offset Perspective any significant effects on longevity with a compensatory Recent advances in the study of aging indicate that this reduction in birth rates.In fact, in many industrialized process is amenable to molecular analysis and may be countries, the current birth rate is sufficiently low to relatively simple.The potential of single gene mutations afford zero or negative growth.Most importantly, if the to greatly extend life span in model systems suggests slowing of aging is associated with improved health and that relatively few limiting cellular or organismal proproductivity of long-lived individuals, there may be a cesses control the rate of aging, at least in these species.",
+      "\t\n\nThen we have those pharmaceutical strategies that are www.impactaging.combased on emulating the pathways implicated in the response of lifespan to dietary restriction, particularly sirtuin-targeting agents like resveratrol [e.g.25].Again, like hormone manipulation, these pathways are heavily bound up with the regulation of reproduction, making the curtailment of the cost of reproduction the most likely mechanism by which the beneficial effects of emulating dietary restriction are achieved [cf. 26].This is a strategy in which longevity is increased by metabolic refrigeration, pseudo-hibernation, or curtailing functions [11].From the standpoint of evolutionary biology, this is, again, not an extension of the period of adaptation.It is instead trading one set of adaptations off against another.Most people do not regard curtailing their metabolism, cognition, affective stability or reproductive functions as a useful approach to the problem of aging.Nonetheless, some are willing to trade-off some of their adaptive functions for an increased lifespan, and for them this \"anti-aging\" strategy will have its attractions.",
+      "\tMetabolism\n\nStudies show that calorie restriction is the most consistent means to prolong life expectancy and health across several experimental models [55], ranging from yeasts to primates.It not only increases life expectancy, but it also delays the onset of many features and hallmarks of ageing, including age-related diseases.Transcriptional profiles are currently being applied and investigated.One of them is a caloric restriction (CR), which increases the response to oxidative stress and reduces the shortening of telomeres in chromosomes; this has a direct intervention in the repair of DNA damage.Data from human trials (such as CALERIE, Biosphere-2 and CRON) indicate that moderate CR accompanied by adequate nutrition has positive effects on health and dramatically reduces the multiple metabolic factors involved in the pathogenesis of disease chronicles, including type 2 diabetes, heart and cerebrovascular diseases, and cancer [56].",
+      "\t\n\nLimitations of translating the results of preclinical studies should be recognized.An important recent example is caloric restriction. 239Although caloric restriction confers significant life span extension and cardiovascular protection in laboratory rodents 5,18,42,97,223,240,241 and in certain cohorts of nonhuman primates, 227,242 its protective effects in nonhuman primates in other studies 243 and in patients with multiple cardiovascular risk factors are less evident. 244Additionally, in cross-sectional studies, the older groups may represent a selected long-lived subset of the younger population.There are existing longitudinal studies in humans (eg, InCHIANTI study) and nonhuman primates, and important information related to mechanisms of vascular aging could be derived from add-on studies to these existing cohorts.",
+      "\t\n\nOn the other hand, the beneficial effects of caloric restriction are associated with alterations in metabolism, particularly the insulin/insulin-like growth factor 1 (IGF-1) pathways, which could reflect an evolution mechanism to ensure survival of a species during period of food shortage [3].Many genetic manipulations affecting nutrient-sensing pathways including the insulin and mTOR (mammalian target of rapamycin) pathways mimic the effect of caloric restriction on lifespan in yeast, worm, flies and mice and support this hypothesis [3].This review will firstly discuss in general terms how trace elements affect ageing and then use Selenium (Se) as an example to illustrate how trace elements influence the ageing process.Furthermore, the review will also illustrate how the so-called \"Omics technologies\" can be used to unravel the modes of action of trace elements and to identify biomarkers to define the optimal intake for health at the molecular level.\t\n\nEvidence is building up showing that caloric restriction, without malnutrition, extends lifespan in species ranging from yeast to non-human primates [3], but it appears, on the contrary, that inadequate/sub-optimal intake of micronutrients contribute to the development of chronic diseases.In his \"Triage theory\", B. Ames suggested that this could reflect the need for an organism to re-allocate micronutrients according to triage priorities to favour short-term survival over long-term wellbeing [4,5].The consequences of this re-allocation may remain unnoticed in the day-to-day experience but are likely to show up late in life as cancers, Alzheimer's disease, Parkinson's disease, diabetes and cardiovascular diseases.",
+      "\t\n\nCaloric restriction (CR) is the only intervention shown to extend lifespan in mammals (5).It is also the most effective means known of reducing cancer incidence and increasing the mean age of onset of age-related diseases and tumors (6).Our studies made use of an experimental design that allowed us to clearly distinguish the effects of diet from those of age on genome-wide expression patterns.Another distinctive aspect of the study allowed us to resolve changes in gene expression induced directly by CR from those that arise over time as a consequence of the interaction between CR and aging.",
+      "\tGenDR-genomics of DR\n\nDR, of which caloric restriction is the most widely studied regimen, is the most robust non-genetic intervention shown to extend lifespan in a multitude of species, from yeast to mammals (12,14).However, the exact mechanisms of how DR extends lifespan remain unknown.To decipher the mechanisms of DR in a systematic fashion, we established GenDR (http://genomics.senescence.info/diet/), the first database of DR-associated genes.Because GenDR and related analysis of DR networks have been recently described elsewhere (15), they will only be briefly described herein.To create GenDR, we compiled from the literature a list of DR-essential genes from model organisms.DR-essential genes were defined as those which, if genetically modified, interfere with DR-mediated lifespan extension and, ideally, do not affect the lifespan of animals on an ad libitum diet (or at least do not appear to be merely causing disease).A subset of these genes act as genetic DR mimetics, as their manipulation leads to an increased lifespan for ad libitum fed animals, which is not further extended by DR.One such example is the growth hormone receptor gene in mice (16), in fact the only mouse gene currently in GenDR.In GenDR, the respective homologues of DR-essential genes are included for all the common model organisms, as well as for humans (15).A complementary data set in GenDR is a list of genes consistently differentially expressed in mammals under DR.In a recent meta-analysis, a common signature of genes differentially expressed in DR across different mammalian species, strains, tissues and experiments was derived.This signature provides a set of genes that are most robustly responding to DR (17).",
+      "\t\n\nIt seems that organisms from yeast to mammals have evolved genetic programs to cope with periods of starvation that can also postpone aging and age-related diseases, but how can we take advantage of those mechanisms to improve human health?Because assaying the longevity effects of CR in humans is practically impossible, studying its molecular mechanisms in lower life forms could be beneficial to humans through the identification of candidate genes, pathways and molecular mechanisms.Although CR will not be suitable for everyone, targeting its mechanisms and developing CR mimetics may lead to drug development for a number of age-related and metabolic diseases.\t\n\nBy far the most widely studied dietary manipulation of aging is caloric restriction (CR), also called dietary restriction.CR consists of restricting the food intake of organisms normally fed ad libitum without triggering malnutrition and is the only dietary intervention shown, to date, to increase longevity and modulate the process of aging in several model organisms (Bishop and Guarente, 2007;Fontana et al., 2010;Spindler, 2010).Even in mammals, such as mice and rats, CR can extend longevity by up to 50%, delay physiological aging, and postpone or diminish the morbidity of most age-related diseases (Masoro, 2005).Ongoing studies in rhesus monkeys suggest that CR can lower the incidence of aging-related deaths in primates (Colman et al., 2009).",
+      "\tINTRODUCTION\n\nGenomic studies into human longevity are inspired by the fact that, in animal models, healthy lifespan has proved to be remarkably plastic, and major pathways of lifespan regulation have been identified.Considerable lifespan extension has been induced in models as diverse as yeast, worms, fish, flies and rodents by applying genetic manipulation and dietary restriction (DR) (see [1] for review).Reduced activity of nutrient-sensing pathways such as insulin/insulin-like growth factor (IGF-1) signalling (IIS) and target of rapamycin (TOR) signalling mediated lifespan extension, and also the extension of lifespan by DR [2].An interesting observation from the perspective of human ageing is that, in rodents and monkeys, diets restricted in glucose, fat or protein uptake reduced or delayed the risk of cancer and metabolic disease, thus extending the healthspan of the animals [2].Following the discovery of genes and pathways involved in animal lifespan extension, human research has focused on the corresponding candidate human genes with genetic, genomic and epigenetic studies into ageing and longevity.The designs of these studies differ with respect to the selection of naturally occurring phenotypes and the study populations, which include population-based, patient-based, family-based and exposure-based cohorts.",
+      "\t\n\nThe 'hormesis' hypothesis of aging is based on the observation that caloric restriction or chronic low-level exposure to any of these stresses induces cross-resistance to other stresses at the same time that it extends life span (41).Hormesis effects on aging are observed in many eukaryotes in addition to budding yeast.Although the mechanistic details of these effects remain unclear, we have argued that they include a general response to environmental stresses that blocks entry into S phase under environmentally stressful conditions that are suboptimal for replicating DNA, thus protecting cells from replication stress (30).",
+      "\tINTRODUCTION\n\nMore than 70 years ago, McCay and his colleagues demonstrated that a reduction in total food intake after weaning significantly increased both mean and maximum life spans of laboratory rats (1).Over the last seven decades, numerous laboratories have successfully repeated McCay's findings using various strains of rats and mice as well as non-mammalian species, such as fish and flies (2)(3)(4)(5)(6).Thus, food restriction has been established as a powerful experimental tool, and the anti-aging action of food restriction has become one of the most active areas of research in the realm of biogerontology (6).While life span extension by food restriction appears to be due to alterations in aging processes, the underlying mechanism(s) by which food restriction exerts its anti-aging effects remain elusive.Identification of important antiaging and anti-tumor targets of food restriction and elucidating the molecular mechanisms by which food restriction exerts its beneficial effects could eventually provide targets for intervention in humans.",
+      "\tIn comparison, caloric\nrestriction, intermittent fasting, or a ketogenic diet generally improve lifespan and health\n811 These dietary effects are not solely dependent on patterns of caloric intake, but are\nmodulated by dietary macro- and micronutrient composition, the amount of time spent in\ndifferent metabolic states, age of onset, periodicity of access to food, sex, and of greatest\nimportance to us in this studydifferences in genometype (strain) and gene-by-dietary\ninteractions 12,13. While the effects of differences in dietary composition and caloric restriction on lifespan\nhave been studied extensively, key results remain controversial 1416.\tThis again indicates that that weight gain\naccounts for only 45% of the change in lifespan. Author Manuscript\n\nOur findings can be compared to strain variation and GXE effects in response to dietary\nrestriction. Dietary restriction without malnutrition is regarded as having an almost universal\nbenefit on longevity 5355. One exception is a pair of studies on the impact of moderately\nintense restrictiona 40% reduction in caloric intakeacross a large family of LXS strains\nof mice (n of up 44 strains with 1020 replicates per strain) 17,19.",
+      "\tNutrition, phenotype and longevity\n\nNo issue so 'vividly' illustrates the power of diet to alter health as the consistent observation of the effect of caloric restriction (CR) on longevity.To date, neither drug, gene nor environmental intervention have been successfully demonstrated to prolong longevity in animals; however, the simple reduction of food calories can increase life span by 30-40% across a number of model organisms, including yeast, Drosophilia, Caenorhabditis elegans, rodents and monkeys [5][6][7].This effect of CR raises one of the most intriguing questions facing life scientists today.Despite the demonstrated positive age-related benefits of a reduction in energy intake -including decreased insulin resistance [8], increased production of glucocorticoids [9] and increased production of heat-shock proteins [10] -the mechanisms by which CR contributes to increased longevity remain unknown.How CR leads to longer life span cannot be attributed to any single factor without considering the simultaneous effects of the others.CR could alter multiple age-related processes, from energy metabolism to oxidative stress and DNA repair.Unravelling the multiparametric links of CR and aging led to the seminal genomic experiment for nutrition: the gene expression analysis of young and old tissues in normal and CR animals [11   ] is a pioneering example of the use of DNA arrays to explore the effects of CR and aging on gene expression in mouse skeletal muscle.The experiment is compelling for its simplicity and its implications, that is, the gene expression profiles for a clear phenotypic difference were compared (young versus old versus CR old mice).The power of the technique was evident by the discovery of a wide range of affected genes, including those involved in protein and energy metabolism, biosynthesis (e.g. of fatty acids), and macromolecular damage, implying immediately that the effects of aging and CR are broad, yet interrelated.More detailed experiments are now being pursued around the world following the identification of the genes that are altered during aging and protected by CR.The publication of this experiment also followed the now routine approach of supplying the raw database through an accessible internet site.",
+      "\t\n\nStudies in various models have revealed that genetic differences and somatic mutations underlie longevity, but non-genetic contributions also play a major role (Cournil and Kirkwood, 2001).Calorie restriction (Bordone and Guarente, 2005), lowering of basal metabolic rate (Ruggiero et al., 2008), upregulated stress response (Migliaccio et al., 1999), restoration of mi-tonuclear protein balance (Houtkooper et al., 2013), and reduced fertility (Westendorp and Kirkwood, 1998) have all been shown to correlate with lifespan extension.These observations illuminate the role of ''epi''-genetic mechanisms in modulating longevity pathways.",
+      "\t\n\nA key question still unresolved is to what extent the mechanisms of aging are conserved between species with vastly different lifespans.Some studies suggest that similar mechanisms are involved in aging in many species.For example, caloric restriction extends lifespan in yeast, worms, flies, mice, and primates (Weindruch 2003).Additionally, signaling through the insulin-like growth factor pathway, chromatin regulation by sir2, and oxidative damage have each been shown to affect lifespan in diverse model organisms (Tissenbaum and Guarente 2002).Other studies emphasize that changes occurring at the end of life are unlikely to be evolutionarily conserved (Kirkwood and Austad 2000).In the wild, very few animals (including humans) survive to their maximal biological lifespan.Thus, the changes in physiology that occur in very old animals have minimal effects on the fitness of individuals, and are unlikely to be evolutionarily conserved.Therefore, aging is likely to be species-specific, and studies of old age in model organisms are unlikely to be relevant to humans.",
+      "\t\n\nIn summary, we postulate that due to metabolic changes and the subsequent increase in stress response, physiological processes evoked by starvation show strong correlation with anti-aging processes (Table 2).These observations suggest that starvation may evoke the same stress response reaction as caloric restriction, which is the only treatment known to prolong lifespan in all organisms tested to date.The difference is that starvation results in a much stronger or prolonged induction.This accentuated response during starvation may facilitate the experimental identification of basic molecular mechanisms linking nutrition and health using a nutrigenomic approach."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "99D2FBCC88055B11FD6F2181CECBFB9C"
+    },
+    {
+      "task_id": "1FBEC3B0E217E49DDB92D2633A8C8A7E"
+    },
+    {
+      "task_id": "2F1DB635DB8670F444D7835B65E10E06"
+    },
+    {
+      "task_id": "F1D310BC7601CB79594B450C7874881E"
+    },
+    {
+      "task_id": "C56D0E0F1C9234ECD5058B1BAC023499"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_4.json
new file mode 100644
index 0000000..9ee18d0
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_aging_4.json
@@ -0,0 +1,109 @@
+{
+  "question": [
+    "How do oxidative stress and the subsequent accumulation of damaged macromolecules contribute to cellular aging?",
+    "How are extracellular matrix remodeling and tissue stiffness implicated in the aging process?",
+    "How do recent developments in autophagy research contribute to our understanding of its role in aging and longevity?",
+    "What are the implications of age-related shifts in stem cell niche composition and function for tissue regeneration capacity?",
+    "How do cross-links and advanced glycation end-products (AGEs) accumulation affect the structural integrity and function of aging tissues?"
+  ],
+  "answer": [
+    "Oxidative stress, primarily caused by reactive oxygen species (ROS) generated from cellular metabolism, leads to damage to various cellular components, including DNA, proteins, and lipids. This damage accumulates over time, leading to functional decline in cells. In particular, damage to DNA can lead to mutations and impaired cellular functions. The balance between DNA damage and its repair is a major determinant of cell longevity. Additionally, oxidative damage to mitochondria, a major source of ROS, can impair energy production and further contribute to aging. This process is supported by the oxidative stress theory of aging and the mitochondrial theory of aging.",
+    "Extracellular matrix (ECM) remodeling plays a significant role in the aging process. Aging results in changes in ECM biosynthesis, modifications of ECM components, and alterations of cell-matrix interactions, which contribute to age-related pathologies. The synthesis of many ECM components, such as elastin, declines with age, impairing the elasticity and resilience of tissues. Age-related ECM changes also alter vascular mechanotransduction, dysregulating cell responses to alterations in the environment. Additionally, aging and cellular senescence increase the secretion of matrix metalloproteinases (MMPs), which compromises the structural integrity of tissues and promotes pathological remodeling. This can lead to increased tissue stiffness, a common feature of aging tissues. Furthermore, dysregulated collagen synthesis contributes to vascular fibrosis and arterial stiffening.",
+    "Recent developments in autophagy research have shown that autophagy, a cellular degradation process, plays a crucial role in aging and longevity. Certain compounds like rapamycin, resveratrol, and polyamines can induce autophagy, with polyamines showing results in human clinical research. Autophagy is also linked to the regulation of various processes that contribute to aging, such as protein degradation, mitochondrial metabolism, and stress response. Studies have shown a decline in autophagy in aging mammals, and increased autophagy is required for lifespan extension in certain organisms. Furthermore, the up-regulation of autophagy by certain compounds has been associated with increased lifespan in various organisms. Dysfunctional autophagy is implicated in many age-related diseases, and the activation of autophagy has been linked with increasing lifespan in animal models.",
+    "Age-related shifts in stem cell niche composition and function can lead to a decrease in tissue regeneration capacity. This is because these shifts can result in a reduced ability of stem cells to self-renew and produce progeny to replenish worn-out and damaged cells in aged tissues. This can lead to a depletion of stem or progenitor cell pools, promoting age-related pathologies. Additionally, the induction of stem cell senescence may compromise tissue renewal. Therefore, understanding these shifts is crucial for developing therapies to counteract age-related decline in tissue regeneration.",
+    "Cross-links and AGEs accumulation in aging tissues can lead to several adverse effects. They can cause structural changes in proteins, lipids, and nucleic acids, leading to altered cellular functions. AGEs can mediate intracellular glycation of mitochondrial respiratory chain proteins, increasing ROS levels and triggering oxidative stress. They can also bind with RAGEs, activating signaling pathways that upregulate inflammatory cytokines and adhesion molecules. In the vascular system, AGEs can cause endothelial dysfunction, arterial stiffness, and vascular remodeling. In diabetes, AGEs can crosslink extracellular matrix proteins, impair degradation by MMPs, and increase cardiac stiffness. Overall, the accumulation of AGEs can lead to inflammation, apoptosis, and other processes related to aging."
+  ],
+  "contexts": [
+    [
+      "\t\n\nCell senescence, telomere shortening, and oxidative stress Attempts at synthesizing two major areas of focus in aging research, cell senescence [287,288] and free radicals, have been made since the 1970s (for a recent review see [289,290]).Early results by Packer and Smith suggested that vitamin E treatment could completely prevent cell senescence [291]; however, this result proved to be irreproducible [292].Nevertheless, it was observed that decreasing oxygen tension, from the customary 21% O 2 to more physiological levels (3% O 2, as would be found in vivo) led to an increase in cell doublings before senescence (i.e., an increase in the Hayflick limit or replicative life span [293][294][295][296]).Similar effects were also reported using antioxidants [296][297][298].In the 1990s, von Zglinicki et al. reported that a mild increase in oxygen tension (40%) triggered senescence within 3 cell divisions in human fibroblasts [299].von Zglinicki and co-workers proposed that oxidative damage to telomeres was responsible for the rapid triggering of senescence [299][300][301] and recent studies show that telomeric DNA may be particularly sensitive to oxidative damage [302].Following von Zglinicki et al. 's report, other investigators, using different oxidative stressors and different cell types, have reported very similar results.Mild oxidative stress reduces clonal life span and conversely, reduction of oxidative stress extends clonal life span [303][304][305][306][307]. Guarente's lab has provided additional evidence in this general direction, with the demonstration that RNAi knockdown of Sod1 triggered early senescence in human fibroblasts [308].This result is consistent with the earlier report by Epstein's laboratory that fibroblasts derived from Sod1 / mice failed to grow at all in culture [188].A great breakthrough in this area occurred when Campisi's lab demonstrated that senescence could be prevented completely in primary mouse cells when the cells were grown at 3% oxygen, instead of the customary 21% [309].This also resulted in a dramatic reduction of oxidative damage-signature mutations [310].In other words, these investigators demonstrated that in vitro senescence in mice cells was directly related to oxygen toxicity, i.e., oxidative damage.",
+      "\t\n\nThe free radical theory of aging, first proposed by Harman in 1956 [21], has received a lot of attention over the years as indicated by the number of scientific reviews on antioxidant interventions in different animal models and human clinical trials.The mitochondrion has been identified as a major source of reactive oxygen species (ROS) and thus oxidative stress potentially contributing to the aging process, although several plasma membrane and cystosolic enzymes may also contribute to the increased intracellular pro-oxidant status observed during aging [22].In the mitochondrial respiratory chain, electrons entering complexes I and II are transferred to complex III, then IV where they are combined with molecular oxygen and hydrogen to form H 2 O. Redox reactions at respiratory complexes I, III, and IV are coupled to the extrusion of protons from the mitochondrial matrix into the intermembrane space.The re-entry of protons into the matrix is coupled to the synthesis of ATP from ADP and P i .This oxidative phosphorylation is responsible for the vast majority of ATP production and oxygen consumption in most types of animal cells [23].Up to 2% of oxygen used in this complex reaction undergoes monoelectronic reduction and results in the formation of superoxide anion and hydrogen peroxide, which can lead to the formation of the more toxic species hydroxyl radicals [24,25].Such reactive species can attack and modify genomic DNA.An important type of oxidative DNA lesion accumulating with age is 8-oxo-deoxyguanine [26].If unrepaired, this adduct in genomic DNA may lead to a point mutation upon DNA replication.During DNA replication, 8-oxo-deoxyguanines present on either strand of DNA can mispair with adenosines and lead to G:C  T:A transversion mutations.A misincorporation of an 8-oxodeoxyguanine as a substrate nucleotide can also lead to the same type of mutational pattern [27].",
+      "\t\n\nOur results are consistent with the oxidative stress theory of aging originally proposed by Denham Harman [26], and the notion that a vicious cycle of ROS generation and oxidative damage is the ultimate driver of aging [27].Our data also indicate that endogenous nuclear DNA damage is able to trigger this cycle of escalating ROS abundance, oxidative damage, senescent cell accumulation and age-related pathology.\t\n\nTo determine if this oxidative stress is pathological, we suppressed it pharmacologically in Ercc1 -/ mice with the mitochondrial-targeted radical scavenger XJB-5-131.Chronic administration XJB-5-131 significantly reduced both oxidative DNA damage and senescence (Fig. 5).The reduced level of senescent cells corresponded to a reduction in agerelated morbidity.This is consistent with numerous recent studies demonstrating that genetic or pharmacologic elimination of senescent cells slows age-related decline [2,4,7,8,[84][85][86].The observation that suppressing oxidant production is sufficient to decreases senescence indicates that reactive species are required to ultimately cause or maintain senescence in response to genotoxic stress.",
+      "\t\n\nIntroduction as replication errors, spontaneous chemical changes to Although aging is nearly universally conserved among the DNA, programmed double-strand breaks (DSBs) (in eukaryotic organisms, the molecular mechanisms unlymphocyte development), and DNA damaging agents derlying aging are only beginning to be elucidated.A that are normally present in cells.The latter category useful conceptual framework for considering the probincludes reactive oxygen species (ROS), such as superlem of aging is the Disposable Soma model (Kirkwood oxide anion, hydroxyl radical, hydrogen peroxide, nitric and Holliday, 1979).This model proposes that organoxide, and others.Major sources of cellular ROS proisms only invest enough energy into maintenance of the duction are the mitochondria, peroxisomes, cytochrome soma to survive long enough to reproduce.Aging oc-p450 enzymes, and the antimicrobial oxidative burst of curs at least in part as a consequence of this imperfect phagocytic cells.ROS can cause lipid peroxidation, maintenance, rather than as a genetically programmed protein damage, and several types of DNA lesions: sinprocess.Although aging may involve damage to varigle-and double-strand breaks, adducts, and crossous cellular constituents, the imperfect maintenance of links.The situation in which ROS exceed cellular antinuclear DNA likely represents a critical contributor to oxidant defenses is termed oxidative stress.As normal aging.Unless precisely repaired, nuclear DNA damage byproducts of metabolism, ROS are a potential source can lead to mutation and/or other deleterious cellular of chronic, persistent DNA damage in all cells and may and organismal consequences.Damage to both nuclear contribute to aging (Sohal and Weindruch, 1996).The DNA, which encodes the vast majority of cellular RNA ROS theory of aging is discussed in depth in this issue and proteins, and mitochondrial DNA have been proof Cell by Balaban et al. (2005).In brief, longer-lived posed to contribute to aging (Karanjawala and Lieber, species generally show higher cellular oxidative stress 2004).The reader is referred to the review by Balaban resistance and lower levels of mitochondrial ROS proet al. in this issue of Cell concerning the potential role duction than shorter-lived species.Caloric restriction, of mitochondrial DNA damage in aging (Balaban et al.,",
+      "\t\n\nWe previously showed that superoxide plays a primary role in chronological age-dependent DNA damage and mutations.Our model is that the DNA damage caused by oxidative and other types of stress accumulated during aging in nondividing cells generates double-strand breaks during the fi rst round of replication after the exit from G 0 .Cells lacking SGS1 attempt to repair this damage by homologous recombination between sister chromatids but generate a large number of GCRs, especially at advanced age.",
+      "\t\n\nReactive oxygen species (ROS) have long been at the center of the debate on causes of aging and a central player in the free-radical theory of aging.One form of oxidative damage that is considered irreversible and has been correlated with age in various organisms, including replicative age in yeast, is protein carbonylation (Nystrom 2005).Protein carbonyls have been proposed as a yeast aging factor based on the observations that both protein carbonyls (Aguilaniu et al. 2003;Erjavec and Nystrom 2007) and aggregates containing heavily carbonylated proteins (Erjavec et al. 2007) are asymmetrically retained in mother cells during division.The proper asymmetric segregation of oxidatively damaged proteins appears to be dependent on a functioning actin cytoskeleton (Aguilaniu et al. 2003;Erjavec et al. 2007), which has independently been linked to ROS and life span through the actin bundling protein, Scp1 (Gourlay et al. 2004).",
+      "\t\n\nThere is some evidence that related processes occur in mammals.First, cells damaged by oxidative stress in vitro undergo stochastic transcriptional changes that parallel those in aged heart tissue (Bahar et al., 2006).Second, a deficiency in the DNA repair factor ERCC1 accelerates aging phenotypes and generates gene expression profiles reminiscent of aged animals (Niedernhofer et al., 2006).Third, cells that senesce because of replicative aging in vitro or in aged tissues in vivo exhibit alterations in heterochromatin (Herbig et al., 2006;Narita et al., 2006) and secrete growth factors that can drive tumorigenesis (Campisi, 2005).Finally, oxidative DNA damage at promoters correlates with gene repression in the aging human brain (Lu et al., 2004) and has been linked to both transcriptional and epigenetic changes that may contribute to Alzheimer's disease (Wu et al., 2008).",
+      "\t\n\nThere are many theoretical considerations on oxidative damage of mitochondria about aging.The \"free radical theory of aging,\" proposed by Harman in 1956 (138), that free radicals cause nonspecific damage to macromolecules, such as DNA, lipids, and proteins, has attracted much attention in recent years due to development in free radical biology.Harman (139) also proposed aging as consequences of mitochondrial aging that free radical reactions may contribute to changes in the mitochondrial inner membrane with age due to effects on both mtDNA and nDNA.Based on the observation of Drosophila, Miquel et al. (238) postulated that there is a distinct possibility of free radical-or lipid peroxide-induced inactivation of the mtDNA of fixed postmitotic cells with the passage of time.Fleming et al. (110) proposed that the site of irreversible injury is the mtDNA rather than the biomembranes.A two-step hypothesis on the mechanisms of in vitro cell aging, \"oxygen radical-mitochondrial injury hypothesis of cell aging,\" was proposed by Miquel and Fleming (239) that the fundamental cause of cell aging is an instability of the mitochondrial genome because of a lack of or balance between mitochondrial repair and the disorganizing effects of oxygen radicals.Thus, deprived of the ability to regenerate their mitochondrial populations, the cells will sustain an irreversible decline in their ability to synthesize ATP, with concomitant senescent degradation of physiological performance, and eventual death.Bandy and Davison (15) suggested that mitochondrial genome mutations may increase oxidative stress as implications for carcinogenesis and aging.",
+      "\tAging\n\nThe oxidative stress theory of aging proposes that accumulation of oxidative DNA damage over the life span of an organism leads to gradual decline of cellular functions and eventual death (Bohr, 2002).This model is supported by several circumstantial evidences including the observation that lower free radical production and/or antioxidant treatment protects against agerelated deterioration, and cognitive decline (Lemon et al., 2003).Further, deficit or decrease in the repair of oxidative DNA damage appears to correlate with premature aging and age-related diseases (Bohr et al., 2007).It appears likely that overall genome repair, specifically the balance between DNA damage and its repair is a major determinant of the longevity and cell viability.A specific defect in processing 5 0 dRP residue at the strand break in Sir2 (SIRT6 homolog)-deficient mice displayed age-related degenerative phenotype (Mostoslavsky et al., 2006).The activities of DGs OGG1, NTH1 and uracil DNA glycosylase (UNG) in brain mitochondria decrease significantly with age (Gredilla et al., 2010).",
+      "\tPrxs and the free radical hypothesis of aging\n\nThe evolved version of Harman's (Harman 2003) free radical theory of aging proposes that organisms age because the constituents of cells and tissues accumulate damage over time caused by reactive oxygen (and/or nitrogen) species originating from endogenous metabolism, including, among many other possible activities, mitochondrial respiration.At first glance, it appears that the data concerning Prxs and aging fit this theory like a glove, as Prxs become ''damaged'' (catalytically inactivated as a peroxidase) during aging due to a modification caused by a reactive oxygen species (ROS), specifically hydrogen peroxide (or organic hydroperoxides), and that counteracting this ''damage'' by elevating the levels of the ''repair'' enzyme Srx1 prolongs life span (Molin et al. 2011).Moreover, as the Prxs themselves act as enzymatic antioxidants and protect the genome against oxidative modifications (see below), it is possible that peroxidedependent inactivation of Prxs gives rise to a negative feedback loop with respect to the cell's capacity for ROS homeostasis.",
+      "\t\n\nAging is a dynamic and complex process defined as the time-dependent functional decline.With age, homeostasis declines and damage accumulates.One of prime candidates that induce macromolecular damage is oxidative stress from reactive oxygen species (ROS) generated from normal physiological activities.Indeed, many long-lived mutants are resistant to oxidative stress [53].Ferroptosis involves metabolic dysfunction that results in the production of both cytosolic and lipid ROS [36,38].Repression of SLC7A11 transcription by p53 results in reduction of cystine uptake.Because of less cystine uptake, the levels of intracellular glutathione (GSH) will be reduced and the cellular system for defending oxidative stress is abrogated.Thus, the sensitivity of ROS-induced ferroptosis is significantly increased in p53-activating cells.We showed that SLC7A11 is downregulated by p53 and that p53mediated ferroptosis is dramatically induced in the testis of p53 3KR/3KR Xrcc4 -/-mice.Thus, it is very likely that the combination of genomic instability and p53-mediated ferroptosis contributes significantly to the aging associated phenotypes observed in p53 3KR/3KR Xrcc4 -/-mice.",
+      "\tSources of Damage Increase with Age\n\nThe free radical theory of aging posits that aging is caused primarily by oxidative damage incurred by ROS that chemically modify critical cellular biomolecules (13).This theory has evolved over the years to become the oxidative stress theory of aging, but the principle is the same, in that the accumulation of oxidative damage drives aging.In support of this theory, a large body of literature indicates that oxidative damage to all cellular macromolecules increases with age.Furthermore, overexpression of antioxidant enzymes that detoxify ROS, such as copper-and zinc-containing superoxide dismutase (SOD), manganese-containing SOD, or catalase, increase the life span of Drosophila melanogaster by as much as 30% (14).Additionally, most long-lived mutants in D. melanogaster and Caenorhabditis elegans have increased resistance to oxidative stress.In mammals, the role of oxidative stress is less clear because overexpression of catalase, SOD1 (pancellular expression), or SOD2 (mitochondrial) does not extend the life span of mice (15).However, overexpression of catalase specifically targeted to the mitochondria does extend the life span of some mice up to 20% (16).Additionally, treatment with the antioxidant nordihydroguaiaretic acid (NDGA) and an activator of NRF2 (master regulator of antioxidant response) extends median life span in male mice (17).\t\n\nThe free radical theory of aging evolved to the mitochondrial theory of aging when mitochondria were implicated as the primary source of ROS.Electrons leaked from the electron transport chain at the inner mitochondrial membrane can react with molecular oxygen to produce a superoxide radical, which can be converted by SOD to yield hydrogen peroxide (H 2 O 2 ).In the presence of transition metal ions (e.g., Fe 2+ or Cu + ), H 2 O 2 can be further converted to the highly reactive hydroxyl radical via the Fenton-type reaction.These ROS react locally to damage genes or proteins necessary for oxidative phosphorylation, leading to further uncoupling of electron transport and increased ROS production in a feed-forward manner.Abundant evidence shows that ROS and oxidative damage increase as organisms age.But which cellular target of these damaging radicals and other reactive molecules is health and life limiting?If the answer is DNA, then one expects DNA damage to accumulate with age.",
+      "\tThe Free Radical Theory of Aging. The free radical theory of aging proposed by Denham Harman more than fifty years ago postulates that aging results from the accumulation of deleterious effects caused by free radicals, and the ability of an organism to cope with cellular damage induced by ROS plays an important role in determining organismal lifespan [3].In agreement with this theory, increased ROS production by mitochondria and increased 8-oxo-dG content in the mtDNA are frequently detected in aged tissues [40,[47][48][49][50], suggesting that progressive accumulation of oxidative DNA damage is a contributory factor to the aging process.Consistently, many studies have found that increased oxidative damage in cells is associated with aging [51][52][53].Furthermore, genetic studies in worm, fly, and mouse have linked enhanced stress resistance or reduced free radical production with increased lifespan [27].Mutant strains of C. elegans that are resistant to oxidative stress have extended lifespan, whereas those more susceptible to free radicals have shortened lifespan [54,55].Mice lacking the antioxidant enzyme superoxide dismutase 1 (SOD1) exhibit a 30% decrease in life expectancy [56].Conversely, simultaneous overexpression of SOD1 and catalase extends lifespan in Drosophila [57].Small synthetic mimetics of SOD/catalase increase lifespan in C. elegans [58], while treatment of antioxidant drugs in mice increases the median lifespan up to 25% [59,60].Further supporting this hypothesis, mice lacking Ogg1 and Myh, two enzymes of the base excision repair pathway that repairs oxidative DNA damage, show a 50% reduction in life expectancy [61].Collectively, these studies demonstrate that interplay between ROS and protective antioxidant responses is an important factor in determining aging and lifespan.\tMitochondria and Aging\n\n3.1.The Mitochondrial Theory of Aging.Because mitochondria are the major producer of ROS in mammalian cells, the close proximity to ROS places mitochondrial DNA (mtDNA) prone to oxidative damage [104].Consistently, many studies have shown that 8-oxo-dG, one of the common oxidative lesions, is detected at higher level in mtDNA than nuclear DNA, suggesting that mtDNA is more susceptible to oxidative damage [52,[105][106][107][108][109][110][111][112][113].As both the major producer and primary target of ROS, mitochondria are thought to play an important role in aging.The mitochondrial theory of aging, extended from the free radical theory, proposes that oxidative damage generated during oxidative phosphorylation of mitochondrial macromolecules such as mtDNA, proteins, or lipids is responsible for aging [114].As mtDNA encodes essential components of oxidative phosphorylation and protein synthesis machinery [115], oxidative damageinduced mtDNA mutations that impair either the assembly or the function of the respiratory chain will in turn trigger further accumulation of ROS, which results in a vicious cycle leading to energy depletion in the cell and ultimately cell death [104,114,[116][117][118].",
+      "\t\n\nThere is an emerging consensus that oxidative damage is of central importance to much of the age-related overall decline of animal cells, from yeast to humans [2][3][4][5][6][7] .Caloric restriction or environmental conditions that favour a decrease in oxidative metabolism also increase lifespan 8 , and transgenic or knockout animals with decreased oxidative metabolism have increased lifespans.For example, flies that consume oxygen at a high rate have a reduced lifespan, and low oxygen-consumption rates and cold temperatures favour a prolonged lifespan 9,10 .Lipids, proteins and DNA have all been argued to be Ageing, repetitive genomes and DNA damage Michael R. Lieber and Zarir E. Karanjawala www.nature.com/reviews/molcellbioP E R S P E C T I V E S to one another, thereby permitting a copying of information from one sister chromatid to the other.This typically restores the information content at the break site back to normal.",
+      "\t\n\nA key macromolecule at risk for ROS-mediated damage is nuclear DNA [1], which is evident from the wide range of oxidative DNA lesions that accumulate gradually in rodents and humans with advancing age [6,7].\tIntroduction\n\nA prevailing hypothesis to explain the molecular basis of ageing is Harman's ''free-radical theory of ageing'', which states that endogenous reactive oxygen species (ROS), which result from cellular metabolism, continually damage biomolecules [1].In line with this hypothesis, it has been shown that increased resistance to oxidative stress (e.g., by improved antioxidant defense) extends the lifespan of Caenorhabditis elegans, Drosophila, and rodents [2][3][4], whereas hypersensitivity to oxygen considerably reduces the lifespan of nematodes [5].",
+      "\tReplication stress, mitochondria and growth signaling\n\nIncreased oxidative damage to DNA and other cellular constituents by ROS produced in dysfunctional mitochondria is an important component of modern versions of the 'free radical theory' of aging (3,71).It is often assumed that the production of ROS in mitochondria is directly proportional to the rate of mitochondrial respiration, and that increased respiration promotes aging.A number of recent studies in budding yeast and mammals argue that these long-held assumptions are incorrect (72).For example, caloric restriction and other experimental manipulations that enhance respiration in budding yeast reduce, rather than increase levels of ROS at the same time that they enhance life span (73).Similarly, budding yeast cells cultured in medium containing glycerol or ethanol, which are metabolized via respiratory pathways, exhibit a longer chronological life span (22).Furthermore, deletion of TOR1 extends chronological life span of budding yeast by enhancing respiration, but reducing ROS (21).As might be expected based on these reports, experimental manipulations that increase the production of ROS in mitochondria shorten the chronological life span of this organism (73,74)."
+    ],
+    [
+      "\tSenescence and apoptosis are thought to contribute\nto aging and age-related disorders by decreasing the proliferative potential of progenitor\nstem cells, altering tissue regenerative capacity, decreasing tissue function and by altered\ntissue architecture and microenvironment caused by altered gene expression and secretion of\ninflammatory cytokines, growth factors, and proteases (Campisi 2003; Coppe et al. 2008;\nGarfinkel et al. 1994; Krtolica and Campisi 2002; Kuilman et al. 2008; Novakova et al. 2010; Ohtani and Hara 2013).",
+      "\t\n\nThere exists a substantial body of research addressing the tissue, cellular and molecular changes that accompany or directly contribute to aging in a range of model organisms (reviewed in [7]).However, the majority of data, generated in model organisms or in vitro (cellular senescence), has yet to be validated in human aging.Moreover the relative contribution of putative gerontogenes to human pathological agerelated processes is unknown.Age-associated impaired healing correlates with increased inflammation, increased matrix proteolysis and delayed re-epithelialization leading to chronic wound states, processes modulated by exogenous estrogen treatment [8].In a recent study we characterized estrogen-regulated changes in gene expression using a model of delayed wound healing in young mice that have been rendered hypogonadal by ovariectomization (hence removing any effects of 'intrinsic aging') [9].Thus, using comparative analysis we are now in a position to address the relative contributions of estrogen and aging to healing in elderly humans.",
+      "\t\nAging alters gene expression of growth and remodeling factors in human skeletal muscle both at rest and in response to acute resistance exercise.\t\n\nAging alters gene expression of growth and remodeling factors in human skeletal muscle both at rest and in response to acute resistance exercise.",
+      "\t\n\nStructural integrity of skeletal muscle.Some noteworthy genes that were differentially expressed only in older subjects after RL support the concept that the muscles of older subjects may have experienced a degree of stress far exceeding that in young subjects despite being exposed to the exact same stressor.For example, gene expression of MyBPH was robustly elevated (4.1-fold) in the old only, as was myosin head domain containing 1 (MYOHD1; 1.4-fold).MyBPH is an integral myosin binding partner in the A band of myofibrils that interacts with the myosin rods and titin to provide structural integrity to the contractile apparatus.Reduced MyBPH expression is associated with muscle weakness in age-related disorders (30).Interestingly, localization of MyBPH to the contractile apparatus is directed by its C terminal domain consisting of two fibronectin type III motifs (24), and our microarray analysis also revealed a 1.6-fold increase among the old in the expression of fibronectin type III domain containing 3B (FNDC3B).As shown in mice, MyBPH is upregulated in the young after more intense eccentric loading (5), again suggesting age differences in the degree of mechanical stress required to activate many of these transcriptional responses (with young muscles requiring greater stress than old).MyBPH expres-sion is modulated by the transcription factor SMARCA4 (SWI/ SNF-related, matrix-associated, actin-dependent regulator of chromatin, subfamily a, member 4), which was also significantly upregulated in the old only.Interestingly, SMARCA4 is activated by glucocorticoid receptor signaling and, in turn, regulates the expression of notable muscle-specific genes including myogenin, troponin T, and MyBPH.A strain on muscle integrity among the old was also suggested by significant downregulation (1.7-fold) of both type IV collagen 3 (COL4A3) and 4 (COL4A4) mRNA expression and 1.6-fold upregulation of TUBA8.Type IV collagen, a major constituent of basement membranes, is degraded by matrix metalloproteinases (MMP-2 and MMP-9) in response to muscle damage (49).These findings suggest that the muscles of the older subjects may have been attempting to launch a compensatory effort to maintain structural integrity-a response to this degree was apparently not sensed as necessary among the younger subjects.",
+      "\tRole of Extracellular Matrix Remodeling in Vascular Aging\n\nThe extracellular matrix (ECM) is an important contributor to health and longevity.This noncellular compartment, ubiquitous to all tissues and organs does not only provide essential mechanical scaffolding but mediates highly dynamic biomechanical and biochemical signals required for tissue homeostasis, morphogenesis, and cell differentiation.Studies on model organisms suggest that evolutionarily conserved pathways regulate ECM remodeling during aging and that promotion of ECM youthfulness by antiaging interventions is an essential signature of longevity assurance. 206Aging in mammals also results in significant changes in ECM biosynthesis, postsynthetic modifications of ECM components, and alterations of cell-matrix interactions, which contribute to the development of a spectrum of age-related pathologies. 207ge-related alterations of the ECM, including the subendothelial basement membrane, intima, media, adventitia, and interstitial matrix (which constitute more than half of the mass of the vascular tissue), play a fundamental role in impairment of both structural and regulatory homeostasis of the vasculature. 208With age, the expression of growth factors that regulate ECM biosynthesis is altered 45 and the synthesis of many ECM components (eg, elastin) declines, which impairs elasticity and resilience of the vascular wall to mechanical damage and rupture induced by bursts in wall tension because of pulsatile pressure waves. 208Age-related ECM changes also likely alter vascular mechanotransduction, dysregulating cell responses to alterations in the hemodynamic environment.Additionally, aging and cellular senescence alter the secretory phenotype of vascular endothelial and smooth muscle cells, increasing MMP secretion. 45This together with increased MMP activation 208 induced by high ROS levels compromises the structural integrity of the vasculature and promotes pathological remodeling (eg, in hypertension), resulting in increased likelihood of aneurysm formation and vessel rupture, including the development of cerebral microhemorrhages. 45The available evidence suggests that many of these age-related ECM alterations are governed by circulating factors and factors produced in the vascular wall, including the extended renin-angiotensin-aldosterone system (see above) and an age-related decline in circulating IGF-1. 209ollagen synthesis is also dysregulated with age in the vascular wall likely because of the effects of increased paracrine action of TGF- (transforming growth factor-), 123 which contributes to vascular fibrosis and arterial stiffening. 208Additional features that contribute to increased arterial stiffness include decreased elastin synthesis, elastin degradation and fragmentation, elastin calcification, alterations in cross-linking of extracellular matrix components (eg, by increased presence of advanced glycation end products). 208,210,211he pathophysiological consequences of age-related ECM remodeling and arterial stiffening have been the subject of a recent comprehensive review by AlGhatrif and Lakatta. 6In brief, as the large conduit arteries stiffen in aging, aortic pulse wave velocity, systolic pressure, and pulse pressure significantly increase, 212 whereas diastolic pressure decreases.Decreased diastolic pressure leads to a decline in coronary blood flow.Increased systolic pressure promotes left ventricular remodeling, diastolic dysfunction, and exacerbates atherogenesis.Because of the dilation of conduit arteries, wall tension significantly increases, contributing to the development of aneurysms.In addition to alterations in the biomechanical properties of large arteries, age-related ECM remodeling likely also affects microvascular transport and barrier functions. 213Age-related alteration of the ECM structure and composition are also manifested in the wall of veins, contributing to the pathogenesis of varicosities. 214\t\n\nFigure 4. Conceptual model for the pathogenic role of cellular senescence in vascular aging.The model predicts that increased presence of senescent endothelial or smooth muscle cells (SMCs) in the aged vasculature and their proinflammatory secretome (SASP [senescence-associated secretory phenotype]) contributes to impaired angiogenesis and microvascular rarefaction, pathological remodeling of the extracellular matrix (ECM), barrier disruption, chronic inflammation, and atherogenesis.MMP indicates matrix metalloproteinase.",
+      "\t\n\nAge-related transcriptional remodeling and mitochondria",
+      "\t\n\nChromatin remodeling in aging, J. G. Wood et al.",
+      "\tAging is only, in part, the result of crosslinking reactions\n\nWhile Bjorksten (1968) proposed that crosslinking was a major feature of the chemical aging of tissues, particularly of collagen, it has become apparent in recent years that many age-dependent chemical modifications of protein are monofunctional.These include oxidative modifications of phenylalanine, tyrosine and methionine residues (Table 1), carboxyalkylation of lysine (Table 4), and deamidation and racemization of amino acids.Extracellular matrix proteins accumulate higher levels of monofunctional chemical modifications, as well as crosslinks, not because they are uniquely sensitive to damage, but because they generally turnover more slowly.There are few quantitative studies on the age-dependent accumulation of biomarkers in intracellular proteins, even in proteins with long half-lives, such as contractile proteins in muscle or histones in post-mitotic cells.These proteins may be exposed to higher levels of reactive oxygen species generated in mitochondria or peroxisomes, or to higher levels of reactive carbonyl intermediates in glycolysis, but are also better protected by intracellular antioxidant and detoxification systems.",
+      "\t\n\nVarious extracellular matrix-related proteins were differentially regulated herein.Extracellular matrix proteins provide structural support, mechanical properties, and strength of tissues, including vocal folds, playing a pivotal role in phonation [62,71,72].Collagens XIV, XVIII, and Fibulin 5 were downregulated in older rabbit vocal folds compared to young tissue.To our knowledge, these specific collagen types have not been investigated in depth in vocal fold tissue; however, studies suggest that the changes in the collagen fiber density and arrangements within the lamina propria may affect phonation [73,74].Collagen type IV is exclusive to extracellular matrix basal membranes [75] and is present in the human vocal fold basal membrane providing support to epithelial and endothelial cells [76].Collagen type IV was upregulated in older rabbit vocal folds compared to young, an effect of aging observed in our study.The relationship between Collagen type IV and aging is not well established.Increased accumulation of Collagen type IV is reported in the basal lamina of cerebral microvessels in humans [77] but decreased in the skin of older adults [78].Conversely, several extracellular matrix proteins were upregulated, including Collagen type XVIII and Fibulin 5, in the presence of dehydration when observing the effect of hydration status alone.These protein changes may be related to the remodeling of the extracellular matrix [79] in response to dehydration.Moreover, the accumulation of collagens and the decrease of elastins may result in extracellular matrix stiffness in aging larynx and other organs [59,79].Finally, Lamin A was upregulated by dehydration, by a smaller magnitude, especially when observing the mean difference within the young groups.Previous data has identified that Lamin proteins A and C are important for imparting the nucleus with its stiffness, and their expression has been reported to scale with tissue stiffness [80].Thus, upregulation of this protein due to dehydration may be related to tissue stiffness in the vocal fold of rabbits.",
+      "\t\n\nRecently, collagen production and extracellular matrix remodeling were determined to be essential for longevity in C. elegans.Collagen may directly affect signaling processes associated with longevity in C. elegans, including signaling through SKN-1 [40,58].We note that HSF-1 was also recently shown to regulate cytoskeletal integrity in a process that can influence stress resistance and longevity in C. elegans [59].Thus, the linkage of both the extracellular matrix and the cytoskeleton to HSF-1 may provide a mechanism by which HSF-1 promotes longevity.\tHSF-1 regulates collagen genes which may affect the aging process\n\nIt is interesting that cuticle structure genes constitute the largest overlap with aging-related genes.In humans, mutations in collagens lead to a large number of heritable human diseases such as osteoporosis and musculoskeletal diseases [53].Collagens are long-lived proteins known to accumulate damage during aging, leading to a decline in tissue health [54].Also, type I collagens become resistant to proteolysis upon age [55,56], affecting their turnover.Interestingly, mice expressing cleavageresistant type I collagen go through an accelerated aging process [57].Thus, cellular aging can be affected by the state of the extracellular matrix in mammals.",
+      "\t\n\nAn observation that is specific for males is the global downregulation with aging of genes involved in the synthesis of the ECM and in particular of different forms of collagen (Table 2).In addition, aging males but not females showed a decrease in collagen type III.Interestingly, collagen type III decreases the size of collagen bundles and thereby increases vascular elasticity (11).Therefore, a decreased expression of collagen type III can participate in the increased stiffness that characterizes the aging aorta (23).An interesting observation from our study that directly relates to the mechanism of vascular remodeling is the upregulation in aging males of the transcript encoding collagen type VIII (Table 3).That specific collagen type, which is upregulated in response to vascular injury (24), promotes VSMC migration (1).The upregulation of this transcript together with the downregulation of other isoforms in aging males again supports the notion that this group is more susceptible to neointimal proliferation, VSMC migration, and potentially atherosclerosis.\t\n\nOur study shows that the genomic adaptation to vascular aging involves not only the genes involved in ECM composition and VSMC differentiation and migration, but also many other categories of genes participating in intracellular functions, such as cell signaling, DNA repair, metabolism, and protein synthesis.Our study also illustrates that most of the changes in gene expression with aging differ between males and females and correspond to different sets of transcription factors.Indeed, 5% of the 600 genes that were regulated by aging were observed in both old males and females.GO analysis also shows that specific subsets of genes are regulated differently between sexes, especially the genes participating in ECM composition and VSMC phenotype.We therefore propose that these transcriptional differences may underlie the different physiological properties of aging arteries between males and females, as well as their different susceptibility to vascular complications, such as hypertension or atherosclerosis.Furthermore, the analyses in young monkeys demonstrated major differences in genes regulating vascular structure, implying that the sex differences in vascular stiffness that develop with aging are programmed at an early age.",
+      "\tChronic liver diseases are characterized by aberrant matrix deposition, calling for our\nattention to the role of ECM in resolution of liver fibrosis. Tissue remodeling is regulated by MMPs,\ninvolved in the ECM degradation, and TIMPs, their endogenous inhibitors. Their subtle balance\nmaintains liver fibrogenesis. Tissue homeostasis is further regulated by proteolytic activity of the\nPLAU/PLAT/plasmin, responsible for the maintenance of the physiologic levels of ECM (40). PLAU promotes ECM degradation through activation of MMPs (MMP-2, -3 and -9; (41, 42),\nincreases the differentiation of hepatic stem cells, and HGF-dependent regeneration of hepatocytes\n(43).",
+      "\t\n\nMechanistically, the age-related increase in elastin degradation may result from augmented activity of proteases with elastinolytic activity, including certain MMPs and cysteinyl cathepsins, enzymes that, in turn, are regulated by inflammatory mediators (54,55).Collagen catabolism falls in aging arteries.\t\n\nAugmented transforming growth factor (TGF)-b activity favors the accumulation of collagen in the aortic wall.The activity of various elastases, including matrix metalloproteinases (MMPs), such as MMP-9 and MMP-12, as well as overexpression of the cysteine proteinases cathepsins S, K, and L, and the serine proteinase neutrophil elastase, elaborated by inflammatory cells, can all contribute to depletion of elastin (11).These alterations in the aorta's extracellular matrix contribute importantly to its loss of distensibility.This increased stiffness raises reflected waves and elevates systolic pressure.Yet diastolic pressure tends to decline with age.As aortic pulse wave velocity increases, pulse pressure rises (12).Indeed, pulse pressure is an independent risk factor for CV events (13).Isolated systolic hypertension accounts for the majority of uncontrolled hypertension in Americans over 50 years of age (14,15).substantially stroke and total mortality, with lesser benefit for ischemic cardiac events (16).Avoiding excessive sodium intake may provide an additional, nonpharmacological intervention for control of hypertension in older individuals (17,18).Some have raised concerns regarding the safety of aggressive lowering of blood pressure in elderly patients, particularly those with concomitant coronary artery disease (19).Indeed, a J-shaped curve relating CV outcomes to blood pressure may pertain to this In addition to reducing stroke, a major impediment to independent living and function in older patients, antihypertensive therapy may limit the development of dementing illnesses, as shown in the Syst-Eur trial (27).Decreased dementia and cognitive decline accrue with longer duration of antihypertensive treatment (28).An asymmetric loss to follow-up of individuals with impaired cognition may have biased the results of dementia in the SHEP study to the null (29).With regard to the former, vascular aging alters the function of the endothelium, the cells that line the lumen of blood vessels.Endothelial dysfunction includes reduced vasodilatory and antithrombotic properties, with an increase in oxidative stress and inflammatory cytokines (33)(34)(35) favoring atherogenesis and thrombosis, and predisposing to CVD (36).Human and experimental studies concur that diminished bioavailability of nitric oxide (NO), a key mediator of vasorelaxation and antiatherogenic processes, underlies age-dependent endothelial dysfunction (37,38).Reduced NO bioavailability can occur due to decreased synthesis or increased degradation of NO.Under normal conditions, endothelial nitric oxide synthase (eNOS) produces NO from L-arginine in the presence of the cofactor tetrahydrobiopterin (BH4) (39).Although studies differ regarding eNOS protein expression with age (34,40,41), recent data suggest an age-related alteration in eNOS function, referred to as eNOS uncoupling (42).",
+      "\tBackground\n\nTissue aging is caused by intrinsic and extrinsic factors that induce complex molecular changes and, in turn, a deterioration of cellular structures and function.These changes are major causes of age-related diseases like cancer or cardiovascular disorders [1,2].The main molecular adaptations occurring during aging are loss of genomic stability due to reduced DNA repair capacities [3], loss of proliferative potential caused by increased senescence [1,4], and age-related alterations in the DNA-methylation patterns that affect cellular plasticity [5,6].Metabolic adaptations are also considered to play a major role in aging [7][8][9][10].For instance, the metabolic function of mitochondria is progressively impaired during aging in different tissues [8,11].This can result in increased generation of reactive oxygen species that foster genomic instability [8,12].Moreover, several studies reported that caloric restrictions and diet adaptations, such as supplementation of food with branched chain amino acids [13,14], can significantly increase lifespan [15].This suggests that metabolic activity as well as nutrient sensing pathways are highly relevant for cellular aging processes (reviewed in [10]).Accordingly, interference with the insulin/IGF1 and the mammalian target of rapamycin (mTOR) pathways increased lifespan in different model organisms [7,[16][17][18].",
+      "\t\n\nWe examined the list of 447 age-regulated genes for functional groups showing a consistent change with age.One group includes genes involved in the formation of the extracellular matrix, which show a consistent increase in expression in old age.Seven age-regulated genes encode proteins known to play key roles in maintaining epithelial polarity (three types of claudins, two cadherins, occludin, and a cell adhesion molecule), all but one of which increase expression in old age (see Table S4).Forty-nine age-regulated genes encode protein components of the extracellular matrix, all but four of which increase expression in old age.In the kidney, the extracellular matrix could play a key role in governing the filtration of blood via the basement membrane, a capacity that declines with age.The observation that genes involved in forming the extracellular matrix increase expression in the kidney with age may be directly relevant to the age-related decline in glomerular filtration rate."
+    ],
+    [
+      "\tStochastic damage\n\nFigure 2. Longevity assurance, ageing and disease.New studies of the biology of ageing are revealing processes that control when and how fast ageing occurs, such as insulin-IGF-1 signalling [6], cellular senescence [4], protein refolding [43][44][45], autophagy [41] and phase 1 and 2 detoxification [36,37,52].These represent major points of intervention against ageing-related disease.As shown here, lifespan pathways control improved cellular maintenance, which leads to slowed ageing (e.g.slowed normal cognitive ageing) and protection against diseases of ageing (e.g.neurodegenerative diseases of ageing, such as Alzheimer's and Parkinson's disease, and cancer).Ageing can evolve via selection to reduce investment in energetically costly somatic maintenance processes and instead to increase early fitness traits such as growth and reproduction [50,51].Arrows denote stimulation, and T bars inhibition, of the process indicated.Red and green denote changes leading to ageing and longevity, respectively.",
+      "\t\n\nFig. 4. Schematic showing how some external interventions trigger longevity, often at least partly through stimulating autophagy.The pink writing refers to dietary, chemical, or therapeutic interventions that can extend life span, in at least some organisms (described in the text).Arrows indicate stimulating effects, and blocked lines indicate inhibitory effects.This schematic is not meant to be exhaustive but highlights the pathways that alter the epigenetic information and autophagy.",
+      "\t\n\nTORC1 regulates several downstream processes that may contribute to its role in aging, including protein degradation via autophagy, mitochondrial metabolism, stress response, and mRNA translation (Stanfel et al. 2009).Autophagy, which literally means \"self eating\", is a degradative process through which cellular components are engulfed by cytoplasmic vesicles and transported to the lysosome/vacuole for degradation (Klionsky 2007).Autophagy is repressed by TOR signaling and is induced in response to starvation or treatment with TOR inhibitors, such as rapamycin (Noda and Ohsumi 1998).A decline in the autophagic response has been reported in aging mammals (Cuervo and Dice 2000), and increased autophagy is required for life span extension in long-lived C. elegans mutants with reduced insulin/IGF-1-like signaling (Melendez et al. 2003).Several recent studies have also uncovered an important role for autophagy in the response to DR. DR induces autophagy in yeast, worms, and flies (Juhasz et al. 2007;Morck and Pilon 2006;Takeshige et al. 1992) and is reported to be required for life span extension from DR or TOR-inhibition in both worms and flies (Hansen et al. 2008;Jia and Levine 2007;Juhasz et al. 2007).Recently, up-regulation of autophagy by spermidine has also been shown to be associated with increased life span in yeast, nematodes, and flies (Eisenberg et al. 2009).",
+      "\tInductors of Autophagy and its Impact on Aging\n\nAutophagy has a role in homeostasis, which plays an essential role in the maintenance of cellular physiology and the prevention of cellular damage.Among the inducers of autophagy have been described the already-mentioned rapamycin, resveratrol, and polyamines; however, only polyamines have demonstrated results in clinical research in humans [65].It is known that these compounds can induce the canonical autophagy pathway, which includes inactivation of the mammalian objective of the rapamycin complex 1 (mTORC1), allowing phosphorylation and activation of the Unc-51 complex (Ulk1/2), where the cascade of the other members of the complex is subsequently activated, ULK as FIP200 and ATG13 [65].\t\n\nOn the other hand, interventions using chemical inducers of macroautophagy, such as rapamycin, an mTOR inhibitor, can increase the life span of middle-aged mice like that induced by spermidine or polyamine-producing gut flora supplementation [87].In an unexpected finding, aged cells showed an increased accumulation of protein aggregates, suggesting a decline in lysosome functionality during aging even though the number of lysosomes increased [72,88].This disparity could be due to changes in the pH, as suggested by the fact that the vacuolar V-type ATPase complex, which is responsible for maintaining vacuolar pH, decreased during aging, suggesting a mechanistic link between altered protein complex composition and lysosome dysfunction [72,88].The stress-induced synthesis of cytosolic and organelle-specific chaperones was also impaired in aging.Mutant mice that were deficient in a co-chaperone of the heat-shock family exhibited accelerated aging phenotypes, whereas long-lived mouse strains showed a marked upregulation of some heat-shock proteins [89].\t\n\n2016;351:173-6.81.Koga H, Kaushik S, Cuervo AM.Protein homeostasis and aging: the importance of exquisite quality control.Ageing Res Rev. 2011;10:205-15.82.Labbadia J, Morimoto RI.The biology of proteostasis in aging and disease.Annu Rev Biochem.2015;84:435-64.83.Rubinsztein DC, Mario G, Kroemer G. Autophagy and aging.Cell.2011;146:682-95.84.Tomaru U, Takahashi S, Ishizu A, Miyatake Y, Gohda A, Suzuki S, et al.Decreased proteasomal activity causes age-related phenotypes and promotes the development of metabolic abnormalities.Am J Pathol.2012;180:963-72.85.Rodriguez KA, Edrey YH, Osmulski P, Gaczynska M, Buffenstein R. Altered composition of liver proteasome assemblies contributes to enhanced proteasome activity in the exceptionally long-lived naked mole-rat.Brodsky JL, editor.PLoS One.2012.https://doi.org/10.1371/journal.pone.0035890.86.Chondrogianni N, Georgila K, Kourtis N, Tavernarakis N, Gonos ES.Enhanced proteasome degradation extends Caenorhabditis elegans lifespan and alleviates aggregationrelated pathologies.Free Radic Biol Med.2014;75:S18.https://doi.org/10.1016/j.freeradbiomed.2014.10.632.87.91.Haigis MC, Yankner BA.The aging stress response.Mol Cell.2010;40:333-44.92.Johnson SC, Rabinovitch PS, Kaeberlein M. mTOR is a key modulator of ageing and agerelated disease.Nature.2013 Jan 16;493:338-45.93.Lamming DW, Ye L, Astle CM, Baur JA, Sabatini DM, Harrison DE.Young and old genetically heterogeneous HET3 mice on a rapamycin diet are glucose intolerant but insulin sensitive.Aging Cell.2013;12:712-8.\tConserved Metabolic Pathways Offer Clues to the Factors of Aging and Longevity\n\nEvolutionarily conserved pathways, from yeast to mammals, robustly correlate with aging and longevity, and their deregulation has been implied with the development of cellular aging and include the mechanistic target of rapamycin (mTOR), insulin/ insulin growth factor 1 signaling (IIS), AMPK sensing, and sirtuin (SIRT) pathways [90].The harmonized regulation of these metabolic pathways maintains cellular and organismal homeostasis, even in the presence of external perturbations like changes in nutrient availability, temperature, oxygen level, or internal alterations, including protein misfolding and DNA damage [91].",
+      "\t\n\npivotal in this aspect providing molecular insights and having huge conceptual contributions in the field.Characterising the contribution of individual mutants in ageing is a continuously active and informative activity in the field.On top of these studies, genome-wide screens have provided insights on the role of evolutionarily conserved processes and signalling pathways in ageing such as nutrient response [17,18], protein translation, oxidative damage [19,20], mitochondrial function [21,22] and autophagy [22,23] opening new avenues for biogerontology research.Yeasts have proved informative and helped in understanding mechanisms of highly conserved pathways (from yeast to human) in physiology, health and disease such as the Target of Rapamycin (TOR) [24], glucose sensing (PKA) and stress response pathways (Sty1/p38) [25].\t\n\nA competitive ageing assay was performed in budding yeast where samples from the ageing pool were collected at specific timepoints [58].Mutants were then detected using a microarray DNA hybridization technique that quantifies abundance of the barcode tags of each mutant.Using this approach multiple short-and long-lived mutants were identified with autophagy mutants being among the short-lived and mutants coding for proteins involved in de novo purine biosynthesis pathway, which ultimately produces IMP and AMP were among the long-lived ones [58].Validation experiments targeting autophagy or purine biosynthesis has the expected lifespan outcomes.In a similar approach, deletion of genes involved in protein sorting in vacuoles, autophagy and mitochondrial function shortened life span, confirming that respiration and degradation processes are essential for long-term survival.Among the genes whose deletion significantly extended life span were genes implicated in fatty acid transport and biosynthesis, cell signalling and transfer RNA (tRNA) methylation such as ACB1, CKA2 and TRM9, respectively [59].",
+      "\t\n\nWe have recently conducted a genome-wide screen using siRNA library to identify genes regulating autophagy in human cells under normal nutritional conditions (5).In this image-based screen we took advantage of the autophagy specific GFP-LC3 reporter whose translocation from the cytosol to autophagosomes can serve as a quantitative measure of autophagy.In this study, we specifically explore the mechanisms that regulate autophagy in neural cells using the hits identified in our screen.We demonstrate that reactive oxygen species (ROS) play a general function in mediation of autophagy upstream of the type III PI3 kinase and that this pathway is essential for the up-regulation of autophagy by A.Interestingly, our data show that genes regulating autophagy are differentially expressed in normal aging and in AD patient brains.Finally, we identify candidate molecular targets that may be safely manipulated to modulate autophagy to treat neurodegenerative diseases.\t\n\nConversely, expression of the key autophagy genes, such as Atg5 and Atg7, was down-regulated in aging.This is consistent with our previous data demonstrating transcriptional down-regulation of beclin 1, in normal human brain aging (11).Together, this suggests, that unlike AD, the normal aging process may lead to transcriptional down-regulation of autophagy.\t\n\nTo further define the biological processes affected by downregulation of autophagy in aging, we used gene ontology canonical pathway analysis.It revealed a significant enrichment in the \"Axon guidance\" (P = 0.0009) and \"Regulation of actin cytoskeleton\" (P = 0.038) pathways, suggesting a connection between regulation of autophagy, axon guidance and actin dynamics.Construction of protein-protein interaction networks anchored by the hit genes belonging to these pathways (12,13) revealed two related networks encompassing, respectively, 27 (11%) and 61 (26%) of the hit genes (Fig. S6 C and D).Importantly, both networks directly connect to the known autophagy machinery through the interaction of the RIP kinase (RIPK1) and PKC (PRKCZ) with p62/sequestrosome (SQSTM1).In addition, syndecan 2 (SDC2), a part of the \"Regulation of actin cytoskeleton\" network, interacts with syntenin, a binding partner of ULK1, the human ortholog of yeast Atg1 (14).ULK1 is known to play a role in the regulation of endocytic processes involved in axon guidance (15) and to promote synapse formation in Drosophila (16).These data suggest that some of the molecular networks involved in the regulation of autophagy are closely connected to those regulating endocytosis, actin dynamics, and neuronal axon guidance, and that autophagy may play a wider role in the development and maintenance of neuronal function.\t\n\nTranscriptional Regulation of Autophagy in Normal Brain Aging.To determine whether the regulation of autophagy may have wider implications in normal aging of the human brain, we analyzed expression of the autophagy screen hit genes in a set of younger versus older human brain samples (10).We observed differential expression of a large subset of genes, including a group of 32 genes significantly (P < 0.05) up-regulated and 46 down-regulated with age (Fig. 6A and Fig. S6 A and B and Table S9).Gene ontology biological process analysis revealed that the age up-regulated group was highly enriched in genes involved in mediation and regulation of the MAP kinase pathway (P = 1.6  10 4 ).An increase in the activity of MAP kinase pathway was predicted by our previous analysis to lead to the suppression of autophagy (5).\t\n\nDifferential Expression of Autophagy Regulators in Normal Aging and in AD.Our gene expression data suggest that autophagy is also differentially regulated at the transcriptional level in normal human brain aging versus in AD.Because autophagy is known to play a protective role against onset of neurodegeneration in animal models (2,3,20,21), its down-regulation in normal aging could contribute to the observed age-dependent predisposition to development of chronic neurodegenerative diseases.In addition, the extensive overlap of the autophagy screen hits with Fig. 6.Expression of autophagy screen hit genes in normal human aging.Clustering analysis (dChip) of mRNA expression levels of select autophagy hit genes in younger (40 y old) versus older (70 y old) human brain samples, based on (i) minimum 1.2-fold change between the average expression, and (ii) P value <0.05 using unpaired t test.\tDiscussion\n\nIn this study, we demonstrate that the type III PI3 kinase plays a fundamental role in the regulation of autophagy and that ROS function as general mediators of autophagy induction upstream of this kinase.This pathway has an essential function in the initiation of autophagy in response to mitochondrial damage following exposure to A, the main pathogen of AD.At the same time, A is able to slow down autophagic processing through ROS independent inhibition of lysosomal degradation.In addition, our analysis of expression of the autophagy screen hits suggests that autophagy is differentially regulated at the transcriptional level in normal human aging and in AD, with overall levels decreased in normal aging but elevated in AD.",
+      "\t\n\nAt least two aspects need to be addressed using a system biology approach in aging research.First, although many different pathways, compartments or processes are known to be closely related to aging, such as the IIS pathway, autophagy, mitochondria, oxidative stress response and so on, it remains unclear as to how they interact, are co-regulated and balanced during aging.To provide a glimpse of this problem, we visualized the network communities among the known aging regulators based on entries in the GenAge database [62,63]  and controlling growth and proliferation (green nodes), DNA damage response for maintaining integrity of the genome (red nodes), mitochondria and oxidative stress response (yellow nodes), and ribosome and translation (blue nodes).It is obvious that the first two are intensively linked and closely entangled, while the latter two are relatively independent processes with only few links connected to the first two processes.Also, it is interesting to note that, by comparing the molecular interaction-based network with the co-citation network, the role of autophagy and protein transport in aging might be either overestimated due to study bias or under-estimated by the incompleteness of the molecular interactions among these genes.\tINTRODUCTION\n\nAging has fascinated researchers since ancient times.The hugely complicated process that has been revealed may be interpreted from different aspects, such as the accumulation of oxidative damage, shortening of telomeres, the costs of reproduction, metabolic rates, cellular senescence, etc., and these have in turn given rise to diverse theories of aging [1].However, thanks to forward and reverse genetic technologies, researchers in the recent decades have established that despite its complexity, a single or a few key genes in a few key pathways can modulate the aging rate.The most important players would appear to be those in nutrient sensing pathways or stress response pathways, such as DAF-2/IGF1R and DAF-16/FOXO in the Insulin/IGF like signaling pathway, AAK-2/AMPK in another nutrient sensing pathway, JNK in the stress response pathway, LET-363/mTOR as an inhibitor of autophagy and activator of translation and SIRT1/SIR2 in genome stability maintenance, to name a few [2,3].In addition to genetic perturbations, dietary perturbations, such as diet restriction (DR) are known to significantly extend lifespan in most organisms examined from yeasts to primates, although different pathways may act under different DR conditions, and alternative DR strategies also effect C.elegans lifespan in different ways [3,4].The main pathways revealed under different DR regimens are summarized in Fig. (1).In this small, convoluted DR response network, DAF-16 and ceTOR/LET-363 *Address correspondence to this author at the Chinese Academy of Sciences, 320 Yue Yang Road, Shanghai, 200031, China; Tel: 86-21-54920458; Fax: 86-21-54920451; E-mail: jdhan@picb.ac.cn  These authors contributed equally to this work.",
+      "\t\n\nIn vitro and animal studies have reported a decline in autophagy with age [26,36,[40][41][42][43]; however, to our knowledge, only one other publication has reported an age-associated decline in expression of autophagy genes, which was carried out in a small number of human brain tissue samples [44].Overall, these findings for major components of core autophagy machinery and upstream regulators provide evidence for a transcriptional decline in autophagy gene expression with age in human monocytes.The identification of key genes contributing to a decline in autophagy are of great interest, as pharmacologic activation of autophagy has been linked with increasing lifespan in animal models, including mice [45].Further, dysfunctional autophagy is now widely implicated in pathophysiological processes of many age-related diseases such as cancer, Alzheimer's, diabetes, and cardiovascular diseases [46].However, longitudinal studies are necessary to validate the age-related transcriptional decline of autophagy gene expression in human monocytes, and to investigate the relationship between these age-related patterns and the development of age-associated diseases.",
+      "\tThe cell-autonomous theory on the\nother hand posits that individual cells are the targets of the aging process, via a timedependent increase in homeostatic dysfunction. The potential mechanisms include\nincreases in the production of reactive oxygen species, telomere shortening and, not\nsurprisingly, genomic instability. An implication of this theory is that long-lived cells in\nthe organism, such as neurons, muscle, and importantly stem cells, would be the\npredominant substrates of aging, while those cells that undergo rapid and continuous\nturnover would be removed before they could exert an effect on tissue function.",
+      "\tConcluding remarks and future perspectives\n\nAging research has rapidly expanded over the past two decades, with studies ranging from lifespan-extending  [68,69,71].However, when their effect on cell death and senescence leads to stem cell loss and tissue degeneration, they might contribute to aging [66,67]."
+    ],
+    [
+      "\tFurther evidence of age-related changes in stem cells include the finding that a\nhigher proportion of Thy-1loSca-1+Lin-Mac-1-CD4-c-kit+ cells from old mice are in\nS/G2/M phases of the cell cycle (Morrison, 1996), and the results of Henckaerts\net al. , who showed that the proliferative response of Lin-Sca-1+c-kit+ marrow cells\nto the early-acting cytokines KL, Flt3L and TPO, decreased dramatically with age\n(Henckaerts et al. 2002). As mentioned previously, the bone marrow niche is the optimal\nmicroenvironment for the growth and functional maintenance of HSCs (Moore\n2004; Nilsson et al. 2001).\t17\nAging Effects on Hematopoietic Stem Cells and Bone Marrow Niche\nAs discussed above, HSC expansion and transplantation is clinically\nimportant to treat patients with hematological and non-hematological disorders. It\nis also well known that cancer risk increases in older people (Balducci and\nExtermann FEB 2000). Therefore, understanding aging effects on hematopoietic\nsystem, especially on HSCs and their bone marrow microenvironment (niche),\nmay not only help to prevent malignant transformation, but also to determine\nefficacy of aging stem cells for transplantation (Pinto et al. 2003; Van Zant and\nLiang 2003) .",
+      "\t\n\nMost mammalian tissues can be described as being comprised of two major cellular components: stem or progenitor cells, which are responsible for regenerative capacity or repair after injury, and differentiated somatic cells, responsible for adult stem cell support and specialized tissue/organ functions.Based on this classification, two major mechanisms can account for tissue degeneration associated with age: loss of stem cell pool division potential (loss of regenerative capacity) and loss of differentiated somatic cell function, which directly leads to loss of organ function.Loss of differentiated somatic cell function can additionally indirectly affect adult stem and progenitor cells by altering the tissue microenvironment that is essential for stem cell support (the stem cell niche).In general, loss of stem cell pool division potential can occur through multiple mechanisms including stem cell senescence, death or dysfunction of the niche.One specific mechanism that can account for the loss of both stem cell and differentiated somatic cell function is the gradual accumulation of persistent DNA damage.Persistent DNA damage and its erroneous resolution *To whom correspondence should be addressed.Tel: +1 415 209 2042; Fax: 415-209-22232; Email: dbhaumik@buckinstitute.org  2007 The Author(s) This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/ by-nc/2.0/uk/)which permits unrestricted non-commercial use, distribution, and reproduction in any medium, provided the original work is properly cited.include telomeric dysfunction (9)(10)(11) and somatic mutations (12), both of which increase with age; both also have been proposed to contribute to the loss of stem and differentiated somatic cell function with age (13,14).DNA damage accumulation in stem cells has been detected in mice and clearly contributes to the attrition of stem cell division potential during aging (15).Thus, it is likely that DNA damage contributes to aging by limiting stem cell division potential and by also interfering with somatic tissue functions, including stem cell niches.",
+      "\t\n\nA diminished capacity to maintain tissue homeostasis is a central physiological characteristic of ageing.As stem cells regulate tissue homeostasis, depletion of stem cell reserves and/or diminished stem cell function have been postulated to contribute to ageing 1 .It has further been suggested that accumulated DNA damage could be a principal mechanism underlying age-dependent stem cell decline 2 .We have tested these hypotheses by examining haematopoietic stem cell reserves and function with age in mice deficient in several genomic maintenance pathways including nucleotide excision repair 3,4 , telomere maintenance 5,6 and non-homologous end-joining 7,8 .Here we show that although deficiencies in these pathways did not deplete stem cell reserves with age, stem cell functional capacity was severely affected under conditions of stress, leading to loss of reconstitution and proliferative potential, diminished self-renewal, increased apoptosis and, ultimately, functional exhaustion.Moreover, we provide evidence that endogenous DNA damage accumulates with age in wild-type stem cells.These data are consistent with DNA damage accrual being a physiological mechanism of stem cell ageing that may contribute to the diminished capacity of aged tissues to return to homeostasis after exposure to acute stress or injury.",
+      "\tSeveral studies have shown\nthat the systemic milieu regulates stem cell decline during aging. Liang et al. showed\nthat HSCs have a reduced ability to home to the bone marrow and spleen after\ntransplantation into old versus young recipients (Liang et al. , 2005). Further experiments\ndemonstrated that the muscle stem cell niche adversely effects stem cell function as\nevidenced by the restoration of old stem cell regenerative potential upon exposure to a\nyoung systemic microenvironment (Conboy et al. , 2005; Conboy and Rando, 2005).\tSince stem cells\nare capable of self-renewal and produce progeny to replenish worn-out and damaged cells\nin aged tissues, the induction of stem cell senescence may compromise tissue renewal by\ndepletion of stem or progenitor cell pools and thus promote age-related pathologies. 6\nIt is apparent that the HSC compartment undergoes considerable age-related\nchanges, however it is not yet clear whether theses changes are intrinsic to the cells\nthemselves or whether they occur due to alterations in the hematopoietic\nmicroenvironment, commonly referred to as the HSC niche.\tHowever, studies do indicate that aged tissues have a diminished capacity to return to a\nhomeostatic state after exposure to stress or injury, therefore indicating a defect in stem\ncell function during the aging process. Since the HSC population provides an ideal\nmodel to study stem cell aging, it is necessary to elucidate the mechanisms of\nhematopoietic aging and expand the findings to other tissues and organ systems. Theories of Aging and Age Related Epigenomic Changes\nThere are two major theories of organismal aging: evolutionary and damage\nbased.\tWith\nthis in mind, it has been hypothesized that the aging or functional failure of tissuespecific stem cells, which fulfill this job, may limit tissue repair and renewal, therefore\ncontributing to overall organismal aging (Krtolica, 2005; Van Zant and Liang, 2003). Because of the unprecedented experimental model systems that are available for the\nexploration of HSCs, stem cell aging research in the field of hematology has been the\nsubject of extensive studies. Indeed, the hematopoietic system has served as an important\nmodel for advancing our understanding of stem cell biology and its association with\naging.\tIn view of the importance of stem cells for maintaining\nimmune function and in a broader sense tissue homeostasis and longevity, there is a\ncritical need to better understand the mechanisms involved in HSC aging. 17\nFigure 1.1 The HSC hierarchy. The HSC compartment can be functionally divided into three populations; long-term\nHSCs, which have extensive self-renewal capacity, short-term HSCs, which have limited\nself-renewal capacity, and multipotent progenitor cells which cannot self-renew and give\nrise to common lymphoid progenitors (CLP) and common myeloid progenitors (CMP).",
+      "\tIn other words, lower HSC proliferation results in a\nmore youthful stem cell, but poorer tissue regeneration, and\nconsequently an aged phenotype; this indicates that stem cell\nproliferation and tissue regeneration are nely balanced to\nmaximize longevity, so that cell cycle disruption results in an\nuncoupling of tissue and organismal aging from the aging of\nthe resident stem cell. Finally, three lines of evidence in our work indicate broad\nchanges in epigenetic regulation with age.\tIf the rejuvenating effect of stem cells were perfect, senescing cells would be\nreplaced indenitely; but even in highly regenerative tissues\nsuch as the skin, the gut, and the hematopoietic system, agerelated decline in function is well established [1]. Still unclear\nare the effects of aging on the stem cells themselves, which\ncould contribute to inferior tissue repair. Hematopoietic stem cells (HSCs) continuously replenish\nthe blood and immune system throughout life. Data from\nmice support an age-related decline in stem cell function [1],\nsuggesting that older HSCs are inadequate to cope with the\ndemands of blood production.",
+      "\tFurthermore, the differentiation potential of the HSC compartment\nappears to become skewed toward the myeloid lineage with age\n(26 28). As HSC have been shown to cycle (29), replicative stress,\neven in the absence of detectable telomere erosion (30, 31), may\nunderlie at least some of the age-related changes in HSC (32). Many traits affecting the hemopoietic stem and progenitor cell\ncompartments also change with age in a mouse strain-dependent\nfashion (2123, 3234) and have been implicated in organismal\nlife span (21, 3234). The responsiveness of LSK cells to TGF-2\nshowed mouse strain-dependent variation in young mice.",
+      "\tFurther evidence of age-related changes in stem cells include the finding that a\nhigher proportion of Thy-1loSca-1+Lin-Mac-1-CD4-c-kit+ cells from old mice are in\nS/G2/M phases of the cell cycle (Morrison, 1996), and the results of Henckaerts\net al. , who showed that the proliferative response of Lin-Sca-1+c-kit+ marrow cells\nto the early-acting cytokines KL, Flt3L and TPO, decreased dramatically with age\n(Henckaerts et al. 2002). As mentioned previously, the bone marrow niche is the optimal\nmicroenvironment for the growth and functional maintenance of HSCs (Moore\n2004; Nilsson et al. 2001).\t17\nAging Effects on Hematopoietic Stem Cells and Bone Marrow Niche\nAs discussed above, HSC expansion and transplantation is clinically\nimportant to treat patients with hematological and non-hematological disorders. It\nis also well known that cancer risk increases in older people (Balducci and\nExtermann FEB 2000). Therefore, understanding aging effects on hematopoietic\nsystem, especially on HSCs and their bone marrow microenvironment (niche),\nmay not only help to prevent malignant transformation, but also to determine\nefficacy of aging stem cells for transplantation (Pinto et al. 2003; Van Zant and\nLiang 2003) .",
+      "\tIntroduction\n\nThe regenerative potential of our body decreases upon aging.Regenerative tissues depend on specialized adult stem cells, thus aging in these tissues can be interpreted as signs of aging in somatic stem cells [1].Adult stem cells are characterized by the dual function to differentiate into different cell lineages and to selfrenew for maintenance of the stem cell pool.It is, however, still controversial if this self-renewal also includes juvenation or if adult stem cells are doomed to undergo aging upon each cell division.It is unclear if adult stem cells undergo functional and molecular changes, if their number decreases because of aging, or if aging is due to extrinsic environmental factors without any effect on the stem cell pool [2,3].\t\n\nThere is emerging evidence that aging is not purely a cell intrinsic process, but rather regulated by interaction with the cellular microenvironment.For example, Ju and co-workers have demonstrated that telomere dysfunction induces alterations in the microenvironment that affect aging of the hematopoietic system [55].In general, adult stem cells have a slow turnover and reside in specialized niches, protected from the environment and only a few are activated at a time [33,56].By keeping adult stem cells in a quiescent state, the stem cell niche might also play a crucial role in regulating replicative senescence.Strong experimental data for this hypothesis derives form serial transplantation experiments of HSC in mice.The reconstituting ability declines continuously within 4 to 5 transfers [57,58] and this decline is thought to be telomereindependent [59], although it has been reported that telomere length decreases by serial transplantation [60].Recently, Wilson and co-workers have demonstrated that there is a dormantfraction of HSC that divides only five times during the lifetime of mice and especially these dormant HSC posses repopulating activity upon serial transplantation [61].The stem cell niche could therefore play a central role in maintaining a dormant pool of HSC to prevent replicative senescence over the lifetime of the organism [62].\t\nThe regenerative potential diminishes with age and this has been ascribed to functional impairments of adult stem cells.Cells in culture undergo senescence after a certain number of cell divisions whereby the cells enlarge and finally stop proliferation.This observation of replicative senescence has been extrapolated to somatic stem cells in vivo and might reflect the aging process of the whole organism.In this study we have analyzed the effect of aging on gene expression profiles of human mesenchymal stromal cells (MSC) and human hematopoietic progenitor cells (HPC).MSC were isolated from bone marrow of donors between 21 and 92 years old.67 genes were age-induced and 60 were age-repressed.HPC were isolated from cord blood or from mobilized peripheral blood of donors between 27 and 73 years and 432 genes were age-induced and 495 were age-repressed.The overlap of age-associated differential gene expression in HPC and MSC was moderate.However, it was striking that several age-related gene expression changes in both MSC and HPC were also differentially expressed upon replicative senescence of MSC in vitro.Especially genes involved in genomic integrity and regulation of transcription were age-repressed.Although telomerase activity and telomere length varied in HPC particularly from older donors, an age-dependent decline was not significant arguing against telomere exhaustion as being causal for the aging phenotype.These studies have demonstrated that aging causes gene expression changes in human MSC and HPC that vary between the two different cell types.Changes upon aging of MSC and HPC are related to those of replicative senescence of MSC in vitro and this indicates that our stem and progenitor cells undergo a similar process also in vivo.\t\n\nThe regenerative potential diminishes with age and this has been ascribed to functional impairments of adult stem cells.Cells in culture undergo senescence after a certain number of cell divisions whereby the cells enlarge and finally stop proliferation.This observation of replicative senescence has been extrapolated to somatic stem cells in vivo and might reflect the aging process of the whole organism.In this study we have analyzed the effect of aging on gene expression profiles of human mesenchymal stromal cells (MSC) and human hematopoietic progenitor cells (HPC).MSC were isolated from bone marrow of donors between 21 and 92 years old.67 genes were age-induced and 60 were age-repressed.HPC were isolated from cord blood or from mobilized peripheral blood of donors between 27 and 73 years and 432 genes were age-induced and 495 were age-repressed.The overlap of age-associated differential gene expression in HPC and MSC was moderate.However, it was striking that several age-related gene expression changes in both MSC and HPC were also differentially expressed upon replicative senescence of MSC in vitro.Especially genes involved in genomic integrity and regulation of transcription were age-repressed.Although telomerase activity and telomere length varied in HPC particularly from older donors, an age-dependent decline was not significant arguing against telomere exhaustion as being causal for the aging phenotype.These studies have demonstrated that aging causes gene expression changes in human MSC and HPC that vary between the two different cell types.Changes upon aging of MSC and HPC are related to those of replicative senescence of MSC in vitro and this indicates that our stem and progenitor cells undergo a similar process also in vivo.\tDiscussion\n\nThe deterioration of the regenerative potential upon aging might be due to functional changes in adult stem cells.To test this hypothesis we have investigated differential gene expression in primary, human MSC and HPC derived from different age groups.In this study, we demonstrate for the first time age-related gene expression changes in human MSC and HPC and that there is a moderate but significant concordance in the expression profiles upon aging in vivo and replicative senescence in vitro.It needs to be pointed out, that chronological age and biological age do not necessarily coincide.Multiparametric assessment of biological age might be valuable in this context.Furthermore, MSC and HPC preparations are heterogeneous and it is conceivable that they represent a mixture of different aged or senescent subsets.Further research will be necessary to address age-related changes on a single cell level to investigate the heterogeneity of aging within cell populations.activating complex, polypeptide 5 (SNAPC5) and peroxisome proliferator-activated receptor gamma (PPARG) were age-repressed.Furthermore, we have validated age associated changes in HPC for 9 genes (B): S100 calcium binding protein A10 (S100A10); vimentin (VIM); myeloid-associated differentiation marker (MYADM); pim-1 oncogene (PIM1) and annexin A2 (ANXA2) were age-induced.Timeless interacting protein (TIPIN); myosin regulatory light chain interacting protein (MYLIP); lymphocyte transmembrane adaptor 1 (LAX1) and Early growth response 1 (ERG1) were agerepressed.Protocadherin 9 (PCDH9) was not amplified in HPC from elderly donors whereas interleukine 7 receptor (IL7R) was not amplified in young samples (not presented in the figure).Differential gene expression was always calculated in relation to the mean of young samples.The mean foldratio (6SD) is demonstrated for median aged and old donor samples.RT-PCR results (red) were always in line with microarray data (blue) for all genes tested.doi:10.1371/journal.pone.0005846.g003",
+      "\tFor instance, mice null for the repair\nprotein Ercc1 show progressive marrow failure resulting in a pancytopenia, while the\nmice exhibit several symptoms of premature aging (Prasher, Lalai et al. 2005). However,\nno studies to date have demonstrated conclusively that diminished DNA repair capacity\nof HSCs with age results in their functional impairment, much less a decreased ability to\nrepair DNA lesions with age. 10\nGenetic regulation of stem cell proliferation\n\nThese many ramifications of the proliferative nature of hematopoietic stem cells\nbegs the question of what are the key molecules regulating this vital feature."
+    ],
+    [
+      "\tHowever, under diabetic conditions, AGEs generated by the exposure of proteins and lipids\nto high glucose levels crosslink ECM proteins, impair ECM degradation by MMPs and\nincrease cardiac stiffness, which together manifest as early diastolic dysfunction33,5254. AGEs can also promote the differentiation of fibroblasts into myofibroblasts, which\nproliferate and induce ECM dyshomeostasis by secreting profibrotic cytokines and matrix\nproteins. Furthermore, the altered cardiac mechanics lead to the release of other stimuli\nincluding transforming growth factor- (TGF), tumour necrosis factor (TNF), angiotensin\nII and various interleukins, which activate profibrotic responses in fibroblasts and\nmyofibroblasts55.",
+      "\t\n\nMuch work has focused on molecular features often observed with advanced age-cellular senescence, autophagy, oxidative stress, and epigenetic changes.Vascular remodeling, as a consequence of these features, is well documented leading to endothelial dysfunction and arterial stiffness.Although such features are also invoked in other conditions such as heart failure with preserved ejection fraction and valvular calcification, disentangling the key causal features suitable for therapeutic modulation remains elusive.",
+      "\t\n\nNonenzymatic glycation of proteins and lipids occurs with aging, a process that is accelerated in the setting of glucose dysregulation, such as diabetes mellitus [7].Advanced glycation end products (AGEs) formation has been implicated in a number of pathological processes associated with micro-and macrovascular diabetic complications [8][9][10].It has been demonstrated that the effects of AGEs are partially mediated through their interactions with cell surface receptor, the receptor for advanced glycation end products (RAGE) [11].The soluble form of RAGE (sRAGE) is a proteolytic cleavage product of RAGE, which has AGE-binding property but lacks the signaling cascade [12].In Caucasians without T2DM, sRAGE has been associated with decreased renal function assessed by estimated glomerular filtration rate (eGFR) or serum creatinine level [13][14][15].In Caucasian T2DM patients, sRAGE has been associated with albuminuria [16], decreased eGFR [17] and new or worsening kidney diseases and mortality [18].However, to date, only two studies reported associations of sRAGE level with renal function in Asians with T2DM [19,20].Although sRAGE is increasingly gaining importance as a biomarker in diabetic complications, it is not clear how sRAGE level is regulated and why it varies among studies.In addition, genetic studies of sRAGE remain very limited.",
+      "\t\n\nAdvanced glycation end-products (AGE) are the result of nonenzymatic glycation, which produces heterogeneous bioactive molecules, such as lipids, proteins, and nucleic acids [59].The accumulation of AGEs in aged tissues leads to several processes, such as inflammation, obesity, apoptosis, and other adverse processes related to ageing [47].These AGEs are detected by various techniques, such as gas chromatography, high-performance liquid chromatography, spectrometry, and immunochemical technique [60], which make them robust biomarkers that can be analyzed by different methodologies.",
+      "\t\n\nCritical areas of vascular aging research include the role of senescence, epigenetics, stress resilience, inflammation, macromolecular damage, proteostasis, mitochondrial and metabolic dysfunction, and impaired stem cell biology.The specific roles for cell-autonomous and noncell-autonomous mechanisms contributing to vascular aging need to be elucidated further.The role of signal transduction pathways linked to regulation of cellular energetics in the vascular aging process should be better defined.Future studies should also lead to improved understanding of the role circadian clocks to vascular aging.New studies investigating cellular heterogeneity in vascular aging are warranted.Stochastic macromolecular damage leads to regional variability in the presence of senescent cells, cells with altered metabolism, mitochondrial dysfunction, and increased ROS production.Such regional variability likely contributes to the focal development of vascular pathologies, ranging from atherosclerotic plaques to microhemorrhages.Single-cell gene expression analysis should facilitate better understanding of the pathophysiological role of functional heterogeneity.Finally, how environmental factors and lifestyle choice impact the vascular aging processes should be better understood.",
+      "\t\n\nThe characteristics of the second pathway include the formation of advanced glycation end-products (AGEs) from excessive imbibing of glucose [7].The AGEs via interaction with their receptor, RAGE, transduce a complex series of signaling events that result in cellular dysfunctions, thus generating an inflammatory response and reactive oxygen species (ROS), which in turn cause oxidative stress [7].Both in vitro and in vivo studies support the relevance of this pathway in the pathogenesis of diabetic nephropathy [7].The fact that several inhibitors of AGEs, such as pyridoxamine, LR-90 and KIOM-79, have been demonstrated to be beneficial in various murine models of diabetes emphasizes the role of AGE:RAGE interactions [8][9][10].Although these inhibitors may be effective in murine models, their efficacy certainly needs to be evaluated in diabetic nephropathy in humans.",
+      "\tAging is only, in part, the result of oxidative, free radical chemistry\n\nThe free radical theory of aging (Harman 1992) proposes that reactive oxygen is the major culprit in aging, leading to age-dependent oxidative modification, crosslinking and denaturation of proteins, with resultant loss of protein and enzyme structure and function.This theory has been expanded in recent years to include not only direct oxidation of proteins by reactive oxygen, but also the modification of proteins by Maillard reaction products, AGEs and ALEs (Thorpe and Baynes 1996).The majority of AGEs that are known to accumulate with age in tissue proteins are glycoxidation products, formed by combined glycation and oxidation reactions of precursors, such as glucose or ascorbate (Baynes 1991).In non-diabetic patients, levels of the glycoxidation products CML and pentosidine correlate with levels of methionine sulfoxide and o-tyrosine in skin collagen, indicating that these products are formed in parallel with one another (Wells-Knecht et al. 1997).Although oxidation appears to be important in the formation of AGEs and crosslinking of protein by glucose and ascorbate (Fu et al. 1994), some AGEs, such as pyrraline and crosslines, are formed non-oxidatively from glucose.The crosslines increase in lens proteins with age (Obayashi et al. 1996), so that oxidation is not essential for an age-dependent increase in crosslinking of protein by carbohydrates.In contrast to AGEs, ALEs require oxidative conditions for their formation -the first intermediate in ALE formation is a lipid peroxide, formed from a polyunsaturated fatty acid (PUFA) by an enzymatic or non-enzymatic autoxidation reaction involving molecular oxygen.The EAGLEs, CEL and MOLD, increase with age in collagen and crystallins, but cannot be classified as oxidative or nonoxidative since they may be formed either oxidatively during peroxidation of PUFA (Fu et al. 1996) or non-oxidatively from glyceraldehyde 3-phosphate or dihydroxyacetone phosphate formed during anaerobic glycolysis (Ahmed et al. 1997).Other modifications of amino acids, including deamidation, racemization and formation of hydroxykynurenine adducts are also age-dependent, non-crosslinking modifications of proteins.\tAging may be accelerated by inflammation and disease\n\nThe relationship between aging and age-related, chronic disease is complex.Healthy aging generally leads to a longer life, while chronic disease and associated inflammatory processes generally accelerate the aging process, i.e. shorten life span.The relationship between aging and chronic disease may be illustrated by diabetes, a disease in which the accumulation of AGEs in tissue proteins is accelerated by hyperglycemia.CML and pentosidine are biomarkers of normal aging of tissue collagens, and their accelerated accumulation in collagen in diabetes is de facto evidence that diabetes is a disease characterized by accelerated aging of collagen (Dyer et al. 1993).The acceleration of protein aging in diabetes is apparent, not only by the increase in AGEs, but also by increases in browning and fluorescence of collagen, and decreased solubility, decreased elasticity and increased thickness of basement membranes in diabetes (Baynes and Thorpe 1999).Notably, the rates of accumulation of other biomarkers, such as o-tyrosine and methionine sulfoxide in skin collagen, do not change significantly in diabetes (Wells-Knecht et al. 1997).Thus, the acceleration of chemical aging of collagen in diabetes is unbalanced or 'pathologic' in nature, apparently driven by the increase in circulating levels of oxidizable substrates (carbohydrates and lipids) (Baynes 1991(Baynes , 1999;;Baynes and Thorpe 1999a, b), rather than an increase in oxidative stress.Diabetes also increases the risk for cardiovascular disease, the major cause of mortality in the western world, while the increased risk for cataracts in diabetes may result from increases in both glycation and oxidative stress in the lens (Stevens 1998).",
+      "\tMG is elevated in the diabetic state and is\nthought to contribute to the development of diabetic complications, particularly through the\nformation of AGEs (60). AGE modification of vascular extracellular matrix proteins causes\n\nW\n\ncross-linking, which alters elastic properties and traps low-density lipoprotein in the vessel wall\n(60). Upon ligating RAGE, AGEs cause endothelial dysfunction, activation of NF-B, release of\n\nIE\n\npro-inflammatory molecules, and formation of vessel-damaging ROS (60). Through detoxifying\nMG, GLO1 is thought to protect against diabetic complications.",
+      "\tIt is based on the tendency of glucose to\nundergo oxydation in the presence of traces of heavy metal\nions, thus creating reactive ketoaldehydes, hydrogen peroxyde, and free radicals. It is clear now that the rearrangement of Schiff bases, Amadori products and/or AGEs is\naccompanied by generation of reactive oxygen species that\ncause conformational changes and fragmentation of the\nglycated proteins (11, 12). The proteins modified by AGEs\nare shown to be toxic, immunogenic, and capable of triggering cellular injury responses after binding to specific\nreceptors (1315).\tTaking into consideration that glycation is a slow process, it has always been regarded as typical for the longliving organisms and as affecting the long-living proteins\n(haemoglobin, crystalline, etc.)only. Surprisingly, our\nrecent studies indicated that glycation takes place also in\nE. coli and affects both the host bacterial and recombinant\nproteins (16, 17). Once started in vivo, glycation can not\nbe stopped after isolation and purification of the protein. Accumulation of AGEs continues even when pure protein preparations are stored in deep frozen solutions. A\ngreat number of studies have been dedicated to the search\nfor inhibitors of glycation.\tMullarkey CJ, Edelstein D, Brownlee M (1990) Free radical generation by early glycation products: a mechanism for accelerated atherogenesis in diabetes. Biochem Biophys Res Commun\n173:932939. Sakurai T, Tsuchiya S (1988) Superoxide production from nonenzymatically glycated protein. FEBS Lett 236:406410\nWendt T, Tanji N, Guo J, Hudson BI, Bierhaus A, Ramasamy R,\nArnold B, Nawroth PP, Yan SF, DAgati V, Schmidt AM (2003)\nGlucose, glycation, and RAGE: implications for amplification of\ncellular dysfunction in diabetic nephropathy. J Am Soc Nephrol\n14:13831395. Wautier JL, Schmidt AM (2004) Protein glycation: a firm link to\nendothelial cell dysfunction. Circ Res 95:233238.",
+      "\t\n\nFigure 15: Aspects of hyperglycemia-related vascular cell dysfunction.Hyperglycemia-induces a range of pathways in cells such as endothelium, and these include the polyol pathway, reactive oxygen species (ROS) formation, and advanced glycation endproducts (AGEs) formation.Excess glucose in endothelial cells enters polyol pathway; the electron donors like reduced nicotinamide adenine dinucleotide (NADH) and Flavin adenine dinucleotide (FADH2) accumulate in the mitochondria, thus affecting the electron transport chain; the excess electrons increase ROS in mitochondria; ROS triggers accumulation of AGEs; ROS and AGEs create mitochondrial DNA damage and mitochondrial dysfunction; protein kinase C (PKC) and AGE mediated activation of nuclear factor kappa B (NFB) activate the expression of inflammation proteins, tumor suppressor p53, and inducible nitric oxide synthase (iNOS); increased nitric oxide (NO) by iNOS is highly reactive with superoxide anions; the peroxynitrite thus generated acts as a strong oxidant and completes the vicious cycle of oxidative stress by increasing ROS production; accumulation of AGEs also increases ROS production independent of glucose levels\tM A N U S C R I P T A C C E P T E D ACCEPTED MANUSCRIPT 50\n\nglycation and lipoxidation end-products and upregulation of the receptor for AGEs (RAGE) has a key role in the hyperglycemia-induced activation of Mller glia and downstream cytokine production in the context of diabetic retinopathy (Berner et al., 2012;Curtis et al., 2011;Yong et al., 2010;Zong et al., 2010).Diabetes has also been reported to accelerate death of Mller glia (Feenstra et al., 2013;Hammes et al., 1995), an effect which has recently been linked to the disruption of retinal vascular integrity and the induction of neural cell dysfunction and death (Shen et al., 2012).A schematic diagram summarising how Mller glia changes are believed to contribute to the sight threatening complications of diabetic retinopathy is presented in Figure 11.Apart from the Mller cells, activated microglial cells adjacent to the vessels also appear to have a key role in vasoregression, the vascular hallmark of the early stages of diabetic retinopathy in both animal models (McVicar et al., 2015) and diabetic patients (Scott et al., 2014b).",
+      "\tIt is based on the tendency of glucose to\nundergo oxydation in the presence of traces of heavy metal\nions, thus creating reactive ketoaldehydes, hydrogen peroxyde, and free radicals. It is clear now that the rearrangement of Schiff bases, Amadori products and/or AGEs is\naccompanied by generation of reactive oxygen species that\ncause conformational changes and fragmentation of the\nglycated proteins (11, 12). The proteins modified by AGEs\nare shown to be toxic, immunogenic, and capable of triggering cellular injury responses after binding to specific\nreceptors (1315).\tTaking into consideration that glycation is a slow process, it has always been regarded as typical for the longliving organisms and as affecting the long-living proteins\n(haemoglobin, crystalline, etc.)only. Surprisingly, our\nrecent studies indicated that glycation takes place also in\nE. coli and affects both the host bacterial and recombinant\nproteins (16, 17). Once started in vivo, glycation can not\nbe stopped after isolation and purification of the protein. Accumulation of AGEs continues even when pure protein preparations are stored in deep frozen solutions. A\ngreat number of studies have been dedicated to the search\nfor inhibitors of glycation.\tMullarkey CJ, Edelstein D, Brownlee M (1990) Free radical generation by early glycation products: a mechanism for accelerated atherogenesis in diabetes. Biochem Biophys Res Commun\n173:932939. Sakurai T, Tsuchiya S (1988) Superoxide production from nonenzymatically glycated protein. FEBS Lett 236:406410\nWendt T, Tanji N, Guo J, Hudson BI, Bierhaus A, Ramasamy R,\nArnold B, Nawroth PP, Yan SF, DAgati V, Schmidt AM (2003)\nGlucose, glycation, and RAGE: implications for amplification of\ncellular dysfunction in diabetic nephropathy. J Am Soc Nephrol\n14:13831395. Wautier JL, Schmidt AM (2004) Protein glycation: a firm link to\nendothelial cell dysfunction. Circ Res 95:233238.",
+      "\tVascular endothelial dysfunction. In diabetes, endothelial dysfunction is linked to the accumulation of toxic lipids 90 , AGEs 91 and/or aggregated proteins 59 in the vasculature.Proteinaceous deposition on blood vessel walls damages endothelial cells 59,91 , increases the production of reactive oxygen species (ROS) 92,93 and impairs production of vasodilatory substances 92 , which results in a reduced cerebral blood flow.Stalled blood flow can lead to neurovascular uncoupling and hypoxic neuronal injury [92][93][94] .Elevated ROS production can further damage cellular structures and activate matrix metalloproteinases, inducing cytoskeletal reorganization and vascular remodelling 93 .Cytoskeletal reorganization affects the stability of tight junction proteins, resulting in increased capillary permeability, depletion of energy resources and altered neural viability 92,93 .",
+      "\t\n\nAdvanced glycation end products (AGEs) are a heterogeneous group of macromolecules that are formed by the nonenzymatic glycation of proteins, lipids, and nucleic acids.Overproduction of AGEs is considered the most important pathophysiological mechanism that induces diabetic complications (Semba et al. 2010).On one hand, AGEs mediate intracellular glycation of mitochondrial respiratory chain proteins and increase ROS levels, thus triggering oxidative stress (Coughlan et al. 2009) and endoplasmic reticulum stress (Piperi et al. 2012).On the other hand, binding of AGEs with receptors for advanced glycation end products (RAGEs) activates the AGE signalling axis to induce activation of NF-KB signalling and JAK/STAT signalling, which upregulate inflammatory cytokines and adhesion molecules (Basta 2008;Basta et al. 2004).The evidence indicates that exposure to AGEs is connected with the risk of adverse ageing-related outcomes.Akt1, Bsk, and P38b have been found to be crucial in the regulation of the AGE-RAGE-signalling pathway.Transforming growth factor beta (TGF-beta) is a major growth factor in joints that is crucial in maintaining chondrocyte homeostasis.However, the TGF-beta-signalling pathway changes with ageing, resulting in an age-related decline in the anabolic response that favours hypertrophy of chondrocytes and the development of osteoarthritis (Baug et al. 2014).In addition, Upadhyay et al. also reviewed the important role of TGF in the developmental processes of D. melanogaster and the role of TGF in regulating hormones, neurons and innate immunity (Upadhyay et al. 2017).Therefore, ageing-induced TGF-beta dysregulation is associated with deleterious effects on longevity and ageing itself.Dpp, Mad, and S6k are functionally crucial in the TGF-beta-signalling pathway.",
+      "\tIntroduction\n\nIn individuals with diabetes, nonenzymatic glycation of proteins leads to the formation of advanced glycation end products (AGE) and this process occurs at an accelerated rate in chronic hyperglycaemia 1 , and also the levels are found to be increased in complications of diabetes, such as diabetic retinopathy (DR). 2 AGE induces a variety of pathological changes, such as increased basement membrane thickening, arterial stiffness, and glomerular sclerosis. 3,4AGEs bind to a specific receptor known as receptor for advanced glycation end products (RAGE).RAGE is expressed in many of the cell types, such as the endothelial cells, monocytes, and lymphocytes, including the beta cells of the pancreas.RAGE-mediated signaling leads to the activation of transcription factors, such as NF-kB, AP-1, and STAT-1, 5,6 the adhesion molecules VCAM, ICAM, and tissue factor, 7,8 which promote a procoagulant state in the microcapillaries of the retina.This results in a hypoxic state that leads to the initiation of the angiogenic process in proliferative DR."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "F66E835853D76F6DE8C2DC6F22DACDA3"
+    },
+    {
+      "task_id": "49C4A8D68287C56E8A7C9DB0F55E223E"
+    },
+    {
+      "task_id": "46C0740EB9753AFA9AFB6BA4E90EB0CA"
+    },
+    {
+      "task_id": "33D49E56B7C81F0F0E66C72E385F8594"
+    },
+    {
+      "task_id": "A483880F1B854CB70D1389C423835FFA"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_1.json
new file mode 100644
index 0000000..03f04f4
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_1.json
@@ -0,0 +1,106 @@
+{
+  "question": [
+    "How do recent advancements in multi-omics approaches, including proteomics and metabolomics, contribute to our understanding of Type 2 diabetes pathogenesis?",
+    "What novel diabetic loci have been identified through the latest meta-analyses of large-scale genome-wide association studies (GWAS)?",
+    "How do epigenetic modifications, such as DNA methylation and histone modification, influence the expression of diabetes-related genes?",
+    "Can you elaborate on the role of the gut microbiome in modulating host genetic predispositions to diabetes?",
+    "How effective are machine learning algorithms in integrating genomic data to predict individual risk and progression of diabetes?"
+  ],
+  "answer": [
+    "Recent advancements in multi-omics approaches, including proteomics and metabolomics, allow for a comprehensive characterization of metabolic changes associated with Type 2 diabetes. These tools can identify and measure thousands of metabolites in a given biological sample, providing insights into the disease's development and progression. They can also identify potential early biomarkers for the disease and its comorbidities. Furthermore, these approaches can help understand the body's responses to environmental and lifestyle factors, and the interactions between genetic and environmental factors that produce changes in the body's biochemical profile. This can aid in early diagnosis, therapy monitoring, and understanding the disease's pathogenesis.",
+    "The latest meta-analyses of large-scale genome-wide association studies (GWAS) have identified novel diabetic loci near several genes. These include JAZF1, CDC123-CAMK1D, TSPAN8-LGR5, THADA, ADAMTS9, NOTCH2, UBASH3A, BACH2, AGMO, GDAP1, PTF1A, SIX3, ALDH2, NKX6-3, ANK1, and a microRNA cluster. Additionally, a locus near the LMO7 gene on 13q22 and another near the EFR3B gene on 2p23 were identified. A novel signal was also detected near AGMO.",
+    "Epigenetic modifications like DNA methylation and histone modification can alter the expression of diabetes-related genes without changing the underlying DNA sequence. DNA methylation involves the addition of a methyl group to a cytosine within cytosine-phosphate-guanine (CpG) dinucleotides, which can regulate gene expression. Histone modifications, on the other hand, involve changes to the proteins around which DNA is wound, affecting the accessibility of genes for transcription. These modifications can be influenced by factors such as hyperglycemia, inflammation, and oxidative stress, leading to changes in gene expression that contribute to diabetes and its complications.",
+    "The gut microbiome plays a significant role in modulating host genetic predispositions to diabetes. It has been observed that alterations in the gut microbiome can precede the onset of Type 1 Diabetes (T1D). Dysbiosis of gut microbiota, characterized by an imbalance in the microbial community, can contribute to insulin resistance and the pathogenesis of T2D. The gut microbiome can influence glucose metabolism and insulin sensitivity, and changes in its composition can affect the development and progression of diabetes. Certain gut microbiota can improve glucose homeostasis and leptin sensitivity, potentially offering therapeutic targets for diabetes prevention and management. However, the interactions between host genetics, metabolism, and the immune system in shaping the microbiome and predilection to disease are still being explored.",
+    "Machine learning algorithms have shown significant effectiveness in integrating genomic data to predict individual risk and progression of diabetes. The most commonly used algorithms are Support Vector Machine (SVM), Artificial Neural Networks (ANN), and Decision Trees (DT), with SVM being the most successful. The prediction accuracy of these algorithms is often above 80%. Recurrent Neural Network (RNN) models have also been used to predict type 2 diabetes with promising results. However, the effectiveness can vary depending on the specific algorithm used, the quality of the data, and the number of features or attributes used in the model."
+  ],
+  "contexts": [
+    [
+      "\t\n\nMechanistic and translational studies that focus on the characterisation of archetypes are likely to be more tractable.For each of the component pathways, we should seek to deepen our understanding of the molecular and physiological machinery responsible for homeostatic control, and of the specific genetic and environmental factors that 'push' individuals towards diabetes.We should aim to identify biomarkers that serve as robust readouts for each of those processes.We already have some examples of these (e.g.islet antibodies, urinary C-peptide) but access to increasingly powerful 'omic' readouts (transcriptomics, proteomics, metabolomics) brings the promise of others [21].We should aim to determine the extent to which the various pharmacological and behavioural interventions that are available influence diabetes progression and management in the different archetype groups.In doing so, we will determine the extent to which we can expect to optimise prevention and therapy on the basis of this improved diagnostic precision.Alternatively, we may find that many treatments work fairly well irrespective of individual pathology, since, to reverse the diabetic phenotype, it may be sufficient to shift enough of the contributing pathways in a beneficial direction.\t\nThe current focus on delivery of personalised (or precision) medicine reflects the expectation that developments in genomics, imaging and other domains will extend our diagnostic and prognostic capabilities, and enable more effective targeting of current and future preventative and therapeutic options.The clinical benefits of this approach are already being realised in rare diseases and cancer but the impact on management of complex diseases, such as type 2 diabetes, remains limited.This may reflect reliance on inappropriate models of disease architecture, based around rare, highimpact genetic and environmental exposures that are poorly suited to our emerging understanding of type 2 diabetes.This review proposes an alternative 'palette' model, centred on a molecular taxonomy that focuses on positioning an individual with respect to the major pathophysiological processes that contribute to diabetes risk and progression.This model anticipates that many individuals with diabetes will have multiple parallel defects that affect several of these processes.One corollary of this model is that research efforts should, at least initially, be targeted towards identifying and characterising individuals whose adverse metabolic trajectory is dominated by perturbation in a restricted set of processes.",
+      "\t\n\nAs discussed earlier, these high-throughput approaches are already being implemented in diabetic complications research.They have been complemented with systems biology and systems genetics efforts to effectively identify new players in and drug targets for diabetic complications [105].There are also ongoing efforts to systematically profile epigenetic marks in tissues, cells and archived genomic DNA from various clinical trials.The major challenge, however, is expected to be in the analysis of the ensuing large datasets, the complexity of bioinformatics/biostatistics and in silico modelling.If these hurdles can be overcome, these efforts are likely to yield novel insights into epigenome variations linked with diabetic complications.",
+      "\t\n\nGriffin JL, Vidal-Puig A. Current challenges in metabolomics for diabetes research: a vital functional genomic tool or just a ploy for gaining funding?Physiol Genomics 34: 1-5, 2008.First published April 15, 2008; doi:10.1152/physiolgenomics.00009.2008.-Metabolomicsaims to profile all the small molecule metabolites found within a cell, tissue, organ, or organism and use this information to understand a biological manipulation such as a drug intervention or a gene knockout.While neither mass spectrometry or NMR spectroscopy, the two most commonly used analytical tools in metabolomics, can provide a complete coverage of the metabolome, compared with other functional genomic tools for profiling biological moieties the approach is cheap and high throughput.In diabetes and obesity research this has provided the opportunity to assess large human populations or investigate a range of different tissues in animal studies both rapidly and cheaply.However, the approach has a number of major challenges, particularly with the interpretation of the data obtained.For example, some key pathways are better represented by high concentration metabolites inside the cell, and thus, the coverage of the metabolome may become biased towards these pathways (e.g., the TCA cycle, amino acid metabolism).There is also the challenge of statistically modeling datasets with large numbers of variables but relatively small sample sizes.This perspective discusses our own experience of some of the benefits and pitfalls with using metabolomics to understand diseases associated with type 2 diabetes.NMR spectroscopy; mass spectrometry; obesity; functional genomics WHILE IT IS DIFFICULT TO DATE the start of any field this is particularly true of -omic technologies.The desire to profile a large number of entities involved in any tier of a biological system has been a common thread in biology.The field of metabolomics is no exception to this statement.While the term metabolomics (23) and the related term metabonomics (22) were coined in the late 90s, it is difficult to distinguish some of the work conducted now under the umbrella of metabolomics from much earlier studies involving largescale profiling of metabolites by mass spectrometry (for example Refs.16,30) and NMR spectroscopy (for example Refs.3,5).Indeed many of the basic processes that occur in current metabolomic laboratories would not be that dissimilar to work carried out by the pioneers of metabolic research who gave their names to the various pathways we study.In this brief article we discuss some of the benefits modern metabolomic approaches provide to functional genomics, with particular reference to diabetes and the metabolic syndrome, and outline some of the challenges the field faces if it is to develop into a mature technology.",
+      "\t\nClinical and epidemiological metabolomics provides a unique opportunity to look at genotypephenotype relationships as well as the body's responses to environmental and lifestyle factors.Fundamentally, it provides information on the universal outcome of influencing factors on disease states and has great potential in the early diagnosis, therapy monitoring, and understanding of the pathogenesis of disease.Diseases, such as diabetes, with a complex set of interactions between genetic and environmental factors, produce changes in the body's biochemical profile, thereby providing potential markers for diagnosis and initiation of therapies.There is clearly a need to discover new ways to aid diagnosis and assessment of glycemic status to help reduce diabetes complications and improve the quality of life.Many factors, including peptides, proteins, metabolites, nucleic acids, and polymorphisms, have been proposed as putative biomarkers for diabetes.Metabolomics is an approach used to identify and assess metabolic characteristics, changes, and phenotypes in response to influencing factors, such as environment, diet, lifestyle, and pathophysiological states.The specificity and sensitivity using metabolomics to identify biomarkers of disease have become increasingly feasible because of advances in analytical and information technologies.Likewise, the emergence of high-throughput genotyping technologies and genome-wide association studies has prompted the search for genetic markers of diabetes predisposition or susceptibility.In this review, we consider the application of key metabolomic and genomic methodologies in diabetes and summarize the established, new, and emerging metabolomic and genomic biomarkers for the disease.We conclude by summarizing future insights into the search for improved biomarkers for diabetes research and human diagnostics.\t\n\nClinical and epidemiological metabolomics provides a unique opportunity to look at genotypephenotype relationships as well as the body's responses to environmental and lifestyle factors.Fundamentally, it provides information on the universal outcome of influencing factors on disease states and has great potential in the early diagnosis, therapy monitoring, and understanding of the pathogenesis of disease.Diseases, such as diabetes, with a complex set of interactions between genetic and environmental factors, produce changes in the body's biochemical profile, thereby providing potential markers for diagnosis and initiation of therapies.There is clearly a need to discover new ways to aid diagnosis and assessment of glycemic status to help reduce diabetes complications and improve the quality of life.Many factors, including peptides, proteins, metabolites, nucleic acids, and polymorphisms, have been proposed as putative biomarkers for diabetes.Metabolomics is an approach used to identify and assess metabolic characteristics, changes, and phenotypes in response to influencing factors, such as environment, diet, lifestyle, and pathophysiological states.The specificity and sensitivity using metabolomics to identify biomarkers of disease have become increasingly feasible because of advances in analytical and information technologies.Likewise, the emergence of high-throughput genotyping technologies and genome-wide association studies has prompted the search for genetic markers of diabetes predisposition or susceptibility.In this review, we consider the application of key metabolomic and genomic methodologies in diabetes and summarize the established, new, and emerging metabolomic and genomic biomarkers for the disease.We conclude by summarizing future insights into the search for improved biomarkers for diabetes research and human diagnostics.\t\n\nIn this brief review, we consider recent applications of metabolomic and related technologies in diabetes together with their use in relation to clinical diagnostics.Technical details of the methodologies involved and their use in basic diabetes research have been covered in several excellent articles and reviews (1,3).",
+      "\tnovEl \"-omics\" TEcHnologiEs\n\nThe number of scientific articles on transcriptomics, proteomics, and metabolomics has been increasing substantively over the state art state art past 10-15 years.The accumulation of information from novel \"-omics\" technologies comes with substantial hope and expectations that these hypothesis-free approaches will yield novel insights into many disease processes and that these insights will eventually translate into clinical applications that will pave the way from current medical routine to the ideal of personalized medicine.With regard to T2D and CVD, the use of data from transcriptomics, proteomics, and metabolomics studies for their predictive potential is still at a very early stage.Here, we aim to provide an overview of studies that are representative of current developments in this research field.",
+      "\tOther 'omics' tools\n\n Given the current epidemic status of T2D, the need for the hour is a deeper understanding of associated pathological mechanisms, for timely intervention. To realize this objective, a range of novel tools and techniques need to be integrated in diabetes research, as no one technique is capable of providing the solution by itself.Epigenomics, transcriptomics, proteomics, metabolomics, and computational biology are some tools of the proposed 'omics' toolbox which may contribute to the field of T2D research.\tReview Siddiqui & Tyagi\n\nThe goal of personalized treatment and care for diabetes can be realized by integrating patient-specific knowledge with data from 'omics' technologies.Advances in genomics (including epigenomics), transcriptomics, proteomics and metabolomics may not only help in identifying, assessing and quantitating individual disease risk early on, but will also be beneficial in understanding the specific responses to drug therapy and lifestyle interventions.This can be further complemented with patient information on their economic status, ease or difficulty of access to healthcare (more of a challenge in developing countries), environment (e.g., exposure to high pollution levels, work culture, social structure among others) and lifestyle (e.g., smoking, physical activity, eating preferences among others).An evidence-based therapy, which is implemented timely and incorporates such personal values, circumstances and data, can be more effective in managing diabetes at an individual level.Although the 'omics' revolution has been more successful in providing insights into monogenic diseases than polygenic disorders, its potential in expanding knowledge of genetic determinants influencing diabetes susceptibility and treatment cannot be overlooked.In diabetes research, omics tools have proven their worth in identifying not only susceptibility genes but also biological markers of disease pathology, thereby adding to the understanding of the disease process.\t\n\nSince data from any one tool is insufficient in providing a comprehensive picture, data from all 'omics' tools (genomics, transcriptomics, proteomics, metabolomics among others) can be used in a systems biology approach for a better understanding at tissue or organ system level.Systems biology integrates the given information into interaction networks [74].These networks assess both functional interactions and mathematical correlations between given data in a biological setting and provide a broader picture.Jain et al. [75] have demonstrated the use of a systems biology approach for uncovering genome to phenome correlations in T2D by identifying pathways known to be associated with disease pathology.Although the field of systems biology holds promise, it is still in its nascent stage and requires extensive work to be able to map diseases in complex tissues and organ systems.",
+      "\tConclusions and Future Perspectives\n\nCurrent approaches such as transcriptome and proteome profiling, as well as molecular genetics, using various cell lines, animal models and human samples have greatly facilitated the understanding of the mechanism(s) relevant to the progression of diabetic nephropathy.Based on the data generated by using these techniques, the newly discovered biomarkers could serve as therapeutic targets for the amelioration of diabetic nephropathy, which certainly contribute to the reduction in mortality and morbidity in chronic kidney disease patients that progress to ESRD.In addition to transcriptome and proteome approaches, the future trends for the identification of the biomarkers and therapeutic target genes could include genome-scale DNA methylation profiling [75].The emerging role of epigenome control of the cancer cells, germ cells and pluripotent stem cells has been emphasized in the transcriptional regulation of various genes that receive sustained long-term injury for years and decades.Intensive long-term versus conventional short-interval symptomatic therapy seems to have remarkable beneficial effects on the risk of cardiovascular disease in patients with type 1 diabetes and this suggests that there may be alterations in the genomic DNA-or histonemethylation pattern which may be linked to the long-term 'metabolic memory' for the progression of vascular complications of diabetes [76].Such a methylation-related profiling would certainly advance the field, especially with respect to development of new biomarkers and various therapeutic strategies.In addition to the delineation of epigenome control of the genes, metabolic phenotyping using 1H spectroscopy [77] and lectin microarray [78] for the glycan profiling would also promote the identification of the new biomarkers of diabetic nephropathy.Finally, integration of the information from different sources using system biology approaches would be an important step in data-mining for the identification of relevant genes that are pertinent to the diagnosis and therapy for diabetic nephropathy.",
+      "\tNovel biomarkers from '-omics' technologies as potential components of risk models\n\nDespite moderate or even good model accuracy in some studies (Table 1, ESM Table 2), current prediction algorithms leave room for improvement and raise the question of whether novel biomarkers could be clinically useful, particularly if they could improve risk models that already contain measures of glycaemia.The range of molecules that could serve as potential biomarkers of diabetes risk includes genetic variants, RNA transcripts, peptides and proteins, lipids and small metabolites, cellular markers and metabolic waste products [39].Owing to current advances in '-omics' technologies, such as genomics, transcriptomics, proteomics and metabolomics, the number of candidate biomarkers keeps growing; however, only a small proportion of these has been investigated with reference to their potential to improve the prediction of type 2 diabetes.",
+      "\t\n\nThe so-called omics (eg, metabolomics, lipidomics, proteomics, genomics, and transcriptomics) are based on the study of constituents of the cell or body in a collective way.The fi ndings made with use of these approaches are being integrated to better understand the pathophysiology of type 2 diabetes and the heterogeneity of responses to diff erent glucose-lowering therapies.Findings from studies that used metabolomics and lipidomics showed that increases in branched-chain and aromatic aminoacids were associated with obesity and type 2 diabetes. 84,85Furthermore, patients with high concentrations of specifi c six-carbon sugars, aminoacids, and fatty acids, and low concentrations of other aminoacids and fatty acids, had an increased risk of developing type 2 diabetes over a 7 year follow-up. 86hether all or some of these substrate markers are associated with genetic determinants, dietary factors, or the actions of gut microbes has not been established.",
+      "\tMetabolomics and novel circulating biomarkers\n\nMetabolomics is a comprehensive characterization of metabolic changes connected to disease development and progression.High sensitivity and resolution of mass spectrometry achieved with liquid or gas chromatography allows the detection and quantification of thousands of metabolites.An alternative method to quantify metabolites is the high-throughput serum nuclear magnetic resonance platform, but the number of metabolites identified using this method is substantially lower compared with mass spectrometry [22].By using high throughput technologies, metabolomics allows the identification and measurement of metabolites recognizable in a given biological sample.Identification of small biomolecules (metabolites) makes it possible to find early biomarkers for a disease of interest, including T2D and its comorbidities.A recent systematic review and meta-analysis covering the years from 2008 to 2017 included 14 studies and 4,592 individuals with T2D and 11,492 without T2D [23].Their report noted a 1.89-, 1.63-, and 1.87-fold higher risk of T2D associated for leucine, alanine, and oleic acid, respectively, whereas lysophosphatidylcholine C18:0 and creatinine were associated with 20% and 37% decreased risk of T2D, respectively.Our 4.6-year follow-up study of the METSIM cohort included 5,181 participants having metabolomics data available for twenty amino acids at baseline.Five amino acids (tyrosine, alanine, isoleucine, aspartate and glutamate) were significantly associated with a decrease in insulin secretion and an increased risk of incident T2D after adjustment for confounding factors [24].All essential amino acids, and especially branch-chain amino acids, stimulate insulin secretion and GLP-1 release [25].The mechanisms of reduced insulin secretion of five amino acids in our study remains to be determined but could be explained, at least in part, by glucagon regulation [26,27].Interestingly, a recent study demonstrated a causal relationship between the gut microbiome, short-chain fatty acids and metabolic diseases.The host-genetic-driven increase in gut production of the fecal short-chain fatty acid butyrate was significantly associated with improved insulin response after an OGTT, and another short-chain fatty propionate, was causally related to an increased risk of T2D in the MR.These data provide evidence of a causal effect of the gut microbiome on metabolic traits [28].The metabolomics approach has limitations in the identification of metabolites for the risk of T2D.There is no consensus on how to standardize metabolomics results, making it difficult to compare the findings across different studies.Additionally, protocols and statistical approaches may differ, and instrumentation can yield varied sets of detectable metabolites [29].Despite these potential limitations, studies applying metabolomics have the potential to identify a unique set of metabolites predictive of T2D.",
+      "\tRecent advances in mass spectrometry have expanded the scope and reliability\nof proteomics and metabolomics measurements. These tools are now capable of identifying thousands of factors driving diverse\nmolecular pathways, their mechanisms, and\nconsequent phenotypes and thus substantially contribute toward the understanding of\ncomplex systems. RATIONALE: Genome-wide association stud-\n\nies (GWAS) have revealed many causal loci\nassociated with specific phenotypes, yet the\nidentification of such genetic variants has\nbeen generally insufficient to elucidate the\nmolecular mechanisms linking these genetic\nvariants with specific phenotypes. A multitude\nof control mechanisms differentially affect\nthe cellular concentrations of different classes of biomolecules.",
+      "\tConclusion\n\nOur study represents the first multi-platform approach to the metabolome-wide analyses of diabetes in a general population.The identification of biomarkers allowing prediction of disease progression and its complications from such studies would be certainly beneficial.However, for the caveats discussed above, we feel that this study should be considered as a pilot for future work.One major finding of our work is the identification of a series of known, and also some novel, deregulated metabolites that associate with diabetes under sub-clinical conditions in the general population.These metabolites have been discovered by integrative metabolomics applying different platforms including nuclear magnetic resonance (NMR) and mass spectrometry (MS).Out of the multitude of metabolites measured, a holistic view of differences reflecting global variations in pathophysiology emerges from our study.The coverage of the metabolome's diversity allows the detection of systemic metabolic imbalances, thereby providing a disease-specific picture of human physiology (Figure 3).A pronounced increase in the sample size in future studies will likely allow for further detection of other metabolites of unrecognized associations with diabetic pathways.Finally, our study shows how functional metabolomics can contribute to obtaining a more sophisticated classification of the disease as well as rational optimization of diagnostic and treatment options, as recently suggested by Bain et al. [4].\t\n\nThe principal concept of metabolomics being able to find some metabolites differing in a control and a type 2 diabetic group is established.It is not our goal here to show this once again.The questions we ask are rather ''How well are different approaches suited to attain this goal? ''and ''What are optimal settings under which such studies can be successful? ''.Others have already investigated these questions before [16,17,18].However, we believe that this topic is much too complex than to be answered fully in a single study.For instance, the work described in the recent paper in this journal by Lanza et al. [19] covers only a small patient group of 7 cases and 7 controls.Our study, in contrast is based on 40 cases and 60 controls from an epidemiological cohort.Work reviewed recently by Madsen et al. [20] overlaps to some extent with our study, but none of them address aspects related to sub-clinical signals in a general population.Our focus is on participants from epidemiological studies rather than on patients under clinical conditions.Herein, we identify a series of differentially ''expressed'' metabolites that associate with diabetes under sub-clinical conditions in the general population.This question has not been addressed to this extent by any published paper.In particular, we see our work as a pilot that bears the potential of being scaled up to much larger sample sizes, since population studies such as KORA eventually provide access to much larger sample sizes, taken under rigorous standardized blood sample collection conditions in dedicated study centers (e.g.overnight fasting, standard protocol for serum and plasma preparation, storage in liquid nitrogen until measurement).These kinds of samples generally have not been available from clinical studies until recently.It is in this light that we provide here a proof of concept that metabolomics can uncover key metabolites differing in a control and a type 2 diabetic group.",
+      "\t\n\nCurrent technologies, such as metabolomics, proteomics, and genomics contribute to the development of a plethora of new biomarkers.In the case of DM, biomarkers may reflect the presence and severity of hyperglycemia or presence and severity of the related complications in diabetes [23].",
+      "\t\n\nMetabolomics studies allow metabolites involved in disease mechanisms to be discovered by monitoring metabolite level changes in predisposed individuals compared with healthy ones (Shaham et al, 2008;Newgard et al, 2009;Zhao et al, 2010;Pietilainen et al, 2011;Rhee et al, 2011;Wang et al, 2011;Cheng et al, 2012;Goek et al, 2012).Altered metabolite levels may serve as diagnostic biomarkers and enable preventive action.Previous cross-sectional metabolomics studies of T2D were either based on small sample sizes (Shaham et al, 2008;Wopereis et al, 2009;Zhao et al, 2010;Pietilainen et al, 2011) or did not consider the influence of common risk factors of T2D (Newgard et al, 2009).Recently, based on prospective nested case-control studies with relative large samples (Rhee et al, 2011;Wang et al, 2011), five branched-chain and aromatic amino acids were identified as predictors of T2D (Wang et al, 2011).Here, using various comprehensive largescale approaches, we measured metabolite concentration profiles (Yu et al, 2012) in the population-based (Holle et al, 2005;Wichmann et al, 2005) Cooperative Health Research in the Region of Augsburg (KORA) baseline (survey 4 (S4)) and follow-up (F4) studies (Rathmann et al, 2009;Meisinger et al, 2010;Jourdan et al, 2012).The results of these crosssectional and prospective studies allowed us to (i) reliably identify candidate biomarkers of pre-diabetes and (ii) build metabolite-protein networks to understand diabetes-related metabolic pathways."
+    ],
+    [
+      "\t\nAims/hypothesis Genome-wide association studies (GWAS) for type 2 diabetes have uncovered >400 risk loci, primarily in populations of European and Asian ancestry.Here, we aimed to discover additional type 2 diabetes risk loci (including Africanspecific variants) and fine-map association signals by performing genetic analysis in African populations.Methods We conducted two type 2 diabetes genome-wide association studies in 4347 Africans from South Africa, Nigeria, Ghana and Kenya and meta-analysed both studies together.Likely causal variants were identified using fine-mapping approaches.Results The most significantly associated variants mapped to the widely replicated type 2 diabetes risk locus near TCF7L2 (p = 5.3  10 13 ).Fine-mapping of the TCF7L2 locus suggested one type 2 diabetes association signal shared between Europeans and Africans (indexed by rs7903146) and a distinct African-specific signal (indexed by rs17746147).We also detected one novel signal, rs73284431, near AGMO (p = 5.2  10 9 , minor allele frequency [MAF] = 0.095; monomorphic in most non-African populations), distinct from previously reported signals in the region.In analyses focused on 100 published type 2 diabetes risk loci, we identified 21 with shared causal variants in African and non-African populations.Conclusions/interpretation These results demonstrate the value of performing GWAS in Africans, provide a resource to larger consortia for further discovery and fine-mapping and indicate that additional large-scale efforts in Africa are warranted to gain further insight in to the genetic architecture of type 2 diabetes.",
+      "\t\n\nIn 2008, to increase the power of identifying variants with modest effects, a meta-analysis of three GWAS, including Diabetes Genetics Initiative (DGI), Finland-United States Investigation of NIDDM Genetics (FUSION), and Wellcome Trust Case Control Consortium (WTCCC), were conducted.This study detected at least six previously unknown loci that reached genome-wide significance for association with T2D ( < 5  10 8 ), with the loci being JAZF1, CDC123-CAMK1D, TSPAN8-LGR5, THADA, ADAMTS9, and NOTCH2 [19].Genetic variants in JAZF1, CDC123-CAMK1D, TSPAN8-LGR5, and THADA have been reported to affect pancreatic -cell functions [59,60].",
+      "\t, for the Diabetes Genetics Replication And Meta-analysis (DIAGRAM) Consortium 9\n\nGenome-wide association (GWA) studies have identified multiple loci at which common variants modestly but reproducibly influence risk of type 2 diabetes (T2D) [1][2][3][4][5][6][7][8][9][10][11] .Established associations to common and rare variants explain only a small proportion of the heritability of T2D.As previously published analyses had limited power to identify variants with modest effects, we carried out meta-analysis of three T2D GWA scans comprising 10,128 individuals of European descent and B2.2 million SNPs (directly genotyped and imputed), followed by replication testing in an independent sample with an effective sample size of up to 53,975.We detected at least six previously unknown loci with robust evidence for association, including the JAZF1 (P  5.0  10 -14 ), CDC123-CAMK1D (P  1.2  10 -10 ), TSPAN8-LGR5 (P  1.1  10 -9 ), THADA (P  1.1  10 -9 ), ADAMTS9 (P  1.2  10 -8 ) and NOTCH2 (P  4.1  10 -8 ) gene regions.Our results illustrate the value of large discovery and follow-up samples for gaining further insights into the inherited basis of T2D.\t\n\nBy combining three GWA scans involving 10,128 samples (enhanced through imputation approaches) and undertaking largescale replication in up to 79,792 additional samples, we identified six additional loci that apparently harbor common genetic variants influencing susceptibility to T2D.These findings are consistent with a model in which the preponderance of loci detectable through the GWA approach (using current arrays and indirect LD mapping) have modest effects (ORs between 1.1 and 1.2).Given such a model, our study (in which we followed up only 69 signals out of over 2 million meta-analysed SNPs) would be expected to recover only a subset of the loci with similar characteristics (that is, those that managed to reach our stage 1 selection criteria).Further efforts to expand GWA metaanalyses and to extend the number of SNPs taken forward to largescale replication should confirm additional genomic loci, as should targeted analysis of copy number variation.However, the present data provide only crude estimates of the overall effect on susceptibility attributable to variants at these loci.The effect of the actual common causal variant responsible for the index association (once identified) will typically be larger, and many of these loci are likely to carry additional causal variants, including, on occasion, low-frequency variants of larger effect: three genes with common variants that influence risk of T2D were first identified on the basis of rare mendelian mutations (in KCNJ11, WFS1 and HNF1B).Regardless of effect size, these loci provide important clues to the processes involved in the maintenance of normal glucose homeostasis and in the pathogenesis of T2D.\t\n [3][4][5]7,10 , for the Diabetes Genetics Replication And Meta-analysis (DIAGRAM) Consortium 9Genome-wide association (GWA) studies have identified multiple loci at which common variants modestly but reproducibly influence risk of type 2 diabetes (T2D) [1][2][3][4][5][6][7][8][9][10][11] .Established associations to common and rare variants explain only a small proportion of the heritability of T2D.As previously published analyses had limited power to identify variants with modest effects, we carried out meta-analysis of three T2D GWA scans comprising 10,128 individuals of European descent and B2.2 million SNPs (directly genotyped and imputed), followed by replication testing in an independent sample with an effective sample size of up to 53,975.We detected at least six previously unknown loci with robust evidence for association, including the JAZF1 (P  5.0  10 -14 ), CDC123-CAMK1D (P  1.2  10 -10 ), TSPAN8-LGR5 (P  1.1  10 -9 ), THADA (P  1.1  10 -9 ), ADAMTS9 (P  1.2  10 -8 ) and NOTCH2 (P  4.1  10 -8 ) gene regions.Our results illustrate the value of large discovery and follow-up samples for gaining further insights into the inherited basis of T2D.",
+      "\t\nDiabetes impacts approximately 200 million people worldwide, of whom approximately 10% are affected by type 1 diabetes (T1D).The application of genome-wide association studies (GWAS) has robustly revealed dozens of genetic contributors to the pathogenesis of T1D, with the most recent meta-analysis identifying in excess of 40 loci.To identify additional genetic loci for T1D susceptibility, we examined associations in the largest meta-analysis to date between the disease and ,2.54 million SNPs in a combined cohort of 9,934 cases and 16,956 controls.Targeted follow-up of 53 SNPs in 1,120 affected trios uncovered three new loci associated with T1D that reached genome-wide significance.The most significantly associated SNP (rs539514, P = 5.66610 211 ) resides in an intronic region of the LMO7 (LIM domain only 7) gene on 13q22.The second most significantly associated SNP (rs478222, P = 3.50610 29 ) resides in an intronic region of the EFR3B (protein EFR3 homolog B) gene on 2p23; however, the region of linkage disequilibrium is approximately 800 kb and harbors additional multiple genes, including NCOA1, C2orf79, CENPO, ADCY3, DNAJC27, POMC, and DNMT3A.The third most significantly associated SNP (rs924043, P = 8.06610 29 ) lies in an intergenic region on 6q27, where the region of association is approximately 900 kb and harbors multiple genes including WDR27, C6orf120, PHF10, TCTE3, C6orf208, LOC154449, DLL1, FAM120B, PSMB1, TBP, and PCD2.These latest associated regions add to the growing repertoire of gene networks predisposing to T1D.",
+      "\t\nOBJECTIVE-Two recent genome-wide association (GWA) studies have revealed novel loci for type 1 diabetes, a common multifactorial disease with a strong genetic component.To fully utilize the GWA data that we had obtained by genotyping 563 type 1 diabetes probands and 1,146 control subjects, as well as 483 case subject-parent trios, using the Illumina HumanHap550 BeadChip, we designed a full stage 2 study to capture other possible association signals.RESEARCH DESIGN AND METHODS-From our existing datasets, we selected 982 markers with P  0.05 in both GWA cohorts.Genotyping these in an independent set of 636 nuclear families with 974 affected offspring revealed 75 markers that also had P  0.05 in this third cohort.Among these, six single nucleotide polymorphisms in five novel loci also had P  0.05 in the Wellcome Trust Case-Control Consortium dataset and were further tested in 1,303 type 1 diabetes probands from the Diabetes Control and Complications Trial/Epidemiology of Dia-betes Interventions and Complications (DCCT/EDIC) plus 1,673 control subjects.RESULTS-Two markers (rs9976767 and rs3757247) remained significant after adjusting for the number of tests in this last cohort; they reside in UBASH3A (OR 1.16; combined P  2.33  10 8 ) and BACH2 (1.13; combined P  1.25  10 6 ).CONCLUSIONS-Evaluation of a large number of statistical GWA candidates in several independent cohorts has revealed additional loci that are associated with type 1 diabetes.The two genes at these respective loci, UBASH3A and BACH2, are both biologically relevant to autoimmunity.",
+      "\t\n\nGenome-wide association studies (GWAS) have recently revealed many novel SNPs associated with type 2 diabetes.These include SNPs located in the regions near TCF7L2, HHEX-IDE, EXT2, FTO, SLC30A8, IGF2BP2, CDKAL1, and CDKN2A-CDKN2B [8][9][10][11][12][13].A second phase of studies identified many additional variants, including those near JAZF1, TSPAN8-LGR5, THADA, ADAMTS9, NOTCH2-ADAM30, CDC123-CAMK1D, and KCNQ1 [14,15].The two genes in which common variants were previously convincingly associated with type 2 diabetes, PPARG and KCNJ11, were also identified in these GWAS [12,16,17].More recently, numerous other SNPs have been identified in additional GWAS and meta-analyses [18].",
+      "\t\n\n. A genome-wide association study identifies novel risk Loci for Type 2 diabetes.Nature 445(7130), 881-885 (2007).31 The Wellcome Trust Case Control Consortium.Genome-wide association study of 14,000 cases of seven common diseases and 3,000 shared controls.Nature 447, 661-678 (2007).Twelve Type 2 diabetes susceptibility loci identified through large-scale association analysis.Nat.Genet.42(7), 579-589 (2010).33 SIGMA Type 2 Diabetes Consortium, Williams AL, Jacobs SB, Moreno-Macas H, Huerta-Chagoya A et al.Sequence variants in SLC16A11 are a common risk factor for Type 2 diabetes in Mexico.Nature 506(7486), 97-101 (2014).34 Ma RC, Hu C, Tam CH et al.Genome-wide association study in a Chinese population identifies a susceptibility locus for Type 2 diabetes at 7q32 near PAX4.Diabetologia 56(6), 1291-1305 (2013).35 Hara K, Fujita H, Johnson TA et al.Genome-wide association study identifies three novel loci for Type 2 diabetes.Hum.Mol.Genet.23(1), 239-46 (2014).36 Palmer ND, McDonough CW, Hicks PJ et al.A genomewide association search for Type 2 diabetes genes in African Americans.PLoS ONE 7(1), e29202 (2012).37 Hanson RL, Muller YL, Kobes S et al.A genome-wide association study in American Indians implicates DNER as a susceptibility locus for Type 2 diabetes.Diabetes 63(1), 369-376 (2014).",
+      "\t\n\nFigure 1 illustrates the metaanalysis of risk estimates for six of the loci (CDKAL1, CDKN2A/B, HHEX, IGF2BP2, SLC30A8, and KCNQ1), using data from published studies in East Asia, including Chinese populations from China (9, 20 -23) and Hong Kong (10) as well as Korean (7,10,24) and Japanese (6,7,25,26) populations.In essence, the metaanalysis showed that these six diabetes susceptibility loci identified through GWAS are associated with T2DM in populations across Asia.",
+      "\t\n\nNovel T2D-associated loci driven by common variants.Beyond the detailed characterization of the known T2D-associated regions, we also identified seven novel loci, among which, five were driven by common variants with modest effect sizes (1.06 < OR < 1.12; Table 1, Fig. 2, Supplementary Fig. 6 and 7).",
+      "\t\n\nA meta -analysis of three GWA scans followed by a large -scale replication (Diagram consortium including more than 50 000 individuals in total) has identifi ed additional susceptibility loci for T2DM, with OR ranging from 1.09 to 1.15, near six genes: JAZF1 , CDC123 -CAMK1D , TSPAN8 -LGR5 , THADA , ADAMTS9 and NOTCH2 [174] .Variants at JAZF1 , CDC123 -CAMK1D and TSPAN8 -LGR5 are associated with small alterations in insulin secretion, whereas the mechanisms linking the other loci to T2DM remain to be clarifi ed [175] .In each GWA scan, other loci showed signifi cant associations with T2DM, but were not fol-with Mendelian forms of diabetes, such as MODY, which are caused by rare mutations in the coding sequence resulting in signifi cant amino acid substitutions or truncated proteins, leading to hyperglycemia even in the absence of other diabetogenic exposures.",
+      "\tZeggini, E., Scott, L.J. , Saxena, R., Voight, B.F., Marchini, J.L. , Hu, T., de\nBakker, P.I. , Abecasis, G.R. , Almgren, P., Andersen, G., et al. 2008. Metaanalysis of genome-wide association data and large-scale replication\nidentifies additional susceptibility loci for type 2 diabetes. Nat. Genet. 40: 638645. Zielenski, J., Corey, M., Rozmahel, R., Markiewicz, D., Aznarez, I., Casals, T.,\nLarriba, S., Mercier, B., Cutting, G.R. , Krebsova, A., et al. 1999. Detection\nof a cystic fibrosis modifier locus for meconium ileus on human\nchromosome 19q13. Nat. Genet. 22: 128129.",
+      "\t\n\nGenetic studies performed since 2012 have identified many additional T2D loci based on risk alleles common in one population but less common in others.Studies in African Americans identified RND3-RBM43 (28), HLA-B and INS-IGF2 (29).Studies in South Asians identified TMEM163 (30) and SGCG (31).One locus, SLC16A11-SLC16A13, was simultaneously identified in Japanese and Mexican Americans (32,33), and studies in East Asians identified ANK1 (34), GRK5 and RASGRP1 (35), LEP and GPSM1 (32), and CCDC63 and C12orf51 (36).A study of individuals from Greenland identified TBC1D4 (37), and a sequencing-based study of Danes with follow-up in other Europeans identified MACF1 (38).Finally, the largest GWAS to date in American Indians identified DNER at near genome-wide significance (P = 6.6  10 8 ) (39).Three of these studies imputed GWAS data using the 1000 Genomes Project sequence-based reference panels, providing better genome coverage (29,32,33,40).Taken together, these studies highlight the value of diverse populations, including founder and historically isolated populations, to detect risk loci.\t\n\nMeta-analyses across populations provide further opportunities to detect loci with shared risk alleles.Meta-analysis of 17 418 T2D cases and 70 298 controls from European, African-American, Hispanic-Latino, and Asian studies using a gene-based CardioChip array was first to identify the BCL2 locus for T2D (26).A recent genome-wide trans-ancestry meta-analysis of 26 488 T2D cases and 83 964 controls from European, East Asian, South Asian and Mexican ancestry, with follow-up in an additional 21 491 T2D cases and 55 647 controls of European ancestry, identified seven new T2D loci (48).The trans-ancestry part of this latter study was performed using variants imputed based on genotype data from the International HapMap Project (49), and follow-up was limited to variants available in Metabochip-typed datasets, suggesting that future trans-ancestry meta-analyses incorporating data imputed to denser reference panels will identify additional loci.",
+      "\t\n\nFinally, a recent study identified additional susceptibility loci for type 2 diabetes by performing a meta-analysis of three published GWAs. 21As acknowledged by the authors, GWAs are limited by the modest effect sizes of individual common variants and the need for stringent statistical thresholds.Thus, by combining data involving 10,128 samples, the authors found in the initial stages of the analysis highly associated variants (they followed only 69 signals out of over 2 million metaanalyzed SNPs) with P values 10 4 in unknown loci, and 11 of these type 2 diabetes' associated SNPs were taken forward to further stages of analysis.Large stage replication testing allowed the detection of at least six previously unknown loci with robust evidence for association with type 2 diabetes.",
+      "\t\n\nTo identify common type 2 diabetes susceptibility variants, large-scale genome-wide association studies (GWAS) have been conducted in white individuals, yielding more than 60 genetic loci to date [5,6].Although many of these regions have been successfully replicated in Asian populations [7][8][9][10][11], discrepancies in allelic frequencies and effect sizes have demonstrated that interethnic differences exist.GWAS conducted in Japanese individuals [12,13], as well as meta-analyses of GWAS in South Asian [14] and East Asian [15] groups, have revealed additional variants not detected in GWAS with white individuals, with several signals, including KCNQ1, later replicated in many populations [12,13].Previous GWAS in Chinese suggested several loci but lacked large-scale replication [16][17][18].\tDiscussion\n\nThis study reports a meta-analysis of GWAS for type 2 diabetes in a Chinese population, and has identified a novel diabetes-associated locus.Furthermore, we replicated the association in additional East Asian samples, and found an association in samples of European descent.In addition to the multiethnic samples used in our study, our study also benefits from a detailed phenotyping of the Chinese samples, which allowed additional analyses of the effect of the risk variant on clinical traits and the course of disease to be carried out.",
+      "\tIdentification of type 2 diabetes loci in 433,540 East Asian individuals\n\nMeta-analyses of genome-wide association studies (GWAS) have identified more than 240 loci that are associated with type 2 diabetes (T2D) 1,2 ; however, most of these loci have been identified in analyses of individuals with European ancestry.Here, to examine T2D risk in East Asian individuals, we carried out a meta-analysis of GWAS data from 77,418 individuals with T2D and 356,122 healthy control individuals.In the main analysis, we identified 301 distinct association signals at 183 loci, and across T2D association models with and without consideration of body mass index and sex, we identified 61 loci that are newly implicated in predisposition to T2D.Common variants associated with T2D in both East Asian and European populations exhibited strongly correlated effect sizes.Previously undescribed associations include signals in or near GDAP1, PTF1A, SIX3, ALDH2, a microRNA cluster, and genes that affect the differentiation of muscle and adipose cells 3 .At another locus, expression quantitative trait loci at two overlapping T2D signals affect two genes-NKX6-3 and ANK1-in different tissues [4][5][6] .Association studies in diverse populations identify additional loci and elucidate disease-associated genes, biology, and pathways.",
+      "\t\n\nTo contend with the stringent significance thresholds that account for the number of independent tests performed across the genome, identification of additional T2D susceptibility loci required larger population samples, which was achieved by combining existing GWA studies in meta-analyses.The Diabetes Genetics Replication And Meta-analysis (DIAGRAM, http://www.diagram-consortium.org/) consortium carried out the first meta-analysis for T2D (Zeggini et al. 2008) of three GWA studies of European-descent individuals, including ~4500 cases and 5500 controls.Differences in the genotyping platforms used for individual GWA studies were overcome by imputation using a common variant set based on haplotype structure of densely characterized reference samples in HapMap (Consortium IH 2005) and extended the analysis to ~2.2 million SNPs across the genome  2.1) for each locus listed on the y-axis.Loci are sorted by descending order of per-allele effect size within each year.Colors highlight the discovery study approach: red, candidate gene; yellow, large-scale association; blue, genome-wide association; dark blue, genome-wide association meta-analysis; sky blue, genome-wide meta-analysis with Metabochip follow-up; green, genome-wide meta-analysis of glycemic traits; pink, genome-wide sex-differentiated meta-analysis with larger effects in women; brown, genome-wide sex-differentiated meta-analysis with larger effects in men; hacky, genome-wide meta-analysis in lean/ obese; gray, whole-exome sequencing.For loci with sex differentiation, the effect size for the sex with larger effect is presented.X-axis lists loci names, labeled by the gene names within region.Yaxis shows odds ratio for T2D observed at a given locus.Loci are split by the year of discovery and are ordered from top to bottom by the decreasing OR on T2D risk within each year.Shadow is used for loci from studies with discovery including non-European individuals The DIAGRAM consortium published two further meta-analyses, each based on increasingly larger case-control samples from European populations.The first combined discovery data from 21 GWA studies in up to 8130 individuals with T2D and 38,987 controls all imputed to a HapMap 2 reference panel, followed by large-scale replication in 34,412 cases and 59,925 controls where 13 (11 novel) out of 23 autosomal signals were confirmed (Tables 2.1 and 2.2) (Voight et al. 2010).This meta-analysis was the first to examine T2D associations on chromosome X (taking X-inactivation into account) and identified an association at DUSP9 with a large effect on T2D risk (OR  1.27, Table 2.2; Fig. 2.1) (Voight et al. 2010).The second meta-analysis, in addition to dramatically increasing the sample size (34,840 cases and 114,981 controls), implemented a novel cost-effective strategy for large-scale replication based on the CardioMetabochip (Metabochip), an Illumina iSelect genotyping array.Metabochip, which was designed through collaboration between six GWA consortia studying metabolic and atherosclerotic/ cardiovascular diseases and traits (Voight et al. 2012), permitted follow-up of ~66,000 putative signals for cardiometabolic phenotypes (~5000 of which were selected for T2D) (Morris et al. 2012).The Metabochip array also contained approximately 120,000 SNP probes to fine map 257 established loci in an attempt to identify causal T2D susceptibility variants.The DIAGRAM meta-analysis with Metabochip follow-up established T2D associations at 10 loci (Tables 2.1 and 2.2), including two at CCND2 and GIPR with larger effects on T2D risk in males and females, respectively (Morris et al. 2012).Among previously established T2D loci, sex differentiation in effect size has been shown for KCNQ1, DGKB, and BCL11A (larger effects in males) and GRB14 (larger effects in females)."
+    ],
+    [
+      "\t\n\nThe identification of affected methylation sites is important because it provides evidence that a particular gene is susceptible to being modified by exposure to maternal diabetes.The direction of change is also important because it suggests that the expression and therefore the function of this gene is likely being modified in an inverse manner if the methylation change occurs in promoters or enhancers; however, the epigenome can also be influenced by other factors (such as microRNA and histone modifications), and as such, the direction of DNA methylation change observed in the overlapping genes in our stud may not be as important relative to the fact that the epigenome of a particular gene is susceptible to being altered.",
+      "\t\n\nIn addition to changes following exposure to intra-uterine hyperglycaemia, epigenetic changes have also been noted in other experimental settings of hyperglycaemia.For example, increased DNA methylation has been described for the promoter region of the peroxisome proliferator-activated receptor-g (PPARg) coactivator-1a gene (PPARGC1A) in diabetic islets (Ling et al., 2008).Similar hypermethylation in the promoter region of the PPARGC1A gene has been noted in the skeletal muscle from diabetic patients, and correlated with mitochondrial content (Barr es et al., 2009).Epigenetic changes have also been suggested to be responsible for the \"legacy effect\" of reduced risk of vascular complications after a period of sustained tight glucose control, or \"metabolic memory\" of transient hyperglycaemia and increased risk of diabetic vascular injury (Pirola et al., 2010).Histone methylation variations have been noted in monocytes cultured in high glucose, as well as blood monocytes of diabetic patients (Miao et al., 2007).In a series of landmark experiments, it was shown that endothelial cells exposed to short-term hyperglycaemia had persistently increased expression of the NF-kB active subunit p65, and was associated with increased promoter H3K4me1 and occupancy by the histone monomethyltransferase SET7/9.In addition, transient hyperglycaemia was also associated with sustained reduction of H3K9 methylation on the NF-kB p65 promoter, as well as recruitment of lysine-specific demethylase (LSD1) (El-Osta et al., 2008;Brasacchio et al., 2009).LSD1 has also been found to regulate H3K4 methylation in vascular smooth muscle cells in hyperglycaemic conditions, and may mediate the vascular inflammation (Reddy et al., 2008).Other epigenetic mechanisms including microRNAs and long noncoding RNAs have also been implicated in the pathogenesis of diabetic complications (Kato et al., 2014).",
+      "\tEpigenetic histone modifications and diabetic complications\n\nExciting recent research has demonstrated a role for epigenetic histone modifications in diabetes and its complications.HATs and HDACs have been found to play important roles in the regulation of several key genes linked to diabetes as reviewed by Gray and De Meyts (46).\t\n\nFigure 3: Scheme for the role of epigenetic mechanisms downstream of hyperglycemia in leading to diabetic complications.Diabetic conditions or hyperglycemia can activate several signal transduction pathways and transcription factors that can lead to sustained expression of pathological genes in the nucleus by co-operating with epigenetic factors.This can occur via a loss of repression and a corresponding gain in activation pathways leading to long-lasting epigenetic changes through gene promoter histone lysine modifications near key transcription factor binding sites or other important chromatin regions.Depending on the specific lysineresidue that is methylated, histone lysine methylation is associated with either gene activation (H3K4me) or repression (H3K9me).Modifications at other lysine residues may also be involved.These associations are further complicated by the gene location modified, either promoter or coding region, and the degree of methylation, all of which can affect accessibility of chromatin and transcriptional outcomes.These epigenetic modifications can be maintained through cell division via mechanisms that are not yet clearly understood but may include DNA methylation as well as transmission of histone lysine methylation marks.The persistence of these epigenetic changes might explain the metabolic memory phenomenon responsible for the continued development of diabetic complication even after glucose control has been achieved.\t\n\nFigure 2: Model for epigenetic regulation of pathological gene expression in diabetes via changes in chromatin histone modifications.Post translational modifications on the Nterminal histone tails in chromatin play essential roles in gene regulation and are regulated by various chromatin modifiers.Histone lysine methyltransferases (HMTs) and lysine demethylases (KDMs) regulate histone lysine methylation (Kme), while histone acetyltransferases (HATs) and histone deacetylases (HDACs) control histone acetylation (Ac).In the proposed model shown, various chromatin modifiers maintain sufficient levels of repressive histone marks to maintain strict control of pathologic gene expression under normal conditions;these would include methylation of H3K9 and demethylation of H3K4 in addition to deacetylation by HDACs.However, under diabetic conditions, including hyperglycemia, the\t\n\nHowever, much less is known about DNA methylation in diabetes.A recent report has shown that the insulin promoter DNA was methylated in mouse embryonic stem cells and only becomes demethylated as the cells differentiate into insulin expressing cells, and both the human and mouse insulin promoters were specifically demethylated in pancreatic beta cells suggesting epigenetic regulation of insulin expression (81).In the agouti mouse, DNA methylation and expression of the agouti gene can affect the tendency to develop obesity and diabetes (103).\t\n\nmodifications have also been found to play an important role in altering gene expression patterns associated with various diseases(91).Clinical as well as experimental studies with animal and cells models have clearly demonstrated the deleterious effects of hyperglycemia and the importance of maintaining good glucose control to prevent the onset or severity of diabetic complications.In addition, evidence shows that hyperglycemia can induce epigenetic changes to the chromatin structure via activation of various factors and signaling pathways.This has implicated specific key HMTs and KDMs related to active and repressed chromatin states and has demonstated epigenetic regulation of key inflammatory genes in vascular cells.It is highly likely that other HMTs and KDMs, DNA methylation and related chromatin factors are also involved in epigenetic changes induced by elevated glucose in multiple target organs and cells Epigenetic Mechanisms in Diabetic Complications 25 and contribute to metabolic memory of several debilitating diabetic complications (Figure3).However, diabetes is much more complicated than a simple state of hyperglycemia.It is associated with several risk factors and, in particular T2D involves insulin resistance, obesity, dyslipidemia, environmental factors, nutrition, lifestyles and genetics, in addition to hyperglycemia.Each of these risk factors could in itself induce epigenetic changes to the chromatin structure ultimately altering gene expression patterns in conjunction with elevated glucose in various target tissues including kidney, heart, liver, retina, nervous system, muscle, blood vessels and blood cells.Alarming estimates indicate that the rates of diabetes, metabolic syndrome and associated complications are rapidly increasing and therefore additional strategies to curb these trends are needed.With respect to diabetic nephropathy, it is imperative to conduct further exploration into the epigenetic causes and related treatment options, given the widespread prevalence, and the rapid transition to ESRD despite the available therapies.Such information can complement the currently available and new genetic and molecular data to begin the development of personalized medicine for diabetic nephropathy(136) and other complications.Well defined cell and animal models with and without treatments with standard diabetes drugs, antioxidants and related interventions will further our understanding of diabetic complications and metabolic memory and how they might be prevented.Epigenetic drugs such as inhibitors of DNA methylation, HATs and HDACs, and some histone demethylases are already being evaluated for cancer and other diseases(2,129,131).Currently available drugs for diabetic complications(18) could be tested for their potential ability to alter epigenetic marks.In recent years, there has been significant progress in the fields of epigenetics and epigenomics mainly due to increased understanding of basic molecular mechanisms and Epigenetic Mechanisms in Diabetic Complications 26 remarkable advances in powerful genome-wide technologies, instrumentation and bioinformatics software.Thus massive parallel next generation sequencing and ChIP-sequencing have been used to simultaneously map several histone marks and DNA methylation in human adult and stem cells and have demonstrated associations with distinct cell and development states and gene",
+      "\tHISTONE PTMS AND DIABETES\n\nHistone PTMs regulate chromatin structure and gene expression by recruiting chromatin remodeling proteins, transcription co-activators, and co-repressors. 26Emerging evidence shows the involvement of key histone PTMs in the regulation of genes associated with the pathogenesis of diabetes.Regulation of insulin gene expression as well as its secretion from islets in response to changing glucose levels is a key process in glucose homeostasis, one that is dysregulated in diabetes.Studies show that the islet-specific TF Pdx-1 can modulate this process of insulin regulation through epigenetic mechanisms. 59In response to increased glucose conditions, Pdx1 recruits co-activator HATs p300 and CBP and a HMT SET7/9 (SET7), which increases activation marks H3/H4Kac and H3K4me2, respectively, at the insulin promoter to promote open chromatin formation accessible to transcription machinery and enhance insulin transcription. 59,60In contrast, under low glucose conditions, Pdx1 recruits corepressors HDAC1 and HDAC2, promoting chromatin compaction and inhibition of insulin expression. 59nterestingly, Pdx-1 also controls the islet-specific expression of SET7 by direct interaction with its promoter. 60Genome-wide mapping of HK4me1, H3K4me3, H3K79me2 in islets revealed several isletspecific promoters and enhancers.Furthermore, several regulatory elements located near diabetes-susceptible loci showed allele-specific differences in their activity. 61Another study also mapped open chromatin regions in islets and identified associations of allele-specific differences in enhancer activity with genetic variations near diabetes-susceptible loci, 62 further highlighting how genetic variations in noncoding regions might affect chromatin structure in diabetes.Histone PTMs along with DNAme also were found to play an important role in epigenetic regulation of Pdx1 and insulin expression in islets of diabetic offspring from intrauterine growth restriction rats, suggesting that histone PTMs can be affected by maternal malnutrition. 34dipogenesis plays an important role in the pathogenesis of metabolic abnormalities and is tightly controlled by the transcription factors CCAAT/ enhancer binding protein (C/EBP)  and peroxisome proliferator activated receptor (PPAR).Dynamic changes in histone PTMs and recruitment of the corresponding modifiers can regulate C/EBP and PPAR-induced gene expression involved in adipocyte differentiation. 63,64Interestingly, epigenetic inactivation of PPAR has been shown in adipocytes from T2D animals, 65 further supporting a role for epigenetic processes in adipocyte dysfunction and T2D.Another study reported increased predisposition to obesity and metabolic syndrome in mice deficient in Jhdm2a, a H3K9me2 demethylase, showing that deficiency in key histone-modifying enzymes might contribute to metabolic abnormalities. 66Overall, these studies highlight how alterations in chromatin structure can contribute to diabetes development.This is clearly a research area likely to show increased activity in the upcoming years.It is possible that epigenetic changes that contribute to the pathology of diabetes also directly or indirectly can affect target organs leading to complications.",
+      "\tDNA or Histone Modifications\n\nNew research investigations have addressed the link between epigenetic factors, type 2 DM and CVD.Hyperglycemia, for example, can induce epigenetic changes that lead to the overexpression of genes implicated in vascular inflammation.In particular, hyperglycemia has been shown to activate the NF-kB signaling pathway in cultured THP-1 monocytes, leading to the production of MCP-1 and other inflammatory factors, and to the expression of adhesion molecules in endothelial cells, providing a plausible molecular mechanism for endothelial dysfunction and atherosclerosis (107).On the other hand, clinical studies have demonstrated that early intensive control of glycemia in diabetic patients is crucial to prevent chronic micro-and macrovascular complications, reinforcing the notion that glycemia may have a longstanding influence on clinical outcomes, a phenomenon called \"metabolic memory\" (108).",
+      "\t1.5) DNA or Histone Modifications\n\nWe discovered a connection between an epigenetic factor of T2DM and CVD in new research investigations.For instance, hyperglycemia can cause epigenetic alterations that result in the enhanced expression of genes that contribute to vascular inflammation.In particular, it has been demonstrated that hyperglycemia activates the NF-kB signalling pathway in cultured THP-1 monocytes, producing MCP-1 and other inflammatory factors as well as causing endothelial cells to express adhesion molecules.This finding suggests a possible molecular mechanism for endothelial dysfunction and atherosclerosis. [24]On the other hand, clinical investigations have supported the idea that glycemia may have a longlasting impact on clinical outcomes, a condition known as \"metabolic memory,\" by demonstrating that early intensive control of glycemia in diabetes patients is critical to avoid chronic micro-and macrovascular challenges.In aortic endothelial cells, it has been proven that exposure to hyperglycemia corresponds with the opposite acetylation of the histone H3K9/K14 and altered pattern of addition of methyl group to DNA, assisting an epigenetic role for hyperglycemia.Following the temporarily elevation of levels of glucose, numerous histone lysine alterations have also been reported.They could be in charge of the RELA gene's ongoing transcriptional activation, which produces the p65 subunit of NF-kB, even when endothelial cells were later exposed to regular glucose concentrations.Overall, this action caused some target genes associated to endothelial dysfunction to become transcriptionally active, while as a result, other target genes become transcriptionally repressed.ICAM, HMOX1, MCP-1, SLC7A11, MMP10, and MMP1 genes' enhanced expression may also be caused by acetylation or hyperacetylation. [25]However, besides glucose toxicity, plenty of other physiological and pathological mechanisms that might have been involved in hyperglycemia and caused epigenetic modifications to have also been reported.These include ROS, PKC stimulation, and AGEs.Therefore, hyperglycemia is not the only factor that can cause epigenetic modifications.Notably, the CpG decreased intensity of methylation of the p66Shc inducer and a rise in H3 histone acetylation can both be considerably induced by ROS production.So, elevated concentrations of p66Shc, a mitochondrial adaptor that regulates a balance of redox in the cells, and meaningful activation of PKC are related to ROS-induced epigenetic alterations, sustaining endothelial dysfunction and vascular impacts.Additional research has examined the relationships between epigenetic changes and the risk of CVD for cardio-metabolic phenotypes like unusual weight gain, imbalance of lipids, impaired insulin sensitivity, inflammation, and high blood pressure.In a new analysis, histone deacetylases (HDACs) behavior and expression in connection to serum glucose, inflammation, and impaired insulin sesitivity in patients with type 2 DM were measured using peripheral blood mononuclear cells.HDAC3 activity and expression were induced by low-grade long-term inflammation and insulin resistance, and they correlated favourably with circulating levels of TNF-, IL-6, and other proinflammatory markers and adversely with Sirt1 expression. [26]Numerous studies have shown a connection between the addition of methyl group to DNA and the probability of cardiovascular disease.Elevated concentrations of methylation were seen in the predisposing haplotype rs8050136 of the FTO gene, a well-known gene linked to a greater risk of becoming obese and cardiovascular diseases; a similar technique has been proposed for the rs9939609 diversity.IGF2 methylation and changes to the lipid profile were linked in an additional candidate gene analysis of obese individuals.An epigenetic marker of metabolic risk, IGF2 higher intensity of methylation was specifically related to greater triglyceride/HDL cholesterol ratios.Some other investigations that merged genome-wide transcriptome and addition of methyl group to CpG profiling by array observed that insulin-resistant patients' adipose tissue had many more differentially methylated predicted sites than controls, including genes associated in signal transduction and the interaction with principal receptors to bind to the extracellular matrix.been discovered to be heavily and impartially related with impaired insulin sensitivity, were also found to have modified methylation.Furthermore, it has been demonstrated that the addition of methyl group of the PPAR promoter contributes to the division of the adipose tissue macrophages in obese mice from an anti-inflammatory (M2) to a proinflammatory (M1) phenotypic expression.Ultimately, there is scientific proof that modifications in the antenatal environment's impacts on epigenetic modifications may affect the risk of Myocardial infarction. [27]",
+      "\tSummary\n\nIncreasing evidence shows that, besides the well-described biochemical mechanisms, epigenetic mechanisms might also participate by fine-tuning gene expression to modulate the aetiology of diabetic complications.Persistence of epigenetic modifications triggered by diabetic stimuli could be one of the key mechanisms underlying metabolic memory.However, the involvement of many epigenetic factors and mechanisms involved in the regulation of the modifications by upstream signal transduction pathways remains unknown.However, this is a rapidly expanding and dynamic field and it is likely that other epigenetic factors related to diabetic complications will soon be uncovered.Epigenomics may also aid in determining the functional roles of complications-associated genetic variants.It would be worthwhile to assess whether lifestyle modifications such as exercise and healthy diets can reduce diabetic complications by altering epigenetic marks.A recent study showed the beneficial effects of exercise on epigenetic marks related to diabetes [106].Because epigenetic changes are potentially reversible in nature, combination therapies with epigenetic drugs (epidrugs) [38] and antagomirs (miRNA inhibitors) [8] could be considered to complement the current treatments for complications.However, there are also key challenges.Since epigenetic patterns are cell specific, data from heterogeneous tissue samples and biopsies could be difficult to interpret.Furthermore, apart from hyperglycaemia, other factors associated with diabetes, including insulin resistance, obesity, dyslipidaemia, environment, lifestyles and genetics, can work independently or co-operatively to also promote epigenetic changes in various affected target tissues.",
+      "\t\n\nEmerging evidence suggests an epigenomic link to T2D development.Reversible epigenetic changes such as histone modifications and DNA methylation may occur during intrauterine development and are believed to have long-term effects on offspring health and survival, including manifestation of disease phenotypes such as obesity or diabetes later in life [59,60].Environmental and nutritional stimuli influence future science group Genetics, genomics & personalized medicine in Type 2 diabetes: a perspective on the Arab region Review  [61].Epigenetic regulation of genes may be responsible for the observed difference in T2D risk and drug response between individuals [62,63].Epigenomics may not only shed light on the environmental (including diet and lifestyle) effect on T2D susceptibility in individuals but epigenetic markers may also help identify those at risk well before disease manifestation.Gene-expression analysis or transcriptomics is used for studying the expression profile of genes.A comparative analysis of expression states of genes between healthy and diseased cells can identify those implicated in disease pathology.The changes in expression of disease susceptibility genes can be monitored during different stages of a disease and help in disease prognosis.Similarly, a comparative expression profile for treated and untreated samples can help identify changes in gene-expression upon treatment with a particular drug.This makes geneexpression analysis an important tool for elucidating the role of genes in different biological states, for identifying potential targets for drug intervention and for biomarker selection to be used in disease diagnosis.In diabetes, gene-expression profiling has been used for establishing differential expression of inflammatory genes [64], for studying the effects of insulin treatment in skeletal muscle [65] and more recently for correlating insulin resistance and an altered lipid profile in peripheral blood [66].",
+      "\tDNA Methylation and Diabetic Kidney Disease\n\nEpigenetic imprinting is thought to be important for determining the predisposition for chronic and latent diseases, like DKD [5].We have previously shown that exposure of microvascular endothelial cells to hyperglycaemia is able to induce changes in DNA methylation on genome wide ChIP-Seq, Fig. 1 The histone code.The specific site, type, extent and diversity of post-translational modifications histone proteins leads to specific signalling effects, including the repression (red signal) or activation (green signal) of gene expression leading to changes in gene expression, including activation of pro-inflammatory pathways implicated in diabetic complications such as DKD [5, 12, 13].Studies in the zebrafish also demonstrate that hyperglycaemia-induced DNA methylation changes.Diabetes is also induces aberrant DNA methylation in the proximal tubules of the kidney, including key targets implicated in glucose metabolism and transport, leading to a resistance to the effects of pioglitazone [14].However, an elevated glucose level is not the only factor that leads to maladaptive epigenetic modifications in diabetes.DNA methylation can also be influenced by reactive oxygen species, both directly through oxidative modification DNA preventing methylation and indirectly through its effects on methylation writing/erasing enzymes [15].Many other factors including hypoxia, inflammation, cytokines and growth factors, drugs, nutrition and even physical activity can modify epigenetic profiles [16,17]; the sum of which and their interactions being the key determinant of the resulting phenotype.\tHistone Modifications and Diabetic Kidney Disease\n\nPost-translational modification of nucleosomal histones are among the best characterised of epigenetic modifications with respect to diabetes and are clearly implicated in the induction in the expression of genes implicated in DKD [8,24].For example, following exposure to glucose there is persistent transcriptional upregulation of expression of the proinflammatory mediator NF-B (p65; Rel (A)) in vitro and in vivo.This is specifically associated with monomethylation of H3K4 adjacent to the p65 proximal promoter, such that inhibition of Set7-dependent methylation at this site is able to prevent its induction without restoring euglycaemia [8,24].We have also recently reported the persistent induction of other pathogenic genes that may be mediated by H3K4m1 writing events, including the induction of IL-8 following exposure to transient hyperglycaemia [25].Exposure to hyperglycaemia also dynamically changes histone acetylation in cells exposed to hyperglycaemia [12, 13] and diabetic patients.More recently, genome-wide increases in monocyte H3 acetylation were associated with conventional treatment compared with intensive treatment group subjects of the Diabetes Control and Complications Trial (DCCT), indicating a possible mechanism of metabolic memory in humans [26].However, overall transcriptional activity is more likely to be dependent on the sum of multiple histone marks, and their interaction with other epigenetic modifications (e.g.DNA methylation) rather than any individual changes [27].For example, glomerulosclerosis in diabetic mice is associated with enrichment of H3 histones dimethylated at K4, acetylated at K9 and K27, and phosphorylated at S10.",
+      "\tEpigenetics, Micro RNAs (miRNAs) and Diet: Are They Involved in DM? Previous epigenetic studies have focused on the heritable alteration of DNA and proteins, linking the DNA and histones, which induces modifications in chromatin structure without changing the nucleotide sequence.Modulations in gene expression can be caused by epigenetic mechanisms such as DNA methylation, histone modifications, small and non-coding RNAs [139].Non-coding RNAs (ncRNAs) have been implicated in the epigenetic regulation of gene expression, and recent studies have shown that miRNAs can induce chromatin remodeling.miRNAs are single-stranded RNA molecules that range in size from 18 to 22 nucleotides.The mammalian genome encodes several hundred miRNAs that fine-tune gene expression through the modulation of target mRNAs [140].These findings suggest that DNA methylation, histone modification and miRNAs may function in concert to regulate gene expression [141].",
+      "\t\nThe global diabetes epidemic poses a major challenge.Epigenetic events contribute to the etiology of diabetes; however, the lack of epigenomic analysis has limited the elucidation of the mechanistic basis for this link.To determine the epigenetic architecture of human pancreatic islets we mapped the genome-wide locations of four histone marks: three associated with gene activation-H3K4me1, H3K4me2, and H3K4me3-and one associated with gene repression, H3K27me3.Interestingly, the promoters of the highly transcribed insulin and glucagon genes are occupied only sparsely by H3K4me2 and H3K4me3.Globally, we identified important relationships between promoter structure, histone modification, and gene expression.We demonstrated co-occurrences of histone modifications including bivalent marks in mature islets.Furthermore, we found a set of promoters that is differentially modified between islets and other cell types.We also use our histone marks to determine which of the known diabetes-associated single-nucleotide polymorphisms are likely to be part of regulatory elements.Our global map of histone marks will serve as an important resource for understanding the epigenetic basis of type 2 diabetes.",
+      "\t\n\nIn addition to genetic factors, epigenetic mechanisms, such as DNA methylation, histone modifications, chromatin remodeling, and RNA editing and biogenesis have recently emerged as a potential link between gene expression and environmental factors [21].DNA methylation refers to the reversible attachment of a methyl group to a cytosine within cytosine-phosphate-guanine (CpG) dinucleotides [22].In differentiated cells, DNA methylation contributes to the maintenance of normal DNA structure, chromosome stability, and gene regulation [23].DNA methylation regulates gene expression without altering the underlying DNA sequence and is of particular interest because of its emerging role in T2D and its complications [24][25][26][27].We recently showed that aberrant DNA methylation is involved in nerve degeneration in T2D and DPN in a small cohort of patients [24].Specifically, our results highlighted the role of DNA methylation in regulating pathways previously shown to be implicated in DPN pathogenesis, including axon guidance, glycerophospholipid metabolism, and MAPK signaling.However, much less is known about the impact of differential DNA methylation on gene expression in DPN and how the interaction between genetic and epigenetic mechanisms may affect biological pathways during DPN pathogenesis.",
+      "\t\n\nDNA methylation can be mitotically stable over time, producing long-term changes in gene expression.The present study suggests that changes in DNA methylation of genes involved in pancreatic development and insulin secretion may result in epigenetic dysregulation of these genes, which may mediate the increased risk of diabetes in individuals exposed to a diabetic intrauterine environment.",
+      "\t\n\nSeveral studies show that key histone post-translational modifications are involved in the regulation of genes associated with the pathogenesis of diabetes, such as insulin and islet-specific transcription factors. 48,60In addition, several groups are examining the role of histone post-translational modifications in adipocytes related to type 2 diabetes, obesity and the metabolic syndrome. 48,60hese endeavours highlight the increasing evidence that histone post-translational modifications can have key roles in the pathogenesis of diabetes.Logically, they can be expected to also affect chromatin structure of target genes in organs associated with complications, including the kidney.",
+      "\t\n\nEpigenetic mechanisms allow alteration of genome function without mutating the underlying sequence.They involve the interacting actions of DNA methylation (the addition of a methyl group to the 5th carbon position of cytosine), histone modifications and noncoding RNAs [18].A number of indirect lines of evidence point to the involvement of epigenetic changes in diabetic nephropathy.Murine models of disease progression displaying temporal variation in gene expression have indicated these supra-sequence devices may be involved in the pathogenesis [19].Gene expression changes reflect dynamic alterations in gene transcription and also messenger RNA stability, which may be influenced by the epigenetic modification of the genome in response to chronic hyperglycaemic stress.Altered DNA methylation has been additionally implicated in vascular disease [20,21].Furthermore, characteristics observed in diabetic nephropathy such as hyperhomocysteinaemia, dyslipidaemia, inflammation and oxidative stress can promote aberrant DNA methylation [22][23][24]."
+    ],
+    [
+      "\t\nFew concepts in recent years have garnered more disease research attention than that of the intestinal (i.e. 'gut') microbiome.This emerging interest has included investigations of the microbiome's role in the pathogenesis of a variety of autoimmune disorders, including type 1 diabetes (T1D).Indeed, a growing number of recent studies of patients with T1D or at varying levels of risk for this disease, as well as in animal models of the disorder, lend increasing support to the notion that alterations in the microbiome precede T1D onset.Herein, we review these investigations, examining the mechanisms by which the microbiome may influence T1D development and explore how multi-disciplinary analysis of the microbiome and the host immune response may provide novel biomarkers and therapeutic options for prevention of T1D.\t\n\nFew concepts in recent years have garnered more disease research attention than that of the intestinal (i.e. 'gut') microbiome.This emerging interest has included investigations of the microbiome's role in the pathogenesis of a variety of autoimmune disorders, including type 1 diabetes (T1D).Indeed, a growing number of recent studies of patients with T1D or at varying levels of risk for this disease, as well as in animal models of the disorder, lend increasing support to the notion that alterations in the microbiome precede T1D onset.Herein, we review these investigations, examining the mechanisms by which the microbiome may influence T1D development and explore how multi-disciplinary analysis of the microbiome and the host immune response may provide novel biomarkers and therapeutic options for prevention of T1D.\tTherapeutic targeting of the gut microbiome to block T1D progression\n\nExperimental microbiome manipulation in young T1D prone rodents provides robust protection from isletautoimmunity and disease, providing proof of principle that microbial therapy could provide effective protection of individuals with high genetic risk [12].The gut microbiome is extensively remodelled during early postnatal development and throughout childhood and puberty [9,41,42].This natural fluctuation in microbial colonization provides a window of opportunity to modify this risk factor in children with risk markers of anti-islet autoimmunity.\t\n\nBased on the available body of literature, it is feasible to suggest that the well-described increased incidence in T1D over the past 50 years [15,16] arises, at least in part, from one of two primary mechanisms related to the intestinal microbiome.In the first notion (Fig. 1), defective development and/or alteration of healthy microbiota in an individual at genetic risk for T1D may result in abnormal immunoregulation that enables autoimmune destruction of insulin-producing  cells.This notion is supported by evidence suggesting that immune education required for self/ non-self immunoregulation is, to a large degree, conferred early in life, through maturation and education of the immune system by microbiota that colonize the gastrointestinal tract, living symbiotically with the host [18,19].The second concept (Fig. 1), acting either independently of or co-incident with the first, is that enhanced leakiness of the gut epithelial barrier (observed in both human patients and animal models of T1D) either results from an altered microbiome or is a key determinant of an altered microbiome, or 'dysbiosis' [17,20].Either type of microbiome-mediated mechanism could underlie the observed combination of increasing disease incidence as well as the younger age of onset [21], resulting from less robust or delayed maturation of immunoregulation in early childhood.Understanding such mechanisms is an important consideration.Indeed, if a central role for the microbiome in T1D risk was confirmed, as will be discussed later, the disease might be preventable by augmenting or accelerating healthy microbiota-induced immunoregulation, as well as by attenuating intestinal leakiness.However, before undertaking such therapeutic efforts, it would appear critical to determine first whether and how an altered microbiome contributes to either defective immunoregulation and/or gut leakiness in T1D.\tUncovering a pathogenic role for the microbiome in T1D -a proposed pathway forward\n\nAs mentioned previously, interactions between susceptibility genes and environmental determinants of T1D remain poorly defined [16].The most pressing outstanding questions regarding the microbiome as an environmental determinant in T1D are (i): does the microbiome hold any additional clues into disease aetiology, including potential viral or bacterial antigens and metabolites; (ii) is there a microbiome-wide dysbiosis linked to pathogenesis (i.e.development of autoimmunity, progression of autoimmunity, onset of clinical disease); and (iii) is defective microbiome-induced immunoregulation contributing to pathogenesis of T1D?\t\n\n Does altered maturation or development of an adult microbiome or a dysbiotic state contribute to the pathogenesis of human type 1 diabetes, what is the mechanism(s), and when does it occur? Does an altered microbiome or dysbiosis act at the level of initiation of autoimmunity and/or progression of type 1 diabetes? What is the basis of healthy microbiome-induced immunoregulation and does the lack of such contribute to the pathogenesis of human type 1 diabetes? Is altered gut epithelial function and integrity important in the pathogenesis of type 1 diabetes, and if so, what is the mechanism(s) and relation to dysbiosis and how do we demonstrate impaired function in humans? How important are the interactions between host genetics, metabolism and the immune system in shaping the microbiome and predilection to disease? Are faecal samples an appropriate representation of the microbiome for type 1 diabetes studies? What are the most promising type 1 diabetes preventive/therapeutic opportunities targeting the microbiome, microbiome-induced immunoregulation, or microbiome-altered gut permeability?",
+      "\t\nAssessment and characterization of gut microbiota has become a major research area in human disease, including type 2 diabetes, the most prevalent endocrine disease worldwide.To carry out analysis on gut microbial content in patients with type 2 diabetes, we developed a protocol for a metagenome-wide association study (MGWAS) and undertook a two-stage MGWAS based on deep shotgun sequencing of the gut microbial DNA from 345 Chinese individuals.We identified and validated approximately 60,000 type-2-diabetes-associated markers and established the concept of a metagenomic linkage group, enabling taxonomic species-level analyses.MGWAS analysis showed that patients with type 2 diabetes were characterized by a moderate degree of gut microbial dysbiosis, a decrease in the abundance of some universal butyrate-producing bacteria and an increase in various opportunistic pathogens, as well as an enrichment of other microbial functions conferring sulphate reduction and oxidative stress resistance.An analysis of 23 additional individuals demonstrated that these gut microbial markers might be useful for classifying type 2 diabetes.\t\n\nAssessment and characterization of gut microbiota has become a major research area in human disease, including type 2 diabetes, the most prevalent endocrine disease worldwide.To carry out analysis on gut microbial content in patients with type 2 diabetes, we developed a protocol for a metagenome-wide association study (MGWAS) and undertook a two-stage MGWAS based on deep shotgun sequencing of the gut microbial DNA from 345 Chinese individuals.We identified and validated approximately 60,000 type-2-diabetes-associated markers and established the concept of a metagenomic linkage group, enabling taxonomic species-level analyses.MGWAS analysis showed that patients with type 2 diabetes were characterized by a moderate degree of gut microbial dysbiosis, a decrease in the abundance of some universal butyrate-producing bacteria and an increase in various opportunistic pathogens, as well as an enrichment of other microbial functions conferring sulphate reduction and oxidative stress resistance.An analysis of 23 additional individuals demonstrated that these gut microbial markers might be useful for classifying type 2 diabetes.",
+      "\t\n\nIn Brief Liu et al. identify the gut microbiota as an important determinant in the responsiveness of individuals with prediabetes to exercise for the improvement of glucose metabolism and insulin sensitivity.These findings may help in the implementation of a personalized lifestyle intervention for diabetes prevention.\t\n\nA growing body of evidence suggests that dysbiosis of gut microbiota plays an important role in the pathogenesis of insulin resistance and T2D (Bouter et al., 2017) through multiple mechanisms, including increased gut permeability and low-grade endotoxemia, changes in production of short-chain fatty acids (SCFAs) and branched-chain amino acids (BCAAs), and perturbation of bile acid metabolism (Utzschneider et al., 2016).Compositional and functional changes of gut microbiota have been observed in individuals with T2D and prediabetes (Allin et al., 2018;Qin et al., 2012), whereas fecal microbial transplantation from healthy donors into patients with metabolic syndrome results in increased microbial diversity and improved glycemic control, as well as insulin sensitivity (Kootte et al., 2017).\t\n\nIn conclusion, our study uncovers gut microbiota and its metabolism as key molecular transducers to the heterogeneous adaption to exercise intervention on glucose metabolism and insulin sensitivity.This finding, together with our demonstration of the predictive value of baseline microbial signatures for individualized responsiveness to exercise, may facilitate clinical implementation of personalized lifestyle intervention for diabetes management.\t\n\nConsidering the important role of the gut microbiota in regulating glucose homeostasis and insulin sensitivity, we next explored whether it was involved in the heterogeneous metabolic effects of exercise in our cohort.",
+      "\t\n\nHere, we unraveled novel mechanisms linking gut microbiota changes and metabolism in genetic obese mice and found that prebiotics improved leptin sensitivity in diet-induced leptin-resistant mice.Further work is required to understand the functional links between the metabolic/ catabolic activities of gut bacteria and their impact on host metabolism.For instance, it would be of interest to establish a causal relationship, instead of correlations as shown here, by using transfer of bacterial communities.An alternative experiment would be to analyze intestinal (fecal) microbiota in a time-series study in view of identifying the specific impact of prebiotics and the gut microbes on the onset of obesity and type 2 diabetes.\t\n\nCONCLUSIONS-We conclude that specific gut microbiota modulation improves glucose homeostasis, leptin sensitivity, and target enteroendocrine cell activity in obese and diabetic mice.By profiling the gut microbiota, we identified a catalog of putative bacterial targets that may affect host metabolism in obesity and diabetes.",
+      "\t\n\nThe intestinal microbiome also seems to be important to the pathophysiology of type 2 diabetes. 46The microbiome has about 100 times more genetic information than has the human genome, together comprising the human metagenome.Many products of the microbiome provide functions beyond that of the host genome, thereby serving an important role in human physiology.These gut communities are thought to play an important part in several conditions and disorders (eg, obesity and type 2 diabetes), although which bacterial species cause changes to human metabolism is not clear. 47Findings from two studies that used faecal samples suggested that functional changes in the gut microbiome might be directly linked to development of type 2 diabetes; 48,49 however, metagenomic markers diff er between populations, suggesting that their ability to predict development of diabetes will probably vary. 49Findings from a recent proof-of-concept study 50 showed improvements in insulin sensitivity in patients with metabolic syndrome 6 weeks after infusion of intestinal microbiota from lean individuals.Lastly, diff erent gut fl ora might aff ect nutrient absorption, because in human beings nutrient load can alter the faecal bacterial community in a short time. 51he nervous system is another important regulator of metabolic processes.Both sympathetic and parasympathetic nervous systems control glucose metabolism, directly through neuronal input, and indirectly through the circulation to aff ect release of insulin and glucagon 52 and production of hepatic glucose. 53In human beings, the vagus is important in regulation of islets, because severing of this nerve results in impaired insulin secretion. 54The hypothalamus is an important integrator, because its ablation in rats results in dysregulation of  cells and development of hyperinsulinaemia. 557][58] Insulin action at this site is also essential in regulation of bodyweight, with decreased activity leading to obesity. 59Infl ammationinduced neuronal injury occurs rapidly in rodents fed a high-fat diet. 60Findings from imaging studies of obese and lean people suggest that structural changes occur in the hypothalamus, consistent with the occurrence of gliosis in obesity. 60Finally, clock genes expressed in the brain are important in establishment of circadian rhythmicity and, together with sleep, have become a focus of investigation because changes in diurnal patterns and quality of sleep can have important eff ects on metabolic processes. 61,62",
+      "\t\n\nOver the last five years, several studies have linked diet/nutrients (mainly dietary fiber), gut microbiota and the expression of genes involved in immune responses.It is well known that the diet has a profound effect on the gut microbiota.In mice and humans, microbes respond differently to dietary components, and long-term dietary habits have been linked to the abundance of certain microbial genera [23].The gut lumen contains large amounts of nutrients that strongly influence the composition of the microbiota, which affects gut immunity.These alterations in gut immunity can precipitate T1DM in individuals prone to T1DM.It has also been observed that diabetes-prone BioBreeding (BBdp) rats housed in specific germ-free (GF) conditions and weaned onto cereal diets displayed an upregulation of the interferon gamma (Ifng) and interleukin 15 (Il15) genes and a downregulation of the forkhead box P3 (Foxp3) gene [24].Both Ifng and IL-15 are proinflammatory cytokines that promote T1DM in non-obese diabetic (NOD) mice [25], whereas Foxp3 is a master transcription factor that directs the differentiation and function of regulatory T cells and plays a central role in the inhibition of autoimmunity and suppression of physiological immune responses [26].When BBdp rats were weaned onto cereal diets and housed in specific pathogen-free conditions (allowing gut microbiota growth), the rats also showed an upregulation of the lymphocyte-specific protein tyrosine kinase (Lck) gene [23].Lck encodes tyrosine kinase/p56, a lymphocyte-specific protein involved in the initiation of T cell activation [27].Finally, in this last condition, BBdp rats showed decreased expression of the cathelicidin antimicrobial peptide (Camp) gene.CAMP is a multifunctional antimicrobial effector and immunomodulatory host defense factor [28], which may alter the gut microbiota.",
+      "\t\n\nSpecific microbiome profiles render individuals prone to develop obesity and altered glucose metabolism 313 .The ability to identify protective microbiome profiles might provide a key to the development of obesity and diabetes interventions.It remains to be determined whether specific dietary components are involved in microbiome changes and induce unfavourable transitions.Probiotics or pharmacological manipulation of microbiome elements that favour more 'healthy' flora may prove to be useful in stemming the 'twin epidemics' of obesity and T2DM 313 .Surgical rearrangement of the gastrointestinal tract has shown remarkable efficacy in treating obese patients with T2DM 307,314 .Development of minimally invasive reversible procedures, such as the duodenal sleeve and temporary mucosal barriers, might replace surgery in the near future.",
+      "\t\n\nIn conclusion, our data suggest that the levels of glucose tolerance or severity of diabetes should be considered while linking microbiota with obesity and other metabolic diseases in humans.It is especially important for developing the strategies to modify the gut microbiota in order to control metabolic diseases, since obesity and diabetes might be associated with different bacterial populations.\t\n\nBackground: Recent evidence suggests that there is a link between metabolic diseases and bacterial populations in the gut.The aim of this study was to assess the differences between the composition of the intestinal microbiota in humans with type 2 diabetes and non-diabetic persons as control.",
+      "\t\n\nIn recent years, several associations between common chronic human disorders and altered gut microbiome composition and function have been reported 1,2 .In most of these reports, treatment regimens were not controlled for and conclusions could thus be confounded by the effects of various drugs on the microbiota, which may obscure microbial causes, protective factors or diagnostically relevant signals.Our study addresses disease and drug signatures in the human gut microbiome of type 2 diabetes mellitus (T2D).Two previous quantitative gut metagenomics studies of T2D patients that were unstratified for treatment yielded divergent conclusions regarding its associated gut microbial dysbiosis 3,4 .Here we show, using 784 available human gut metagenomes, how antidiabetic medication confounds these results, and analyse in detail the effects of the most widely used antidiabetic drug metformin.We provide support for microbial mediation of the therapeutic effects of metformin through short-chain fatty acid production, as well as for potential microbiota-mediated mechanisms behind known intestinal adverse effects in the form of a relative increase in abundance of Escherichia species.Controlling for metformin treatment, we report a unified signature of gut microbiome shifts in T2D with a depletion of butyrate-producing taxa 3,4 .These in turn cause functional microbiome shifts, in part alleviated by metformininduced changes.Overall, the present study emphasizes the need to disentangle gut microbiota signatures of specific human diseases from those of medication."
+    ],
+    [
+      "\t\n\nIn this review, we limit our summary to data obtained from studies that compared clinical risk scores with scores derived from extended models containing multiple genetic markers for T2D or CVD; we also report the AUCs for the relevant risk models.To assess the issue of prediction, prospective studies are warranted.However, given the scarcity of appropriate studies, our overview includes studies with both prevalent and incident cases, as indicated in Tables 3 and 4.",
+      "\t\n\nIn this review, we limit our summary to data obtained from studies that compared clinical risk scores with scores derived from extended models containing multiple genetic markers for T2D or CVD; we also report the AUCs for the relevant risk models.To assess the issue of prediction, prospective studies are warranted.However, given the scarcity of appropriate studies, our overview includes studies with both prevalent and incident cases, as indicated in Tables 3 and 4.",
+      "\tSummary and outlook\n\nA lot of work has been performed to assess the incremental value of novel markers, beyond established risk factors, for the prediction of diabetes.Nevertheless, several questions remain to be answered.First, the addition of biomarkers to conventional diabetes risk scores has so far not or, at best, only slightly improved the predictive ability of the models.This raises the question, under which condition novel markers may have a larger incremental value.Often biomarkers are strongly correlated with conventional risk factors so that they do not provide additional predictive information [98,100].While in the near future many novel biomarkers are expected to be described as a result of technological progress, these will only improve diabetes prediction if they are at best weakly correlated with established risk factors.Moreover, it is conceivable that the slope of a biomarker trajectory (the change of the biomarker over time) captures incremental predictive information above the last measurement of the marker alone.However, the potential of trajectories has not yet been assessed for diabetes prediction.\t\n\nThird, beyond optimising the predictive ability of diabetes risk scores, there is a wide range of issues which have not been considered in this review.From a public health perspective, it has to be asked whether diabetes risk scores are accepted by physicians, and which barriers might prevent physicians from using them; how scores are best implemented in clinical practice; to what extent intuitive risk assessments made by physicians are concordant with score-based assessments; and how good is the effectiveness and efficiency of diabetes prediction models.All these questions have hardly been addressed so far.Another issue to consider regarding noneconomic costs relates to false positive test results (which could increase anxiety) and false negative risk estimates (which could lead to false reassurance).Finally, the successful implementation of any prognostic diabetes model will depend on a cost-effective intervention strategy for those persons for whom a high risk of developing type 2 diabetes is diagnosed.This list demonstrates that the assessment of the performance of novel biomarkers in risk models needs to be investigated in a substantially larger context than it is currently before recommendations for their widespread use can be given with certainty.",
+      "\tVelu in [12] employed the most emerged three techniques for classification of the\ndiabetic patients, i.e. , EM algorithms, H Means + clustering, and Genetic Algorithm\n(GA) [6]. From their result analysis, H Means + clustering techniques give a better\nresult as compared to other two techniques in case of diabetes disease. Ganji in\n[13] adopted fuzzy ant colony optimization techniques to find the set of rules for the\nadiabatic patient and their diagnosis. Now it is also used for the prima Indian diabetes\ndatasets. Jayalakshmi T. in [14] diagnoses the adiabatic patient through their new\napproachANN techniques.\t: Prediction of diabetes using classification algorithms. Proc. Comput. Sci. 132, 15781585 (2018)\n10. Aljumah, A.A., Ahamad, M.G. , Siddiqui, M.K. : Application of data mining: diabetes health\ncare in young and old patients. J. King Saud Univ. Comput. Inf. Sci. 25(2), 127136 (2013)\n11. Iyer, A., Jeyalatha, S., Sumbaly, R.: Diagnosis of diabetes using classification mining\ntechniques. arXiv preprint arXiv:1502.03774\n12. Velu, C.M. , Kashwan, K.R. : Visual data mining techniques for classification of diabetic patients. In: 2013 3rd IEEE International Advance Computing Conference (IACC), pp. 10701075. IEEE (2013)\n13. Ganji, M.F. , Abadeh, M.S.\tThe analytical process can be done by different machine learning\nalgorithms. This paper presents two sets of machine learning approach for prediction\nof diabetes. One of them is a classification-based algorithm, and the other one is a\nhybrid algorithm. In classification, we have taken the random forest algorithm. For\nhybrid approach, we have chosen XGBoost algorithm. These two algorithms were\nimplemented and compared in order to explore the prediction accuracy in diabetes\nfor two different machine learning approaches and got the mean score 74.10% which\nis better than the Random Forest algorithm.\tIn: International Conference on Remote\nEngineering and Virtual Instrumentation, pp. 306314 (2019)\n17. Aishwarya, R., Gayathri, P., Jaisankar, N.: A method for classification using machine learning\ntechnique for diabetes. Int. J. Eng. Technol. 5, 29032908 (2013)\n18. Rashid, T.A. , Abdulla, S.M. , Abdulla, R.M. : Decision support system for diabetes mellitus\nthrough machine learning techniques. Int. J. Adv. Comput. Sci. Appl. 7, 170178 (2016)\n19. Wang N, Kang G (2012) Monitoring system for type 2 diabetes mellitus. In: IEEE Conference\non E-health Networking, pp. 6267\n20.",
+      "\tComputational Insight into Diabetes Research\n\nWhen it comes to machine learning and data mining, significant conclusions are drawn through the present detailed account.It is worth mentioning that the vast majority of the reported articles enhanced classification accuracy, above 80%, in the prediction of DM.With regard to the prediction task itself, almost all of the common known classification algorithms have been employed.However, the most commonly used ones are SVM, ANN, and DT.It should be mentioned that SVM rises as the most successful algorithm in both biological and clinical datasets in DM.A great deal of articles (~85%) used the supervised learning approaches, i.e. in classification and regression tasks.In the remaining 15%, association rules were employed mainly to study associations between biomarkers.More specifically, concerning the part dealing with the evaluation task, in all reported research reports, the identified subsets of biomarkers (features) were evaluated through appropriate procedures, such as splitting the dataset into train and test set or via cross-validation.By analogy, the same approaches have been followed in DM prediction.\t\n\nIn the case of nephropathy, Huang et al. employed a Decision Tree-based prediction tool that combines both genetic and clinical features in order to identify diabetic nephropathy in patients with T2D [81].Leung et al. compared several machine learning methods that include partial least square regression, classification and regression tree, the C5.0 Decision Tree, Random Forest, naive Bayes, neural networks and support vector machines [82].The dataset used consists of both genetic (Single Nucleotide Polymorphisms -SNPs) and clinical data.Age, age of diagnosis, systolic blood pressure and genetic polymorphisms of uteroglobin and lipid metabolism arose as the most efficient predictors.",
+      "\tOverview of the risk assessment algorithms\n\nWe tested a machine-learning approach called Support Vector Machine (SVM, see Methods), as well as logistic regression (LR, see Methods) in order to assess individual disease risk for type 1 diabetes (T1D) using three GWAS datasets (Table 1).SVM is one of the most popular classifiers in the field of machine learning and achieves state-of-the-art accuracy in many computational biology applications [28].In essence, SVM is a supervised machinelearning algorithm that produces a linear boundary to achieve maximum separation between two classes of subjects (cases versus controls), by mathematical transformation (kernel function) of the input features (SNP genotypes) for each subject.Unlike most regression-based methods, SVM allows more input features (such as SNPs or genes) than samples, so it is particularly useful in classifying high-dimensional data, such as microarray gene expression data [29].We also applied LR as a control algorithm, since it is widely used in genetic studies to model the joint effects of multiple variants.Unlike previous disease assessment studies that typically use genotype data from a handful of validated susceptibility loci, we examined a large ensemble of SNP markers with suggestive evidence for association with T1D, using a few Pvalue cutoff thresholds ranging from 1610 23 to 1610 28 , as well as highly stringent quality control measures (see Methods).When more relaxed P-value criteria are being used, the contributing SNPs scatter across the genome; when more stringent criteria are used (P,1610 28 ), only a few independent loci contribute (assuming that all MHC markers represent a single locus).Furthermore, we included the 45 known T1D susceptibility markers [4] into the prediction models to ensure that their predictive values were accounted for.Although these SNP lists may contain some false positive loci that are not genuinely associated with T1D, recent advancements in machine-learning, such as regularization, have made classifiers more tolerant to irrelevant input features [30].Since we cannot completely eliminate falsely associated loci from the list of predictors, our goal is to include them in the prediction models (using various thresholds) and then assess their influence on performance.\tDiscussion\n\nIn this study, we tested the plausibility of building a classifier and using a large number of SNPs for disease risk assessment on three large T1D datasets.In general, the SVM algorithm achieved satisfactory performance when hundreds of SNPs were included in prediction models, with AUC scores of ,0.84 for predicting disease risk for T1D in several GWAS datasets.In contrast, the SVM or the LR algorithm achieved only an AUC score of 0.66-0.68when 45 known T1D susceptibility loci were used.This difference clearly indicates that the predictive value lies in utilizing a large number of SNPs in a sophisticated machine-learning algorithm.We note that another recent study also reported that using thousands of SNPs improve the performance of disease risk assessment compared to using fewer SNPs for diseases studied by WTCCC [39], although the study used a cross-validation design.On the other hand, we observed a decrease in the predictive accuracy when too many SNPs were used, suggesting an upper bound of the number of SNPs for T1D risk assessment before noises from falsely associated markers lead to degraded performance.However, we caution that this upper bound depends on the sample size and the power of the study to rank truly associated SNPs higher than background noises.\t\n\nFigure2.Performance of risk assessment models trained on the CHOP/Montreal-T1D dataset.For both the WTCCC-T1D and the GoKind-T1D datasets, the SVM (support vector machine) algorithm consistently outperforms LR (logistic regression), and the best performance is achieved when SNPs were selected using P-value cutoff of 1610 26 or 161025 .doi:10.1371/journal.pgen.1000678.g002",
+      "\tMethodology\n\nThis study is focused on predicting future illnesses such as type-2 diabetes from genomic and tabular data.Genomic data are analyzed for possible gene expression highly likely to be affected by type-2 diabetes.Tabular data from the PIMA dataset with various features are also explored through the proposed RNN model by identifying the feature vector's pivotal features.The proposed model relies on the Deep Neural Networks (DNN) framework for analyzing the genomic data, making the precise assessment of possible future illnesses with better Accuracy than the conventional pattern-matching techniques.DNN is a probabilistic measure that would summarize the possible illness outcome that would better assist in decision-making by the physicians.The working procedure and implementation details are discussed in the current section.The models are trained from the available gene base from scratch initially, and at the later stages, the model learns from the experimental outcomes.\t\n\nVarious studies have been presented to predict future illness through existing patient data using machine learning algorithms.Predicting future illness has become a demanding topic in healthcare [29].Several studies have used machine intelligence techniques to analyze the Pima Indian Diabetes Dataset.C. Yue [30] has investigated various hybrid approaches, including Neural Networks, integrated Quantum Particle Swarm Optimization (QPSO), and Weighted Least Square (WLS) Support Vector Machine (SVM) for diabetes prediction, with the WLS-SVM hybrid model showing a classification accuracy of 82.18%.However, the hybridization model needs considerable effort in the evaluation process.In addition, the SVM model is not suitable for working with larger data [31].Moreover, the SVM model underperforms if the number of attributes for every data point exceeds the training samples.The combinational models for diabetes prediction using Cross-validation and Self-Organizing Maps (SOM) have achieved an accuracy of 78.4% [32,33].SOM can rely on the associated weights of neurons for precise classification.Inappropriate assignment of initial weights may impact the model's performance.A C4.5 technique [34] has been used to analyze the PIMA dataset, attaining an Accuracy of 71.1%.The model works through the entropy value associated with the feature vector.The conventional classification models exhibit poor performance when working with distinct feature vectors [35].\tExperimental Outcome of Genomic Data\n\nThe performance of the proposed RNN model for predicting type 2 diabetes was analyzed using performance evaluation metrics such as sensitivity, specificity, F1 score, Mathews correlation Coefficient, and accuracy measures [76].The above-discussed metrics are assessed through true positive, true negative, false positive, and false negative values approximating experimental outcomes.The dataset is split into a training set and a validation set at a ratio of 70:30.In the following graph, as shown in Figure 7, it is clear that data values are skewed toward data instances, indicating that no diabetes exists.The percentage of available data records of non-diabetic patients (or those who do not have diabetes) is almost double that of diabetic patients.\t\n\nAll the mentioned models rely on tabular datasets such as PIMA and ECG signals [47] in classifying the records with possible diabetic illnesses.The current study considers that genomic data yields a better patient-centric outcome than tabular data.\tResults and Discussion\n\nThe proposed model has been evaluated on genomic data and the tabular data by using the same feature engineering mechanism and the layered approach for predicting the type-2 diabetes.The proposed RNN-based type-2 diabetes is evaluated against genomic and tabular data from the PIMA Indian dataset independently and the evaluations are presented independently in the current section.The model was evaluated against two datasets concerning various evaluation metrics such as sensitivity, specificity, Accuracy, and F1 score.The classification efficiency of the proposed model was assessed using true positive (TuP, the number of times that the model accurately predicted the gene with a high possibility of diabetes correctly), true negative (TuN, identifying the gene with less possibility of diabetes precisely), false positive (FsP, misinterpreting the gene with the high possibility of diabetes as low possibility of diabetes), and false negative (FsN, misinterpreting the low diabetes gene as a high possibility of illness).The sensitivity metric determines the ratio of how many were accurately recognized as positive samples out of how many were truly positive samples in the complete dataset.The specificity measure determines the ratio of how many were recognized as negative samples out of how many among the samples are truly negative from the complete dataset.The Accuracy measures the correctly predicted True positives and Negative samples against the overall sample in the complete dataset.The harmonic mean of sensitivity and specificity measures are determined as the F1 score.MCC is the best single-value classification score for summarizing the confusion matrix.The formulas for the aforementioned metrics are presented through Equations ( 27)-( 32) [75].\tRecurrent Neural Network Model for Type 2 Diabetes Forecasting Based on Genomic Data\n\nPredictions of future illness can be performed through Convolutional Neural Networks (CNN), as stated by Leevy J.L. et al. [51] and Yadav S.S. and Jadhav S. M. [52] using Recurrent Neural Network (RNN) module-based architecture described by SivaSai J.G. et al. [53].CNN model consists of many intermediate nodes connected.Each node is significant in delivering the output following the anticipated outcome.RNN is robust in handling variable-length input sequences with the help of internal auxiliary memory modules [54].The detailed architecture along with the implementation procedure for the proposed approach, is presented in this section.\t\n\nA fuzzy entropy approach for feature selection for a similarity classifier has been evaluated against various medical datasets, such as Pima-Indian diabetes, exhibiting an accuracy of 75.29% [36].A fuzzy model primarily depends on the membership evaluation that requires considerable effort.Non-linearity in evaluating the model will limit the model's performance [37].Genetic Algorithm (GA) with Radial Basis Function Neural Network (RBF NN) has been used in the evaluation process of diabetes data, exhibiting an accuracy of 77.39% over the testing dataset [38].Moreover, for artificial evolutionary algorithms such as GA, the most prohibitive and restricting element is frequently repeated fitness function assessment for complex gene patterns.Hybridization of models with GA would need more computational efforts than neural networks alone.Various cutting-edge technologies for the classification and prediction of type-2 diabetes are presented in Table 1."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "034CBC335A5D1820E523A0A1CF93FCB8"
+    },
+    {
+      "task_id": "4ADB4C703E90EC89A3B3F7605F9C00E8"
+    },
+    {
+      "task_id": "62A20F96A8B7FE15B0B6D25C97A96794"
+    },
+    {
+      "task_id": "C94269DE09DD00872EC23EC6D7093632"
+    },
+    {
+      "task_id": "5E472FF7C262791E739F6BD6707642D5"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_2.json
new file mode 100644
index 0000000..3dc276d
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_2.json
@@ -0,0 +1,119 @@
+{
+  "question": [
+    "What are the implications of recent findings on the role of long non-coding RNAs (lncRNAs) in the regulation of insulin secretion and sensitivity?",
+    "How do post-translational modifications of proteins affect key signaling pathways involved in glucose homeostasis?",
+    "What insights have been gained from studying the genetic basis of syndromic forms of diabetes, such as Wolfram Syndrome and Alstr\u00f6m Syndrome?",
+    "How do genetic and epigenetic differences between monozygotic twins discordant for diabetes inform our understanding of its etiology?",
+    "What potential therapeutic targets have been identified through recent studies on the interaction between genetic variants and environmental factors in diabetes development?"
+  ],
+  "answer": [
+    "Recent findings suggest that long non-coding RNAs (lncRNAs) play a significant role in the regulation of insulin secretion and sensitivity. They are involved in the regulation of islet development and function, and their abnormal expression is associated with diabetes. For instance, lncRNAs like H19, HI-LNC25, LOC283177, TUG1, MEG3, and PLUTO have been shown to influence islet structure, insulin synthesis, secretion, and glucose homeostasis. However, the exact molecular mechanisms through which lncRNAs influence pancreatic biology and diabetes are still under investigation.",
+    "Post-translational modifications (PTMs) such as phosphorylation, acetylation, -Olinked N-acetylglucosamine (O-GlcNAc), SUMOylation, and ubiquitination contribute to the activation of PPAR, a key player in glucose homeostasis. These PTMs can influence ligand affinity, DNA binding, coactivator recruitment, and/or proteasomal degradation, thereby affecting the signaling pathways involved in glucose homeostasis. For instance, in the insulin signaling pathway, phosphorylation events play a crucial role in the regulation of glucose uptake and metabolism.",
+    "Studying the genetic basis of syndromic forms of diabetes, such as Wolfram Syndrome and Alstrm Syndrome, has led to the discovery of rare, but highly penetrant, alleles that could be tracked using family-based linkage approaches. This has provided valuable insights into the cellular and molecular processes operating in the pancreatic islet and other tissues that control glucose homeostasis. Furthermore, it has uncovered a whole class of diseases, the ciliopathies, that result from defects in the genetic control of ciliary development and function.",
+    "The genetic and epigenetic differences between monozygotic twins discordant for diabetes suggest that both genetic and environmental factors contribute to the disease's etiology. While monozygotic twins share 100% of their genetic material, the discordance in diabetes incidence (30-70%) indicates the influence of environmental factors. These may include diet, gestational infections, and viral infections. Epigenetic modifications, such as altered DNA methylation, also play a role in gene expression regulation and contribute to diabetes etiology. Therefore, the study of these twins helps to understand the complex interplay of genetic predisposition and environmental triggers in the development of diabetes.",
+    "Recent studies have identified several therapeutic targets through the interaction between genetic variants and environmental factors in diabetes development. These include the PPARG and thiazolidinediones, KCNJ11 and sulfonylurea therapy, and the glucagon-like peptide-1 receptor (GLP1R), which is the target of GLP1R agonists. Other potential targets include drug receptors or drug metabolizers such as OCT genes, ABCC8, and CYP2C9."
+  ],
+  "contexts": [
+    [
+      "\tUsing microarray analysis, we discovered that gene-targeting of the 7 nAChR\nresults in up-regulation of an insulin-signaling network in the NAc. A genetic correlation\nnetwork of insulin-related genes and Chrna7 was independently elucidated in the NAc\nacross the BXD panel, thus validating that our microarray results are likely not due to\ndevelopmental compensation in 7 KO mice. Insulin-degrading enzyme, Ide, mRNA\nwas significantly decreased and previous rodent studies have demonstrated that both\nknock-out of this gene (Farris, 2003), as well as a mutation decreasing its catabolic\nactivity (Fakhrai, 2000), results in hyperinsulinemia and glucose intolerance.",
+      "\t\n\nSome recently-identified miRNAs have been associated with insulin secretion, insulin resistance, and inflammation, and differences have emerged in some circulating miRNA levels between individuals with and without type 2 diabetes (40).Zhao and others (41) examined some miRNAs in pregnant women at 16-19 weeks of gestation (WG), finding a significantly lower expression of 3 miRNAs (miR-29a, miR-132 and miR222) in women who went on to develop GDM at 24-28 WG than in those who did not develop GDM.MiR-29 plays a part in glucose homeostasis: its overexpression inhibits insulinstimulated glucose uptake and downregulates gluconeogenesis (42).MiR-132 targets the insulin-mediated regulation of cytochrome P450 (which is involved in hepatic metabolism), and it has a role in trophoblast expansion (its reduced expression impairs normal trophoblast development) (42,43).MiR-222 is involved in regulating the cell cycle (controlling the cyclindependent kinase inhibitor).",
+      "\t\n\nA human islet cis-regulatory network has been generated by integrating chromatin accessibility data, RNA-sequencing data and chromatin immunoprecipitation-sequencing data for five key -cell transcription factors (FOXA2, MAFB, NKX2.2, NKX6.1 and PDX1) 25 .Using this regulatory network, loci associated with T2DM risk that influence fasting glycaemia were found to be enriched in active islet enhancers.Furthermore, these loci were predicted to alter enhancer activity by disrupting transcription factor binding sites 25 .For example, a T2DM risk variant (rs58692659) falls within the ZFAND3 locus and was demonstrated to disrupt a NEUROD1 binding site, which is an important islet transcription factor for islet cell development and function, thereby preventing NEUROD1 binding 25 .Furthermore, T2DM risk loci are enriched in and predicted to disrupt regulatory factor X (RFX) transcription factor binding sites 27 .These data provide compelling evidence that islet-specific regulatory regions have a central role in T2DM pathophysiology and suggest a direct link between genetic variation and changes in gene expression.",
+      "\t\n\nThe inability to detect insulin-signaling changes in both studies can be explained by a number of technical and biological hypotheses.First, perhaps the number of insulinsignaling genes that were transcriptionally deregulated was too few to be considered significant by statistical procedures.Second, perhaps the assembled insulin-signaling gene set used in our analysis did not accurately capture the transcriptional alterations in insulin signaling.Alternatively, it is plausible that the changes in a diabetic state were produced by phosphorylation-mediated signaling that was not detected by transcriptional profiling.",
+      "\t\n\nUpon further epigenetic regulatory elements in diabetes, micro-RNAs, such as miR-15a and miR-29b, were found to be downregulated in type 2 diabetes, whereas miR-27a and miR-320a were upregulated and might open the possibility for new diagnostic markers [187, [231][232][233].",
+      "\t\n\nAs ER stress markers were not activated to potentially explain reduced insulin secretion, genes related to insulin secretion pathway were investigated using real-time-PCR, which revealed downregulation of the glucose-stimulated insulin secretion (GSIS) pathway and the glucose uptake pathway in RIN-m -cells when compared to the control, indicating impairment of these pathways.mRNA levels by real-time PCR (Fig. 4c) showed a decrease in glucose transporter 2 (Glut2 [MIM: 138160]) to 54% compared to the control, p < 0.001.Pancreatic and duodenal homeobox 1 (Pdx1 [MIM: 600733]) was also suppressed to 85.7%, p = 0.01.On the other hand, the forkhead box protein A2 (Foxa2 [MIM: 600288]) mRNA level, which regulates PDX1, was unchanged, while the mRNA of glucokinase (Gck [MIM: 138079]), which phosphorylates glucose in the first step of the GSIS pathway in -cells, was slightly elevated (11.5%, p = 0.008).",
+      "\t\n\nIt has been hypothesized that most of the new genetic variants affect -cell function, development or survival but not insulin sensitivity [6].Consistent with this, we found all of the genes except Adam30 and Cdkn2a were expressed in pancreatic islets.These genes were expressed, however in the transformed -cell line, MIN6.The expression of all the genes except Lgr5 decreased following incubation of the islets in high glucose concentrations.It can thus be hypothesized that these genes may normally play a beneficial role in islet function, and a reduction in the expression of these genes could contribute to glucotoxic -cell dysfunction or survival.However, we also found evidence that most of the genes could have potential roles in other metabolically-relevant tissues.Genes affecting insulin sensitivity may be expected to be expressed in peripheral insulin sensitive tissues, such as liver and adipose tissue, and be responsive to metabolic status.Consumption of a high fat diet was associated with a tendency for the expression of several of these genes to be decreased.Similarly, many of the genes were regulated by feeding and fasting.Only the two splice isoforms of Cdkn2a had no evidence of metabolic regulation in any of the other tissues examined.",
+      "\t\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\t\n\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\tDiscussion\n\nUsing next-generation sequencing, we have established the first catalog of miRNAs in human pancreatic islets and beta-cells, and explored the overlap between these miRNAs and T2D genetic susceptibility.Our catalog not only serves as a valuable resource for those interested in the roles of specific miRNAs in normal islet physiology and beta-cell function, it also provides a reference for the study of miRNA mediated abnormalities in islets from type 2 diabetic donors.The abundance of miR-375 in the miRNA profile provides valuable support for a critical role in human pancreatic beta-cells, mirroring the well-established role in rodent islet biology.miR-375 null mice are hyperglycaemic and exhibit reduced beta-cell mass [40].In a clonal rodent beta-cell line (MIN6), knockdown or over-expression of this miRNA influences glucose-stimulated insulin secretion [7].Furthermore, knockdown of miR-375 in obese ob/ ob mice results in a more profound effect on glycaemia leading to a severe diabetic phenotype in these mice [40].Our study establishes that miR-375 is also abundantly expressed in human islets and warrants further studies to define the contribution of miR-375 to the pathogenesis of T2D.\t\n\nFew of the 10 most islet-specific miRNAs (Figure 2B; all with specificity scores .0.8) have previously been implicated in islet function.For miR-184, miR-182-5p and miR-127-3p, there is published evidence for a role in insulin biosynthesis and secretion, though for miR-184 and miR-127-3p this is restricted to a correlation between islet expression levels and glucose-stimulated insulin secretion [17,18].For other miRNA transcripts, such as miR-409-5p and miR-183-5p, the high degree of islet-specificity may point to novel roles in the development and maintenance of islet cellular phenotype.",
+      "\t\n\nIn sum, this work provides new information about how CDKN2A/B T2D SNPs impact islet biology, suggests that the ANRIL lncRNA may play a role in human islets, and uncovers a link between a T2D SNP and b-cell proliferation.Further studies into the CDKN2A/B locus to develop a mechanistic understanding of how these SNPs impact islet biology to influence T2D risk could one day open the door for using personalized genomic information to inform T2D subtype definitions and therapeutic choice.",
+      "\t\n\nThe following section will discuss the roles of lncRNAs in metabolic tissues and deregulation of which are implicated in varied metabolic phenotypes associated with diabetes.\tLncRNAs as regulators of islet function\n\nThe pancreatic islet is an important central node to researchers to understand the pathophysiology of diabetes [53].The possible regulation of islet development and function by lncRNAs was first demonstrated by Ding et al., where the lncRNA, H19 (Fig. 4), was shown to be involved in transgenerational transmission of gestational diabetes mellitus which leads to impaired islet structure and function [54].To understand the roles of lncRNAs in regulating pancreatic function, several research groups have profiled lncRNA expression in mouse and human pancreatic islets [55,56].Transcriptome analysis in pancreatic -cells of type 2 diabetes patients identified tissue-specific and dynamically regulated abnormally expressed lncR-NAs.These lncRNAs are often located near islet-specific chromatin domains containing islet-specific coding genes or mapped to diabetes susceptible genetic loci.Knockdown of HI-LNC25, a  cell-specific lncRNA conserved between mouse and human resulted in decreased GLIS3, an important islet transcription factor, thereby suggesting its functional importance in pancreatic  cells [56] (Fig. 4).A coexpression analysis has identified that the lncRNA, LOC283177, correlates with the expression of insulin synthesis and secretion [51] (Fig. 4).Yin et al. demonstrated that silencing of the lncRNA, TUG1 in vivo increased apoptosis in pancreatic  cells and decreased insulin secretion leading to elevated fasting glucose levels (Fig. 4).Expression of TUG1 is decreased in a non-obese diabetic (NOD) mouse and is suppressed by glucose treatment in pancreatic Nit-1 cells, indicating its association with diabetes [57].Another lncRNA, MEG3 was reported to be downregulated in the pancreatic tissue of Type 1 Diabetic (T1D) and T2D mice models and its expression was dynamically modulated by glucose in Min6 and primary mouse islet cells (Fig. 4).In vivo silencing of MEG3 led to impaired glucose tolerance and decreased insulin secretion, as also evident by the reduced insulin-positive cells.There was a significant decrease in the Pdx-1 and MafA levels indicating MEG3 as a novel -cell regulator [58].Deletion of a conserved lncRNA, linc1 (-cell long intergenic non-coding RNA 1) in adult mice results in defective islet development and disruption of glucose homeostasis [59] (Fig. 4).Decreased levels of the lncRNA, PLUTO (Fig. 4) in islets of T2D or impaired glucose tolerant subjects affect the 3D chromatin structure and transcription of Pdx-1, a key  cell transcription factor implicating its role in insulin synthesis and  cell-specific regulatory network [60].In spite of these reports, the elucidation of lncRNAmediated molecular mechanisms in pancreatic biology still awaits further detailed investigations.",
+      "\t\n\nThe known tissue specificity of gene expression regulation means that the most informative studies will measure transcript levels in the specific tissue(s) relevant to the disease.In the case of type 2 diabetes, characterization of physiological responses (e.g., stimulus-induced insulin secretion, insulin sensitivity) suggests most loci are associated with defects in pancreatic b-cell function (2,3,7).Therefore there is a real need to measure gene expression in human b-cells (or whole islets, as these have been shown to be a suitable proxy [8]).There have, however, been very few reports linking type 2 diabetesassociated variation with islet gene expression using the classical eQTL approach (9,10).",
+      "\tInsulin secretion\n\nProgression from altered glucose metabolism to overt diabetes occurs as the reduction in -cell mass and function is further aggravated.Thus, an attractive intervention is one that will halt the progressive decline in -cell mass and function and prevent the need for exogenous insulin replacement that otherwise follows 1 .Agents that suppress inflammation, including IL-1 blockers and salsalate (a potent inhibitor of NF-B), have shown some promise in improving glycaemic control and -cell function 143,269,270 .MicroRNAs play a pivotal part in the physiological and pathological processes involved in glucose metabolism by post-transcriptional regulation of gene expression.Particular microRNAs can regulate -cell function 271 , exposing key regulatory signalling pathways involved in restoration of -cell mass, and provide a promising strategy for improving insulin secretion and -cell health in T2DM.Identification of novel insulin secretagogues that act directly on -cells and enteroendocrine K cells and L cells in the intestine are under investigation, and members of the G protein-coupled class of receptors have shown promise 272 .GLP1 receptor agonists induce -cell proliferation in rodents 273 , but studies in humans have not demonstrated a similar effect 237 .A series of novel signalling pathways have been reported to be strongly associated with -cell mass restoration.For example, the PI3K-PKC pathway has been shown to augment glucose-mediated -cell prolifer ation, and activation of PKC may provide a novel approach to increase human -cell proliferation 274 .",
+      "\t\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\tGWAS-Identified Genes\n\nFollowing the successful identification of genetic loci by GWAS, several candidate genes within or surrounding genetic loci which are thought to play roles in b cell function, in particular, in proinsulin processing and secretion, have been examined in mechanistic studies.Gene editing tools have quickly replaced techniques such as shRNA-based silencing and HDR-mediated deletion to become a mainstream technique in studies of gene function.For example, the critical b cell-enriched NEUROD1 and SLC30A8 genes were deleted in EndoC-bH1 cells using these approaches in recent studies (243).Similarly, pancreatic duodenum homeobox-1 (PDX1), an important regulator of the INS gene, was also mutated by CRISPR-Cas9 resulting in a line with defective glucose-induced Ca 2+ influx and insulin secretion (244).Our laboratory has inactivated the type 2 diabetes-related STARD10 and FCHSD2 genes in EndoC-bH1 cells using a lentiviral approach and demonstrated effects on insulin secretion (and see above) (117).Furthermore, Fang et al. used CRISPR screening technology and identified several genes involved in insulin regulation in mouse MIN6 cells (172).\t\n\ninsulin secretion.We begin by providing examples of genes and loci associated with altered T2D risk.Finally, we review the CRISPR tools that may offer the potential to correct these variants in the human b cell.",
+      "\t\n\nT2D loci were also identified at clusters of noncoding RNAs with roles in islet  cell function.One locus includes a set of microRNAs specifically expressed in islet  cells, the maternally expressed noncoding RNA MEG3, and the paternally expressed gene DLK1.Targets of these microRNAs increase  cell apoptosis 40 , and reduced Meg3 expression impairs insulin secretion 41 .DLK1 inhibits adipocyte differentiation, thereby protecting against obesity 3 , and promotes pancreatic ductal cell differentiation into  cells, increasing insulin secretion 42,43 .Other variants near MEG3 have been associated with type 1 diabetes 44 (EAS and EUR LD r 2 = 0 with EAS lead variant).The other noncoding RNA locus is the MIR17HG cluster of miRNAs, which regulate glucose-stimulated insulin secretion and pancreatic  cell proliferation stress 45 ; one of these microRNAs, miR-19a, affects hepatic gluconeogenesis 46 .Yet another T2D locus is located near TRAF3, which is a direct target of the MIR17HG microRNA cluster and promotes hyperglycaemia by increasing hepatic glucose production 47,48 .The T2D association results suggest that these noncoding RNAs influence disease susceptibility."
+    ],
+    [
+      "\tThis\nphosphorylation triggers the activation of the docking protein IR substrate 1 (IRS1), which\nsubsequently activates phosphatidylinositol 3-kinase (PI3K) and RAC serine/threonineprotein kinase 2 (AKT2), which has a critical role in glucose metabolism. PI3K and AKT2\nactivation promotes the translocation of glucose transporter 4 (GLUT4) and the free fatty\nacid (FFA) transporter CD36 from intracellular stores to the plasma membrane, thereby\n\nNat Rev Cardiol. Author manuscript; available in PMC 2021 February 01. Tan et al. Page 48\n\nAuthor Manuscript\nAuthor Manuscript\n\nleading to increased glucose and FFA uptake.",
+      "\tProtein kinase B (c-Akt) in phosphatidylinositol-3-OH\nkinase\nsignal\ntransduction. Nature. 1995;376(6541):599-602.\ndoi:10.1038/376599a0\n\n53. Herzig S, Long F, Jhala US, et al. CREB regulates hepatic gluconeogenesis\nthrough\nthe\ncoactivator\nPGC-1. Nature. 2001;413(6852):179-183.\ndoi:10.1038/35093131\n\n54. Matsumoto M, Pocai A, Rossetti L, Depinho RA, Accili D. Impaired regulation of\nhepatic glucose production in mice lacking the forkhead transcription factor\nFoxo1 in liver. Cell Metab. 2007;6(3):208-216. doi:10.1016/j.cmet.2007.08.006\n\n55. Wang ND, Finegold MJ, Bradley A, et al. Impaired energy homeostasis in\nC/EBP alpha knockout mice. Science. 1995;269(5227):1108-1112.\ndoi:10.1126/science.7652557\n\n56.\tIt exerts its functions through\n\nactivating the phosphatidylinositol-3-kinase (PI3K)-AKT signaling pathway and\nphosphorylating a variety of substrates, including glycogen synthase kinase-3 (GSK3)\n51\n\n, the forkhead (FOXO) transcription factors, and cAMP regulatory element-binding\n\nprotein (CREB)\n\n52\n\ngluconeogenesis\n\n. CREB, FOXO1, and C/EBP are transcription factors involved in\n\n5355\n\n. The detailed mechanisms of how insulin maintains albumin\n\nexpression require further investigation. Insulin resistance occurs in patients with sepsis\n\n56\n\n, obesity and diabetes\n\n57\n\n, implying\n\na role for severe or persistent inflammation.",
+      "\t\n\n) including PABPC4, NRBP1, CALCRL, CTC-498M16.4,and FADS1.Shared TWAS associations suggested the involvement of glucose and energy homeostasis via PKB/AKT signaling or epigenetic modulator (methylation, acetylation, or lncRNA) in RHR and T2D/cardiometabolic, and provided potential biological shared pathways, mechanisms, or potential therapeutic targets to follow-up in the future.",
+      "\t\n\nThe above discussion remarkably converges on the TGF-beta signaling effector SMAD3.TGF-beta signaling is involved in the regulation of insulin gene transcription, pancreatic islets b cell function, and glucose tolerance and energy homeostasis [36,[59][60][61].SMAD3 is known to localize at insulin gene promoter and repress insulin gene transcription [61].SMAD3 knock-out mice are associated with improved glucose tolerance and insulin sensitivity [36].Exhibiting altered expression of genes related to adipogenesis, lipid accumulation, and fatty acid b oxidation, these mice show resistance to obesity and insulin resistance induced by high fat diet [36,59].Further, levels of TGF-beta1 have been found to positively correlate with adiposity in human subjects [59].Also, systemic blockade of TGF-beta signaling has been found to protect mice from obesity, diabetes and hepatic steatosis [59].Indeed, pharmacological manipulation of TGF-beta signaling is considered to offer a potential therapeutic strategy in obesity and diabetes [59,60].",
+      "\tSignal transduction\n\nMAPK1 is an important regulator of -cell function (Lawrence et al, 2008), for example contributing directly to short-versus long-term insulin response and regulation of pro-apoptotic CHOP10 (Lawrence et al, 2007).MAPK1 constitutes the center of a regulatory network implicated in elevated free fatty acid (FFA) levels (Sengupta et al, 2009) common in T2D patients.MAPK/ERK signalling is exacerbated by FFA that lead to dephosphorylation of cascade proteins by PP2A/PPP2R4 (Guo et al, 2010) pointing towards a certain level of interwovenness between the identified processes, in this case signal transduction (adaptation category) and ER stress (dysfunction/cell death category, cf. Figure 5B). (Figure 2C) CDK5R1 acts as an activator of CDK5 (Ubeda et al, 2004) whose expression is regulated by glucose and which inhibits insulin secretion (Wei et al, 2005).Hyperglycaemia-caused overactivation of CDK5 may contribute to -cell glucotoxicity (Ubeda et al, 2006). (Figure S4C)",
+      "\tThe binding of insulin with its ligand specific\nreceptor increases glucose metabolism, lipid synthesis\nand cellular proliferation via PKB/AKT signaling [27, 28]. In fact, dysregulation of PKB/AKT signaling provokes a\nbroad range of diseases such as cancer, diabetes and heart\ndisease [29, 30]. CTMP was first identified as a PKB/AKT\nbinding partner with tumor-suppressor function. PKB/\nAKT is negatively regulated by the binding of CTMP\nwith the C-terminal regulatory domain of pPKB/AKT\n[31, 32]. Together with CTMP, LETM1 is associated with\nmitochondrial morphology via optic atrophy 1 (OPA1)\nregulation [33].",
+      "\t\n\nWith T2D status, and with increases in fasting glucose, fasting insulin and BMI, we observed lower expression of genes involved in endoplasmic reticulum protein localization and translational elongation.For T2D, the most significant trends were for decreased expression of cellular respiration genes (q-value  1.4  10  35 ), consistent with previous observations in skeletal muscle samples from T2D and NGT individuals following hyperinsulinemic-euglycemic clamp 7 .Mitochondrial regulatory protein PGC-1alpha (PPARGC1A) was identified by Mootha et al. 7 as a potential master regulator of mitochondrial expression.We observed lower, non-significantly different expression levels of PPARGC1A (b   0.24, q-value  0.57) in individuals with T2D.Decreased mitochondrial function is a component of the mTOR pathway which is dysregulated in metabolic diseases; downregulation of the pathway shifts cells away from protein synthesis and cell growth and towards protein catabolism 8 .Consistent with this, for T2D, we observed lower expression of genes involved in generation of precursor metabolites, translational elongation and higher expression of genes involved in protein polyubiquitination (Fig. 1c).",
+      "\t\n\nTwo negative feedback loops in this insulin signaling pathway are of interest.Additionally to tyrosine phosphorylation, both the insulin receptor and IRS proteins are also phosphorylated on serine residues, which may attenuate ) inhibition under certain conditions described in the review; green: insulinomimetic effects of zinc; red: effects of zinc deficiency leading to insulin resistance.After binding of insulin to the  subunits of the tetrameric insulin receptor, the kinase activity of the  subunit is stimulated, which results in transphosphorylation of the  subunit [35,130].This induces phosphorylation of members of the IRS family and subsequent interaction with signaling molecules like the p85 subunit of the PI3K [131].PI3K in turn triggers phosphorylation of PDK1, a serine kinase that activates Akt/PKB [132,133].Akt leads to stimulation of GLUT 4 translocation in adipocytes and to inhibition of GSK-3, thereby allowing activation of glycogen synthase in adipocytes, translocation of GLUT to the cell surface and induction of glucose metabolism [35,[134][135][136][137][138][139][140][141].In addition, inhibition of GSK-3 results in enhanced protein synthesis and gene expression [35,142].Zinc leads to tyrosine phosphorylation of the  subunit of the insulin-receptor [143 a ] and to inhibition of PTP1B which dephosphorylates the insulin receptor, thus increasing phosphorylation of the receptor [144 b ].Akt is activated by zinc in a PI3K-dependent way [143 c ] and zinc inhibits GSK-3, just like insulin [145 d ].Moreover, zinc plays a role in glucose transport since it is part of IRAP, a molecule probably required for maintenance of normal GLUT levels [129 e ].Zn: zinc.\t\n\nsignaling by decreasing insulin-stimulated tyrosine phosphorylation.This is mediated by PI3K, Akt, GSK-3 and mammalian target of rapamycin [35].GSK-3 is capable of phosphorylating IRS-1, subsequently converting this molecule into an inhibitor of the insulin receptor tyrosine kinase activity in vitro and in insulin-resistant rat muscle after insulin stimulation [141,158].A second mechanism negatively influencing insulin signaling is the rapid dephosphorylation of the insulin receptor and its substrates by protein tyrosine phosphatase 1B (PTP1B) [35].",
+      "\tDiscussion\n\nThe G protein/cAMP/PKA mediated signal transduction pathway is of high importance for growth, cell differentiation and metabolism due to extracellular ligands.The a-subunit of stimulatory G proteins Gsa is crucial for mediating these effects.In the present study, we report the positive results of the largest mutation screening of the a subunit of stimulatory G proteins described so far, leading to the identification of two new hotspots and 33 mutations that have not been reported before.Furthermore, we demonstrate for the first time a connection between the severity of the mutation and the phenotypical signs of subcutaneous calcifications and brachymetacarpia in patients with PHPIa.",
+      "\t\n\nFigure 1: Schematic representation of the insulin-signaling pathway.Dashed light-blue line borders indicate insulin-signaling inhibitor proteins.PTPRF = protein tyrosine phosphatase receptor type F; ENPP1 = ectonucleotide pyrophosphatase/phosphodiesterase 1; PTPN1 = protein tyrosine phosphatase nonreceptor type 1; IRS = insulin receptor substrate; PI3K = phosphoinositides 3 kinase; nck = noncatalytic region of tyrosine kinase adaptor protein 1; INPPL1 = inositol polyphosphate phosphatase-like 1; TRIB3 = tribbles homolog 3; mTOR = mammalian target of rapamycin; Foxo = forkhead box protein O1; BAD = Bcl-2-associated death promoter; PHAS-I = phosphorylated heatand acid-stable protein regulated by insulin; and p70S6K = p70-ribosomal S6 kinase.",
+      "\t\n\nand although complex, occur largely in a canonical sequence resulting in a single outcome (Fig. 2) -hence perturbation at any stage in this sequence will almost inevitably result in decreased release of the hormone into the portal circulation.In contrast, variations in function of a single gene product involved in insulin signalling are unlikely to have an effect on all aspects of insulin action and hence would not present with major effects on glucose metabolisms (Fig. 2).",
+      "\t\n\nUnder normal conditions, the glucose regulation process commences when insulin binds to its corresponding insulin receptor (IR), which results in auto-phosphorylation of its tyrosine residues [171].This allows IR to phosphorylate insulin receptor substrate 1 (IRS-1) on tyrosine residues, which further triggers the phosphorylation of downstream molecules and induces the phosphatidylinositol 3-kinase (PI3K) signaling transduction cascade [171,172].PI3K, when activated, results in the conversion of phosphatidylinositol 4,5-bisphosphate (PIP2) to phosphatidylinositol (3,4,5)-triphosphate (PIP3).Consequently, downstream 3-phosphoinositide dependent protein kinase1 (PDK1) is activated, which subsequently activates, among other kinases, Akt, resulting in phosphorylation of its substrate (AS160), which regulates translocation of glucose transporter 4 (GLUT4) to the transmembrane and allows for glucose uptake and regulation of protein and lipid metabolism [171,172] (Figure 4).\t\n\nUnder normal conditions, the glucose regulation process commences when insulin binds to its corresponding insulin receptor (IR), which results in auto-phosphorylation of its tyrosine residues [171].This allows IR to phosphorylate insulin receptor substrate 1 (IRS-1) on tyrosine residues, which further triggers the phosphorylation of downstream molecules and induces the phosphatidylinositol 3-kinase (PI3K) signaling transduction cascade [171,172].PI3K, when activated, results in the conversion of phosphatidylinositol 4,5-bisphosphate (PIP2) to phosphatidylinositol (3,4,5)-triphosphate (PIP3).Consequently, downstream 3-phosphoinositide dependent protein kinase1 (PDK1) is activated, which subsequently activates, among other kinases, Akt, resulting in phosphorylation of its substrate (AS160), which regulates translocation of glucose transporter 4 (GLUT4) to the transmembrane and allows for glucose uptake and regulation of protein and lipid metabolism [171,172] (Figure 4).Insulin binds to the insulin receptor, causing autophosphorylation of its tyrosine residues.This causes phosphorylation of insulin receptor substrate-1 (IRS-1) on its tyrosine residues, which leads to the phosphorylation of the phosphatidylinositol 3-kinase (PI3K) signaling transduction cascade.PI3K catalyzes the phosphorylation of phosphatidylinositol 4,5-bisphosphate (PIP2) to phosphatidylinositol (3,4,5)-triphosphate (PIP3).PIP3 activates 3-phosphoinositide-dependent protein kinase-1 (PDK-1) as a result, which in turn, phosphorylates the downstream protein \"AKT\", which phosphorylates its substrate AS160.AS160 regulates glucose translocator 4 (GLUT4) and aids in its translocation to the plasma membrane, where it allows glucose to flow.\t\n\nFigure 4. PI3K/Akt signaling pathway.Insulin binds to the insulin receptor, causing autophosphorylation of its tyrosine residues.This causes phosphorylation of insulin receptor substrate-1 (IRS-1) on its tyrosine residues, which leads to the phosphorylation of the phosphatidylinositol 3-kinase (PI3K) signaling transduction cascade.PI3K catalyzes the phosphorylation of phosphatidylinositol 4,5-bisphosphate (PIP2) to phosphatidylinositol (3,4,5)-triphosphate (PIP3).PIP3 activates 3-phosphoinositide-dependent protein kinase-1 (PDK-1) as a result, which in turn, phosphorylates the downstream protein \"AKT\", which phosphorylates its substrate AS160.AS160 regulates glucose translocator 4 (GLUT4) and aids in its translocation to the plasma membrane, where it allows glucose to flow.\t\n\nIn GDM pregnancies, decreased expression levels of the following insulin signaling components: IRS1, PIP3, PIK3, and GLUT4, have been reported [173][174][175].Furthermore, alternative phosphorylation of IRS1 at serine residues was exhibited in GDM patients, which prevents the PI3K signaling cascade from taking place, and thus, inhibits insulin action [176].The exact underlying mechanism through which disrupted insulin signaling Insulin binds to the insulin receptor, causing autophosphorylation of its tyrosine residues.This causes phosphorylation of insulin receptor substrate-1 (IRS-1) on tyrosine residues, which leads to the phosphorylation of the phosphatidylinositol 3-kinase (PI3K) signaling transduction cascade.PI3K catalyzes the phosphorylation of phosphatidylinositol 4,5-bisphosphate (PIP2) to phosphatidylinositol (3,4,5)-triphosphate (PIP3).PIP3 activates 3-phosphoinositide-dependent protein kinase-1 (PDK-1) as a result, which in turn, phosphorylates the downstream protein \"AKT\", which phosphorylates its substrate AS160.AS160 regulates glucose translocator 4 (GLUT4) and aids in its translocation to the plasma membrane, where it allows glucose to flow.",
+      "\tIn conclusion, by employing a combination of pharmacological and genetic gain- and loss-of-function genetic approaches,\nour studies show that the activation of the TGR5 signaling\npathway counteracts the metabolic dysfunction associated\nwith diabesity. TGR5 activation results in a range of beneficial\nmetabolic effects that include resistance to weight gain and\nhepatic steatosis, preservation of liver and pancreatic function,\nand the maintenance of glucose homeostasis and insulin sensitivity. These effects are due to enhanced mitochondrial function\nin muscle, BAT, and enteroendocrine cells, resulting in an\nincrease in energy expenditure and incretin secretion (Figure 7).",
+      "\tInsulin and DHEA signaling\n\nIn addition to the changes in central metabolic pathways, we found significant regulation of hormonal pathways.We could reproduce the transcriptional regulation of IGFs (insulin-like growth factors) and IGFBPs (IGF binding proteins).IGF1 is a major growth signaling molecule that is transcriptionally activated by insulin and growth hormone (GH) under good nutrient conditions, thereby allowing cell growth and proliferation (Kelley et al., 1996)  sion is strongly reduced, while its deactivating binding proteins IGFBP1 and IGFBP2 are up-regulated.",
+      "\tPost-Translational Modifications Control PPAR Signaling Affecting Drug Effectiveness\n\nDistinct biological networks converge into PPAR signaling and several molecular effectors directly or indirectly regulate its activation [19], resulting in finely regulated tissue-specific responses.A large number of endogenous/exogenous compounds, coactivators, and corepressors affect PPAR activity, inducing different signal transduction pathways and biological effects.Beyond epigenetic, transcriptional, and translational regulatory mechanisms, different post-translational modifications (PTMs), such as phosphorylation, acetylation, -Olinked N-acetylglucosamine (O-GlcNAc), SUMOylation, and ubiquitination, contribute to PPAR activation [120].Each PTM represents a separate feature to be exploited for cell-or tissue-specific modulation [17], allowing rapid responses to internal and external stimuli.Of note, PTMs control PPAR activity, potentially influencing ligand affinity, DNA binding, coactivator recruitment, and/or proteasomal degradation."
+    ],
+    [
+      "\tA GLIMPSE INTO THE FUTURE\n\nGetting from the extremes to a comprehensive view of diabetes genetics.As described above, success in the identification of genes impacting on individual risk of diabetes has come from two distinct approaches to gene discovery.The first, linkage mapping within monogenic and syndromic families, has delivered causal variants that are rare but highly penetrant.The second, large-scale association mapping, is now yielding growing numbers of common variants: these have, at best, modest effect sizes and low penetrance.Several genes are featured in the lists generated by both approaches.For example, mutations in KCNJ11, PPARG, WFS1, and TCF2 (HNF1B) are causal for syndromic and/or monogenic forms of diabetes, while common variants in these same genes influence predisposition to typical type 2 diabetes (55,56,64 -66).While common variants in GCK (another gene causal for MODY) do not influence type 2 diabetes risk per se, they have a clear impact on fasting glucose levels within the population (88).\tLESSONS LEARNED FOR MULTIFACTORIAL DISEASE\n\nMonogenic and syndromic forms account for only a small, though highly informative, proportion of cases of nonautoimmune diabetes.The challenge for medical science lies in bringing equivalent mechanistic insights and translational benefits to the hundreds of millions of people already affected by, or at risk of, more common, typical forms of diabetes.For type 2 diabetes, there is abundant evidence that individual susceptibility is influenced by both the combination of genetic variation at multiple sites and a series of environmental exposures encountered during life (52).Tracking down the specific genetic variants involved has been tougher than for monogenic forms of disease, since the correlations between genotype and phenotype are far weaker (53,54).However, recent efforts have now identified at least 17 confirmed type 2 diabetessusceptibility variants (  (69), and development and exploitation of this methodology has had the greatest impact on susceptibility gene discovery.Even so, many of these discoveries have been hard-won.One reason for this is that the \"candidate\" gene-based approach has proved, with notable exceptions (55,56), to be an inefficient route to susceptibility gene discovery; it is only with the advent of functionally agnostic genome-wide approaches that the floodgates have opened (70).Another reason is that detection of the variants of modest effect that appear to be responsible for much of type 2 diabetes susceptibility (per-allele odds ratios [ORs] 1.10 -1.40, for risk-allele frequencies 10 -90%) has required association studies conducted in extremely large sample sizes (thousands of individuals) (54).Variants within TCF7L2 have the largest effects seen so far, with a per-allele OR of 1.4 (57): the 15% of Europeans carrying two copies of the risk allele are at approximately twice the lifetime risk of type 2 diabetes as the 40% who have none.",
+      "\tLessons from GWA studies\n\nThe most important lesson is the demonstration of the power of genetics to provide novel insights into disease aetiology.Of the 11 genes or regions now implicated in type 2 diabetes, only four were strong biological candidates (PPARG, KCNJ11, WFS1, TCF2) [8,9,[11][12][13][14].Three had some corroborating evidence (IGF2BP2, the HHEX-IDE gene region, SLC30A8) [2][3][4][5][6], but for the remainder, evidence of their link to diabetes came as a complete surprise.These studies provide the first evidence implicating Wnt-signalling pathways (TCF7L2) and cell cycle control (CDKAL1 and CDKN2A/2B) in the pathogenesis of type 2 diabetes [2,3,5,6].For type 1, the key new discoveries highlight the contribution to disease pathogenesis of the PTPN gene family and IL-2 signalling [1,7].",
+      "\t\n\nMajor consortia addressing the genetic basis of diabetes complications and associated traits",
+      "\t\n\nGenetic determinants of diabetes and metabolic syndromes.",
+      "\t\n\nUnfortunately, these questions are not yet answered.The early 1990s was the beginning of the era of molecular biol- ogy, and it was generally assumed that within a few years this powerful new technology would identify the genetic defects in type 2 diabetes.Indeed, the genetic basis for many monogenic forms of diabetes has been discovered such as mitochondrial genome defects and the association with diabetes and deafness, Wolfram's syndrome, several rare syndromes of extreme insulin resistance and obesity, and many of the MODY syndromes (maturity onset diabetes of youth).Still, these account for only a small proportion of diabetes.",
+      "\t\n\nGenome-wide association studies (GWAS) have made a significant contribution to our current knowledge of the role(s) of genetic variation in population-level susceptibility to T1D (Mychaleckyj et al., 2010).",
+      "\t\nIt has proven to be challenging to isolate the genes underlying the genetic components conferring susceptibility to type 1 and type 2 diabetes.Unlike previous approaches, 'genome-wide association studies' have extensively delivered on the promise of uncovering genetic determinants of complex diseases, with a number of novel disease-associated variants being largely replicated by independent groups.This review provides an overview of these recent breakthroughs in the context of type 1 and type 2 diabetes, and outlines strategies on how these findings will be applied to impact clinical care for these two highly prevalent disorders.\t\n\nIt has proven to be challenging to isolate the genes underlying the genetic components conferring susceptibility to type 1 and type 2 diabetes.Unlike previous approaches, 'genome-wide association studies' have extensively delivered on the promise of uncovering genetic determinants of complex diseases, with a number of novel disease-associated variants being largely replicated by independent groups.This review provides an overview of these recent breakthroughs in the context of type 1 and type 2 diabetes, and outlines strategies on how these findings will be applied to impact clinical care for these two highly prevalent disorders.",
+      "\t\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.",
+      "\t\n\nThe molecular mechanisms involved in the development of type 2 diabetes are poorly understood.Starting from genome-wide genotype data for 1924 diabetic cases and 2938 population controls generated by the Wellcome Trust Case Control Consortium, we set out to detect replicated diabetes association signals through analysis of 3757 additional cases and 5346 controls and by integration of our findings with equivalent data from other international consortia.We detected diabetes susceptibility loci in and around the genes CDKAL1, CDKN2A/CDKN2B, and IGF2BP2 and confirmed the recently described associations at HHEX/IDE and SLC30A8.Our findings provide insight into the genetic architecture of type 2 diabetes, emphasizing the contribution of multiple variants of modest effect.The regions identified underscore the importance of pathways influencing pancreatic beta cell development and function in the etiology of type 2 diabetes.",
+      "\t\n\nIn the past decade, genome-wide association (GWAS) and sequencing studies have identified genetic loci that help explain the inherited basis of T2D and glycemic traits.These studies are providing insights into the genetic architecture of T2D, including the number, frequency and effect sizes of risk variants in populations around the world.The polygenic nature of T2D is now well established, and multiple risk variants are being identified at some loci, suggesting allelic heterogeneity.Concurrently, increasing numbers of genes and variants have been implicated in monogenic forms of diabetes, including maturity onset diabetes of the young (MODY) and neonatal diabetes (7), and at least five genes have been implicated in both monogenic and polygenic diabetes (8).A recent simulation study evaluated genetic architectures for consistency with results from T2D genetic studies and found that many different disease models were still possible with respect to the number of loci, allele frequencies and level of selective pressure (9).Ongoing studies should more substantially narrow the bounds on feasible architectures (9).",
+      "\t\n\nIn the case of relatively uncommon monogenic and syndromic forms of diabetes, such as maturity onset diabetes of the young (MODY) and neonatal diabetes, identification of rare causal mutations has delivered both knowledge and clinical translation [4,5].In contrast, progress in unravelling the genetic architecture of more typical, common, multifactorial type 2 diabetes has been painfully slow [6].The reasons have been well-rehearsed [7].The complex web of susceptibility factors-genetic, environmental, social-that contributes to individual risk of developing type 2 diabetes means that most predisposing genetic variants will have only a modest marginal impact on disease risk.The majority of genetic studies performed to date have simply had insufficient power to uncover these reliably [7].The few type 2 diabetes-susceptibility variants convincingly demonstrated-notably the P12A variant in PPARG and E23K in KCNJ11 [8,9]-have only modest effects on disease risk (odds ratios ~1.2), far too small to offer (either individually or in combination) clinically useful predictive testing.Since these variants lie within genes whose products are already known to be therapeutic targets, these particular discoveries have also had limited capacity to deliver novel pathophysiological insights.Among those working on the genetics of type 2 diabetes, there was growing apprehension that these two genes might be providing a representative view of the genetic architecture of type 2 diabetes.",
+      "\t\n\nThe molecular mechanisms involved in the development of type 2 diabetes are poorly understood.Starting from genome-wide genotype data for 1924 diabetic cases and 2938 population controls generated by the Wellcome Trust Case Control Consortium, we set out to detect replicated diabetes association signals through analysis of 3757 additional cases and 5346 controls and by integration of our findings with equivalent data from other international consortia.We detected diabetes susceptibility loci in and around the genes CDKAL1, CDKN2A/CDKN2B, and IGF2BP2 and confirmed the recently described associations at HHEX/IDE and SLC30A8.Our findings provide insight into the genetic architecture of type 2 diabetes, emphasizing the contribution of multiple variants of modest effect.The regions identified underscore the importance of pathways influencing pancreatic beta cell development and function in the etiology of type 2 diabetes.",
+      "\t\nWhilst the heritable nature of Type 2 diabetes has been recognized for many years, only in the past two decades have linkage analyses in families and genome-wide association studies in large populations begun to reveal the genetic landscape of the disease in detail.Whilst the former have provided a powerful means of identifying the genes responsible for monogenic forms of the disease, the latter highlight relatively large genomic regions.These often harbour multiple genes, whose relative contribution to exaggerated disease risk is uncertain.In the present study, the approaches that have been used to dissect the role of just a few (TCF7L2, SLC30A8, ADCY5, MTNR1B and CDKAL1) of the ~500 genes identified at dozens of implicated loci are described.These are usually selected based on the strength of their effect on disease risk, and predictions as to their likely biological role.Direct determination of the effects of identified polymorphisms on gene expression in disease-relevant tissues, notably the pancreatic islet, are then performed to identify genes whose expression is affected by a particular polymorphism.Subsequent functional analyses then involve perturbing gene expression in vitro in b-cell lines or isolated islets and in vivo in animal models.Although the majority of polymorphisms affect insulin production rather than action, and mainly affect the b cell, effects via other tissues may also contribute, requiring careful consideration in the design and interpretation of experiments in model systems.These considerations illustrate the scale of the task needed to exploit genome-wide association study data for the development of new therapeutic strategies.\t\n\nWhilst the heritable nature of Type 2 diabetes has been recognized for many years, only in the past two decades have linkage analyses in families and genome-wide association studies in large populations begun to reveal the genetic landscape of the disease in detail.Whilst the former have provided a powerful means of identifying the genes responsible for monogenic forms of the disease, the latter highlight relatively large genomic regions.These often harbour multiple genes, whose relative contribution to exaggerated disease risk is uncertain.In the present study, the approaches that have been used to dissect the role of just a few (TCF7L2, SLC30A8, ADCY5, MTNR1B and CDKAL1) of the ~500 genes identified at dozens of implicated loci are described.These are usually selected based on the strength of their effect on disease risk, and predictions as to their likely biological role.Direct determination of the effects of identified polymorphisms on gene expression in disease-relevant tissues, notably the pancreatic islet, are then performed to identify genes whose expression is affected by a particular polymorphism.Subsequent functional analyses then involve perturbing gene expression in vitro in b-cell lines or isolated islets and in vivo in animal models.Although the majority of polymorphisms affect insulin production rather than action, and mainly affect the b cell, effects via other tissues may also contribute, requiring careful consideration in the design and interpretation of experiments in model systems.These considerations illustrate the scale of the task needed to exploit genome-wide association study data for the development of new therapeutic strategies.",
+      "\tA\n\nnumber of studies have implicated a genetic basis for type 2 diabetes (1).The discovery of monogenic forms of the disease underscored the phenotypic and genotypic heterogeneity, although monogenic forms account for only a few percent of the disease (1).Defining the genetic basis of the far more common polygenic form of the disease presents more difficulties (2,3).Nevertheless, some interesting results have recently emerged.A genome scan of Hispanic-American families (330 affected sib-pairs [ASPs]) found linkage to chromosome 2q37 (logarithm of odds [LOD] 4.15) (4), and the causative gene has been recently reported (5).A number of other genome scans in various racial groups have identified other putative susceptibility loci (6 -8).The largest genome-wide scan for type 2 diabetes loci reported to date studied 477 Finnish families (716 ASPs) and found evidence for linkage to chromosome 20q12-13.1(LOD 2.06 at D20S107) (9).Interestingly, similar results have been reported by at least three other groups (10 -12).",
+      "\t\n\nThe earliest successes for genetic discovery in diabetes and obesity arose from the study of monogenic and syndromic forms of disease, for which the segregation of rare, but highly penetrant, alleles could be tracked using family-based linkage approaches that are well suited to that setting.Maturity-onset diabetes of the young, for example, accounts for ~1-2% of cases of nonautoimmune diabetes presenting in early adulthood. 14ost cases of maturity-onset diabetes of the young are now known to result from rare coding mutations in either the hepatocyte nuclear factor-1A (HNF1A) or glucokinase (GCK) genes.In patients with these conditions, a precise molecular diagnosis brings important benefits in terms of individual prognostication and treatment optimization. 14These discoveries have also generated valuable insights into the cellular and molecular processes-operating in the pancreatic islet and other tissuesthat control glucose homeostasis. 15To give a further example, identification of the mutations underlying syndromic forms of obesity, including Bardet-Biedl, has uncovered a whole class of diseases, the ciliopathies, that result from defects in the genetic control of ciliary development and function. 16arly attempts to apply family-based linkage approaches to more common forms of diabetes and obesity proved to be unrewarding.In their seminal paper in 1996, Risch and Merikangas 17 highlighted the merits of association, as opposed to linkage, analysis for the detection of the low-penetrance alleles most likely to be relevant to common disease.It would take a decade before the density of available markers would allow genomewide screens for association to be implemented. 18In the interim, association analyses that focused attention on genetic variation within presumed biological candidates resulted in some successes in risk variant detection.For T2D, these included associations with variants in the genes encoding key therapeutic targets such as the peroxisome proliferator-activated receptor- (PPARG) and the islet K ATP channel (KCNJ11); 19,20 an equivalent example for obesity would relate to variants in the melanocortin 4 receptor (MC4R) gene. 21More often than not, however, these candidate gene studies were plagued by inadequate sample size and overly liberal significance thresholds, a lethal combination that led to a profusion of unreliable reports of association. 22][25][26] Given the content of the genotyping arrays employed, these studies have focused on the detection of signals attributable to common variants (typically of a minor allele frequency above 5%).9][30][31] In the case of T2D, the current count of risk loci, each confirmed to genome-wide significance, is around 65; [27][28][29] for BMI and obesity, the count is about half that number. 25Looking across these loci, several important features emerge.",
+      "\t\n\nThe molecular mechanisms involved in the development of type 2 diabetes are poorly understood.Starting from genome-wide genotype data for 1924 diabetic cases and 2938 population controls generated by the Wellcome Trust Case Control Consortium, we set out to detect replicated diabetes association signals through analysis of 3757 additional cases and 5346 controls and by integration of our findings with equivalent data from other international consortia.We detected diabetes susceptibility loci in and around the genes CDKAL1, CDKN2A/CDKN2B, and IGF2BP2 and confirmed the recently described associations at HHEX/IDE and SLC30A8.Our findings provide insight into the genetic architecture of type 2 diabetes, emphasizing the contribution of multiple variants of modest effect.The regions identified underscore the importance of pathways influencing pancreatic beta cell development and function in the etiology of type 2 diabetes.",
+      "\t\n\nGenetic predisposition to diabetes mellitus type 2: will large collaborative efforts be able to overcome the geneticist's nightmare?"
+    ],
+    [
+      "\tGenes\n\n2][43][44][45][46][47] Twin studies need to be considered carefully, however, as the intrauterine environments of dizygotic-twin (separate placentas), monozygotic-twin (60-70% share one placenta), and singleton pregnancies (one placenta without competition for maternal nutrients) will all be diff erent, and this can be a confounder in the inter pretation of eff ects. 44A large study from Sweden on familial risk of type 2 diabetes showed that the relative risks were highest in individuals with at least two aff ected siblings, irrespective of parental diabetes status. 42This fi nding suggests that a recessive pattern of inheritance from uncommon genetic defects, the sharing of similar intrauterine, postnatal, or both environments by siblings (eg, breastfeeding or bottle feeding or childhood nutrition), or a combination of these factors is important.9][50] A greater number of these loci are associated with impaired -cell function (KCNJ11, TCF7L2, WFS1, HNF1B, SLC30A8, CDKAL1, IGF2BP2, CDKN2A, CDKN2B, NOTCH2, CAMK1D, THADA, KCNQ1, MTNR1B, GCKR, GCK, PROX1, SLC2A2, G6PC2, GLIS3, ADRA2A, and GIPR) than impaired insulin sensitivity (PPARG, IRS1, IGF1, FTO, and KLF14) or obesity (FTO). 38,48,50Of these, TCF7L2 is the strongest susceptibility locus for type 2 diabetes, being associated with -cell dysfunction. 48Most patients with monogenic forms of diabetes also have gene defects that aff ect islet -cell function. 51,52Nevertheless, only around 10% of the heritability of type 2 diabetes can be explained by susceptibility loci identifi ed so far, with each locus having a low eff ect size. 36The remaining heritability might be related to a large number of less common variants (allele frequency <5%) that are diffi cult to fi nd with current approaches of genome-wide association studies, and/or epigenetic phenomena.",
+      "\t\n\nAnother component of T1D that aids in our understanding of the disease and assessment of risk is genetic inheritance.A longterm (up to 40 year) study of twin pairs in Finland revealed a monozygotic (MZ) pairwise concordance for T1D of 27.3% while the concordance for dizygotic (DZ) twins was 3.8% [4].The impact of genetics was further made clear in this study because upon diagnosis of T1D in one twin, the length of time to diagnosis in the other twin in the concordant pairs was a maximum of 6.9 years in MZ twins and 23.6 years in DZ twins [4].In addition to measuring incidence of T1D in twin studies, islet antigen-specific autoimmunity can also be determined.As a precursor to T1D, autoimmunity is defined as the presence of antibodies to islet autoantigens in sera [5].In another study, 83 unaffected monozygotic twins were followed for nearly 44 years and incidence of autoimmunity or diagnosis of T1D was recorded.This study showed a 65% cumulative incidence of T1D by 60 years of age and more than 75% tested positive for an islet autoantibody during the course of the study.Once autoimmunity was established, the risk of diabetes was 89% within 16 years of the first positive autoantibody test.\t\n\nClearly genetics play an important role in the T1D disease process as both MZ and DZ twins have the same environmental exposures but different concordance rates and length to diagnosis of the second twin.Numerous genes have been associated with T1D, the most significant being the HLA region on chromosome 6 [6].More than 90% of type 1 diabetics carry HLA alleles DR3-DQ2 or DR4-DQ8 compared to no more than 40% of the general population [7].Alleles at HLA-DQB1 are known to be, in part, protective [8].Single nucleotide polymorphisms (SNPs) are also associated with T1D.A recent genome-wide association study of approximately 2,000 patients with each of 7 common, chronic diseases, including T1D, and 7,000 shared controls confirmed the association of SNPs in 5 previously identified regions with T1D and discovered 5 novel associations.However, the authors concluded that these regions, with the exception of the HLA on chromosome 6, confer only modest effects on T1D, and ''the association signals so far identified account for only a small proportion of overall familiality'' [9].These results suggest that additional genetic variants contribute to inheritance of T1D.",
+      "\t\n\nGenetic predisposition for the development of NIDDM has been strongly indicated by higher concor-dance rates in monozygotic than in dizygotic twins (Barnett et al., 1981;Newman et al., 1987), by clustering in families (Bennett, 1990), and by a strong correlation with the degree of population admixture (Zimmet et al., 1982;Chakraborty et al., 1986;Groop and Toumi, 1997).Although some rare monogenic forms of early onset NIDDM-like diseases in humans have been identified (reviewed in Froguel et al., 1997), genes responsible for the common forms of late-onset NIDDM remain unknown.Genome-wide scans for such genes have detected linkages of diabetes phenotypes with NIDDM1 on chromosome 2q in Mexican Americans (Hanis et al., 1996) and NIDDM2 on chromosome 12q in Finnish families (Mahtani et al., 1996).In a major effort, complex haplotypes in the Calpain 10 gene (CAPN10) at the NIDDM1 locus have recently been associated with increased risk for developing type II diabetes in Mexican Americans and Northern Europeans (Horikawa et al., 2000).CAPN10 is the first NIDDM gene cloned thus far.",
+      "\t\n\nAlthough there are rare monogenic, immune-mediated forms of type 1 diabetes, 2,3 the common form is thought to be determined by the actions, and possible interactions, of multiple genetic and environmental factors.The concordance for type 1 diabetes in monozygotic twins is less than 100%, and although type 1 diabetes aggregates in some families, it does not segregate with any clear mode of inheritance. 4-7Despite these complexities, knowledge of genetic factors that modify the risk of type 1 diabetes offers the potential for improved prediction, stratification of patients according to risk, and selection of possible therapeutic targets.As germ-line factors, genetic risk variants are present and amenable to study at all times -before, during, and after the development of diabetes.Thus, genetic information can serve as a potential predictive tool and provide insights into pathogenetic factors occurring during the preclinical phase of the disease, when preventive measures might be applied.\t\nIn 1976, the noted human geneticist James Neel titled a book chapter \"Diabetes Mellitus: A Geneticist's Nightmare.\" 1 Over the past 30 years, however, the phenotypic and genetic heterogeneity of diabetes has been painstakingly teased apart to reveal a family of disorders that are all characterized by the disruption of glucose homeostasis but that have fundamentally different causes.Recently, the availability of detailed information on the structure and variation of the human genome and of new high-throughput techniques for exploiting these data has geneticists dreaming of unraveling the genetic complexity that underlies these disorders.This review focuses on type 1 diabetes mellitus and includes an update on recent progress in understanding genetic factors that contribute to the disease and how this information may contribute to new approaches for prediction and therapeutic intervention.Type 1 diabetes becomes clinically apparent after a preclinical period of varying length, during which autoimmune destruction reduces the mass of beta cells in the pancreatic islets to a level at which blood glucose levels can no longer be maintained in a physiologic range.The disease has two subtypes: 1A, which includes the common, immune-mediated forms of the disease; and 1B, which includes nonimmune forms.In this review, we focus on subtype 1A, which for simplicity will be referred to as type 1 diabetes.Although there are rare monogenic, immune-mediated forms of type 1 diabetes, 2,3 the common form is thought to be determined by the actions, and possible interactions, of multiple genetic and environmental factors.The concordance for type 1 diabetes in monozygotic twins is less than 100%, and although type 1 diabetes aggregates in some families, it does not segregate with any clear mode of inheritance. 4-7Despite these complexities, knowledge of genetic factors that modify the risk of type 1 diabetes offers the potential for improved prediction, stratification of patients according to risk, and selection of possible therapeutic targets.As germ-line factors, genetic risk variants are present and amenable to study at all times -before, during, and after the development of diabetes.Thus, genetic information can serve as a potential predictive tool and provide insights into pathogenetic factors occurring during the preclinical phase of the disease, when preventive measures might be applied. Gene tic S t udiesBecause of the uncertainty regarding the number and action of genes involved in type 1 diabetes, genetic studies have tended to focus on approaches that require few assumptions about the underlying model of disease risk.The two primary approaches have been linkage studies (using pairs of affected relatives, typically siblings) and association studies (using either case-control or family-based designs).Linkage studies using affected sibling pairs seek to identify regions of the genome that are shared",
+      "\t\n\nThe marked increase of T1D incidence cannot be solely attributed to genetic risk (Snouffer, 2018).In fact, disease discordance in monozygotic twins (30-70%) strongly suggests environmental factors contribute to the aetiology of T1D (Redondo et al., 2008).These contributions may manifest through epigenetic modification including altered DNA methylation (Cepek et al., 2016;Paul et al., 2016;Stefan et al., 2014), which has been reported to play a key role in the transcriptional regulation of gene expression, and in some part, contributes to the aetiology of T1D (Stefan et al., 2014).Other environmental exposures attributable to the rising prevalence of T1D include diet (Hansen et al., 2006), gestational infections (Rei Lindehammer et al., 2012), and viral infections (Lnnrot et al., 2000).As such, it is highly likely that these non-genetic triggers interact with susceptibility genes in genetically predisposed individuals to influence the development of T1D.",
+      "\t\n\nWhile these data indicate a major role for inborn susceptibility, they also underscore the role of environment and random chance.Secular trends in diet and physical activity are associated with a rising rate of T2D, demonstrating the impact of environment.Monozygotic twins are less than 100% concordant for both T1D and T2D, demonstrating that environment and/or random chance plays a major role in disease.Formal estimates of heritability (100) and long-term follow-up of monozygotic twins ascertained without disease bias (131) confirm the role of these nongenetic factors.",
+      "\t\n\nGenetic susceptibility to type 1 diabetes (T1D) is well supported by epidemiologic evidence; however, disease risk cannot be entirely explained by established genetic variants identified so far.This study addresses the question of whether epigenetic modification of the inherited DNA sequence may contribute to T1D susceptibility.Using the Infinium HumanMethylation450 BeadChip array (450k), a total of seven long-term disease-discordant monozygotic (MZ) twin pairs and five pairs of HLA-identical, disease-discordant non-twin siblings (NTS) were examined for associations between DNA methylation (DNAm) and T1D.Strong evidence for global hypomethylation of CpG sites within promoter regions in MZ twins with TID compared to twins without T1D was observed.DNA methylation data were then grouped into three categories of CpG sites for further analysis, including those within: 1) the major histocompatibility complex (MHC) region, 2) non-MHC genes with reported T1D association through genome wide association studies (GWAS), and 3) the epigenome, or remainder of sites that did not include MHC and T1D associated genes.Initial results showed modest methylation differences between discordant MZ twins for the MHC region and T1D-associated CpG sites, BACH2, INS-IGF2, and CLEC16A (DNAm difference range: 2.2%e5.0%).In the epigenome CpG set, the greatest methylation differences were observed in MAGI2, FANCC, and PCDHB16, (DNAm difference range: 6.9%e16.1%).These findings were not observed in the HLA-identical NTS pairs.Targeted pyrosequencing of five candidate CpG loci identified using the 450k array in the original discordant MZ twins produced similar results using control DNA samples, indicating strong agreement between the two DNA methylation profiling platforms.However, findings for the top five candidate CpG loci were not replicated in six additional T1Ddiscordant MZ twin pairs.Our results indicate global DNA hypomethylation within gene promoter regions may contribute to T1D; however, findings do not support the involvement of large DNAm differences at single CpG sites alone in T1D.",
+      "\tParticipants\n\nTwo cohorts of monozygotic (MZ) and dizygotic (DZ) twins discordant for type 1 diabetes were tested for TPOA to determine the relative influence of genetic and environmental factors.Initially, type 1 diabetes-discordant twin pairs were selected from the British Diabetic Twin Study [5] and a US twin cohort [4].The basic characteristics of the twins are shown in Table 1.These individuals fulfilled the following criteria: (1) twin pairs initially disease discordant; (2) both twins available for study; (3) neither twin receiving drugs other than human insulin; (4) all had normal plasma creatinine; and (5) diabetes initially excluded in the co-twin by OGTT and random whole-blood glucose <7.0 mmol/l.Monozygosity was established using both clinical data and DNA fingerprinting (data not shown) and type 1 diabetes was defined by standard criteria [9].\t\n\nChapter 3 evaluates the heritability of TPOA, which was estimated in type 1 diabetes discordant MZ and DZ twin pairs from UK and US twin cohorts.To address the problem of limited sample size and power, a meta-analysis was carried out using structural equation model fitting.We further investigated whether the same environmental factors that caused type 1 diabetes in discordant twin pairs also caused a higher risk of thyroid autoimmunity as defined by TPOA.",
+      "\t\n\nTwin studies provide further evidence for heritability of type 1 diabetes susceptibility.Monozygotic twins are 100% genetically identical (excepting epigenetic events such as the rearrangements of immunoglobulin and T-cell receptor genes, which occur differently in each individual).Dizygotic twins share only 50% of their genetic material.In contrast to the difference in the degree of genetic similarity, both twin pairs are exposed to environmental factors that are likely equally similar for monozygotic and dizygotic twins (especially samesex dizygotic twins).Thus, the degree to which monozygotic twins show greater concordance for disease susceptibility compared with dizygotic twins indicates the degree to which genetic factors contribute to disease susceptibility [see Boomsma et al. (19) for review].\t\n\nPerhaps the most informative twin studies for this purpose are those based on large twin registries, because they avoid ascertainment bias that can confound clinic-based studies.In clinic-based studies, where ascertainment of a twin pair depends on at least one twin being affected, concordant affected pairs have two chances to be identified, whereas discordant pairs, with only one affected sibling, have only one chance.Thus, concordance rates can be overestimated using diagnosis-based ascertainment strategies [reviewed in Redondo et al. (20)].Prospective studies of initially discordant pairs can also be used to avoid this bias, and, furthermore, provide information about the rate of concordance over time.For type 1 diabetes, the concordance rate for monozygotic twins from these studies has been estimated as 21-53%, with most estimates between 30-50% [see Redondo et al. (20) and references therein].One study (21) estimated a cumulative concordance rate as high as 70%, adjusted for age of onset of the affected twin and last observation of the unaffected twin.As expected, the concordance rate increases over time as new diagnoses of diabetes are made (22).Interestingly, much of the risk to a co-twin is within the first 3 yr after the index twin's diagnosis (23), perhaps consistent with a shared environmental exposure, but also consistent with a genetic role in determining age of diagnosis (24).From the excess concordance in monozygotic compared with dizygotic twins, it has been estimated that as much as 66-72% of the variation in type 1 diabetes risk is attributable to genetic factors (21, 24a), although other studies have yielded lower estimates (23).This fraction is also referred to as the heritability, or h 2 .The concordance rate is much higher for monozygotic twins when one twin is diagnosed at an early age (23,25), suggesting that heritability might be highest for very early onset type 1 diabetes.\t\nFamily and twin studies indicate that a substantial fraction of susceptibility to type 1 diabetes is attributable to genetic factors.These and other epidemiologic studies also implicate environmental factors as important triggers.Although the specific environmental factors that contribute to immune-mediated diabetes remain unknown, several of the relevant genetic factors have been identified using two main approaches: genome-wide linkage analysis and candidate gene association studies.This article reviews the epidemiology of type 1 diabetes, the relative merits of linkage and association studies, and the results achieved so far using these two approaches.Prospects for the future of type 1 diabetes genetics research are considered.\tType 1 diabetes is an environmental disease\n\nThere are convincing data that non-genetic factors, perhaps environmental factors in early childhood, also play a role in diabetes susceptibility.First, the heritability of type 1 diabetes is only 72% or less, implying that at least a quarter of the risk of type 1 diabetes is not determined by inherited sequence variation.Consistent with this concept, the concordance rate for type 1 diabetes in monozygotic twins is estimated at 70% or less.It is possible that genetic events that distinguish monozygotic twins, such as the rearrangement of the T-cell receptor genes, or other stochastic, random events play a role in type 1 diabetes susceptibility.However, shared environmental factors are implicated by comparing the concordance rates for siblings and for dizygotic twins.While both siblings and dizygotic twins share 50% of their genetic material in common, dizygotic twins are exposed to a more similar environment than are siblings.Thus, the fact that dizygotic twins exhibit a higher rate of concordance for type 1 diabetes than do siblings [13 vs. 7% in Denmark; see Kyvik et al. (21)] implies that shared environmental factors affect the risk of type 1 diabetes.These shared environmental influences could be prenatal (intrauterine), or related to diet, infectious exposure, or other factors.Additional epidemiologic evidence confirms the importance of environmental factors: there is seasonality both in the month of birth (generally lower in winter) and in the month of diagnosis (generally peaking in winter), although the degree of seasonality varies among populations (12,(31)(32)(33)(34).",
+      "\tMonogenic vs. polygenic diabetes\n\nMonogenic and polygenic diabetes are traditionally considered distinct, with monogenic diabetes resulting from one highly penetrant variant in one gene in a given individual, and polygenic diabetes resulting from the contribution of several variants with smaller effects in the context of environmental/lifestyle factors.In T1D, autoimmune dysfunction is the prominent mechanism, with variation in the major histocompatibility locus and other genomic factors combining with apparent environmental triggers to result in beta cell loss and diabetes.In monogenic diabetes, highly penetrant variants, mostly Finally, while lack of features of either autoimmunity or obesity/metabolic syndrome raises the likelihood of monogenic diabetes, these features can co-exist with monogenic diabetes, particularly obesity given its high prevalence especially in youth.In the Treatment Options for Diabetes in Adolescents and Youth (TODAY) clinical trial in which overweight or obesity was required for the newly diagnosed youth with T2D enrolled, at least 4.5% were identified as having MODY.Those with HNF4A-MODY had poor response to metformin, representing a previously missed opportunity for optimal treatment 9 .In summary, monogenic and polygenic forms of diabetes exist along more of a continuum than previously appreciated.Therefore, knowledge about P R E V I E W monogenic diabetes not only provides opportunities for etiology-based treatment of the minority of individuals with highly penetrant variants, but also informs broader understanding of diabetes etiology.",
+      "\t\n\nRecent GWAS have successfully identified more than 40 independent T1DM-associated tagging SNPs; however, the sum of these loci does not fully explain the heritability estimated from familial studies [16].For example, twin studies have shown that for di-zygotic twins, the pairwise T1DM concordance rate is 10%, whereas for mono-zygotic twins, the concordance rate is approximately 50% [17].Thus, dietary and other environmental factors also influence T1DM incidence and development.These factors primarily include the use of breast milk vs. infant formula [18], highly hydrolyzed infant formula vs. conventional infant formula [19], early/late exposure to gluten [20] and vitamin D [21].Interestingly, a newly diagnosed child fed a gluten-free diet was shown to remain healthy without insulin therapy for 20 months [22].",
+      "\t\n\nBecause close relatives of diabetic patients share common environmental factors, it could be argued that shared environment alone accounts for the increased risk of Type I diabetes among relatives of diabetic patients.More definitive evidence for a genetic basis is obtained by comparing the diabetes concordance rates in monozygotic (MZ, 100 % shared genes) and dizygotic twins (DZ, average 50 % shared genes), because twins experience similar environments both before and after birth.These studies have consistently shown a higher Type I diabetes concordance rate in MZ twins than DZ twins [1013], demonstrating a clear genetic basis for this disorder.The MZ twin concordance rate also provides a rough idea of the degree of genetic compared with non-genetic determination in specific environments.This concordance rate has been variously estimated as 34 % by age 30 [11], 43 % within 12 years of diagnosis of the index case [14], and 50 % within 40 years of index diagnosis [15], implying strong non-genetic factors (reflected as discordance) in the aetiology of Type I diabetes.",
+      "\tType 1 Diabetes\n\nDiscordance rates in twins, the rise in global incidence, variance in geographic prevalence, and assimilation of local disease incidence rates when individuals migrate from low-to high-incidence countries all support an environmental influence on risk for developing type 1 diabetes.Furthermore, many lines of evidence suggest that environmental factors interact with genetic factors in both the triggering of autoimmunity and the subsequent progression to type 1 diabetes.Supporting this gene-environment interaction is the fact that most subjects with the highest-risk HLA haplotypes do not develop type 1 diabetes.",
+      "\t\n\nIt is therefore intriguing that A1C levels are significantly correlated in monozygotic twins whether they are concordant for type 1 diabetes or not (4): in a discordant twin pair one twin is treated with insulin, whereas the other one isn't, and thus this degree of correlation suggests that genetic contributors to A1C may be detectable despite the superimposition of a strong environmental modifier.Rig-orous estimates of heritability of treated A1C, however, are not available."
+    ],
+    [
+      "\tFuture directions\n\nDelays in identifying genetic variants that are robustly associated with differences in individual predisposition to the complications of diabetes, have constrained progress towards a mechanistic understanding of these conditions.Some approaches to overcome these limitations are outlined in Figure 4.",
+      "\t\n\nAn individual's risk of developing T2D is influenced by a combination of lifestyle, environmental, and genetic factors.Uncovering the genetic contributors to diabetes holds promise for clinical impact by revealing new therapeutic targets aimed at the molecular and cellular mechanisms that lead to disease.Genome-wide association studies performed during the past decade have uncovered more than 100 regions associated with T2D (5)(6)(7)(8)(9)(10)(11)(12).Although these studies have provided a better understanding of T2D genetics, the majority of identified variants fall outside protein-coding regions, leaving the molecular mechanism by which these variants confer altered disease risk obscure.Consequently, T2D genome-wide association studies have identified few loci with clear therapeutic potential.",
+      "\tGENETIC SUSCEPTIBILITY AND GENE-ENVIRONMENT INTERACTIONS-\n\nThe recent advent of genome-wide association studies (GWAS) has led to major advances in the identification of common genetic variants contributing to diabetes susceptibility (40).To date, at least 40 genetic loci have been convincingly associated with type 2 diabetes, but these loci confer only a modest effect size and do not add to the clinical prediction of diabetes beyond traditional risk factors, such as obesity, physical inactivity, unhealthy diet, and family history of diabetes.Many diabetes genes recently discovered through GWAS in Caucasian populations have been replicated in Asians; however, there were significant interethnic differences in the location and frequency of these risk alleles.For example, common variants of the TCF7L2 gene that are significantly associated with diabetes risk are present in 20-30% of Caucasian populations but only 3-5% of Asians (41,42).Conversely, a variant in the KCNQ1 gene associated with a 20-30% increased risk of diabetes in several Asian populations (43,44) is common in East Asians, but rare in Caucasians.It is intriguing that most diabetes susceptibility loci that have been identified are related to impaired b-cell function, whereas only a few (e.g., peroxisome proliferator-activated receptor-g, insulin receptor substrate 1, IGF-1, and GCKR) are associated with insulin resistance or fasting insulin, which points toward b-cell dysfunction as a primary defect for diabetes pathogenesis.It should be noted that most of the single nucleotide polymorphisms uncovered may not be the actual causal variants, which need to be pinpointed through fine-mapping, sequencing, and functional studies.",
+      "\t\n\nConclusions: Together these results provide further evidence for the implication of genetic factors in the development of type 2 diabetes complications and highlight several potential key loci, able to modify the risk of developing these conditions.Moreover, the candidate variant approach proves a strong and consistent effect for multiple variants across different populations.",
+      "\tGenomics of T2D\n\nDiet, lifestyle, environment, and even genetic variation influence an individual's response to disease therapy.Like GWAS which identify genetic variants conferring risk for a disease, studies have been carried out for identifying genetic variants responsible for patient differences in drug response.Pharmacogenomics in diabetes focuses on the study of gene polymorphisms which influence an individual's response to antidiabetic drugs.Such genetic variants influence the pharmacodynamics and/or pharmacokinetics of the drug, thus affecting its efficacy or toxicity in an individual.The difference in response to treatments and therapies across individuals on account of these factors strengthens the case for personalized medicine in diabetes.",
+      "\t\nThe aim of this study was to summarize current knowledge and provide perspectives on the relationships between human genetic variants, type 2 diabetes, antidiabetic treatment, and disease progression.Type 2 diabetes is a complex disease with clear-cut diagnostic criteria and treatment guidelines.Yet, the interindividual response to therapy and slope of disease progression varies markedly among patients with type 2 diabetes.Gene-gene, gene-environment, and gene-treatment interactions may explain some of the variation in disease progression.Several genetic variants have been suggested to be associated with response to antidiabetic drugs.Some are present in drug receptors or drug metabolizers (OCT genes, KCNJ11, ABCC8, and CYP2C9).Numerous type 2 diabetes risk variants have been identified, but genetic risk score models applying these variants have failed to identify 'disease progressors' among patients with diabetes.Although genetic risk scores are based on a few known loci and only explain a fraction of the heritability of type 2 diabetes, it seems that the genes responsible for the development of diabetes may not be the same driving disease progression after the diagnosis has been made.Pharmacogenetic interactions explain some of the interindividual variation in responses to antidiabetic treatment and may provide the foundation for future genotype-based treatment standards.Pharmacogenetics and Genomics 25:475-484\t\n\nThe aim of this study was to summarize current knowledge and provide perspectives on the relationships between human genetic variants, type 2 diabetes, antidiabetic treatment, and disease progression.Type 2 diabetes is a complex disease with clear-cut diagnostic criteria and treatment guidelines.Yet, the interindividual response to therapy and slope of disease progression varies markedly among patients with type 2 diabetes.Gene-gene, gene-environment, and gene-treatment interactions may explain some of the variation in disease progression.Several genetic variants have been suggested to be associated with response to antidiabetic drugs.Some are present in drug receptors or drug metabolizers (OCT genes, KCNJ11, ABCC8, and CYP2C9).Numerous type 2 diabetes risk variants have been identified, but genetic risk score models applying these variants have failed to identify 'disease progressors' among patients with diabetes.Although genetic risk scores are based on a few known loci and only explain a fraction of the heritability of type 2 diabetes, it seems that the genes responsible for the development of diabetes may not be the same driving disease progression after the diagnosis has been made.Pharmacogenetic interactions explain some of the interindividual variation in responses to antidiabetic treatment and may provide the foundation for future genotype-based treatment standards.Pharmacogenetics and Genomics 25:475-484\tPharmacogenetics in disease progression\n\nOver the recent years, more than 90 susceptibility genes have been identified by genome-wide association studies (GWAS) [55][56][57][58].However, the knowledge of the potential interactions between T2D predisposing genetic variants and the efficacy of treatment of T2D is sparse.Identification of gene-treatment interactions is challenging and requires large sample sizes and sophisticated analytical methods.Furthermore, detailed information on lifestyle and compliance to treatment as well as a long follow-up period are necessary for analysis of pharmacogenomics in T2D.\t\n\nTo date, a number of genetic variants have been identified to be associated with response to antidiabetic drugs.Of these, some variants are present in either drug receptors or drug metabolizers as for OCT genes, KCNJ11, ABCC8, and CYP2C9.Other variants are known T2D susceptibility variants such as TCF7L2.To identify variants of importance for antiglycemic drug response, GWAS in large cohorts of patients with diabetes with detailed measures of pharmacotherapy are lacking.The pharmacologic management of patients with diabetes often involves drug classes other than antidiabetics.Pharmacogenetic studies on statin and antihypertensive treatment have reported several genetic variants associated with treatment response and adverse drug reactions [101,102].It therefore seems natural to conclude that the future perspectives in pharmacogenetics is to conduct genetic studies in large cohorts with wellphenotyped individuals, thorough data collection on baseline treatment, concomitant treatment, adherence to therapy as well as data collection on comorbidity and additional disease diagnoses.These types of pharmacogenetic studies may provide unique opportunities for future genotype-based treatment standards and may help in delaying or changing the slope of disease progression among patients with T2D.",
+      "\t\n\nGenetic determinants of diabetes and metabolic syndromes.",
+      "\t\n\nOver the past two years, there has been a spectacular change in the capacity to identify common genetic variants that contribute to predisposition to complex multifactorial phenotypes such as type 2 diabetes (T2D).The principal advance has been the ability to undertake surveys of genome-wide association in large study samples.Through these and related efforts, $20 common variants are now robustly implicated in T2D susceptibility.Current developments, for example in high-throughput resequencing, should help to provide a more comprehensive view of T2D susceptibility in the near future.Although additional investigation is needed to define the causal variants within these novel T2Dsusceptibility regions, to understand disease mechanisms and to effect clinical translation, these findings are already highlighting the predominant contribution of defects in pancreatic b-cell function to the development of T2D.",
+      "\t\n\nThe availability of detailed information on gene  environment interactions may enhance our understanding of the molecular basis of T2D, elucidate the mechanisms through which lifestyle exposures influence diabetes risk, and possibly help to refine strategies for diabetes prevention or treatment.The ultimate hope is genetics might one day be used in primary care to inform the targeting of interventions that comprise exercise regimes and other lifestyle therapies for individuals most likely to respond well to them.",
+      "\t\n\nThere is strong evidence that novel T2D genes will be potentially exciting pharmaceutical targets.There is strong evidence in favour of this already, as the most established T2D susceptibility genes are also well-known drug targets, namely PPARG and thiazolidinediones [45] and KCNJ11 and sulfonylurea therapy [46,128].",
+      "\tFUTURE PERSPECTIVES\n\nContinued investment in studies of G  E interactions for T2D holds promise on several grounds.First, such studies may provide insight into the function of novel T2D loci and pathways by which environmental exposures act and, therefore, yield a better understanding of T2D etiology (66).They could also channel experimental studies in a productive direction.Second, knowledge of G  E interactions may help identify high-risk individuals for diet and lifestyle interventions.This may also apply to pharmacological interventions if individuals carrying certain genotypes are more or less responsive to specific medications.The finding that patients with rare forms of neonatal diabetes resulting from KCNJ11 mutations respond better to sulfonylurea than to insulin therapy is just one example demonstrating the potential for this application of G  E interaction research (69).Third, we are fast approaching an era when individuals can feasibly obtain their complete genetic profile and thus a snapshot of their genetic predisposition to disease.It will therefore be the responsibility of health professionals to ensure that their patients have an accurate interpretation of this information and a means to curb their genetic risk.A long-held goal of genetic research has been to tailor diet and lifestyle advice to an individual's genetic profile, which will, in turn, motivate him or her to adopt and maintain a protective lifestyle.There is currently no evidence that this occurs.Findings to date, however, indicate that behavioral changes can substantially mitigate diabetogenic and obesogenic effects of individual or multiple risk alleles, which has much broader clinical and public health implications.",
+      "\t\n\nRegulatory authorities have indicated that new drugs to treat type 2 diabetes (T2D) should not be associated with an unacceptable increase in cardiovascular risk.Human genetics may be able to guide development of antidiabetic therapies by predicting cardiovascular and other health endpoints.We therefore investigated the association of variants in six genes that encode drug targets for obesity or T2D with a range of metabolic traits in up to 11,806 individuals by targeted exome sequencing and follow-up in 39,979 individuals by targeted genotyping, with additional in silico followup in consortia.We used these data to first compare associations of variants in genes encoding drug targets with the effects of pharmacological manipulation of those targets in clinical trials.We then tested the association of those variants with disease outcomes, including coronary heart disease, to predict cardiovascular safety of these agents.A low-frequency missense variant (Ala316Thr; rs10305492) in the gene encoding glucagon-like peptide-1 receptor (GLP1R), the target of GLP1R agonists, was associated with lower fasting glucose and T2D risk, consistent with GLP1R agonist therapies.The minor allele was also associated with protection against heart disease, thus providing evidence that GLP1R agonists are not likely to be associated with an unacceptable increase in cardiovascular risk.Our results provide an encouraging signal that these agents may be associated with benefit, a question currently being addressed in randomized controlled trials.Genetic variants associated with metabolic traits and multiple disease outcomes can be used to validate therapeutic targets at an early stage in the drug development process.\t\nRegulatory authorities have indicated that new drugs to treat type 2 diabetes (T2D) should not be associated with an unacceptable increase in cardiovascular risk.Human genetics may be able to guide development of antidiabetic therapies by predicting cardiovascular and other health endpoints.We therefore investigated the association of variants in six genes that encode drug targets for obesity or T2D with a range of metabolic traits in up to 11,806 individuals by targeted exome sequencing and follow-up in 39,979 individuals by targeted genotyping, with additional in silico followup in consortia.We used these data to first compare associations of variants in genes encoding drug targets with the effects of pharmacological manipulation of those targets in clinical trials.We then tested the association of those variants with disease outcomes, including coronary heart disease, to predict cardiovascular safety of these agents.A low-frequency missense variant (Ala316Thr; rs10305492) in the gene encoding glucagon-like peptide-1 receptor (GLP1R), the target of GLP1R agonists, was associated with lower fasting glucose and T2D risk, consistent with GLP1R agonist therapies.The minor allele was also associated with protection against heart disease, thus providing evidence that GLP1R agonists are not likely to be associated with an unacceptable increase in cardiovascular risk.Our results provide an encouraging signal that these agents may be associated with benefit, a question currently being addressed in randomized controlled trials.Genetic variants associated with metabolic traits and multiple disease outcomes can be used to validate therapeutic targets at an early stage in the drug development process.\tDISCUSSION\n\nAnticipating the side effects of drugs before phase 3 clinical trials could support drug discovery and development, reducing attrition rates and saving considerable time and money.The promise of human genetics in this endeavor (2, 3, 7, 27) depends on the availability of genetic variants that mimic pharmaceutical interventions.We undertook a systematic study to identify such genetic variants in the context of diabetes and obesity and identified an association between fasting glucose and T2D with a missense variant in GLP1R, the gene encoding the GLP-1 receptorthe target of the GLP1R agonist class of T2D therapies.Regulatory authorities require evidence that therapies for T2D are not associated with unacceptable increases in cardiovascular risk.The reduced risk associated with the glucose-lowering genetic variant in GLP1R provides evidence that not only will GLP1R agonists meet this regulatory hurdle but they may also reduce CHD events.Ongoing trials of GLP1R agonists are designed to resolve this uncertainty and will also augment the evidence on the broader validity of genetic approaches in drug target validation.",
+      "\tConclusions\n\nRecent large collaborative studies to clarify the genetics of T2DM have identified variants in nine gene areas that are associated with a moderately increased risk of developing the disease.Further studies may identify more of these variants and ultimately improve the possibility of predicting disease risk in healthy subjects.Search for the patho-physiological role of these variants has not been easy, although evidence is emerging for their involvement in either pancreatic development or in the control of insulin secretion.The elucidation of novel pathways involved to the etiology of T2DM may contribute to improved prevention and treatment of the disease.The influence of environmental factors such as lifestyle and diet must not be overlooked, and future studies should be especially focused on the interactions between dietary factors and the genetic variants involved in T2DM risk.In the light of the recent investigative efforts, the genetics of T2DM is probably no longer ''the geneticist's nightmare'', but it certainly remains an intriguing puzzle that is yet to be solved.",
+      "\t\nIntroduction: Genetic and environmental factors play an important role in susceptibility to type 2 diabetes mellitus (T2DM).Several genes have been implicated in the development of T2DM.Genetic variants of candidate genes are, therefore, prime targets for molecular analysis.\t\n\nIntroduction: Genetic and environmental factors play an important role in susceptibility to type 2 diabetes mellitus (T2DM).Several genes have been implicated in the development of T2DM.Genetic variants of candidate genes are, therefore, prime targets for molecular analysis."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "267860332B035B03D684CFB2CBB42ECF"
+    },
+    {
+      "task_id": "31595629DC7ABAE42ABEE4B01B1599DE"
+    },
+    {
+      "task_id": "A3D28FFFE853D22D58BE99FFC84F2DC8"
+    },
+    {
+      "task_id": "AF799975123DFCE3735C1802F530B8B0"
+    },
+    {
+      "task_id": "4487D79862055ACAFD215A9D700626FC"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_3.json
new file mode 100644
index 0000000..eac65b9
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_3.json
@@ -0,0 +1,104 @@
+{
+  "question": [
+    "How do rare variants identified through whole-genome sequencing contribute to the heritability of Type 2 diabetes?",
+    "What are the latest findings on the role of non-coding RNAs in the pathogenesis of diabetes?",
+    "How does the interaction between multiple polygenic risk scores (PRS) improve the prediction of Type 1 and Type 2 diabetes?",
+    "What are the mechanistic insights into the beta-cell failure pathways gleaned from recent single-cell RNA-sequencing studies?",
+    "How does the epigenetic landscape of key metabolic tissues change in diabetic versus non-diabetic individuals?"
+  ],
+  "answer": [
+    "Rare variants identified through whole-genome sequencing can contribute to the heritability of Type 2 diabetes by revealing genetic determinants that are not detected by Genome-Wide Association Studies (GWAS). These rare variants, especially those with significant effects, can increase our understanding of Type 2 diabetes heritability and help identify individuals at risk early on. However, current studies suggest that these rare variants are likely scattered across many genes, rather than being clustered in a small number of genes.",
+    "Recent findings suggest that non-coding RNAs, specifically long noncoding RNAs (lncRNAs) and microRNAs (miRNAs), play significant roles in the pathogenesis of diabetes and its complications. They are involved in various cellular processes such as inflammation, fibrosis, and hypertrophy in renal cells, which contribute to the progression of diabetic nephropathy. They can also affect DNA methylation and histone modifications, resulting in increased chromatin accessibility to transcription factors near pathological genes. Furthermore, lncRNAs and miRNAs can increase the expression of pathological genes via post-transcriptional mechanisms. Some specific lncRNAs like MALAT1, MEG3, ANRIL, PVT1, MIAT, MGC, Gm4419, and TUG1 have been implicated in complications like diabetic retinopathy and nephropathy. Similarly, miRNAs have been found to regulate important pathogenic responses and hold potential as diagnostic biomarkers and therapeutic targets.",
+    "The interaction between multiple polygenic risk scores (PRS) improves the prediction of Type 1 and Type 2 diabetes by aggregating the genetic risk of individual alleles across the genome. This provides a comprehensive view of an individual's genetic predisposition to diabetes. The PRS can capture information on individual patterns of disease predisposition, which can help predict diabetes risk, support differential diagnosis, and understand phenotypic and clinical heterogeneity. However, the effectiveness of PRS can vary across different ethnic groups and populations.",
+    "Recent single-cell RNA-sequencing studies have revealed that multiple monogenic diabetes genes are highly expressed in beta cells. However, other non-beta cell types also express genes mutated in monogenic diabetes. Dysregulated glucagon secretion in type 1 diabetic islets is accompanied by decreased expression of important islet transcription factors and increased expression of stress response factors, suggesting changes in alpha cell identity may lead to their dysfunction. Transcriptomic heterogeneity in normal and T2D islets is associated with variability in alpha cell electrophysiological measures. These studies implicate the dysfunction of both alpha and beta cells in diabetes pathogenesis.",
+    "In diabetic individuals, there are significant differential DNA methylation profiles in pancreatic islets compared to non-diabetic individuals. This includes 276 CpG loci affiliated to promoters of 254 genes displaying significant differential DNA methylation in diabetic islets. These methylation changes were not present in blood cells from diabetic individuals nor were they experimentally induced in non-diabetic islets by exposure to high glucose. These changes can affect over 250 genes, some of which are also differentially expressed, and may be linked to b-cell functionality, cell death, and adaptation to metabolic stress. These epigenetic changes are not observed in other tissues, indicating tissue-specificity."
+  ],
+  "contexts": [
+    [
+      "\t\n\nIt should be noted that a great number of low frequency variants might not be identified by GWAS owing to the required genome-wide significance level.According to the existing studies, many important loci are also obscured as a result of borderline associations.The known variants account for only a small amount of the overall estimated genetic heritability; therefore, there is still a long way to go in terms of understanding the pathogenesis of type 2 diabetes.",
+      "\t\n\nIf common causal alleles explain a substantial component of T2D susceptibility, the contribution of rare and low-frequency risk variants may be less than is often assumed: resequencing studies will soon provide empirical data to address this hypothesis.In particular, it will be important to determine whether, as the number of susceptibility loci increases, there is evidence that the pathophysiological mechanisms implicated by human genetics coalesce around a limited set of core pathways and networks.Our data suggest that this may be the case, with a variety of analytical approaches pointing to cell cycle regulation, adipocytokine signaling and CREBBP-related transcription factor activity as key processes involved in T2D pathogenesis.",
+      "\tFuture perspective\n\nGiven the rapid pace of technological advancement in genetics, discovery of many more genetic determinants of T2D may be expected in future.At present, GWAS are limited in their ability to detect rare variants.Sequencing, which is expected to become much more economical, may benefit greatly in this respect by identifying rare genetic variants with significant effects on T2D risk in a given population.This would result in an increased understanding of T2D heritability so that at risk individuals may be detected early on.However, functional studies need to evolve at an equally rapid pace to be able to translate these discoveries into clinical practice.\tGenetics & genomics of T2D\n\n Genome-wide association studies (GWAS) have been helpful in identifying a large number of genetic variants conferring risk to T2D.However, only close to 10% heritability is explained by these variants.Other genetic variants, particularly those which are rare but with significant effects need to be identified. Genetic variability is responsible for the difference in response to antidiabetic drugs seen across individuals.",
+      "\t\n\nOver the past two years, there has been a spectacular change in the capacity to identify common genetic variants that contribute to predisposition to complex multifactorial phenotypes such as type 2 diabetes (T2D).The principal advance has been the ability to undertake surveys of genome-wide association in large study samples.Through these and related efforts, $20 common variants are now robustly implicated in T2D susceptibility.Current developments, for example in high-throughput resequencing, should help to provide a more comprehensive view of T2D susceptibility in the near future.Although additional investigation is needed to define the causal variants within these novel T2Dsusceptibility regions, to understand disease mechanisms and to effect clinical translation, these findings are already highlighting the predominant contribution of defects in pancreatic b-cell function to the development of T2D.",
+      "\tGenetic variants\n\nThe heritability of glycaemic traits and type 2 diabetes is high [40], and the large genome-wide association studies published to date since the first in 2007, based on up to >10 5 study participants, has helped us to better understand the genetic architecture of this disease.Single nucleotide polymorphisms (SNPs) in more than 60 regions throughout the genome (so-called susceptibility loci containing multiple genes) were found to be associated with the risk of type 2 diabetes [39, 41-44].Most of these SNPs are common, with minor allele frequencies of 10-90%.Interestingly, loci associated with diabetes risk show only a partial overlap with loci that determine levels of fasting glucose, 2 h glucose and HbA 1c .Thus, some loci influence both disease risk and glycaemic traits, whereas others seem to mainly regulate glucose levels within the physiological range without affecting the development of overt type 2 diabetes, and vice versa [45,46].",
+      "\t\n\nFigure 3 displays results for three representative models: a 'purifying selection' model in which low-frequency and rare variants explain approximately 75% of T2D heritability; an intermediate model in which both common and lower-frequency variants contribute substantially; and a 'neutral' model in which common variants explain about 75% of T2D heritability.The predictions of the first two models differ markedly from the empirical data with respect to the numbers of low-frequency and rare risk variants that are associated with T2D.Specifically, these two models predict a larger number and greater effect size of low-frequency variants should be found in our whole-genome sequencing study as compared to those observed in the empirical data.By contrast, the empirical data are consistent with predictions under the 'neutral' commonvariant model.\t\nThere is compelling evidence that the individual risk of type 2 diabetes (T2D) is strongly influenced by genetic factors 1 .Progress in characterizing the specific T2D-risk alleles responsible has been catalysed by the ability to perform genome-wide association studies (GWAS).Over the past decade, successive waves of T2D GWAS-featuring ever larger samples, progressively denser genotyping arrays supplemented by imputation against more complete reference panels, and richer ethnic diversity-have delivered more than 80 robust association signals 2-8 .However, in these studies, the alleles interrogated for association were predominantly common (minor allele frequency (MAF) >5%), and with limited exceptions 7,9 , the variants driving known association signals were also common, with individually modest impacts on T2D risk [2][3][4][5][6][7][8]10 . Varation at known loci explains only a minority of observed T2D heritability 2,3,11 .Residual genetic variance is partly explained by a long tail of common variant signals of lesser effect 2 .However, the contribution to T2D risk that is attributable to lower-frequency variants remains a matter of considerable debate, not least because of the relevance of disease architecture to clinical application 11 .Next-generation sequencing enables direct evaluation of the role of lower-frequency variants to disease risk 7,12,13 .This paper describes the efforts of the coordinated, complementary strategies pursued by the Genetics of Type 2 Diabetes (GoT2D) and Type 2 Diabetes Genetic Exploration by Next-generation sequencing in multi-Ethnic Samples (T2D-GENES) consortia.GoT2D collected comprehensive genomewide sequence data from 2,657 T2D cases and controls; T2D-GENES focused on exome sequence variation, assembling data (after inclusion of GoT2D exomes) from a multiethnic sample of 12,940 individuals.Both consortia used genotype data to expand the sample size available for association testing for a subset of the variants exposed by sequencing.",
+      "\t\n\nRecent data (67) and ongoing investigations indicate that other types of common genetic variation (e.g., copy number or structural variants, such as deletions and duplications) may contribute little to the observed familial clustering of type 1 diabetes risk.However, rare loss-offunction structural gene variants could still make an important contribution to type 1 diabetes risk, through identification of which particular gene in a region of association could harbor a causal variant.With further advances in array and sequencing technologies, it is anticipated that such loss-of-function variants will be identified that influence susceptibility to type 1 diabetes (68).Inferences from genetic studies.Each newly identified association of a candidate locus with type 1 diabetes presents new challenges.Finding the causal genes and the causal variants, understanding how they affect disease pathophysiology, and dissecting their contribution to type 1 diabetes risk remain the major undertakings.For some genes, the effect sizes of risk alleles are such that larger collections of patients will be needed to identify the causal genes and limit the number of potential causal variants.Genotype-phenotype fine-mapping studies, however, can be performed with much smaller sample sizes while still achieving convincing statistical evidence (e.g., 42).Each confirmed gene, based on both statistical and functional evidence, provides a key piece of the etiology of type 1 diabetes, regardless of the magnitude of the odds ratio as a measure of the population association.\t\n\nCombinations of many alleles, possibly hundreds, combine with effects of environmental factors (probably numerous and ubiquitous) to establish the risk profile for type 1 diabetes.Each common variant in isolation has a subtle effect on disease risk, but each may alter a key function in the immune system and its interaction with pancreatic -cells.Recent discussion of \"missing heritability\" for complex human traits has considered the source of this variation and appropriate research strategies to detect these genetic effects (61).Studies in populations that are distinct from Europeans or European ancestry, such as populations of recent African ancestry or from Asian countries, are likely to narrow the large chromosomal regions of association identified in current studies and to increase the yield of rare variants (69).Future studies examining rare variants, structural variation, and polymorphisms not well imputed should be helpful in uncovering the remaining missing heritability in type 1 diabetes.",
+      "\t\n\nUntil recently, genome-wide linkage and candidate studies have been the main genetic epidemiological approaches to identifying the precise genetic variants underlying T2D heritability.These efforts confirmed only a few susceptibility variants, including those in PPARG, KCNJ11, WFS1, HNF1A, HNF1B, HNF4A, TCF7L2, and ADIPOQ (1,6,27,56,81,102).Recent genome-wide association studies (GWAS) have unveiled over 50 novel loci associated with T2D and more than 40 associated with T2D-related traits including fasting insulin, glucose, and proinsulin (16,48,57,82,87,97,105) (Table 1).Clinical investigations of some of the T2D loci, thus far, suggest that the genetic components of T2D risk act preferentially through -cell function (20).This pattern may only be a function of case diagnostic criteria, which weigh heavily on parameters reflecting advanced stages of the disease.This notion is supported by the incomplete overlap of single-nucleotide polymorphisms (SNPs) contributing to variation in quantitative traits with those associated with overt T2D (20).With the exception of TCF7L2, most variants contribute modestly to T2D risk and together explain only a small proportion of the familial clustering of T2D, suggesting that many more loci await discovery (10,12,97).",
+      "\tDiscussion\n\nIt has been hypothesized that rare genetic variants with moderate effects on disease risk could account for much of the missing heritability of complex traits. 6,9,10,62We have taken a first step toward testing this hypothesis for type 2 diabetes.We did not detect any significant associations between rare coding variants and common forms of diabetes.Our study was underpowered to detect weak genetic effects, but if much of the heritability of type 2 diabetes is explained by variants in a modest number of genes, we should have detected at least one associated locus at our Bonferroni significance threshold.Thus, our empirical results, combined with the statistical power simulations, suggest that when clustered in fewer than 20 genes, coding variants of moderate effect do not account for much of the missing heritability of a common polygenic disorder such as type 2 diabetes.\t\n\nOne common disease that has been subjected to intense genetic study is type 2 diabetes. 32The heritability of type 2 diabetes has been estimated to be around 30%. [33][34][35] Through GWASs, 63 loci have been reproducibly associated with type 2 diabetes. 36However, as for other complex traits, the associated SNPs can only account for <20% of the heritability estimated from family studies. 36ere, we seek to evaluate the role that rare coding variants play in the genetic basis of common forms of type 2 diabetes.We performed a deep whole-exome sequencing study of 2,000 Danish individuals.We applied both single-marker and gene-based association tests.Although we failed to detect any significant association after multiple test corrections, our simulations suggest that our results are informative about the genetic architecture of type 2 diabetes.In particular, our study suggests that when clustered in a small number of genes, rare coding variants of moderate to strong effect are unlikely to account for much of the missing heritability.Rather, if rare coding variants are an important factor in type 2 diabetes risk, they are most likely scattered across many genes.Our results have important implications for the design and interpretation of future medical resequencing studies.\t\n\nOur empirical and simulation results are compatible with a variety of different genetic architectures for type 2 diabetes.First, if rare coding variants are responsible for the majority of the heritability of the trait, the variants are most likely scattered across many (>20) different genes.Thus, genetic variants in no one gene can account for much of the heritability of the trait.Biologically, such a model would postulate that there are a large number of genes that can be mutated to cause type 2 diabetes in a given individual.Each individual would then carry a subset of genetic variants located in several of the many causal genes.Our finding that genes previously implicated in obesity risk through GWASs showed unusually low SKAT p values in our study supports a scenario in which low-frequency and rare variants in multiple genes could be responsible for risk of common metabolic diseases.It also suggests that genes carrying common variants associated with a trait could also carry additional low-frequency and rare coding variants that increase disease risk.\t\n\nAlthough our results argue that low-frequency and rare coding variants in a modest number of genes do not account for the majority of the heritability of common forms of type 2 diabetes, it is not clear how generalizable this result is to other complex traits.Several other exome sequencing studies have failed to detect any significant associations between low-frequency variants and schizophrenia, 77 epilepsy, 78 autism, 79 or autoimmune diseases. 80][83] Thus, the genetic architecture and the role of low-frequency and rare variants are likely to be trait dependent and will need to be addressed empirically.",
+      "\tType 2 Diabetes\n\nWhile a subset of genetic variants are linked to both type 1 and type 2 diabetes (42,43), the two diseases have a largely distinct genetic basis, which could be leveraged toward classification of diabetes (44).Genome-wide association studies have identified more than 130 genetic variants associated with type 2 diabetes, glucose levels, or insulin levels; however, these variants explain less than 15% of disease heritability (45)(46)(47).There are many possibilities for explaining the majority of type 2 diabetes heritability, including disease heterogeneity, gene-gene interactions, and epigenetics.Most type 2 variants are in noncoding genomic regions.Some variants, such as those in KCNQ1, show strong parent-of-origin effects (48).It is possible that children of mothers carrying KCNQ1 are born with a reduced functional b-cell mass and thereby are less able to increase their insulin secretion when exposed to insulin resistance (49).Another area of particular interest has been the search for rare variants protecting from type 2 diabetes, such as loss-of-function mutations in SLC30A8 (50), which could offer potential new drug targets for type 2 diabetes.",
+      "\t\n\nAt least three large exome and genome sequencing projects are ongoing to discover variants influencing type 2 diabetes and related traits.The Go-T2D study is performing lowcoverage whole-genome sequencing, deep exome sequencing, and 2.5 M SNP array genotyping of 1,425 type 2 diabetes cases and 1,425 controls from Northern Europe [41].The T2D-GENES Project 1 study is performing exome sequencing of 5,000 type 2 diabetes cases and 5,000 controls from five ancestral groups, and the T2D-GENES Project 2 study is performing deep whole-genome sequencing of >500 individuals from 20 large Mexican American pedigrees [42].These projects will detect many novel lowfrequency and rare variants that, when analyzed in sufficiently large numbers of subjects, can be expected to identify new insights into the genetic basis for disease.\tConclusions\n\nHow will sequencing genomes influence the health of people at risk for or affected with diabetes?The more complete understanding of the biological mechanisms underlying diabetes derived from these studies may lead to identification of novel drug targets.Individuals with variants in genes responsible for MODY or neonatal diabetes respond better to specific drugs [50,51], and sequencing may identify small numbers of individuals with combinations of rarer, more highly penetrant variants that respond better to specific therapeutic options.Although sets of known variants for type 2 diabetes do not add substantially to prediction of type 2 diabetes development in the overall population [52,53], identification of individuals at greater or lower genetic risk for diabetes within the overall population or in specific subgroups, such as younger onset or leaner individuals [54,55], could lead to better targeted health information and also allow identification of higher risk individuals leading to more efficient design of clinical trials for disease prevention.",
+      "\t\nGenome-wide association (GWAS) and sequencing studies are providing new insights into the genetic basis of type 2 diabetes (T2D) and the inter-individual variation in glycemic traits, including levels of glucose, insulin, proinsulin and hemoglobin A1c (HbA1c).At the end of 2011, established loci (P < 5  10 8 ) totaled 55 for T2D and 32 for glycemic traits.Since then, most new loci have been detected by analyzing common [minor allele frequency (MAF)>0.05]variants in increasingly large sample sizes from populations around the world, and in trans-ancestry studies that successfully combine data from diverse populations.Most recently, advances in sequencing have led to the discovery of four loci for T2D or glycemic traits based on low-frequency (0.005 < MAF  0.05) variants, and additional low-frequency, potentially functional variants have been identified at GWAS loci.Established published loci now total 88 for T2D and 83 for one or more glycemic traits, and many additional loci likely remain to be discovered.Future studies will build on these successes by identifying additional loci and by determining the pathogenic effects of the underlying variants and genes.\t\n\nGenome-wide association (GWAS) and sequencing studies are providing new insights into the genetic basis of type 2 diabetes (T2D) and the inter-individual variation in glycemic traits, including levels of glucose, insulin, proinsulin and hemoglobin A1c (HbA1c).At the end of 2011, established loci (P < 5  10 8 ) totaled 55 for T2D and 32 for glycemic traits.Since then, most new loci have been detected by analyzing common [minor allele frequency (MAF)>0.05]variants in increasingly large sample sizes from populations around the world, and in trans-ancestry studies that successfully combine data from diverse populations.Most recently, advances in sequencing have led to the discovery of four loci for T2D or glycemic traits based on low-frequency (0.005 < MAF  0.05) variants, and additional low-frequency, potentially functional variants have been identified at GWAS loci.Established published loci now total 88 for T2D and 83 for one or more glycemic traits, and many additional loci likely remain to be discovered.Future studies will build on these successes by identifying additional loci and by determining the pathogenic effects of the underlying variants and genes."
+    ],
+    [
+      "\t\n\nIt is important to find better treatments for diabetic nephropathy (DN), a debilitating renal complication.Targeting early features of DN, including renal extracellular matrix accumulation (ECM) and glomerular hypertrophy, can prevent disease progression.Here we show that a megacluster of nearly 40 microRNAs and their host long non-coding RNA transcript (lnc-MGC) are coordinately increased in the glomeruli of mouse models of DN, and mesangial cells treated with transforming growth factor-b1 (TGF-b1) or high glucose.Lnc-MGC is regulated by an endoplasmic reticulum (ER) stress-related transcription factor, CHOP.Cluster microRNAs and lnc-MGC are decreased in diabetic Chop  /  mice that showed protection from DN. Target genes of megacluster microRNAs have functions related to protein synthesis and ER stress.A chemically modified oligonucleotide targeting lnc-MGC inhibits cluster microRNAs, glomerular ECM and hypertrophy in diabetic mice.Relevance to human DN is also demonstrated.These results demonstrate the translational implications of targeting lnc-MGC for controlling DN progression.\t\nIt is important to find better treatments for diabetic nephropathy (DN), a debilitating renal complication.Targeting early features of DN, including renal extracellular matrix accumulation (ECM) and glomerular hypertrophy, can prevent disease progression.Here we show that a megacluster of nearly 40 microRNAs and their host long non-coding RNA transcript (lnc-MGC) are coordinately increased in the glomeruli of mouse models of DN, and mesangial cells treated with transforming growth factor-b1 (TGF-b1) or high glucose.Lnc-MGC is regulated by an endoplasmic reticulum (ER) stress-related transcription factor, CHOP.Cluster microRNAs and lnc-MGC are decreased in diabetic Chop  /  mice that showed protection from DN. Target genes of megacluster microRNAs have functions related to protein synthesis and ER stress.A chemically modified oligonucleotide targeting lnc-MGC inhibits cluster microRNAs, glomerular ECM and hypertrophy in diabetic mice.Relevance to human DN is also demonstrated.These results demonstrate the translational implications of targeting lnc-MGC for controlling DN progression.",
+      "\t\n\nNumerous recent reports have demonstrated abnormal expression of various miRNAs in renal, vascular and retinal cells under diabetic conditions, and in vivo models of related diabetic complications [8,[87][88][89][90][91]. Notably, the functional relevance of these miRNAs has been highlighted by the fact they target key genes associated with the progression of, or protection against, these complications.In particular, the role of miRNAs in diabetic nephropathy has been extensively studied, including in the actions of TGF- related to fibrosis and other key renal outcomes in vitro and in vivo [8,[87][88][89][90].In diabetic retinopathy, several miRNAs have been reported to modulate the disease by targeting factors associated with angiogenesis, inflammation, and oxidant stress in RECs and in diabetic retinas [88,89].Reports have also implicated various miRNAs in the aberrant expression of genes associated with diabetic cardiomyopathy [88,91].In addition, effective in vivo targeting of miRNAs has now been demonstrated thanks to advances in nucleotide chemistry and the design of nuclease-resistant anti-miRNAs, which suggest future translational potential of miRNA-based therapies for human diabetic complications [8].Importantly, since miRNAs are stable in biological fluids such as urine and serum [8], they are being assessed in samples from various clinical cohorts as valuable biomarkers for the early detection of diabetic complications, for which there is a major unmet clinical need.It is clear that research in the field of miRNAs and diabetic complications will continue at a rapid pace.",
+      "\tIntroduction\n\nDiabetes-related complications represent one of the most important health problems worldwide with dire social and economic projections (Cooper, 2012).One of the most important medical concerns of the diabetes epidemic is diabetic nephropathy (DN).Diabetic nephropathy is regarded as a prototypical disease of gene and environmental interactions because not all diabetic subjects with traditional risk factors develop clinically evident nephropathy, indicating a role for individual susceptibility.The majority (>85%) of GWAS-identified single nucleotide polymorphisms (SNPs) are located in the non-coding regions of the genome and thus their functional implication lies in identifying the target genes, cell types, and the mode of dysregulation caused by these non-coding SNPs (Maurano et al., 2012).Recent studies indicate that complex trait-causing variants localize to cell-type-specific, functionally important gene regulatory regions where they can disrupt or create transcription factor binding sites to alter transcript levels only in disease-target cell types (Ko and Susztak, 2013;Susztak, 2014).Several elements of the immune system including cytokines and resident chemokines, macrophage recruitment, T lymphocytes, and immune complex deposition have recently been associated with DN (Navarro-Gonzlez and Mora-Fernndez, 2008;Gaballa and Farag, 2013).Since renal cells are also capable of synthesizing pro-inflammatory cytokines such as tumor necrotic factor-alpha (TNF-), interleukin-1 (IL-1) and interleukin-6 (IL-6), therefore, these cytokines acting in a paracrine or autocrine manner may induce significant effects leading to the development and progression of several renal disorders (Matoba et al., 2010;Pruijm et al., 2012;Shankar et al., 2011).The rationale of this study involved a concerted effort of genotyping, correlation and gene expression techniques involving three pro-inflammatory cytokine genes  in the development and progression of DN as well as identification of high risk patients involving susceptibility or poor clinical outcome.",
+      "\t\n\nThese studies indicated limited detection of certain biological processes that are also relevant to the pathogenesis of diabetic nephropathy.These included genes pertinent to inflammation and angiogenesis.The limited detection was thought to be attributed to the apparent lack of sensitivity that was associated with the geneoriented averaging probe signals.This shortcoming was rectified by the use of ChipInspector, which is based on single probe analysis and de novo gene annotation that bypasses the probe set definition based on the out-of-date genomic data.In doing so, the single probe-based analysis yielded reduced background noise with enhanced sensitivity and fewer false positives.It also successfully identified the Wnt signaling pathway activated in diabetic nephropathy [63].\t\n\nOne of the major problems facing clinical nephrology currently throughout the world is an exponential increase in patients with end-stage renal disease (ESRD), which is largely related to a high incidence of diabetic nephropathy.The latter is characterized by a multitude of metabolic and signaling events following excessive channeling of glucose, which leads to an increased synthesis of extracellular matrix (ECM) glycoproteins resulting in glomerulosclerosis, interstitial fibrosis and ultimately ESRD.With the incidence of nephropathy at pandemic levels and a high rate of ESRD, physicians around the world must treat a disproportionately large number of diabetic patients with upto-date innovative measures.In this regard, identification of genes that are crucially involved in the progression of diabetic nephropathy would enhance the discovery of new biomarkers and could also promote the development of novel therapeutic strategies.Over the last decade, we focused on the recent methodologies of high-throughput and genome-wide screening for identification of relevant genes in various animal models, which included the following: (1) single nucleotide polymorphism-based genome-wide screening; (2) the transcriptome approach, such as differential display reverse transcription polymerase chain reaction (DDRT-PCR), representational difference analysis of cDNA (cDNA-RDA)/suppressive subtractive hybridization, SAGE (serial analysis of gene expression) and DNA Microarray; and (3) the proteomic approach and 2-dimensional polyacrylamide gel electrophoresis (2D-PAGE) coupled with mass spectroscopic analysis.Several genes, such as Tim44 (translocase of inner mito-chondrial membrane-44), RSOR/MIOX (renal specific oxidoreductase/myo-inositol oxygenase), UbA52, Rap1b (Ras-related GTPase), gremlin, osteopontin, hydroxysteroid dehydrogenase-3 isotype 4 and those of the Wnt signaling pathway, were identified as differentially expressed genes in kidneys of diabetic rodents.Functional analysis of these genes and the subsequent translational research in the clinical settings would be very valuable in the prevention and treatment of diabetic nephropathy.Future trends for identification of the biomarkers and therapeutic target genes should also include genome scale DNA/histonemethylation profiling, metabolomic approaches (e.g.metabolic phenotyping by 1H spectroscopy) and lectin microarray for glycan profiling along with the development of robust data-mining strategies.\tNewly Identified Genes Relevant in the Progression of Diabetic Nephropathy\n\nThe cellular events such as increased flux of polyols and hexosamines; generation of AGEs; increased activity of PKC, transforming growth factor--Smad-MAPK (mitogen-activated protein kinase) pathway and GTP-binding proteins; G1 cell cycle arrest associated with altered expression of cyclin kinases and their inhibitors; and generation of ROS are responsible for a final outcome of increased synthesis and deposition of ECM.The ROS, whether mitochondrial or cell membrane-derived, are also responsible for the activation of the renin-angiotensin system that eventually contributes to glomerular hyperfiltration and subsequent renal fibrosis (fig. 1) [71].In addition to these macromolecules, newly identified genes, such as RSOR/MIOX, Tim44 and Rap1b, may also be an integral part of the hyperglycemia-induced cytosolic and mitochondrial processes that culminate in the development of diabetic nephropathy [48][49][50][51][52][53][54][55].\t\nOne of the major problems facing clinical nephrology currently throughout the world is an exponential increase in patients with end-stage renal disease (ESRD), which is largely related to a high incidence of diabetic nephropathy.The latter is characterized by a multitude of metabolic and signaling events following excessive channeling of glucose, which leads to an increased synthesis of extracellular matrix (ECM) glycoproteins resulting in glomerulosclerosis, interstitial fibrosis and ultimately ESRD.With the incidence of nephropathy at pandemic levels and a high rate of ESRD, physicians around the world must treat a disproportionately large number of diabetic patients with upto-date innovative measures.In this regard, identification of genes that are crucially involved in the progression of diabetic nephropathy would enhance the discovery of new biomarkers and could also promote the development of novel therapeutic strategies.Over the last decade, we focused on the recent methodologies of high-throughput and genome-wide screening for identification of relevant genes in various animal models, which included the following: (1) single nucleotide polymorphism-based genome-wide screening; (2) the transcriptome approach, such as differential display reverse transcription polymerase chain reaction (DDRT-PCR), representational difference analysis of cDNA (cDNA-RDA)/suppressive subtractive hybridization, SAGE (serial analysis of gene expression) and DNA Microarray; and (3) the proteomic approach and 2-dimensional polyacrylamide gel electrophoresis (2D-PAGE) coupled with mass spectroscopic analysis.Several genes, such as Tim44 (translocase of inner mito-chondrial membrane-44), RSOR/MIOX (renal specific oxidoreductase/myo-inositol oxygenase), UbA52, Rap1b (Ras-related GTPase), gremlin, osteopontin, hydroxysteroid dehydrogenase-3 isotype 4 and those of the Wnt signaling pathway, were identified as differentially expressed genes in kidneys of diabetic rodents.Functional analysis of these genes and the subsequent translational research in the clinical settings would be very valuable in the prevention and treatment of diabetic nephropathy.Future trends for identification of the biomarkers and therapeutic target genes should also include genome scale DNA/histonemethylation profiling, metabolomic approaches (e.g.metabolic phenotyping by 1H spectroscopy) and lectin microarray for glycan profiling along with the development of robust data-mining strategies.",
+      "\t\n\nThe current study takes an important first step towards this goal by identifying specific sets of genes whose expression accurately classifies patient samples with regard to diabetic neuropathy progression and by analysing their interactions within known cellular pathways.Identifying common elements in these complex networks will yield novel insights into disease pathogenesis, provide new therapeutic targets and identify potential diabetic neuropathy biomarkers.The genes identified in the current study confirm data gathered from experimental models of diabetes and provide a comprehensive picture of the expression of multiple targets in a single human tissue sample.",
+      "\tM A N U S C R I P T A C C E P T E D\n\nIn relation to the regulation of gene expression, the role of microRNAs (miRNAs) in diabetic retinopathy has been gaining more emphasis.miRNAs are non-coding small RNAs which modulate post-transcriptional control of gene expression through degradation or translational repression of key messenger RNAs.miRNAs can be detected in serum (free, associated with proteins or within membrane-bound particles) (Weiland et al., 2012), vitreous (Ragusa et al., 2013) and aqueous (Dunmire et al., 2013).As reviewed by Mastropasqua et al., miRNAs hold considerable interest for diabetic retinopathy since they can regulate important pathogenic responses such as angiogenesis, blood flow, neural cell dysfunction, tissue-specific inflammation and glucose metabolism (Mastropasqua et al., 2014).Although based on a small patient sample, it has been reported that three separate miRNAs (miR-21, miR-181c, and miR-1179) in serum of patients with diabetic retinopathy have potential to be used as biomarkers for early detection of disease (Li et al., 2014;Qing et al., 2014).While this is still a growing research area, miRNAs hold considerable clinical potential in the diabetic retinopathy field, both as possible drug-targets for regulation of dysfunctional cell responses and as diagnostic biomarkers.",
+      "\t\n\nAll these suggest towards important roles of various lncRNAs in complications associated with diabetes and, therefore, assume importance to be studied in detail.\tRoles of lncRNAs in diabetic complications\n\nApart from being involved in major metabolic tissues during diabetes as discussed above, lncRNAs are implicated in complications associated with diabetes.Diabetic retinopathy is one of the common complications in diabetic patients, which leads to impaired or loss of vision.Altered expression of lncRNAs, namely MALAT1 [82,83] and MEG3 [84], are reported to be associated with diabetic retinopathy.In STZ-induced diabetic rats, the expression of MALAT1 is elevated in the endothelial cells of the retina and knockdown of MALAT1 ameliorates retinopathy in STZ-induced rats [82].The lncRNA, MEG3, was also found to be downregulated in the retina of STZ-induced diabetic mice and its in vitro knockdown in retinal endothelial cells was found to regulate cell proliferation, viability, and migration [84].Hyperglycemia as in diabetes causes upregulation of ANRIL levels in endothelial cells [85,86], and this elevates the levels of the PRC2 subunit, EZH2 that consequently promotes the expression of VEGF, a key promoter of angiogenesis [85].Another major complication associated with diabetes is diabetic nephropathy, and this is considered a major cause of end-stage renal disease and disability in diabetic patients [87].Recent studies show that lncRNAs play important roles in the development of diabetic nephropathy and accumulation of extracellular matrix (ECM) proteins.There is higher expression of the lncRNA, PVT1, during diabetic nephropathy, and this increase leads to increased fibrosis due to accumulation of ECM proteins in renal cells [88]; downregulation of PVT1 reduces ECM accumulation [88].LncRNA PVT1 is also a host to miR-1207-5p and this miRNA is shown to regulate the expression of fibronectin1 (FN1), plasminogen activator inhibitor-1 (PAI1), and transforming growth factor beta 1 (TGF1) [89].In renal tube injury during diabetes, the lncRNA, MIAT, is under-expressed, and this negatively correlates with creatinine and BUN levels in the serum of these subjects.It has been shown to regulate cell viability of proximal convoluted renal tubules [90].In diabetic nephropathic mice, the lncRNA, MGC, is increased in renal mesangial cells.Interestingly, this lncRNA harbours a cluster of approximately 40 miRNAs, and is regulated by the ER stress marker C/EBP homologous protein (CHOP) [91].In CHOP -deficient mice, there is decreased expression of the lncRNA, MGC, and the clustered miRNAs, and these mice have shown an improvement in diabetic nephropathy [91].Diabetic nephropathy is also associated with increased levels of lincRNA, Gm4419, and this exerts its action by interacting with NF-.Knockdown of this lincRNA in renal mesangial cells lowers cellular proliferation and inhibits expression of NF- in hyperglycemic states [92].The lncRNA, TUG1, that is upregulated in diabetic nephropathy acts as sponge for miR-377 and regulates PPAR- expression which further modulates the expression of FN1, collagen type IV alpha 1 chain (COL4A1), PAI1, and TGF1 in renal mesangial cells [93].Diabetic cardiomyopathy is a critical end-stage complication associated with diabetes.Several such cardiovascular complications and myocardial dysfunction in diabetic patients lead to heart failure [94].Differential expression analysis in cardiac tissue from normal and diabetic rats shows that the lncRNA, MALAT1, is upregulated during cardiomyopathy and knockdown of this lncRNA improves left ventricular systolic function by reducing myocardial inflammation in diabetic rats [95,96].Decreased expression of the lncRNA, H19, is also reported during diabetes [68,70], and this often results in decreased expression of the exonic miRNA, miR-675 [97,98].mir-675 directly targets the voltage-dependent anion channel 1 (VDAC1) which is involved in mitochondria-mediated apoptosis in the cardiac tissue during diabetes.H19 overexpression in diabetic rats reduces oxidative stress, apoptosis, and inflammation, and improves ventricle function [98].LncRNAs NONRATT021972 and uc.48+ are reported to be associated with diabetic neuropathic pain [99,100], and inhibition of both have been shown to alleviate such neuropathic pain by activating the P2X3 receptor.Impaired wound closure is a notable complication associated with diabetes and a recent report shows decreased levels of the lncRNA, Lethe in such impaired dorsal wounds of diabetic mice.This was demonstrated to be associated with increased ROS production, possibly through regulation of NOX2 expression [101].",
+      "\t\n\nSkol et al. developed methods to study genomics and transcriptomics together to help discover genes that cause diabetic retinopathy.Genes involved in how cells respond to high blood sugar were first identified using cells grown in the lab.By comparing the activity of these genes in people with and without retinopathy the study identified genes associated with an increased risk of retinopathy in diabetes.In people with retinopathy, the activity of the folliculin gene (FLCN) increased more in response to high blood sugar.This was further verified with independent groups of people and using computer models to estimate the effect of different versions of the folliculin gene.",
+      "\t\n\nUnderstanding how these various pathways translate to cognitive dysfunction in humans with T2DM needs further investigation.",
+      "\t\nInsight into the molecular mechanisms that underlie the origin and progression of diabetic nephropathy remains limited in part because conventional research tools have restricted investigators to focus on single genes or isolated pathways.Microarray technologies provide opportunities for evaluating genetic factors and environmental effects at a genomic scale during the pathogenesis of diabetic nephropathy.Despite",
+      "\t\n\nDR. HARRINGTON: You mentioned Liu's data from China [abstract; Liu Z-H et al J Am Soc Nephrol 14:400A, 2003], which overwhelmed me.Apparently there are 182 genes whose expression is up-or down-regulated significantly in patients with diabetes.If I asked you to pick the \"top three\" genes other than the ACE polymorphisms, which three would you choose and why?DR.ADLER: Well, actually I didn't see all of their results nor did they report all 182.But I guess my favorite ones would be some that relate to the ROS pathway because this is an all-purpose pathway of cell injury fueled by a hyperglycemic environment; some that relate to podocyte structure to explain the development of proteinuria; and TGF-b, which is a master regulator of sclerosis and fibrosis.",
+      "\tIncRNAs and microRNAs\n\nFigure 1 | Emerging molecular mechanisms of diabetic nephropathy.Diabetic conditions induce the expression of growth factors such as transforming growth factor 1 and angiotensin II, cytokines and AGEs to promote inflammation, fibrosis and hypertrophy, which contribute to the progression of diabetic nephropathy.These factors stimulate various signal transduction mechanisms that activate downstream transcription factors.They can also affect DNA methylation and histone modifications, which result in increased chromatin accessibility to transcription factors near pathological genes in renal cells.Coordinated interactions between transcription factors and epigenetic mechanisms can increase the expression of not only coding RNAs, but also noncoding RNAs such as microRNAs and lncRNAs.Furthermore, microRNAs and lncRNAs can also increase the expression of pathological genes via post-transcriptional mechanisms.Notably, the induction of key coding genes and proteins, lncRNAs and microRNAs can also 'lock' open chromatin states to create persistent expression of genes, which could be one mechanism of metabolic memory.Abbreviations: AGE, advanced glycation end-product; lncRNA, long noncoding RNA.\tReview criteria\n\nA search for original published articles focusing on \"diabetic nephropathy\", \"signal transduction\", \"noncoding RNAs\", \"microRNAs\", \"long noncoding RNAs\", \"genetics\" and \"epigenetics\" was performed in MEDLINE and PubMed.All articles identified were English-language, full-text papers.We also searched the reference lists of identified articles for further relevant papers.\t\n\n| microRNAs relevant to the pathogenesis of diabetic nephropathy\tKey points\n\n Diabetic conditions induce inflammation, fibrosis and hypertrophy in renal cells through various cytokines and growth factors such as transforming growth factor 1, angiotensin II and platelet-derived growth factor  The engagement of cytokines and growth factors with their receptors triggers signal transduction cascades that result in the activation of transcription factors to increase expression of inflammatory and fibrotic genes  These signalling mechanisms affect epigenetic states-such as DNA methylation and chromatin histone modifications-to augment the expression of profibrotic and inflammatory genes, as well as noncoding RNAs  Noncoding RNAs that are induced by diabetic conditions can also promote the expression of pathological genes via various post-transcriptional and post-translational mechanisms  These epigenetic mechanisms and noncoding RNAs can lead to persistently open chromatin structures at pathological genes and sustained gene expression, which can also be a mechanism for 'metabolic memory'  Key epigenetic regulators, microRNAs and long noncoding RNAs could serve as new therapeutic targets for diabetic nephropathy"
+    ],
+    [
+      "\t\n\nGenetic risk scores (GRSs) that combine information from multiple genetic variants have been evaluated as a tool for the prediction of type 2 diabetes.Meigs et al. (23) found that a GRS with 18 variants was significantly associated with the risk of developing type 2 diabetes in the Framingham Heart Study (FHS) (odds ratio [OR] 1.12 per variant allele) and that persons in the highest out of three risk categories had an OR of 2.6 for developing type 2 diabetes compared with persons in the lowest risk category.However, this GRS did not improve the prediction of diabetes beyond traditional nongenetic risk factors (23), and the same was true for an updated GRS that included 65 variants (24).To put this into perspective, a prognostic marker with an OR of 3.0 that correctly identifies 80% of persons who will develop diabetes would incorrectly classify 60% of persons who will not develop diabetes (25); this degree of discrimination is not useful clinically (26).",
+      "\t\n\nDespite heterogeneity across populations in risk allele frequency or effect size in type 2 diabetes genes, the combined effects of multiple genetic variants using genetic scores based on the number of risk alleles appear to be similar across different ethnic groups.Typically, each risk allele increment is associated with a 10-20% increased risk of type 2 diabetes (41,42).These data suggest that the overall contribution of the identified genetic loci to type 2 diabetes is similar between Caucasians and other ethnic groups, and that these loci do not appear to explain ethnic differences in diabetes risk.In predicting future risk of diabetes, the clinical utility of these cumulative genetic risk scores appears to be limited in either high-or low-risk populations.",
+      "\t\n\nThe promise of genetic risk scoring for diabetes can be evaluated in the framework of three perspectives.First is the potential for robust prediction of diabetes risk.Second is the prospect of designing targeted preventive and therapeutic interventions (personalized medicine).Thirdly, increased knowledge could provide genomic clues to ethnic disparities in diabetes.Regarding robustness of prediction, results from the Framingham Offspring Study showed that clinical risk assessment (using age, sex, family history, BMI, fasting glucose level, systolic blood pressure, high-density lipoprotein cholesterol level, and triglyceride level) performed as well as cumulative genotype score at 18 loci in predicting incident type 2 diabetes during 28 years of follow-up of initially normoglycemic subjects (14).Also, cumulative genotype score at 34 loci did not add significantly to clinical risk factors in predicting progression from impaired glucose tolerance to type 2 diabetes among the multiethnic cohort enrolled in the Diabetes Prevention Program (15).One current limitation is the incomplete framework from which GRS is constructed.For example, the 17 SNPs studied in the present report (17) represent just about half of the .30diabe-toSNPs identified to date.Even the latter do not represent all possible risk loci, and important information on structural variants that might increase diabetes risk is often lacking.Thus, current experience renders the promise of robust genetic prediction and personalized diabetes intervention a distant hope.",
+      "\tDISCUSSION\n\nType 2 diabetes is a highly polygenic trait, and hundreds of loci associated with the disease have been identified, mostly via large GWAS meta-analyses conducted under additive genetic models (2,3).This prior work has produced useful results, identifying potential therapeutic targets and also enabling the creation of polygenic scores capable of quantifying one's genetic risk (34).A sizeable fraction of the heritability of type 2 diabetes, however, remains unexplained by loci identified using additive models.Recessive modeling offers a way to identify new associations, creating opportunities for discovery and improved genetic risk stratification.",
+      "\t\n\nTwo more recent population -based studies using a longitudinal design with prospectively investigated cohorts have examined the predictive value of a genotype score in addition to common risk factors for prediction of T2DM [194,195] .Meigs et al. [194] reported that a genotype score based on 18 risk alleles predicted new cases of diabetes in the community but provided only a slightly better prediction of risk than knowledge of common clinical risk factors alone [195] .A similar conclusion was drawn in the paper by Lyssenko et al. [196] , along with an improved value of genetic factors with an increasing duration of follow -up, suggesting that assessment of genetic risk factors is clinically more meaningful the earlier in life they are measured.They also showed that  -cell function adjusted for insulin resistance (using the disposition index) was the strongest predictor of future diabetes, although subjects in the prediabetic stage presented with many features of insulin resistance.It is also noteworthy that many of the variants that were genotyped appear to infl uence  -cell function.The addition of DNA data to the clinical model improved not only the discriminatory power, but also the reclassifi cation of the subjects into different risk strategies.Identifying subgroups of the population at substantially different risk of disease is important to target these subgroups of individuals with more effective preventative measures.As more genetic variants are now identifi ed, tests with better predictive performance should become available with a valuable addition to clinical practice.",
+      "\t\n\nRecent large-scale genome-wide association studies (GWAS) in diverse populations have identified hundreds of genetic loci associated with T2D [7][8][9].Polygenic risk scores (PRS), which aggregate the genetic risk of individual alleles across the genome, are thus promising to predict future T2D occurrence and improve early diagnosis, intervention, and prevention of T2D [10][11][12][13][14][15].However, to date, T2D PRS were most widely developed and validated in individuals of European descent.Given that the predictive performance of PRS often attenuates in non-European populations [16], and communities of color are experiencing continuing increased rates of T2D [2][3][4][5], it is critically important to assess and optimize the transferability of T2D PRS in diverse populations before they can be deployed in clinical settings.\t\n\nRecent studies have demonstrated in European individuals that T2D PRS can provide predictive power for incident T2D above and beyond established risk factors such as age, body mass index (BMI), smoking, physical activity levels, and history of high glucose and hypertension and can identify high-risk individuals and stratify lifetime risk trajectories of T2D patients [42,43], suggesting potential for clinical translation.However, most existing T2D scores were developed and validated in individuals of European descent.As the interest in the clinical implementation of PRS for common diseases like T2D continues to grow, a major challenge is the uncertainty about how best to combine multi-ethnic GWAS and estimate polygenic risk in diverse populations.\t\n\nBackground: Type 2 diabetes (T2D) is a worldwide scourge caused by both genetic and environmental risk factors that disproportionately afflicts communities of color.Leveraging existing large-scale genome-wide association studies (GWAS), polygenic risk scores (PRS) have shown promise to complement established clinical risk factors and intervention paradigms, and improve early diagnosis and prevention of T2D.However, to date, T2D PRS have been most widely developed and validated in individuals of European descent.Comprehensive assessment of T2D PRS in non-European populations is critical for equitable deployment of PRS to clinical practice that benefits global populations.\t\nBackground: Type 2 diabetes (T2D) is a worldwide scourge caused by both genetic and environmental risk factors that disproportionately afflicts communities of color.Leveraging existing large-scale genome-wide association studies (GWAS), polygenic risk scores (PRS) have shown promise to complement established clinical risk factors and intervention paradigms, and improve early diagnosis and prevention of T2D.However, to date, T2D PRS have been most widely developed and validated in individuals of European descent.Comprehensive assessment of T2D PRS in non-European populations is critical for equitable deployment of PRS to clinical practice that benefits global populations. Methods:We integrated T2D GWAS in European, African, and East Asian populations to construct a trans-ancestry T2D PRS using a newly developed Bayesian polygenic modeling method, and assessed the prediction accuracy of the PRS in the multi-ethnic Electronic Medical Records and Genomics (eMERGE) study (11,945 cases; 57,694 controls), four Black cohorts (5137 cases; 9657 controls), and the Taiwan Biobank (4570 cases; 84,996 controls).We additionally evaluated a post hoc ancestry adjustment method that can express the polygenic risk on the same scale across ancestrally diverse individuals and facilitate the clinical implementation of the PRS in prospective cohorts. Results:The trans-ancestry PRS was significantly associated with T2D status across the ancestral groups examined.The top 2% of the PRS distribution can identify individuals with an approximately 2.5-4.5-fold of increase in T2D risk, which corresponds to the increased risk of T2D for first-degree relatives.The post hoc ancestry adjustment",
+      "\t\n\nThe currently known risk variants have rather modest effect sizes; the presence of each risk variant or allele is only associated with increases in diabetes risk of between 5% and 40% (ORs 1.05-1.4).Therefore, these loci do not explain more than 10-15% of the estimated genetic heritability of type 2 diabetes [44,49].This estimate is in line with the observation that known risk variants explain only a small fraction of family history-associated diabetes risk [50].Combinations of up to 40 SNPs resulted in AROCs of 0.55-0.63,which is substantially lower than those achieved by age, sex and BMI alone.In some studies, the addition of genotype information to models based on established anthropometric and clinical  It should be noted that the effect of genetic markers on risk prediction may be more pronounced in younger individuals, in leaner persons and in studies with long follow-up periods [53,54], but few studies on young populations, in which the assessment of future genetic risk may be most relevant, are currently available [55].The initial age of individuals is closely related to the time horizon for any model to predict type 2 diabetes.Several prospective studies have applied genetic risk scores for follow-up times of approximately 10 years.This time period corresponds to that in tools such as the Framingham Risk Score, which estimates an individual's 10-year risk for incident cardiovascular disease.It has been proposed that genetic risk scores might be more helpful in longer term prediction because, in contrast to variables used in clinical risk scores, genetic variants do not change over time [52,56].Eventually, the time horizon for risk models needs to correspond to the period before the onset of type 2 diabetes in which preventive efforts are most effective.",
+      "\t\n\nIn conclusion, the inclusion of common genetic variants that are associated with type 2 diabetes very slightly improved the prediction of future type 2 diabetes, as compared with the inclusion of clinical risk factors alone.Although this effect might be too small to allow for individual risk prediction, it could be useful in reducing the number of subjects who would need to be included in intervention studies aimed at the prevention of type 2 diabetes.Supported by grants from the Swedish Research Council (including Linn grant 31475113580), the Heart and Lung Foundation, the Swedish Diabetes Research Society, a Nordic Center of Excellence Grant in Disease Genetics, the Diabetes Program at the Lund University, the Finnish Diabetes Research Society, the Sigrid Juselius Foundation, the Phlsson Foundation, the Crafoord Foundation, the Folkhlsan Research Foundation, the Novo Nordisk Foundation, the European Network of Genomic and Genetic Epidemiology, the Wallenberg Foundation, and the European Foundation for the Study of Diabetes.",
+      "\t\n\nIdentification of individuals at increased genetic risk for T2D may enhance screening strategies and allow for targeted prevention.Previous attempts to deploy genetic data for disease prediction have shown limited utility 44,45 .We used a revised BMI-unadjusted meta-analysis, generated from all samples other than the UK Biobank samples, to develop genome-wide polygenic risk scores (PRSs) 46 , which we then applied to predict T2D status in the 18,197 cases and 423,697 controls from the UK Biobank (Europeans only; Methods) 46 .Maximal discrimination (area-under-the-curve C statistic of 66%, equivalent to that derived from BMI, age, and sex in the same sample) was obtained from a PRS of 136,795 variants (r 2 > 0.6, P < 0.076; Supplementary Fig. 10).Individuals in the top 2.5% of the PRS distribution were at 3.4-fold-increased risk (prevalence = 11.2%)compared with the median (prevalence = 3.3%), and at 9.4-fold-increased risk compared with the bottom 2.5% (prevalence = 1.2%).Low T2D prevalence in the UK Biobank reflected the age distribution of the cohort and preferential ascertainment of healthy individuals; however, similar prevalence ratios were observed in the subset of individuals > 55 years of age at recruitment (14.2% versus 1.6%).If applied to the general UK population, an equivalent performance would equate to lifetime T2D risks of ~59.7% and ~6.7% for individuals from those extremes, on the basis of current UK general-population prevalence rates for individuals > 55 years of age 47 .",
+      "\t\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.\t\n\nDuring the last decade, there have been substantial advances in the identification and characterization of DNA sequence variants associated with individual predisposition to type 1 and type 2 diabetes.As well as providing insights into the molecular, cellular, and physiological mechanisms involved in disease pathogenesis, these risk variants, when combined into a polygenic score, capture information on individual patterns of disease predisposition that have the potential to influence clinical management.In this review, we describe the various opportunities that polygenic scores provide: to predict diabetes risk, to support differential diagnosis, and to understand phenotypic and clinical heterogeneity.We also describe the challenges that will need to be overcome if this potential is to be fully realized.\t\n\n During the last decade, there have been major advances in our understanding of the genetic basis of the most common subtypes of type 1 (T1D) and type 2 diabetes (T2D), with .500robust associations identified  Although individual variants typically have only a modest effect on risk, when combined into a polygenic score, they offer increasing power to capture information on individual patterns of disease predisposition with the potential to influence clinical management\tSummary and Further Discussion\n\nAfter many years of frustration at the slow progress that had been made in the translation of recent discoveries in human genetics-notably the many risk variants for common, multifactorial forms of diabetes identified through GWAS and sequencing-there is now growing optimism that the use of polygenic scores will offer substantial clinical benefit and contribute to efforts to forestall the growing morbidity and mortality associated with these conditions.Some early clinical applications have emerged, mostly related to positive identification of those who have developed, or are at the highest imminent risk of developing, TD (, -).\tPolygenic Scores in Action\n\nPredicting T2D onset The slow onset of TD, coupled to evidence that the damaging consequences often predate the clinical diagnosis by some years (), emphasizes the clinical value of early diagnosis.The capacity for drugs and lifestyle interventions to lead to substantial reductions in the progression to diabetes (, ) motivates efforts to identify those at the greatest future risk of developing TD.As discussed above, genetic predictors have the particular advantage of offering predictive information that is stable throughout life.\t\n\nIn this review, however, we focus on a different route from human genetics to translation, one that derives estimates of an individual's predisposition to diabetes and its subtypes (in the form of polygenic scores) from the patterns of individual geneticvariation at sites known to influence diabetes predisposition.\t\n\n The generation of polygenic scores based on overall T2D predisposition can identify individuals with a high future risk of diabetes who may benefit from targeted interventions",
+      "\t\n\nThe discriminatory capacity of genetic variants for T2D risk prediction and patient stratification has been assessed in longitudinal studies by examining whether inclusion of genetic risk scores (GRS) in predictive models increases the area under the receiver-operating-characteristic curve compared to predictive models including only clinical parameters.Early studies suggested that inclusion of GRS provided little improvement in T2D risk prediction compared to clinical risk factors and family history alone (Lyssenko et al. 2008;Meigs et al. 2008;Balkau et al. 2008;Talmud et al. 2010;de Miguel-Yanes et al. 2011).More recent studies, incorporating increasing numbers of T2D risk variants into the GRS, have also had mixed results (Hivert et al. 2011;Muhlenbruch et al. 2013;Vaxillaire et al. 2014).For example, while a recent study incorporating 43 T2D associated variants showed little improvement in T2D prediction, inclusion of the GRS in predictive models improved the receiver-operating-characteristic curve for subgroups of subjects at increased risk of T2D, including obese subjects, older participants, and those with a family history of diabetes (Muhlenbruch et al. 2013).Similarly, Hivert et al. have shown that a GRS with 34 variants was significantly associated with increased risk of progression to T2D in high-risk individuals, as well as a reduced effect of lifestyle interventions on genetic risk (Hivert et al. 2011)."
+    ],
+    [
+      "\tA measure of -cell exocytosis based on electrical current. the scalability of such studies.Moreover, a genome-wide CRISPR loss-of-function screen performed in 2019 identified 373 potential regulators of insulin production in the mouse insulinoma-derived Min6 -cell line 178 .Extending genome-wide screens to human -cell models and increasing the diversity of cellular read-outs will provide orthogonal data sets for integration with existing genetic and genomic resources, in order to elucidate downstream biology.As the current protocols for hiPSC differentiation are expensive, are time-consuming and have variability in differentiation efficiency, continued advancements in differentiation protocols will enable similar approaches in these cell models.",
+      "\t\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\t\n\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\tDiscussion\n\nUsing next-generation sequencing, we have established the first catalog of miRNAs in human pancreatic islets and beta-cells, and explored the overlap between these miRNAs and T2D genetic susceptibility.Our catalog not only serves as a valuable resource for those interested in the roles of specific miRNAs in normal islet physiology and beta-cell function, it also provides a reference for the study of miRNA mediated abnormalities in islets from type 2 diabetic donors.The abundance of miR-375 in the miRNA profile provides valuable support for a critical role in human pancreatic beta-cells, mirroring the well-established role in rodent islet biology.miR-375 null mice are hyperglycaemic and exhibit reduced beta-cell mass [40].In a clonal rodent beta-cell line (MIN6), knockdown or over-expression of this miRNA influences glucose-stimulated insulin secretion [7].Furthermore, knockdown of miR-375 in obese ob/ ob mice results in a more profound effect on glycaemia leading to a severe diabetic phenotype in these mice [40].Our study establishes that miR-375 is also abundantly expressed in human islets and warrants further studies to define the contribution of miR-375 to the pathogenesis of T2D.",
+      "\t\n\nOne strategy to study these monogenic syndromes would be to derive hiPSCs from these patients, differentiate them into pancreatic progenitors and then transplant these progenitors into immunocompromised (SCID-Beige or NSG) mice for in vivo maturation (Figure 2).This methodology has been recently used to successfully model MODY2, demonstrating that beta cells derived from hiPSCs with GCK mutation are indeed less sensitive to glucose levels [7].Endoplasmic reticulum (ER) stress-related diabetes in patients with Wolfram syndrome has also been modeled using hiPSC-derived beta cells, demonstrating that WFS1 protein maintains ER function in beta cells by acting upstream of the unfolded protein response (UPR) pathways [8].phenotypes occurring in humans.Likewise, the stepwise analysis of human pancreatic development with this strategy would likely provide mechanistic insights into the ability of a single gene mutation (PDX1, PTF1A, HNF1B, GATA6 and GATA4) to promote pancreatic agenesis/ atrophy.Further, studying mutations in KCNJ11 and ABCC8 using hiPSC-derived beta cells may elucidate the mechanistic differences between permanent and transient neonatal diabetes [64].Overall, insulin production and secretion could be compared between diseased and gene-corrected pancreatic cells to understand the underlying cause of each type of monogenic diabetes (Figure 2).",
+      "\tPRECISE CELLULAR GENOMICS\n\nElucidating the molecular mechanisms that lead to beta cell dysfunction and T2D pathogenesis has been a major focus of diabetes research for decades.However, advances in single cell genomic profiling techniques have led to greater understanding of non-beta cell type transcriptional regulation and suggest that they may play important roles in hallmark features of beta cell insufficiency and failure linked to T2D genetic risk and pathophysiology.Single cell transcriptome analysis of human islet cells indicate that multiple monogenic diabetes genes are highly expressed in beta cells (e.g., PDX1, PAX4, INS, HNF1A, and GCK) [27].However, other non-beta cell types express genes mutated in monogenic diabetes (such as PAX6 and RFX6), congenital hyperinsulinemia (HADH, UCP2) and those implicated as T2D GWAS target/effector genes [28].Recent study of type 1 diabetic (T1D) human islets has provided surprising insights into alpha cell biology.In T1D islets, the alpha cell proportions remain relatively unchanged despite abnormal glucagon secretion [29].This dysregulated glucagon secretion is instead accompanied by decreased expression of important islet transcription factors including ARX, MAFB, and RFX6 and increased expression of stress response factors such as ATF4, ERN1, and HSPA5 [29] suggesting that changes in alpha cell identity may ultimately lead to their dysfunction.Analysis of normal and T2D islet single cells with simultaneous RNA-seq and patch clamping (patch-seq) also revealed subpopulations of alpha cells with varying enrichment for ER stress response genes (e.g., DDIT3, XBP1, PPP1R15A) [30].Interestingly, this transcriptomic heterogeneity was consistent in normal and T2D islets and associated with variability in alpha cell electrophysiological measures; ER stressed alpha cells had lower cellular size and Na  peak current.Prior single cell transcriptomic analyses have also noted subpopulations of ER-stressed beta cells [31,32] which implicates the dysfunction of both alpha and beta cells in diabetes pathogenesis.Similarly, the integrity of beta and alpha cell functions seem to be dependent on each other, as under hypoglycemic conditions, T2D islets show reduced insulin, C-peptide, and glucagon secretion [33].Additionally, during a glycemic clamp experiment, an increase in glucagon secretion was positively correlated with beta cell function suggesting that signaling between the two islet cell types is crucial for maintaining glucose homeostasis.Studies of delta cells in Sst-Cre transgenic mouse models [34e36] reveal that timely regulation of insulin secretion is controlled by various delta-cell specific pathways.Induction of the ghrelin receptor (Ghsr) in delta cells was correlated with enhanced somatostatin release and ultimately reduced insulin and glucagon secretion [35,36].Furthermore, the peptide hormone Ucn3 was shown to be co-released with insulin from beta cells to activate type 2 corticotropin-releasing hormone receptor (Crhr2) on delta cells in an alternate pathway that promotes somatostatin release and negatively regulates insulin levels [34].Delta cells are also notably enriched for G protein-coupled receptors (e.g., GLP1R, GIPR, GPR120) which exert careful control over metabolism [37].These receptors are also common therapeutic targets of T2D, suggesting that treatment and management of the disease should not neglect delta cell (dys)function and/or survival.Efforts to characterize the epigenomes of each islet cell type are emerging and revealing new insights of cellular fate and differentiation.Two groups have performed open chromatin profiling of purified beta and alpha cell fractions [10,12] and identified between 1850 and 3999 beta and 5316-27,000 alpha-specific peaks.These cell-specific regions were enriched for transcription factor motifs implicated in cell development and were enriched for diabetes-associated SNPs.Arda and colleagues also suggest that the beta cell epigenome is plastic and capable of being derived from other endocrine and exocrine precursor cells.Discrepancies in the numbers of cell-specific peaks determined by both groups are likely due to the cell surface markers used to enrich for each.CD26/DPP4, used by Arda et al., is a strong positive selector for alpha cells, which then enables negative selection for beta and other minor cell populations.However, this method of enrichment for beta cells will not remove contaminating delta and PP/gamma cells.Continued development of new tools and markers for islet cell enrichment, such as NTPDase3 [38] should continue to help us to understand changes elicited by genetic and environmental factors in each distinct cell type.Iterative proteomic screens in human islets are also proving useful for identifying putative cell-specific surface markers for isolation [39], wherein beta and delta cell populations were obtained by co-enrichment for CD9 and CD56.Challenges currently remain to exclusively enrich for the minor islet cell types (delta, gamma/PP), thus strategies that negatively select for these cells may be needed.Study of the rarer gamma/PP cells, which constitute roughly <1e5% of the total islet volume, remain limited due to the lack of known cell-surface markers for enrichment and purification (Figure 2).Whole islet analyses are unable to capture cell type-specific changes and therefore preclude analysis of their potential roles in T2D genetics and pathophysiology.Given the clear and extensive genotype effects on cis-RE usage [13,15] and gene expression [11,16,17] in islets, more extensive analysis of sorted cell types from multiple individuals is warranted to define a representative set of islet cell-specific REs and distinguish condition-specific from genotype-driven effects on their use and activity.\t\n\nunderstand each cell type's genomic architecture and better characterize their roles in islet resilience and failure.Experimental manipulation of the regulatory elements and/or the target genes identified by (epi)genomic approaches described above and modeling the putative pathways and processes they implicate in human islet cell lines (e.g., EndoC-bH1-H3) is essential to progress from correlation to causation.Similarly, transitioning from \"the\" mouse (C57BL/6) to multiple mouse models for insights into the effects of naturally occurring genetic variation on islet function and physiology [61] and for manipulation of key genomic elements should also help characterize the dynamic range of islet behavior and response.T2D is a heterogeneous, complex, and progressive disorder, as multiple subtypes have been identified and associated with different genetic risk and clinical outcome profiles.Future islet genomics studies that focus on identifying the distinct subgroups of individuals with distinct genes/pathways that are disrupted and/or contributing to islet (dys)function at basal and/or responsive states are needed.Furthermore, priority should be given to profiling more islets from pre-diabetic and T2D individuals to characterize the transition between basal to stressed to T2D state and determine if there are intermediate signatures for islet failure and T2D onset.Together, this multi-pronged approach toward studying T2D genetics and islet pathophysiology will help identify additional targets and opportunities for intervention that can be exploited for more precise and effective preventative, treatment, and management options for T2D.\t\n\nFigure2: Moving towards a more precise understanding of islet cellular genomics and responses.Proper elucidation of islet (dys)function and its association with T2D pathogenesis is confounded by individual genetic variation as well as islet cellular heterogeneity.To obtain a better understanding of both, future studies must prioritize strategies to obtain purified islet cell type populations (e.g., beta, alpha, delta, gamma/PP) via sorting with specific cell surface markers.Characterization of each cell type-specific genomic profile at baseline, stimulated, and diseased conditions will provide clearer understanding of key cellular and molecular processes that are altered and important in T2D development.Additionally, by sampling islets from multiple individuals and leveraging genotypes, it will be possible to identify cis-regulatory elements and genes that are influenced by genetics rather than disease state.SNP  single nucleotide polymorphism; QTL  quantitative trait locus; ER  endoplasmic reticulum.\t\n\nFigure3: Challenges with identifying gene expression alterations in type 2 diabetes.Gene expression measurements from RNA-seq data typically represent only a snapshot of tissues' or cell types' transcriptome at a given point in time.In recent comparative analyses of islet intact and single cell transcriptomes from T2D and ND individuals, relatively few genes are significantly altered despite the clear phenotypic differences between them.This may suggest that the mechanisms that precede islet failure and T2D pathogenesis are post-transcriptional and cannot be detected in conventional RNA-seq analyses.However, it is also possible that the putative paths of these genes' alterations over the course of islet physiological decline and T2D development are simply being missed.Genes that are important for islet function and resilience (e.g., Gene A) and those whose expression directly induces or is the consequence of islet failure (e.g., Gene C) may be detected in a comparative analysis between islets at healthy and decompensated states.However, response genes that are temporarily induced by islet stress (e.g., Gene B) would not be detected in this comparison.",
+      "\tModels of beta cell function\n\nThe beta cell plays a central role in the development of both type 1 and type 2 diabetes as well as playing a key role in less common classifications of diabetes such as maturity onset diabetes of the young (MODY), gestational diabetes, neonatal diabetes and other beta cell syndromes such as hyperinsulinism.Therefore, models of beta cell function are highly relevant in understanding pathways that can lead to the inability of beta cells to secrete appropriate amounts of insulin.Such models are often genetically manipulated, such as mutations of Kir6.2 to study KATP channel function (Girard et al., 2009) or mutations in glucose kinase to understand the function of the glucose sensor in beta cells (Fenner et al., 2011).A role for serotonin in the expansion of islets in pregnancy has recently been elucidated by studying the islets of mice lacking the serotonin receptor Htr2b (Kim et al., 2010).Studies such as these can increase our knowledge of beta cell function and its role in a variety of conditions.However, it should be pointed out that the same mutation in humans can lead to different symptoms in mice as recently shown by Hugill et al., where a mutation in Kcnj11 (encoding a subunit of the KATP channel) caused hypersecretion of insulin and hypoglycaemia in their patient, but glucose intolerance and reduced insulin secretion in mice (Hugill et al., 2010).However, this may prove useful in understanding the transition from hyperinsulinism of infancy (HI) to diabetes in some patients (Hugill et al., 2010).",
+      "\t\nHuman genetic studies have emphasised the dominant contribution of pancreatic islet dysfunction to development of Type 2 Diabetes (T2D).However, limited annotation of the islet epigenome has constrained efforts to define the molecular mechanisms mediating the, largely regulatory, signals revealed by Genome-Wide Association Studies (GWAS).We characterised patterns of chromatin accessibility (ATAC-seq, n = 17) and DNA methylation (whole-genome bisulphite sequencing, n = 10) in human islets, generating high-resolution chromatin state maps through integration with established ChIP-seq marks.We found enrichment of GWAS signals for T2D and fasting glucose was concentrated in subsets of islet enhancers characterised by open chromatin and hypomethylation, with the former annotation predominant.At several loci (including CDC123, ADCY5, KLHDC5) the combination of fine-mapping genetic data and chromatin state enrichment maps, supplemented by allelic imbalance in chromatin accessibility pinpointed likely causal variants.The combination of increasingly-precise genetic and islet epigenomic information accelerates definition of causal mechanisms implicated in T2D pathogenesis.\t\n\nHuman genetic studies have emphasised the dominant contribution of pancreatic islet dysfunction to development of Type 2 Diabetes (T2D).However, limited annotation of the islet epigenome has constrained efforts to define the molecular mechanisms mediating the, largely regulatory, signals revealed by Genome-Wide Association Studies (GWAS).We characterised patterns of chromatin accessibility (ATAC-seq, n = 17) and DNA methylation (whole-genome bisulphite sequencing, n = 10) in human islets, generating high-resolution chromatin state maps through integration with established ChIP-seq marks.We found enrichment of GWAS signals for T2D and fasting glucose was concentrated in subsets of islet enhancers characterised by open chromatin and hypomethylation, with the former annotation predominant.At several loci (including CDC123, ADCY5, KLHDC5) the combination of fine-mapping genetic data and chromatin state enrichment maps, supplemented by allelic imbalance in chromatin accessibility pinpointed likely causal variants.The combination of increasingly-precise genetic and islet epigenomic information accelerates definition of causal mechanisms implicated in T2D pathogenesis.",
+      "\t\n\nA number of mechanisms could contribute to the reduced insulin secretion in vivo that has been associated with several T2D susceptibility variants.Dissection of the underlying cellular pathology requires 1) access to relevant human tissues from nonrisk and risk genotype carriers, which facilitates the correct translation of association signals compared with studying genetically modified animals, and 2) characterization of the effect of genotype on detailed cellular phenotypes.There are fundamental electrophysiological and secretory differences between human and rodent b-cells, making the study of human islets essential to investigate the influence of T2D susceptibility variants on b-cell function.The biophysical and ultrastructural examination of human b-cells in the current study identified four T2D variants that were associated with reduced exocytosis and enabled characterization of the mechanisms for the exocytotic impairment.The results shed new light on the pathophysiology linked with these risk variants, near TCF7L2, ADRA2A, KCNJ11, and KCNQ1, and demonstrate that defective b-cell exocytosis can be an important pathogenic mechanism in genetic subgroups of T2D.The data  suggest that there may be considerable heterogeneity in the cellular pathways that lead to reduced insulin secretion, which may explain why the reduction of exocytosis is evident only in genetic subgroups and not in the entire T2D cohort.Stratification based on genetic variants may therefore be useful to better resolve the disease mechanisms.Similar approaches may therefore be valuable to study the T2D susceptibility variants that were not associated with defective b-cell exocytosis in the current study (Table 1) and may instead impair systemic insulin release through effects on b-cell mass and/or glucose sensing or indirectly via incretins and innervation.",
+      "\t\n\nNevertheless, for diseases such as diabetes and obesity, limited access to the tissues most obviously implicated in disease pathogenesis-the pancreatic b cell and hypothalamus, respectively-represents a serious obstacle to such studies.Advances in stem cell science offer the exciting prospect of overcoming this limitation through re-differentiation of patient-derived induced pluripotent stem (iPS) cells to generate authentic cellular models of key tissues.In parallel, ongoing large-scale sequencing studies are likely to reveal novel low frequency and rare risk alleles in coding sequence, some with larger effects than those encountered by existing GWAS.The expectation is that these will be inherently more amenable to experimental follow-up, accelerating the pace of functional discovery and delivering biological insights that will underpin the development of novel diagnostic and therapeutic options.",
+      "\t\n\nIt is worth mentioning that in [132], a meta-analysis study was conducted, where a collection of gene expression datasets of pancreatic beta-cells, conditioned in an environment resembling T1D induced apoptosis, such as exposure to proinflammatory cytokines, in order to identify relevant and differentially expressed genes.The specific genes were then characterized according to their function and prior literature-based information to build temporal regulatory networks.Moreover, biological experiments were carried out revealing that inhibition of two of the most relevant genes (RIPK2 and ELF3), previously unknown in T1D literature, have a certain impact on apoptosis.",
+      "\t\n\nNotably, single-cell transcriptome profiling has been utilized in the past few years to discern cellular heterogeneity within the islets of Langerhans (Fischer et al. 2019;Tritschler et al. 2019Tritschler et al. , 2017)), particularly for beta cells (Baron et al. 2016;Lawlor et al. 2017a;Segerstolpe et al. 2016;Teo et al. 2018;Xin et al. 2016).Segerstolpe et al. ( 2016) investigated cell-type specific gene expression in the pancreas of healthy and type 2 diabetic individuals and uncovered major gene expression differences (transcriptional signatures) between exocrine and endocrine cell types, including the less abundant cell types such as human delta, gamma and epsilon cells.Previously, these cells had been difficult to observe due to bulk characterization methods (Lawlor et al. 2017a), however, single-cell RNA sequencing has shed light on the novel roles for each rare cell type based on their activated signalling pathways and receptor proteins (Lawlor et al. 2017a;Segerstolpe et al. 2016).For example, insight into the transcriptome of the minority cell type, epsilon cells and its ghrelin-producing capability was provided (Segerstolpe et al. 2016), as well as the expression of the rare delta and gamma cell types that are prompted by hormonal cues from leptin, ghrelin and dopamine signalling pathways to facilitate metabolic signalling in the pancreas (Lawlor et al. 2017a).Further single-cell RNA investigations by Xin et al. (2016) showed a total of 245 genes to be affected by type 2 diabetes when compared to non-diabetic single-cell transcriptomes.Among the common transcript expression profiles found between the human islet cells, only 20 genes (for example, RBP4, DLK1, ADCYAP1, RGS16, SOX4, BMP5, TIMP2, TSPAN1, MAFB and TFF3) were specific to a certain cell type (Xin et al. 2016).Lastly, a few recent reviews have tracked the progress of genes linked to specific endocrine cell types in these studies (see Chiou et al. 2019;Tritschler et al. 2017), with some going as far as to re-analyse the single-cell transcriptome datasets using a machine learning approach (Ma and Zheng 2018).The in-depth analyses reported on oxidative stress being the perpetrator to enhance beta-cell dysfunction as a final result, together with the potential activation of pathways linked to beta-cell apoptosis that may be the resulting cause of an insulin gene expression deficit in type 2 diabetes (Ma and Zheng 2018).",
+      "\t\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.",
+      "\t\n\nOur primary intent was to employ an integrative genomics approach to identify mitogenic mechanisms with potential application for human beta cell expansion (Supplementary Fig. 1).This approach entails integrating whole-exome and RNAsequencing data into network analysis to computationally model insulinoma molecular events relative to normal adult and juvenile human beta cells.We reasoned that although some molecular events in insulinoma are likely relevant to the mechanisms of tumor formation, some may serve to uncover the genetic mechanisms that enforce beta cell quiescence, and are bypassed in such benign tumors.We further validated combinations of lead candidate genes derived from this approach as beta cell mitogenic mediators.Notably, we focused on insulinomas from subjects not known to be members of multiple endocrine neoplasia type 1 (MEN1) kindreds, as the MEN1 gene has been previously reported as one of the most frequently mutated genes in hereditary pancreatic neuroendocrine tumors (PNETs), although MEN1 mutations are uncommon in sporadic insulinomas [5][6][7] .Despite attempting to exclude MEN1 subjects, we nevertheless find widespread abnormalities in genes functionally related to MEN1, revealing a previously unsuspected unifying mechanism underlying insulinoma.",
+      "\t\n\nIn summary, we established an isogenic hESC platform to systematically evaluate the role of disease-associated loci in the survival and function of human pancreatic beta-like cells in vitro and in vivo.The platform can be used to study other disease-associated loci/variants with respect to beta-like cell function.It is worth noting that the glucose-responding cells derived using the current reported protocols are not equivalent to primary human beta cells.Ca 2+ flux assays suggested that approximately 30%-40% of the insulin-GFP + cells show increased cytosolic Ca 2+ concentrations in response to glucose stimulation (Figure S7Q), whereas robust glucose-induced signaling was observed in more than 70% of human beta cells based on the previous report (Rezania et al., 2014).The restricted functionality of pancreatic beta-like cells derived using current protocols might limit their application for evaluating subtle contributions of genes to glucose metabolism and Ca 2+ signaling.Thus, additional work is needed to further improve the protocol to derive mature pancreatic beta-like cells.In addition, the platform established here can also be applied to study the role of disease-associated loci/variants in other diabetes-related cell types, such as hepatocytes, adipocytes, muscles, and/or intestinal neuroendocrine cells.Finally, the system may be used as a highthroughput/content chemical screening platform to identify candidate drugs correcting allele-specific defects for precision therapy of metabolic diseases.\t\n\nWe built on recent work deriving glucose-responsive pancreatic beta-like cells from hESCs/iPSCs (Pagliuca et al., 2014;Rezania et al., 2014) and used isogenic hESC-derived glucose-responding cells to systematically examine the role of several GWAS-identified genes in pancreatic beta cell function and survival.Whereas the mutations do not affect the generation of insulin + cells, they impaired insulin secretion both in vitro and in vivo, coinciding with defective glucose homeostasis.CDKAL1 / insulin + cells also displayed hypersensitivity to glucolipotoxicity.A high-content chemical screen identified a candidate drug that rescued CDKAL1 / -specific defects by inhibiting the FOS/JUN pathway.These studies represent a proof of principle for the use of isogenic hESC-derived cells to define the precise role of genes associated with disease though GWASs in human pancreatic beta cells, as well as the leadcompound identification for pharmacological intervention of T2DM."
+    ],
+    [
+      "\t\n\nAlthough these proof-of-concept studies provide exciting insights into possible epigenetic mechanisms that may underpin the developmental origins of obesity and metabolic disorders later in life, one has to bear in mind their limitations.The early studies in general investigated only a small sample, lacked independent replication, and the methylation changes detected through the hypothesis-free genome-wide approach often do not reach biological levels of significance.Additional considerations include the use of tissues that are not embryonic in origin (e.g.placental tissue), tissues that contain a mixture of different cell types (e.g.umbilical cord or cord blood) as well as tissue of mixed maternal or fetal origin (placenta again).Therefore, epigenetic changes in the tissues studied thus far may not represent the full spectrum, or the most relevant epigenetic changes associated with maternal hyperglycaemia and its metabolic consequences, given the difficulty of investigating relevant metabolic tissues such as the pancreatic islet, muscle, liver, adipose tissue and brain.It is expected that some of the changes present in accessible tissue such as cord blood may also be present in other tissues, though the relationship between epigenetic markers in different tissues remains to be clarified because epigenetic marks are likely to be tissue-and context-specific.Recent studies suggest there are some consistent changes in methylation that are observed in blood and other tissues such as brain, signifying that peripheral blood may be useful for identifying functionally relevant epigenetic pathways in disease-relevant tissues (Davies et al., 2012).Another important issue is the need for prospective studies to eliminate the effect of reverse causality.This has been more of a problem in epigenetic studies in other disciplines, but less so in the field of developmental origins of health and disease, where there are large numbers of well-characterized longitudinal birth cohorts with longterm follow-up and a variety of biological specimens collected.We recently conducted a genome-wide analysis of GDM methylation changes by comparing offspring of mothers with GDM or controls from our longitudinal follow-up study (Tam et al., 2008(Tam et al., , 2010)).We found several consistent differentially methylated regions between GDM-offspring and non-exposed offspring at 8 and 15 years, suggesting that, at least for some of these markers, once the epigenetic changes are set they may persist through adolescence and beyond (Luan et al., 2014).\t\n\nIn addition to changes following exposure to intra-uterine hyperglycaemia, epigenetic changes have also been noted in other experimental settings of hyperglycaemia.For example, increased DNA methylation has been described for the promoter region of the peroxisome proliferator-activated receptor-g (PPARg) coactivator-1a gene (PPARGC1A) in diabetic islets (Ling et al., 2008).Similar hypermethylation in the promoter region of the PPARGC1A gene has been noted in the skeletal muscle from diabetic patients, and correlated with mitochondrial content (Barr es et al., 2009).Epigenetic changes have also been suggested to be responsible for the \"legacy effect\" of reduced risk of vascular complications after a period of sustained tight glucose control, or \"metabolic memory\" of transient hyperglycaemia and increased risk of diabetic vascular injury (Pirola et al., 2010).Histone methylation variations have been noted in monocytes cultured in high glucose, as well as blood monocytes of diabetic patients (Miao et al., 2007).In a series of landmark experiments, it was shown that endothelial cells exposed to short-term hyperglycaemia had persistently increased expression of the NF-kB active subunit p65, and was associated with increased promoter H3K4me1 and occupancy by the histone monomethyltransferase SET7/9.In addition, transient hyperglycaemia was also associated with sustained reduction of H3K9 methylation on the NF-kB p65 promoter, as well as recruitment of lysine-specific demethylase (LSD1) (El-Osta et al., 2008;Brasacchio et al., 2009).LSD1 has also been found to regulate H3K4 methylation in vascular smooth muscle cells in hyperglycaemic conditions, and may mediate the vascular inflammation (Reddy et al., 2008).Other epigenetic mechanisms including microRNAs and long noncoding RNAs have also been implicated in the pathogenesis of diabetic complications (Kato et al., 2014).",
+      "\tEpigenetic Mechanisms in Diabetic Complications 22\n\nsupportive animal studies demonstrated that mice exposed to short-term hyperglycemia followed by glucose normalization displayed sustained increases in promoter H3K4me1 and p65 expression in aortic endothelial cells (35).It is likely that similar epigenetic changes also occur in cells such as retinal pericytes and endothelial cells, or renal mesangial cells, tubules and podoctyes that are involved in common diabetic complications, retinopathy and nephropathy.\t\n\nOverall, these results indicate that prior exposure to hyperglycemia and even periods of transient high glucose or metabolic control can lead to epigenetic changes in target cells altering chromatin structure and resulting in long lasting repercussions for gene expression levels associated with the pathology of diabetic micro-and macro-vascular complications (Figure 2).",
+      "\tSummary\n\nIncreasing evidence shows that, besides the well-described biochemical mechanisms, epigenetic mechanisms might also participate by fine-tuning gene expression to modulate the aetiology of diabetic complications.Persistence of epigenetic modifications triggered by diabetic stimuli could be one of the key mechanisms underlying metabolic memory.However, the involvement of many epigenetic factors and mechanisms involved in the regulation of the modifications by upstream signal transduction pathways remains unknown.However, this is a rapidly expanding and dynamic field and it is likely that other epigenetic factors related to diabetic complications will soon be uncovered.Epigenomics may also aid in determining the functional roles of complications-associated genetic variants.It would be worthwhile to assess whether lifestyle modifications such as exercise and healthy diets can reduce diabetic complications by altering epigenetic marks.A recent study showed the beneficial effects of exercise on epigenetic marks related to diabetes [106].Because epigenetic changes are potentially reversible in nature, combination therapies with epigenetic drugs (epidrugs) [38] and antagomirs (miRNA inhibitors) [8] could be considered to complement the current treatments for complications.However, there are also key challenges.Since epigenetic patterns are cell specific, data from heterogeneous tissue samples and biopsies could be difficult to interpret.Furthermore, apart from hyperglycaemia, other factors associated with diabetes, including insulin resistance, obesity, dyslipidaemia, environment, lifestyles and genetics, can work independently or co-operatively to also promote epigenetic changes in various affected target tissues.\tEpigenetics and the epigenome: rationale for study in diabetic complications\n\nEpigenetic control of gene regulation plays an important role in development, cell identity, stable inheritance of gene expression patterns in differentiated cells, genomic imprinting, X chromosome inactivation, stem cell plasticity, differential disease susceptibility between monozygotic twins, and cellular responses to environmental signals [34,35].",
+      "\t\nIn addition to genetic predisposition, environmental and lifestyle factors contribute to the pathogenesis of type 2 diabetes (T2D).Epigenetic changes may provide the link for translating environmental exposures into pathological mechanisms.In this study, we performed the first comprehensive DNA methylation profiling in pancreatic islets from T2D and non-diabetic donors.We uncovered 276 CpG loci affiliated to promoters of 254 genes displaying significant differential DNA methylation in diabetic islets.These methylation changes were not present in blood cells from T2D individuals nor were they experimentally induced in non-diabetic islets by exposure to high glucose.For a subgroup of the differentially methylated genes, concordant transcriptional changes were present.Functional annotation of the aberrantly methylated genes and RNAi experiments highlighted pathways implicated in b-cell survival and function; some are implicated in cellular dysfunction while others facilitate adaptation to stressors.Together, our findings offer new insights into the intricate mechanisms of T2D pathogenesis, underscore the important involvement of epigenetic dysregulation in diabetic islets and may advance our understanding of T2D aetiology.\t\n\nIn addition to genetic predisposition, environmental and lifestyle factors contribute to the pathogenesis of type 2 diabetes (T2D).Epigenetic changes may provide the link for translating environmental exposures into pathological mechanisms.In this study, we performed the first comprehensive DNA methylation profiling in pancreatic islets from T2D and non-diabetic donors.We uncovered 276 CpG loci affiliated to promoters of 254 genes displaying significant differential DNA methylation in diabetic islets.These methylation changes were not present in blood cells from T2D individuals nor were they experimentally induced in non-diabetic islets by exposure to high glucose.For a subgroup of the differentially methylated genes, concordant transcriptional changes were present.Functional annotation of the aberrantly methylated genes and RNAi experiments highlighted pathways implicated in b-cell survival and function; some are implicated in cellular dysfunction while others facilitate adaptation to stressors.Together, our findings offer new insights into the intricate mechanisms of T2D pathogenesis, underscore the important involvement of epigenetic dysregulation in diabetic islets and may advance our understanding of T2D aetiology.\t\n\nThe goal of the present work was to clarify the hitherto poorly understood connection between DNA methylation and T2D pathogenesis and to determine whether identified epigenetic changes translate into functional effects that impinge on pancreatic b-cell function.For this, we have explored DNA methylation landscapes in islets isolated from T2D patients and non-diabetic individuals.\t\n\nIn conclusion, we report the first comprehensive and detailed analysis of epigenetic changes in T2D, specifically an altered DNA methylation profile in the pancreatic islets of T2D patients with a major preponderance of hypomethylation in sequences outside CGIs.These aberrant methylation events affect over 250 genes, a subset of which is also differentially expressed.The dysregulation of these genes in T2D may notably be linked to b-cell functionality, cell death and adaptation to metabolic stress.Examination of two genes identified by methylation profiling, NIBAN and CHAC1, revealed their biological functions in distinct processes of the ER stress response.Furthermore, our data highlight genes belonging to biological processes whose involvement in T2D\t\n\nAn important question with regard to epigenetic changes is: are the observed DNA methylation changes reflected in gene activity?By comparing the obtained DNA methylation profiles with microarray gene expression data, we were able to determine that a high proportion of genes in whose promoter T2D-related differential DNA methylation occurs are actively transcribed in pancreatic islets.A comparison with expression data of islet cell types (Dorrell et al, 2011) showed that most of the differentially methylated genes are expressed in b-cells.This allowed us to conclude that T2Drelated aberrant DNA methylation partially happens in the promoters of active genes.One has to keep in mind though that the expression studies in islets as well as in the b-cells analysed non-diabetic material.We observed mostly DNA hypomethylation in diabetic islets, not infrequently accompanied by elevated gene expression.Therefore, it can be assumed that the T2D-related hypomethylation leads, in part, to the induction of formerly silent genes.",
+      "\t\n\nEmerging evidence suggests an epigenomic link to T2D development.Reversible epigenetic changes such as histone modifications and DNA methylation may occur during intrauterine development and are believed to have long-term effects on offspring health and survival, including manifestation of disease phenotypes such as obesity or diabetes later in life [59,60].Environmental and nutritional stimuli influence future science group Genetics, genomics & personalized medicine in Type 2 diabetes: a perspective on the Arab region Review  [61].Epigenetic regulation of genes may be responsible for the observed difference in T2D risk and drug response between individuals [62,63].Epigenomics may not only shed light on the environmental (including diet and lifestyle) effect on T2D susceptibility in individuals but epigenetic markers may also help identify those at risk well before disease manifestation.Gene-expression analysis or transcriptomics is used for studying the expression profile of genes.A comparative analysis of expression states of genes between healthy and diseased cells can identify those implicated in disease pathology.The changes in expression of disease susceptibility genes can be monitored during different stages of a disease and help in disease prognosis.Similarly, a comparative expression profile for treated and untreated samples can help identify changes in gene-expression upon treatment with a particular drug.This makes geneexpression analysis an important tool for elucidating the role of genes in different biological states, for identifying potential targets for drug intervention and for biomarker selection to be used in disease diagnosis.In diabetes, gene-expression profiling has been used for establishing differential expression of inflammatory genes [64], for studying the effects of insulin treatment in skeletal muscle [65] and more recently for correlating insulin resistance and an altered lipid profile in peripheral blood [66].",
+      "\t\n\nWhether epigenetic changes pre-exist or are a consequence of T1D can only be established by long-term longitudinal studies of DNA methylation in subjects at risk for the disease.Since it will a priori remain almost impossible to investigate  cells and mTEC in T1D patients, the question of tissue-specific methylation changes should have to be solved in animal models of T1D, like the NOD mouse.It is possible that the observed pattern of CpG methylation at the insulin locus may vary in other T1D and control populations as a reflect of gene-environment interactions proper to these populations.Until larger studies can be performed in such populations, the observed variations in DNA methylation should be considered restricted to the European people studied here.",
+      "\tISLET RESPONSES; MOVING BEYOND STEADY STATE MEASUREMENTS\n\nTo date, the overwhelming majority of studies including and assessing genetic variation have profiled the steady state patterns of epigenetic modifications and gene expression in islets or their constituent cell types.Others have compared how these steady state measures differ between T2D and non-diabetic (ND) individuals [13,16,40e44].Surprisingly, these studies, especially transcriptome analyses, have identified only modest alterations despite clear phenotypic differences in HbA1c and other metabolic traits in T2D vs. ND donors.This suggests that alterations in transcriptional regulation may not contribute to T2D pathogenesis, or that these (epi)genomic comparative studies are not effectively capturing the alterations associated with islet (patho) physiologic decline or T2D onset.Genomic assays such as RNA-seq provide only a snapshot of tissues' or cell types' transcriptomes at a given point in time.Genes that are important for islet function and resilience (e.g., Gene A) and genes whose expression induces islet failure (e.g., Gene C) would be detected in a comparative analysis between islets at healthy and T2D states (Figure 3).In contrast, genes that are temporarily induced by the initiation of islet stress or in the compensation or pre-diabetic stages (e.g., Gene B) before decline towards disease state would be missed.Furthermore, T2D is a complex disease with dynamic ranges of severity and secondary health complications across individuals.Thus, comparing single snapshots of gene expression in T2D individuals at different stages of islet health and disease progression may simply lead to obfuscation.Longitudinal studies of in vivo epigenetic and gene expression changes in islets of severe, early onset (db/db) or polygenic, late-onset (Tallyho, NZO) [45e47] diabetic mouse models may be the only practical solution to identify the temporal nature of these changes and identify the molecular features of islet dysfunction, compensation, and failure in T2D pathogenesis.Indeed, longitudinal analyses of aging islets in mice identified DNA methylation changes in key genomic regions associated with beta cell proliferation and metabolism [48].These findings suggest that changes in the islet (epi)genome and transcriptome may also be dynamic during the course of T2D development and progression.Alternatively, in vitro, it may be possible to subject human islets to diabetic-like conditions through the use of inflammatory cytokines and/ or oxidative and ER stress.Already, studies from a few groups have demonstrated clear differences in islet gene expression, including the modulation of putative T2D target genes, during stimulatory or stress responses, and certain epigenetic and gene expression features in islets are only revealed upon these in vitro or in vivo exposures, such as glucose-stimulated insulin secretion, palmitate, inflammatory cytokines or other response defects [49e53].Examining the transcriptomic and (epi)genomic changes of human islets under these various stressors over time may provide greater knowledge of the epigenetic and gene expression changes preceding islet stress, failure, and ultimately diabetes onset.",
+      "\t\n\nInteractions between environmental factors and genetic predisposition leading to epigenetic changes could provide a powerful risk association to diabetic complications, especially in relation to the metabolic memory phenomenon (Reddy et al., 2015).",
+      "\t\n\nRecent studies using vascular and inflammatory cells treated in vitro with high glucose (HG), or target cells and tissues derived from models of diabetes complications, provide strong evidence that alterations in epigenetic histone PTMs play key roles in diabetes-induced inflammation and vascular complications, and potentially in the metabolic memory phenomenon (17)(18)(19)(20)(21)(22)(23)(24)(25)(33)(34)(35)(36)(37)(38)(39)(40)(41).However, studies have not yet been performed directly in humans with diabetes and metabolic memory.To examine whether epigenetic mechanisms are related to glycemic history, the progression of complications and metabolic memory in human diabetes, we explored variations in the profiles of key histone PTMs at promoter regions in peripheral blood lymphocytes and monocytes obtained from selected EDIC cohort subjects.\t\n\nIn conclusion, we conducted comprehensive epigenomic profiling using cells from two selected subsets of DCCT/EDIC participants who experienced different rates of complications following a period with different levels of hyperglycemia to explore an epigenetic mechanism for metabolic memory in individuals with type 1 diabetes.Our results suggest that this metabolic memory phenomenon can in part be explained by increased epigenetic differences at key complication-related genes among individuals with higher HbA 1c levels that may contribute to further progression of complications during EDIC.",
+      "\tFuture research prospects\n\nalthough some of the fundamental mechanisms involved in generegulating epigenetic changes associ ated with hyperglycemia have now been identified, a number of funda mental challenges in this area remain to be addressed, such that the contribution of epigenetic changes to the etiology of diabetes mellitus can be under stood.From a clinical perspective, the continued follow up of participants in the DCCt-eDiC and uKPDs studies will enable investigators to determine the clinical effect of exposure to hyperglycemia, and whether tight glycemic control will appreciably lower the incidence of diabetic complications, further supporting the concept of metabolic memory.From a basic research perspective, the transfer of knowledge of epigenetic changes that drive gene expression will be critical to improved understand ing of the epigenome using highthroughput sequencing technologies.the development of more sensitive and sophisticated methodologies than those currently avail able and the advent of affordable, largescale, genome wide profiling and new bioinformatics tools will provide the means to determine the extent of specific epigenetic events that drive gene responses in patients with dia betes mellitus.Defining the molecular events that confer metabolic memory and its association with diabetic cell reviewS dysfunction will provide critical insights into the inter pretation of persistent epigenetic geneactivating events associated with Dna methylation and other histone modifications, as well as mirna expression patterns.\tCharting the epigenetic landscape\n\nthe studies discussed in this review have described important discoveries that mark the emergence of the epi genome and the tremendous influence of epi genetics on the etiology of diabetes mellitus.the identification of gene activating epigenetic changes mediated by hyper glycemia is of particular importance.the immunopurifica tion of chromatin and its associated protein determinants has profoundly influenced the investigation of chromatin structure and function. 79this investigation has resulted in a fundamental shift in our understanding of transcrip tional regulation and, specifically, the importance of struc tural and chemical variations of the chroma tinized Dna template in primary cellular models of hyper glycemia.the application of chromatin immuno purification can chart and distinguish gene sequences associated with histone modifications, transcription al coregulators and chromatin accessibility. 80,81he distinct patterns of gene expression associated with oxidative stress and the geneactivating changes in models of hyperglycemic variability have highlighted the contribution of cellular memory to the etiology of diabetes mellitus and inflammation of the vasculature.30 although the risk of persistent complications after return to normo glycemia is beginning to be appreciated, the molecular determinants that drive critical nuclear processes associ ated with metabolic memory are still not completely understood.82 emerging evidence suggests the patho genesis of diabetic complications could be influenced by gene-environment inter actions.although the nature of the epigenetic changes in models of glycemic vari ability have not been precisely mapped, regionalization of histone modifications is probably involved.24 to what extent does glucose regulate the transcriptional control afforded by structural and chemical modification of the chromatin template?Charting the epigenetic land scape is a major challenge and will probably reveal some surprising and unanticipated results.indeed, genomewide approaches to studying epigenetic determinants will add new levels of information that will help to establish an atlas of generegulatory events me diated by hyperglycemia.a profile of hyperacetylation events associated with geneactivating epigenetic changes has been developed to enable detailed study of the effects of hyperglycemia.this study used a novel approach to immunopurify the H3 acetylation moiety coupled with massive parallel sequencing approaches. 83Genomewide studies indi cate that human aortic cells are highly enriched with H3 acetylation in response to hyperglycemia and that such acetylation demonstrates specific regionalization in pro moter regions that often extend into transcribed areas of the gene sequence.Critical primary experiments to determine the hyperacetylation signature conferred by hyperglycemia will show the importance of genomewide epigenomic changes, such as those on human chromo somes 4q28.3,6q25.1, 12q23.3 and 22q12.3(Figure 5). intead of focusing on epigenetic changes at single loci, 28 which are often difficult to determine empirically, this discoverybased screening approach is unambiguous and indicates that histone acetylation has a widespread regu latory role that is correlated with geneactivating events.surprisingly, these studies distinguished major changes in genomewide hyperacetylation profiles as a result of physiologically relevant hyperglycemia that regulate specific histone code signatures precisely annotated to human gene expression patterns.with the identification of epigenetic changes, which will undoubtedly include other posttranslational modifications to histone and nonhistone proteins, we anticipate that understanding the genomic profiles will identify molecular pathways and signaling networks critical to the development of diabetes mellitus and its associated complications.",
+      "\t\n\nTo summarize: although there is ample evidence that epigenetic effects are likely to play a role in the pathogenesis of T2D and obesity, as well as to contribute to the observed familial aggregation, experimental studies that conclusively define the key loci responsible in disease-relevant tissues have yet to be performed (Table 1).It is also worth noting that existing studies have focused almost exclusively on DNA methylation, leaving other components of the epigenetic machinery (such as chromatin state) largely unexplored.Given limited access to diseaserelevant human tissues, progress will almost certainly depend on centralized community efforts such as the International Human Epigenome Consortium, which is generating reference epigenomes (including detailed methylome maps) for a panel state art state art of human tissues and cell types. 69This epigenetic counterpart of the Human HapMap effort will provide tissue-specific maps of methylation correlation structures, document the positions of variably methylated sites, and empower future epigenome-wide association study efforts."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "251083E08BA7D70253243E7B75002E47"
+    },
+    {
+      "task_id": "A6AC9E9314DDA1708A83D3B8F9D07EF6"
+    },
+    {
+      "task_id": "DB518D0E92266848B81A1447F03D302C"
+    },
+    {
+      "task_id": "8736099EC8F109703C73C7B7AE2046CA"
+    },
+    {
+      "task_id": "E357FAAAD185EB55A4FB3E802EC9A57B"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_4.json
new file mode 100644
index 0000000..fee1f31
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_diabetes_4.json
@@ -0,0 +1,109 @@
+{
+  "question": [
+    "What recent advancements have been made in leveraging CRISPR-based approaches to correct monogenic forms of diabetes in vivo?",
+    "How do genome-wide association studies (GWAS) integrate with multi-omics data to elucidate the complex genetic architectures of diabetes?",
+    "What is the impact of genomic imprinting on the susceptibility and progression of diabetes?,",
+    "How do longitudinal genomics studies help in understanding gene-environment interactions in diabetes onset and management?",
+    "How have recent integrative genomics approaches, such as the use of single-cell RNA sequencing combined with epigenomic profiling, advanced our understanding of cellular heterogeneity and gene regulatory networks in pancreatic beta cells under diabetic conditions?"
+  ],
+  "answer": [
+    "The text does not provide specific recent advancements in leveraging CRISPR-based approaches to correct monogenic forms of diabetes in vivo. However, it mentions the potential of using CRISPR/Cas9 gene editing tools to understand the impact of identified variants on cell function, growth, and survival, which might ultimately provide a means of treating the disease, likely after the transplantation of genetically",
+    "Genome-wide association studies (GWAS) integrate with multi-omics data by identifying genetic variants associated with diabetes and then examining these variants in the context of other biological data. This includes protein-protein interactions, gene expression data, and epigenomic data. The integration of this data can help to identify key pathways and mechanisms involved in the disease, such as insulin secretion and signaling. Additionally, the integration can help to identify potential drug targets and provide insights into the role of environmental factors and gene-environment interactions in disease development.",
+    "Genomic imprinting can impact the susceptibility and progression of diabetes by permanently programming the developing offspring's response to certain environmental factors. This can increase the risk of diabetes in subsequent generations, suggesting that these changes also affect the germ cell line. The imprinting can be influenced by factors such as maternal undernutrition, infant's low birthweight, and rapid postnatal child growth. Additionally, certain specific sncRNAs changes associated with paternal diets can impair glucose tolerance in offspring, potentially leading to type II diabetes. However, the exact mechanisms of this imprinting and its effects can vary between populations and are not fully understood.",
+    "Longitudinal genomics studies help in understanding gene-environment interactions in diabetes by tracking changes over time and identifying how genetic variants and environmental factors interact to influence diabetes risk. They can provide insights into the function of novel diabetes loci and the pathways through which environmental exposures act, thereby improving our understanding of diabetes etiology. These studies can also help identify high-risk individuals for diet and lifestyle interventions, and potentially inform pharmacological interventions if certain genotypes are found to be more or less responsive to specific medications. Furthermore, they can contribute to the development of personalized medicine in diabetes by identifying genetic variants that influence an individual's response to antidiabetic drugs.",
+    "Recent integrative genomics approaches have significantly advanced our understanding of cellular heterogeneity and gene regulatory networks in pancreatic beta cells under diabetic conditions. Single-cell RNA sequencing has been used to discern cellular heterogeneity within the islets of Langerhans, particularly for beta cells. This has uncovered major gene expression differences between exocrine and endocrine cell types, including less abundant cell types. It has also shed light on the novel roles for each rare cell type based on their activated signalling pathways and receptor proteins. Epigenomic profiling, on the other hand, has provided detailed genome-wide patterns of methylation and chromatin accessibility in human islet material. This has led to a refined regulatory map which offers more granular annotation of functional impact. The combination of these techniques has helped to pinpoint likely causal variants in T2D pathogenesis and has accelerated the definition of causal mechanisms implicated in T2D pathogenesis."
+  ],
+  "contexts": [
+    [
+      "\t\n\nThe advancements in both differentiation protocols and genome-editing technologies make it now possible to study the effect of genetic perturbations on human -cell development.\tA measure of -cell exocytosis based on electrical current. the scalability of such studies.Moreover, a genome-wide CRISPR loss-of-function screen performed in 2019 identified 373 potential regulators of insulin production in the mouse insulinoma-derived Min6 -cell line 178 .Extending genome-wide screens to human -cell models and increasing the diversity of cellular read-outs will provide orthogonal data sets for integration with existing genetic and genomic resources, in order to elucidate downstream biology.As the current protocols for hiPSC differentiation are expensive, are time-consuming and have variability in differentiation efficiency, continued advancements in differentiation protocols will enable similar approaches in these cell models.\tGlucose\n\nPresently, there are several examples of patientderived hiPSC cell lines that have been used to determine the molecular mechanisms of diabetes mellitus.For example, hiPSC lines derived from patients with monogenic diabetes have been generated for several MODY genes, including GCK 79 , HNF1B 79 , HNF4A 79 , HNF1A 79,80 and CEL 79 .In one patient with NDM, an activating mutation located in the DNA-binding domain of STAT3 (Lys392Arg) was identified 81 .Of note, patient-derived STAT3 Lys392Arg hiPSC cells had premature endocrine cell differentiation owing to upregulation of NEUROG3 and INS that was rescued by correction of the mutation 82 , which is consistent with a pancreatic hypoplasia phenotype.In two other patients with NDM, heterozygous mutations in the INS gene (Cys96Arg and Cys109Tyr) were identified that were predicted to disrupt disulfide bonds in proinsulin 83 .Furthermore, hiPSC-derived -like cells derived from skin biopsies of affected individuals carrying these two mutations had increased endoplasmic reticulum stress and reduced proliferation 83 , suggesting a mechanistic cause of diabetes mellitus through decreased -cell mass.In addition, patient-specific hiPSCs carrying common heterozygous missense mutations found in the transactivation domain of the MODY gene PDX1 (Pro33Thr and Cys18Arg) had defects in the formation of pancreatic progenitors, which resulted in impaired glucose-stimulated insulin secretion 84 .",
+      "\tCONCLUSIONS\n\nhPSCs and the advancing genome editing tools appear to be a timely and potent combination for probing molecular mechanism(s) underlying diseases such as diabetes and metabolic syndromes.Studying monogenic forms of diabetes and syndromes of insulin resistance using these tools would be extremely useful given the lack of an autoimmune attack and confounding effects of insulin resistance and obesity.One caveat of this methodology at the moment is the \"low\" efficiency of deriving human beta cells in vitro [75,76], possibly due to our incomplete knowledge on human pancreatic development.Another explanation would be the lack of in vivo environmental cues emanating from proximal tissues such as the vasculature.Nonetheless, successful disease modeling of MODY2 [7] and Wolfram Syndrome [8] already suggests a high possibility of success.These technologies have the potential to elucidate the underlying pathophysiology that stem from defects in 1) beta cell development, metabolism or survival or 2) development of adipocyte.For instance in the case of MODY2, it is now clear that GCK mutation affects glucose-stimulated insulin secretion but not insulin synthesis or beta cell proliferation [7].With the latest advances in the derivation of mature and functional human pancreatic beta-like cells from hPSCs in vitro [75e77], eventually circumventing the requirement for in vivo maturation, disease modeling of diabetes is expected to progress exponentially.The knowledge gained from these hiPSC-based disease modeling studies can potentially be translated into the clinics by guiding clinicians on the appropriate type of medication to use for each condition based on the mechanism of action of the disease.Findings from these proposed studies could also offer clues to the pathophysiology of the \"garden variety\" of type 2 diabetes which is known to manifest defects in each of these tissues.hPSCs and genome editing tools may also provide an opportunity to better understand the relevance of gene variants identified from GWAS studies, in causing T1D, T2D, obesity and metabolic syndromes, given that they exhibit only modest effects and w85% of the variants map onto noncoding regions such as enhancers or regulatory elements [104].Investment into hPSCs and genome editing would allow a better mechanistic understanding of the pathophysiology of monogenic and complex diseases relevant for organismal homeostasis and therefore an improved approach to stratified personalized medicine.By identifying the impact of gene variants on disease predisposition, prophylactic measures in the form of lifestyle alterations or medication could be adopted early on in life to delay or even prevent the onset of diabetes and/or metabolic diseases.It is also likely that these hiPSCbased disease modeling studies would provide insights into approaches to predict the susceptibility of disease.Henceforth, the translational potential of studying human diabetes and metabolic syndrome disease mechanisms is huge, with opportunities for early prophylactic intervention that could have long-term implications for global health care and reduction of economic burden.While the derivation of hiPSCs from human tissues is relatively easier and gaining popularity compared to just a few years ago [2], it is likely that the modern technology of generating site-specific nucleases will also rapidly mature to make in vitro disease modeling a routine approach.\tEmploying hPSCs and genome editing tools to study diabetes and metabolic syndromes\n\nIn general, the strategy to carry out in vitro disease modeling of diabetes and related metabolic syndromes with hPSCs and genome editing tools would be to 1) derive hiPSCs from patients with these conditions, 2) generate \"repaired/corrected\" isogenic controls [53] and then 3) differentiate them into pancreatic cells or target cells of relevance, such as immune cells in the case of T1D or myocytes, adipocytes and hepatocytes in the case of T2D (Figure 2).If patient material is inaccessible, one could introduce (naturally occurring) mutations or gene variants into hESCs and differentiate them accordingly to study disease mechanisms.Since excellent reviews have been published recently, we will provide a brief overview to familiarize the reader with the classification of diabetes and metabolic disorders.\t\n\nBackground: Diabetes and metabolic syndromes are chronic, devastating diseases with increasing prevalence.Human pluripotent stem cells are gaining popularity in their usage for human in vitro disease modeling.With recent rapid advances in genome editing tools, these cells can now be genetically manipulated with relative ease to study how genes and gene variants contribute to diabetes and metabolic syndromes.Scope of review: We highlight the diabetes and metabolic genes and gene variants, which could potentially be studied, using two powerful technologies e human pluripotent stem cells (hPSCs) and genome editing tools e to aid the elucidation of yet elusive mechanisms underlying these complex diseases.Major conclusions: hPSCs and the advancing genome editing tools appear to be a timely and potent combination for probing molecular mechanism(s) underlying diseases such as diabetes and metabolic syndromes.The knowledge gained from these hiPSC-based disease modeling studies can potentially be translated into the clinics by guiding clinicians on the appropriate type of medication to use for each condition based on the mechanism of action of the disease.\t\n\nOne strategy to study these monogenic syndromes would be to derive hiPSCs from these patients, differentiate them into pancreatic progenitors and then transplant these progenitors into immunocompromised (SCID-Beige or NSG) mice for in vivo maturation (Figure 2).This methodology has been recently used to successfully model MODY2, demonstrating that beta cells derived from hiPSCs with GCK mutation are indeed less sensitive to glucose levels [7].Endoplasmic reticulum (ER) stress-related diabetes in patients with Wolfram syndrome has also been modeled using hiPSC-derived beta cells, demonstrating that WFS1 protein maintains ER function in beta cells by acting upstream of the unfolded protein response (UPR) pathways [8].phenotypes occurring in humans.Likewise, the stepwise analysis of human pancreatic development with this strategy would likely provide mechanistic insights into the ability of a single gene mutation (PDX1, PTF1A, HNF1B, GATA6 and GATA4) to promote pancreatic agenesis/ atrophy.Further, studying mutations in KCNJ11 and ABCC8 using hiPSC-derived beta cells may elucidate the mechanistic differences between permanent and transient neonatal diabetes [64].Overall, insulin production and secretion could be compared between diseased and gene-corrected pancreatic cells to understand the underlying cause of each type of monogenic diabetes (Figure 2).",
+      "\t\n\nMoving beyond cancer phenotypes, indirect in vivo screens are beginning to be used in other disease models.A genome-scale knockout screen in pancreatic beta-cells transplanted into a mouse model for Type 1 Diabetes identified genetic factors preventing autoimmune clearance of transplants.Inhibition of an identified gene hit, Rnls , with pargyline [101] prevented an autoimmune reaction and confirmed that the screen was able to identify candidates of therapeutic relevance [11] .",
+      "\t\n\nIn addition, knock-out and transgenic mice have become powerful tools in elucidating the influence of specific genes in glucose metabolism and the pathogenesis of diabetes.This includes understanding which transcription factors are involved in pancreas development (Habener et al., 2005) and elucidation of insulin signalling pathways (Kahn, 2003;Wang and Jin, 2009).Tissue-specific knockouts have proven to be particularly useful in studying insulin signalling (Neubauer and Kulkarni, 2006) as the global insulin receptor knock-out is non-viable (Accili et al., 1996).",
+      "\t\n\nThe use of gene-editing tools to create targeted monogenic animal models to explore the physio logical role of specific genes has burgeoned in the past 20 years.Although this endeavour has taught us a great deal about the cellular and molecular underpinnings of energy homeostasis, it is becoming increasingly clear that metabolic characterization of transgenic animal models might be less predictive of the physiological function of the gene of interest than is often assumed.For example, genetic manipulation could impose compensatory biological changes during development that in turn take over the function of an otherwise key gene.Exemplifying the predictive limitations of germline gene knockouts, mice deficient in glucagon-like peptide 1 receptor (GLP-1R) are protected from DIO and exhibit only mild defects in glucose tolerance.Taken at face value, these data imply that GLP-1R agonism would have little to no metabolic benefits 220,221 .Yet, GLP-1R agonists belong to the currently best-in-class therapeutics for treating obesity and T2DM, exemplifying the hazards of determining gene function on the basis of germline transgenic models and also illustrating the possibility of overlooking relevant therapeutic utility 222 .",
+      "\t\n\nIn the present study we devised a new strategy for predicting which proteins and biological pathways would be altered in vivo under such circumstances (Figure S1 in Additional file 1).Our approach was built on the in vitro molecular rules encompassed by the site-specific context score criteria, as these criteria can significantly enrich a gene list in genuine targets when a single miRNA is studied in a cell-based system [34].Using three to nine times the number of human subjects (n = 118) as previous studies [1][2][3][4] and a more comprehensive 'genomewide' RNA profiling strategy (>47,000 mRNA sequences, and >500 miRNA sequences), we aimed to identify the global molecular nature of skeletal muscle insulin resistance in human T2D and provide new bioinformatic and protein level validation for our conclusions.",
+      "\t\n\nIn this study, we set out to expand upon previous studies of the islet regulome in several ways.First, we explored the human islet methylome in unprecedented depth using Whole-Genome Bisulphite Sequencing (WGBS) applied to a set of 10 human islet preparations.Second, we explored both basal and genotype-dependent variation in chromatin accessibility through ATAC-seq in 17 human islet samples.Third, we integrated these genome-wide data with existing islet regulatory annotations to generate a high-resolution, epigenome map of this key tissue.Finally, we used this detailed map to interpret GWAS signals for T2D (and the related trait of fasting glucose) and deduce the molecular mechanisms through which some of these loci operate.",
+      "\t\n\nTargeted Allelic Expression Profiling in Human Islets Identifies cis-Regulatory Effects for Multiple Variants Identified by Type 2 Diabetes Genome-Wide Association Studies Diabetes 2015;64:1484-1491 | DOI: 10.2337/db14-0957",
+      "\t\n\nIt is increasingly clear that genetic variants may act through multiple tissues, e.g.liver, neurons and other islet cells, even though the major endpoint is often an alteration in circulating insulin levels [34,44,45]; thus, a purely 'b-cell-centric' approach to the unravelling of their actions is likely to have only partial success.Important challenges therefore remain to understand the underlying physiology and the tissue interactions through which variants may act.The deployment in animal models of new tools for genome editing optogenetics may help by providing a means to rapidly and selectively control gene expression in a single cell type, thus shining new light on the action of genes identified through genome-wide association study.",
+      "\t\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\t\n\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\t\n\nIn vivo delivery of CRISPR editing tools into pancreatic b cells in people with diabetes is likely to face enormous challenges for two main reasons: 1. b cells are postmitotic, thus disfavouring HDR-mediated CRISPR editing.2. Selective targeting to these cells will be required, likely involving cell type-tropic viruses (272), raising evident concerns over off-target effects and toxicity.Hence, the most likely and feasible way of CRISPR editing has to be an ex vivo system where b cells can first be engineered by CRISPR editing and then transplanted into patients (Figure 2).\t\n\ninsulin secretion.We begin by providing examples of genes and loci associated with altered T2D risk.Finally, we review the CRISPR tools that may offer the potential to correct these variants in the human b cell.\tIn Vitro and In Vivo b Cell Models for Studying Genetic Variants\n\nIn order to understand the pathogenic role of diabetes-associated genetic variants, tractable b cell models are essential.Mouse models, either transgenic or knock-out, are valuable for examining the roles of single genes, but their use is more limited in studies of intergenic regions given more substantial inter-species (mouse versus human) differences in these regions.As sources of human b cells, there are currently three possibilities.Firstly, primary islets isolated from organ donors: This source is, however, limited in terms of the availability and quality of islets (226).Secondly, clonal human b cells.Immortalized human EndoC-bH1 cells were developed in recent years after infection of foetal islets with large T antigen and further inoculation of islets in immunocompromised mice (227).Later generation EndoC-bH2 (228) and EndoC-bH3 (229) cell lines were subsequently established with more advanced features including regulated deletion of the immortalizing gene.The limitation of these cell lines, however, is their extremely slow growth rate which hampers their use.Given this slow growth rate -and the fact that these lines poorly tolerate expansion from a single cell-it is virtually impossible to modify them by HDR via CRISPR editing.A third possibility are therefore islet-like cells differentiated from human embryonic stem cells (hESC) or patient-derived induced pluripotent stem cells (iPSC).In light of the limitations of the above cellular models, laboratories are now focusing on hESC or iPSC in studies of gene function throughout b cell development by differentiating hESC/iPSC cells into mature b cells (230,231).Such directed differentiation protocols have recently been improved (21,159).",
+      "\t\n\ntreatment of T2DM.T5224 is able to strikingly rescue CDKAL1mutation-mediated pancreatic beta cell dysfunction in vivo, which is a proof of concept for a T2DM drug candidate rescuing a gene-specific defect in vivo."
+    ],
+    [
+      "\t\n\nInsights from integration of genetic and epigenomic data.Using genome-wide association studies (GWAS) data for related glycaemic (for example, fasting glucose, 2-hour glucose), lipid (for example, triglycerides) and anthropometric traits (for example, BMI), a 2018 study proposed distinct clusters of T2DM GWAS loci, three of which showed clear evidence for islet cell dysfunction 21 (Fig. 1).Another study used soft clustering to group T2DM genetic loci on the basis of their associations with related traits, and similarly found loci that are associated with islet cell dysfunction 22 .Although for many of these loci neither the causal variants nor the effector transcripts are known, the most probable mechanism for modulation of the risk of T2DM is through islet cell dysfunction 21 .\tKey points\n\n Genome-wide association studies (GWAS) have identified >400 signals associated with the risk of type 2 diabetes mellitus (T2DM). The pancreatic islet has been identified as a key tissue involved in mediating GWAS signals in T2DM risk. Integrating genetic, epigenomic and cellular data can unlock the biology behind GWAS signals.",
+      "\t\n\nGenes identified in GWASs when evaluated in the context of complementary systems level data such as that related to proteinprotein interactions and to and gene expression can provide insights into the mechanisms underlying pathogenesis of complex traits [22][23][24].Here, we have combined these approaches toward deciphering genome to phenome correlation in T2D (Figure 1).Given that T2D GWAS genes do not directly relate to disease pathophysiology, our main aim was to examine if this genome to phenome correlation gap can be abridged by considering GWAS genes in conjunction with physical and genetic interaction, and gene expression data.\t\nGenome-wide association studies (GWASs) have discovered association of several loci with Type 2 diabetes (T2D), a common complex disease characterized by impaired insulin secretion by pancreatic b cells and insulin signaling in target tissues.However, effect of genetic risk variants on continuous glycemic measures in nondiabetic subjects mainly elucidates perturbation of insulin secretion.Also, the disease associated genes do not clearly converge on functional categories consistent with the known aspects of T2D pathophysiology.We used a systems biology approach to unravel genome to phenome correlation in T2D.We first examined enrichment of pathways in genes identified in T2D GWASs at genome-wide or lower levels of significance.Genes at lower significance threshold showed enrichment of insulin secretion related pathway.Notably, physical and genetic interaction network of these genes showed robust enrichment of insulin signaling and other T2D pathophysiology related pathways including insulin secretion.The network also overrepresented genes reported to interact with insulin secretion and insulin action targeting antidiabetic drugs.The drug interacting genes themselves showed overrepresentation of insulin signaling and other T2D relevant pathways.Next, we generated genomewide expression profiles of multiple insulin responsive tissues from nondiabetic and diabetic patients.Remarkably, the differentially expressed genes showed significant overlap with the network genes, with the intersection showing enrichment of insulin signaling and other pathways consistent with T2D pathophysiology.Literature search led our genomic, interactomic, transcriptomic and toxicogenomic evidence to converge on TGF-beta signaling, a pathway known to play a crucial role in pancreatic islets development and function, and insulin signaling.Cumulatively, we find that GWAS genes relate directly to insulin secretion and indirectly, through collaborating with other genes, to insulin resistance.This seems to support the epidemiological evidence that environmentally triggered insulin resistance interacts with genetically programmed b cell dysfunction to precipitate diabetes.\t\n\nGenome-wide association studies (GWASs) have discovered association of several loci with Type 2 diabetes (T2D), a common complex disease characterized by impaired insulin secretion by pancreatic b cells and insulin signaling in target tissues.However, effect of genetic risk variants on continuous glycemic measures in nondiabetic subjects mainly elucidates perturbation of insulin secretion.Also, the disease associated genes do not clearly converge on functional categories consistent with the known aspects of T2D pathophysiology.We used a systems biology approach to unravel genome to phenome correlation in T2D.We first examined enrichment of pathways in genes identified in T2D GWASs at genome-wide or lower levels of significance.Genes at lower significance threshold showed enrichment of insulin secretion related pathway.Notably, physical and genetic interaction network of these genes showed robust enrichment of insulin signaling and other T2D pathophysiology related pathways including insulin secretion.The network also overrepresented genes reported to interact with insulin secretion and insulin action targeting antidiabetic drugs.The drug interacting genes themselves showed overrepresentation of insulin signaling and other T2D relevant pathways.Next, we generated genomewide expression profiles of multiple insulin responsive tissues from nondiabetic and diabetic patients.Remarkably, the differentially expressed genes showed significant overlap with the network genes, with the intersection showing enrichment of insulin signaling and other pathways consistent with T2D pathophysiology.Literature search led our genomic, interactomic, transcriptomic and toxicogenomic evidence to converge on TGF-beta signaling, a pathway known to play a crucial role in pancreatic islets development and function, and insulin signaling.Cumulatively, we find that GWAS genes relate directly to insulin secretion and indirectly, through collaborating with other genes, to insulin resistance.This seems to support the epidemiological evidence that environmentally triggered insulin resistance interacts with genetically programmed b cell dysfunction to precipitate diabetes.",
+      "\t\nBackground: Genome-wide association studies (GWAS) have recently identified many new genetic variants associated with the development of type 2 diabetes.Many of these variants are in introns of known genes or between known genes, suggesting they affect the expression of these genes.The regulation of gene expression is often tissue and context dependent, for example occurring in response to dietary changes, hormone levels, or many other factors.Thus, to understand how these new genetic variants associated with diabetes risk may act, it is necessary to understand the regulation of their cognate genes.Results: We identified fourteen type 2 diabetes-associated genes discovered by the first waves of GWAS for which there was little prior evidence of their potential role in diabetes (Adam30,",
+      "\t\n\nGenomic variations and DNA profiling of those at risk for type 2 diabetes Despite many candidate gene studies and genome-wide linkage studies, very few susceptibility loci for type 2 diabetes have been identified until the recent emergence of genomic-wide association (GWA) data and large-scale replication studies (Table 2).Meta-analysis of GWA studies provides the unique opportunity to investigate the heterogeneity or consistency of genomic associations across diverse datasets and study populations.Recently, Voight et al. (32), using large-scale association analyses combining the data from eight GWA studies, identified 12 new susceptibility loci for type 2 diabetes.",
+      "\t\n\nGenome-wide association studies (GWAS) have made a significant contribution to our current knowledge of the role(s) of genetic variation in population-level susceptibility to T1D (Mychaleckyj et al., 2010).",
+      "\tIntroduction\n\nGenome-wide association studies (GWAS) have identified approximately 80 loci robustly associated with predisposition to type 2 diabetes (T2D) [1][2][3] and a further 70 influencing a range of continuous glycemic traits [4][5][6][7][8][9][10] in non-diabetic subjects.There is substantial, though far from complete, overlap between these two sets of loci.Physiological studies in non-diabetic individuals indicate that most of these loci primarily influence insulin secretion rather than insulin sensitivity, highlighting a key role for the pancreatic islets of Langerhans in the mechanistic underpinnings of these association signals [11,12].These findings have motivated efforts to catalogue the epigenomic and transcriptional landscape of human islets and to apply these findings to deliver biological insights into disease pathogenesis.Recently, it has been shown, for example, that GWAS signals for T2D and fasting glucose show significant co-localization with islet enhancers [13,14].",
+      "\tIntroduction\n\nGenome wide association studies (GWAS) of type 2 diabetes mellitus and relevant endophenotypes have shed new light on the complex etiology of the disease and underscored the multiple molecular mechanisms involved in the pathogenic processes leading to hyperglycemia [1].Even though these studies have successfully mapped many diabetes risk genetic loci that could not be detected by linkage analysis, the risk single nucleotide polymorphisms (SNP) have small effect sizes and generally explain little of disease heritability estimates [2].The poor contribution of risk loci to diabetes inheritance suggests a prominent role of environmental factors (eg.diet, physical activity, lifestyle), gene  environment interactions and epigenetic mechanisms in the pathological processes leading to the deterioration of glycemic control [3,4].",
+      "\t\n\nGenome-wide interaction studies have potential to identify gene variants that influence diabetes risk that might not be detected using hypothesis-driven approaches.However, the statistical power limitations of such studies when applying conventional tests of interaction, combined with the challenges of identifying large cohort collections with appropriately characterized environmental, genetic, and phenotypic data, pose challenges that conventional genetic association studies do not face.Several methods have been developed to mitigate these challenges; among the most promising is the joint meta-analysis approach, which is derived from the model with two degrees of freedom popularized by Kraft et al. (45) and developed further by Manning et al. (46).Manning et al. (47) went on to apply the joint meta-analysis approach in a genome-wide study of 52 cohorts in which they tested for SNP main effects and interactions (with BMI) on fasting glucose and insulin levels.The analysis yielded novel experiment-wide association signals for main effects, but none was discovered for interactions.",
+      "\t\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.\t\n\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.",
+      "\t\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.\t\n\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.",
+      "\t\nGenome-wide association (GWAS) and sequencing studies are providing new insights into the genetic basis of type 2 diabetes (T2D) and the inter-individual variation in glycemic traits, including levels of glucose, insulin, proinsulin and hemoglobin A1c (HbA1c).At the end of 2011, established loci (P < 5  10 8 ) totaled 55 for T2D and 32 for glycemic traits.Since then, most new loci have been detected by analyzing common [minor allele frequency (MAF)>0.05]variants in increasingly large sample sizes from populations around the world, and in trans-ancestry studies that successfully combine data from diverse populations.Most recently, advances in sequencing have led to the discovery of four loci for T2D or glycemic traits based on low-frequency (0.005 < MAF  0.05) variants, and additional low-frequency, potentially functional variants have been identified at GWAS loci.Established published loci now total 88 for T2D and 83 for one or more glycemic traits, and many additional loci likely remain to be discovered.Future studies will build on these successes by identifying additional loci and by determining the pathogenic effects of the underlying variants and genes.\t\n\nIn the past decade, genome-wide association (GWAS) and sequencing studies have identified genetic loci that help explain the inherited basis of T2D and glycemic traits.These studies are providing insights into the genetic architecture of T2D, including the number, frequency and effect sizes of risk variants in populations around the world.The polygenic nature of T2D is now well established, and multiple risk variants are being identified at some loci, suggesting allelic heterogeneity.Concurrently, increasing numbers of genes and variants have been implicated in monogenic forms of diabetes, including maturity onset diabetes of the young (MODY) and neonatal diabetes (7), and at least five genes have been implicated in both monogenic and polygenic diabetes (8).A recent simulation study evaluated genetic architectures for consistency with results from T2D genetic studies and found that many different disease models were still possible with respect to the number of loci, allele frequencies and level of selective pressure (9).Ongoing studies should more substantially narrow the bounds on feasible architectures (9).",
+      "\tIntroduction\n\nType 2 diabetes is a complex metabolic disease with a substantial heritable component [1].Over the past seven years, genome-wide association studies (GWAS) have successfully identified over 70 common risk variants associated with type 2 diabetes [2][3][4][5].Association signals at many of these loci localize to nonprotein-coding intronic and intergenic regions and likely harbor regulatory variants altering gene transcription.In recent years great advances have facilitated identification of regulatory elements genome-wide using techniques including DNase-seq and FAIRE-seq (formaldehyde-assisted isolation of regulatory elements), which identify regions of nucleosome depleted open chromatin, and ChIP-seq (chromatin immunoprecipitation), which identify histone modifications to nucleosomes and transcription factor binding sites.Several studies have successfully integrated trait-associated variants at GWAS loci with publicly available regulatory element datasets in disease-relevant cell types to guide identification of regulatory variants underlying disease susceptibility [6][7][8][9][10].",
+      "\tINTRODUCTION\n\nMultiple genome-wide association studies (GWASs) have correlated type 2 diabetes mellitus (T2DM) with genetic variants, yielding a large number of loci and associated gene products that are linked to the disease phenotype-often with little or no insight into the mechanism underlying that link (Hivert et al., 2014).The current challenge is to establish robust systems to systematically evaluate the role of these loci using disease-relevant cells.Previous studies have used patient samples, cell lines, or animal models to seek mechanistic insight but with significant limitations.Large variation is observed in primary patient samples, perhaps due to genetic heterogeneity, whereas animal models present major physiological and metabolic differences that hamper understanding of the precise function of human genes in T2DM.Therefore, a robust system to systematically evaluate the role of T2DM-associated genes using disease-relevant human cells will provide an important tool for diabetes research and spur the development of precision (allele-specific) therapies, exemplified by the use of sulfonylurea drugs to treat patients carrying certain KCNJ11 mutations (Gloyn et al., 2004).",
+      "\t\n\nBackground: Genome-wide association studies (GWAS) have identified several hundred susceptibility loci for type 2 diabetes (T2D).One critical, but unresolved, issue concerns the extent to which the mechanisms through which these diverse signals influencing T2D predisposition converge on a limited set of biological processes.However, the causal variants identified by GWAS mostly fall into a non-coding sequence, complicating the task of defining the effector transcripts through which they operate.Methods: Here, we describe implementation of an analytical pipeline to address this question.First, we integrate multiple sources of genetic, genomic and biological data to assign positional candidacy scores to the genes that map to T2D GWAS signals.Second, we introduce genes with high scores as seeds within a network optimization algorithm (the asymmetric prize-collecting Steiner tree approach) which uses external, experimentally confirmed protein-protein interaction (PPI) data to generate high-confidence sub-networks.Third, we use GWAS data to test the T2D association enrichment of the \"non-seed\" proteins introduced into the network, as a measure of the overall functional connectivity of the network."
+    ],
+    [
+      "\tA. Genetic Screening\n\nWe have discussed above the genetic component of T1D.The genetic susceptibility to T1D is determined by genes related to immune function with the potential exception of the insulin gene (434).The genetic susceptibility component of T1D allows some targeting of primary preventive care to family members of diagnosed T1D patients, but there is no complete inheritance of the disease.Nevertheless, the risk for developing T1D compared with people with no family history is 10 -15 times greater.Although 70% of individuals with T1D carry defined risk-associated genotypes at the HLA locus, only 3-7% of the carriers of such genetic risk markers develop diabetes (3).",
+      "\tIntrauterine environment and imprinting\n\nIntrauterine and postnatal environment can aff ect future risk of diabetes and cardiovascular disease via fetal programming. 117The thrifty genotype and thrifty phenotype hypotheses seem to apply to Asian populations.Maternal undernutrition, infant's low birthweight, and rapid postnatal child growth are all associated with increased risk of diabetes in off spring, and these factors might be especially relevant to developing countries such as India 88 and China. 1188][119] In view of the increase in childhood obesity and increasing number of women with young-onset diabetes in Asia, this link will further exacerbate the situation by creating a vicious cycle of diabetes begetting diabetes.",
+      "\tIf an environmental contributor is near ubiquitous and the genetic\npredisposition common as well, interventions are most sensibly weighted towards\nenvironmental risk factor modification. Even here, though, there is room for further research, since the etiopathogenesis\nof type 2 diabetes may not be as well understood as some suggest. Specifically,\nChaufan implies that dietary intervention to prevent prenatal programming\nleading to susceptibility to develop type 2 diabetes (the fetal origins of adult onset\ndisease hypothesis) is as evidence-based as dietary management of the adult diabetic state. However, many questions remain in this area.",
+      "\t\nIn 1976, the noted human geneticist James Neel titled a book chapter \"Diabetes Mellitus: A Geneticist's Nightmare.\" 1 Over the past 30 years, however, the phenotypic and genetic heterogeneity of diabetes has been painstakingly teased apart to reveal a family of disorders that are all characterized by the disruption of glucose homeostasis but that have fundamentally different causes.Recently, the availability of detailed information on the structure and variation of the human genome and of new high-throughput techniques for exploiting these data has geneticists dreaming of unraveling the genetic complexity that underlies these disorders.This review focuses on type 1 diabetes mellitus and includes an update on recent progress in understanding genetic factors that contribute to the disease and how this information may contribute to new approaches for prediction and therapeutic intervention.Type 1 diabetes becomes clinically apparent after a preclinical period of varying length, during which autoimmune destruction reduces the mass of beta cells in the pancreatic islets to a level at which blood glucose levels can no longer be maintained in a physiologic range.The disease has two subtypes: 1A, which includes the common, immune-mediated forms of the disease; and 1B, which includes nonimmune forms.In this review, we focus on subtype 1A, which for simplicity will be referred to as type 1 diabetes.Although there are rare monogenic, immune-mediated forms of type 1 diabetes, 2,3 the common form is thought to be determined by the actions, and possible interactions, of multiple genetic and environmental factors.The concordance for type 1 diabetes in monozygotic twins is less than 100%, and although type 1 diabetes aggregates in some families, it does not segregate with any clear mode of inheritance. 4-7Despite these complexities, knowledge of genetic factors that modify the risk of type 1 diabetes offers the potential for improved prediction, stratification of patients according to risk, and selection of possible therapeutic targets.As germ-line factors, genetic risk variants are present and amenable to study at all times -before, during, and after the development of diabetes.Thus, genetic information can serve as a potential predictive tool and provide insights into pathogenetic factors occurring during the preclinical phase of the disease, when preventive measures might be applied. Gene tic S t udiesBecause of the uncertainty regarding the number and action of genes involved in type 1 diabetes, genetic studies have tended to focus on approaches that require few assumptions about the underlying model of disease risk.The two primary approaches have been linkage studies (using pairs of affected relatives, typically siblings) and association studies (using either case-control or family-based designs).Linkage studies using affected sibling pairs seek to identify regions of the genome that are shared",
+      "\t\n\nGenetic susceptibility to type 1 diabetes (T1D) is well supported by epidemiologic evidence; however, disease risk cannot be entirely explained by established genetic variants identified so far.This study addresses the question of whether epigenetic modification of the inherited DNA sequence may contribute to T1D susceptibility.Using the Infinium HumanMethylation450 BeadChip array (450k), a total of seven long-term disease-discordant monozygotic (MZ) twin pairs and five pairs of HLA-identical, disease-discordant non-twin siblings (NTS) were examined for associations between DNA methylation (DNAm) and T1D.Strong evidence for global hypomethylation of CpG sites within promoter regions in MZ twins with TID compared to twins without T1D was observed.DNA methylation data were then grouped into three categories of CpG sites for further analysis, including those within: 1) the major histocompatibility complex (MHC) region, 2) non-MHC genes with reported T1D association through genome wide association studies (GWAS), and 3) the epigenome, or remainder of sites that did not include MHC and T1D associated genes.Initial results showed modest methylation differences between discordant MZ twins for the MHC region and T1D-associated CpG sites, BACH2, INS-IGF2, and CLEC16A (DNAm difference range: 2.2%e5.0%).In the epigenome CpG set, the greatest methylation differences were observed in MAGI2, FANCC, and PCDHB16, (DNAm difference range: 6.9%e16.1%).These findings were not observed in the HLA-identical NTS pairs.Targeted pyrosequencing of five candidate CpG loci identified using the 450k array in the original discordant MZ twins produced similar results using control DNA samples, indicating strong agreement between the two DNA methylation profiling platforms.However, findings for the top five candidate CpG loci were not replicated in six additional T1Ddiscordant MZ twin pairs.Our results indicate global DNA hypomethylation within gene promoter regions may contribute to T1D; however, findings do not support the involvement of large DNAm differences at single CpG sites alone in T1D.",
+      "\t\n\nIt has been suggested that maternal imprinting of IDDM2 could contribute to the observation that type 1 diabetes appears to be transmitted less frequently to the offspring of diabetic mothers than to those of diabetic fathers [18,27].This, however, cannot be the explanation because there is no evidence for maternal imprinting in families from the UK, and yet in the 332 UK type 1 diabetes multiplex families studied here, there are 26 fathers with type 1 diabetes and only 7 affected mothers.The preferential transmission of predisposing IDDM2-VNTR alleles from fathers is consistent with a maternal imprinting effect in families from France [18], the USA [10,18,21] (Figure 2; Table 3) and Canada [27].However, in a large family data set from the UK, and in smaller data sets from Denmark and Sardinia, the transmission of VNTR susceptibility alleles is more pronounced from mothers than from fathers, and now significantly so in UK families (Figure 2; Table 3).Comparison of the results from the USA with those from the UK suggest that unexplained inter-population differences in this parent-of-origin effect may exist (P<0.025).However, it would appear that in some populations, and in particular the UK, maternal imprinting cannot provide a simple explanation for parent-of-origin effects in type 1 diabetes.Expression of insulin in the adult pancreas appears to be related to the length of the VNTR, with class III alleles associated with lower levels of INS mRNA.Our results are consistent with those of Lucassen et al. [24] and Owerbach and Gabbay [33] who have found a similar 1.5-to 3-fold lower expression associated with class III alleles in transiently transfected rodent pancreatic -cell lines in vitro.Also, in this issue, Vafiadis et al. [1] report that in 10 human foetal pancreas samples, the class III VNTR alleles are associated with significantly lower levels of INS mRNA than class I alleles.Kennedy et al. [25], on the other hand, also using transfected pancreatic -cell lines, found that the INS mRNA levels were higher in a class III VNTR compared with a class I VNTR transfectant.One explanation for this apparent discrepancy might lie in the type of VNTR alleles Kennedy et al. transfected into the cell line.We have found that there are over twenty class I VNTR alleles defined by length [10], and that alleles of a given length can vary in sequence composition [26] (S.T.B. & J.A.T., unpublished data).The transmission of some class I VNTR alleles (e.g.allele 814 mobility units; corresponding to 42 repeat units) from class I/III heterozygous parents to diabetic offspring does not reflect the overall significant positive transmission of the class I as a whole [10].",
+      "\t\nFamily and twin studies indicate that a substantial fraction of susceptibility to type 1 diabetes is attributable to genetic factors.These and other epidemiologic studies also implicate environmental factors as important triggers.Although the specific environmental factors that contribute to immune-mediated diabetes remain unknown, several of the relevant genetic factors have been identified using two main approaches: genome-wide linkage analysis and candidate gene association studies.This article reviews the epidemiology of type 1 diabetes, the relative merits of linkage and association studies, and the results achieved so far using these two approaches.Prospects for the future of type 1 diabetes genetics research are considered.",
+      "\t\n\nGenome-wide search for genes affecting the age at diagnosis of type 1 diabetes.\t\nGenome-wide search for genes affecting the age at diagnosis of type 1 diabetes.\t\n\nGenes affecting type 1 diabetes diagnosis age / A. Syreeni et al.",
+      "\tIntroduction\n\nGenetic susceptibility to the major autoimmune disor- ders, including insulin-dependent diabetes mellitus (IDDM), is complex.Much evidence suggests that IDDM is polygenic, explaining the paucity of ex- tended pedigrees and the high frequency of nonfamil- ial disease (Risch 1987; Thomson et al. 1988).To date, only a single genetic region, the major histocom- patibility complex (MHC) on chromosome 6, has Received May 29, 1990; revision received September 19, 1990.Address for correspondence and reprints: J. I. Bell, Institute of Molecular Medicine, University of Oxford, Oxford OX3 9DU, England.",
+      "\t\n\nThus, the most likely scenario is that these genes are more poised for activation in the case group compared with the control group, contributing to various diabetes complications in the long term.This could be a consequence of the early exposure to hyperglycemia (measured by HbA 1c level), which is known to be associated with increased rates of long-term diabetes complications.",
+      "\tType 1 Diabetes\n\nThe higher type 1 diabetes prevalence observed in relatives implies a genetic risk, and the degree of genetic identity with the proband correlates with risk (22)(23)(24)(25)(26). Gene variants in one major locus, human leukocyte antigen (HLA) (27), confer 50-60% of the genetic risk by affecting HLA protein binding to antigenic peptides and antigen presentation to T cells (28).Approximately 50 additional genes individually contribute smaller effects (25,29).These contributors include gene variants that modulate immune regulation and tolerance (30)(31)(32)(33), variants that modify viral responses (34,35), and variants that influence responses to environmental signals and endocrine function (36), as well as some that are expressed in pancreatic b-cells (37).Genetic influences on the triggering of islet autoimmunity and disease progression are being defined in relatives (38,39).Together, these gene variants explain ;80% of type 1 diabetes heritability.Epigenetic (40), gene expression, and regulatory RNA profiles (36) may vary over time and reflect disease activity, providing a dynamic readout of risk.",
+      "\tPerspectives\n\nThe studies described in this review systematically indicate an association between paternal diets, quantitative changes in specific sncRNAs, and impaired glucose tolerance in firstgeneration offspring.The potential importance of these findings for humans is obvious, considering that type II diabetes is one of the fastest growing health problems of our time and that impaired glucose tolerance defines a pre-diabetic state.If the described results are indeed applicable to humans, measures of specific sncRNAs (e.g.miRNA-let-7, tRF-Gly-GCC, and tRF modifications m 5 C and m 2 G) could potentially work as assayable quantitative biomarkers.Obesity biomarkers have significant potential to improve characterization of an obesity phenotype, which may prove relevant in assessing the risk of type II diabetes, thereby helping to counteract the global rise of obesity and diabetes.Identification of these epigenetic biomarkers could help identify younger individuals who are predisposed to the development of obesity and type II diabetes, allowing for personalized intervention.",
+      "\t\n\nThe diabetogenic effects of manipulating the intrauterine environment are probably mediated by a permanent programming of the developing offspring, e.g. by the mechanism of imprinting.Of interest, the increased risk of diabetes continues into subsequent generations, suggesting the changes also affect the germ cell line [143].",
+      "\tDiabetes 2004, 53:1905-1910. Page 8 of 9\n(page number not for citation purposes)\nBMC Medical Genetics 2006, 7:85\n\n17. 18. 19. 20. 21. 22. 23. 24. 25. 26. 27. 28. 29. 30. 31. 32. 33. 34. 35. 36. 37. Schulze MB, Hu FB: Primary prevention of diabetes: what can\nbe done and how much can be prevented? Annu Rev Public\nHealth 2005, 26:445-467. King H, Aubert RE, Herman WH: Global burden of diabetes,\n19952025: prevalence, numerical estimates, and projections. Diabetes Care 1998, 21:1414-1431. Permutt MA, Wasson J, Cox N: Genetic epidemiology of diabetes. J Clin Invest 2005, 115:1431-1439.",
+      "\t\nExtensive epidemiological and experimental evidence have shown that exposure to an adverse intrauterine environment as observed in offspring of pregnancies complicated by obesity or diabetes, can program susceptibility to metabolic, endocrine and cardiovascular disorders later in life.Although most studies have concentrated on the maternal environment, it is also becoming evident that paternal exposure to obesity or diabetes can result in the later development of metabolic disorders in the offspring.Such programmed effects might not be limited to the first directly exposed generation, but could be transmitted to subsequent generations.This suggests the existence of mechanisms by which metabolic changes in parental phenotype are transmissible to offspring.The mechanisms which underpin the transmission of the programmed effects across generations are still unclear.However, epigenetic regulation of transcription has emerged as a strong candidate for mediating the heritability of metabolic diseases.Here, we review the most relevant evidence from human and animal studies showing transmission of programming effects of obesity or diabetes across generations, and the current mechanisms underlying either maternal or paternal influences on the metabolic status of offspring.\t\n\nAlthough most studies have concentrated on the maternal environment, it is also becoming evident that paternal exposure to obesity or diabetes can result in the later development of metabolic disorders in the offspring.Such programmed effects might not be limited to the first directly exposed generation, but could be transmitted to subsequent generations.This suggests the existence of mechanisms by which metabolic changes in parental phenotype are transmissible to offspring.The mechanisms which underpin the transmission of the programmed effects across generations are still unclear.However, epigenetic regulation of transcription has emerged as a strong candidate for mediating the heritability of metabolic diseases.Here, we review the most relevant evidence from human and animal studies showing transmission of programming effects of obesity or diabetes across generations, and the current mechanisms underlying either maternal or paternal influences on the metabolic status of offspring.",
+      "\t\n\nPresently, 48 other genomic regions, referred to as susceptibility regions, have been found to also confer susceptibility to T1D (Burren et al., 2011;Steck and Rewers, 2011;Yang et al., 2011;Bluestone et al. 2010;Poicot et al., 2010;Todd et al., 2010;Todd et al., 2007).But their contribution is minimal in comparison to the HLA locus (Gillespie, 2014).Also, research has shown that less than 10% of individuals with HLA-conferred diabetes susceptibility actually progress to clinical disease (Knip andSiljandera, 2008, Wenzlau et al., 2008).This implies that additional factors are needed to trigger and drive -cell destruction in genetically predisposed persons (Knip and Siljandera, 2008).Environmental factors are believed to influence the expression of T1D.The reason being that in the case of identical twins, if one twin has T1D, the other twin only has it 30%-50% of the time, despite having the same genome.This means that other factors contribute to the prevalence or onset of this disease (Knip et al., 2005).\tCONTRIBUTION TO KNOWLEDGE\n\nThrough this research, the following facts have been discovered about the genomics of T1D:"
+    ],
+    [
+      "\t\n\nThe fact that all these technologies are relatively high throughput also means that large scale studies can be performed.This is particularly appropriate to type 2 diabetes, obesity, and their related disorders, which are on the whole polygenic disorders.This necessitates either the cross comparison of a number of monogenic animal models of the disease to produce an understanding of the extremes of the metabolic interactions associated with the diseases or the investigation of a disease process in a large population to investigate how a specific gene mutation or disease process interacts with the genetic diversity found in a normal population.",
+      "\t\n\nIn conclusion, genome-wide studies have added valuable scientific data to our repertoire of diabetes knowledge.However, there have been few genomic nuggets that enable a more robust prediction of diabetes than is achieved by using common environmental risk factors and none that clarify the peculiar ethnic proclivities of type 2 diabetes.The latter realization ought to temper enthusiasm for the indiscriminate use of genetic testing for diabetes.",
+      "\t\n\nSuccessful integration of genotyping data with longitudinal phenotypic information produced from several national health registries has provided strong support for 10 loci showing a genome-wide significance for the association with T2DM complications, some of them with already known importance to the comorbid conditions analyzed.We believe that these findings provide deeper insight into the pathogenesis of T2DM complications and suggest novel candidate genes for further functional studies, while our targeted approach highlights several susceptibility loci showing a directionally consistent impact on phenotype in multiple populations.",
+      "\tGenomics of T2D\n\nDiet, lifestyle, environment, and even genetic variation influence an individual's response to disease therapy.Like GWAS which identify genetic variants conferring risk for a disease, studies have been carried out for identifying genetic variants responsible for patient differences in drug response.Pharmacogenomics in diabetes focuses on the study of gene polymorphisms which influence an individual's response to antidiabetic drugs.Such genetic variants influence the pharmacodynamics and/or pharmacokinetics of the drug, thus affecting its efficacy or toxicity in an individual.The difference in response to treatments and therapies across individuals on account of these factors strengthens the case for personalized medicine in diabetes.",
+      "\t\n\nThe availability of detailed information on gene  environment interactions may enhance our understanding of the molecular basis of T2D, elucidate the mechanisms through which lifestyle exposures influence diabetes risk, and possibly help to refine strategies for diabetes prevention or treatment.The ultimate hope is genetics might one day be used in primary care to inform the targeting of interventions that comprise exercise regimes and other lifestyle therapies for individuals most likely to respond well to them.",
+      "\t\n\nIn the Framingham Offspring Cohort, knowledge of common genetic variation aptly reclassifies younger people for T2D risk beyond clinical risk factors, but not older people (12).In the Whitehall II Cohort, common genetic variants for 2-h glucose contributed to the agerelated rise of 2-h glucose levels, whereas associations of variants for fasting glucose were constant over time (40).Although these two studies do not include G  E interactions, they support the notion that genetic variants that modify T2D susceptibility to a particular exposure may do so only when the exposure occurs during specific developmental stages (34).It is therefore important to consider the dynamic or timedependent nature of G  E interactions (2).\tFUTURE PERSPECTIVES\n\nContinued investment in studies of G  E interactions for T2D holds promise on several grounds.First, such studies may provide insight into the function of novel T2D loci and pathways by which environmental exposures act and, therefore, yield a better understanding of T2D etiology (66).They could also channel experimental studies in a productive direction.Second, knowledge of G  E interactions may help identify high-risk individuals for diet and lifestyle interventions.This may also apply to pharmacological interventions if individuals carrying certain genotypes are more or less responsive to specific medications.The finding that patients with rare forms of neonatal diabetes resulting from KCNJ11 mutations respond better to sulfonylurea than to insulin therapy is just one example demonstrating the potential for this application of G  E interaction research (69).Third, we are fast approaching an era when individuals can feasibly obtain their complete genetic profile and thus a snapshot of their genetic predisposition to disease.It will therefore be the responsibility of health professionals to ensure that their patients have an accurate interpretation of this information and a means to curb their genetic risk.A long-held goal of genetic research has been to tailor diet and lifestyle advice to an individual's genetic profile, which will, in turn, motivate him or her to adopt and maintain a protective lifestyle.There is currently no evidence that this occurs.Findings to date, however, indicate that behavioral changes can substantially mitigate diabetogenic and obesogenic effects of individual or multiple risk alleles, which has much broader clinical and public health implications.\t\n\nCross-sectional studies of G  E interactions for quantitative traits such as measures of insulin sensitivity, glucose tolerance, and adiposity have also been informative.Focusing on continuously distributed traits may produce insight to some causal pathway underlying disease that is not adequately captured by studies of overt T2D (24).",
+      "\t\nThe genome is often the conduit through which environmental exposures convey their effects on health and disease.Whilst not all diseases act by directly perturbing the genome, the phenotypic responses are often genetically determined.Hence, whilst diseases are often defined has having differing degrees of genetic determination, genetic and environmental factors are, with few exceptions, inseparable features of most diseases, not least type 2 diabetes.It follows that to optimize diabetes, prevention and treatment will require that the etiological roles of genetic and environmental risk factors be jointly considered.As we discuss here, studies focused on quantifying gene-environment and gene-treatment interactions are gathering momentum and may eventually yield data that helps guide health-related choices and medical interventions for type 2 diabetes and other complex diseases.\t\n\nThe literature on gene-environment interactions in diabetes-related traits is extensive, but few studies are accompanied by adequate replication data or compelling mechanistic explanations.Moreover, most studies are cross-sectional, from which temporal patterns and causal effects cannot be confidently ascertained.This has undermined confidence in many published reports of gene-environment interactions across many diseases; although interaction studies in psychiatry have been especially heavily criticized [3], many of the points made in that area relate to other diseases, not least to T2D, where the diagnostic phenotype (elevated blood glucose or HbA1c) is a consequence of underlying and usually unmeasured physiological defects (e.g., at the level of the pancreatic beta-cell, peripheral tissue, liver, and gut), and the major environmental risk factors are difficult to measure well.Nevertheless, several promising examples of geneenvironment interactions relating to cardiometabolic disease exist, as discussed below and described in Table 1, and interaction studies with deep genomic coverage in large cohorts are now conceivable; the hope is that these studies will highlight novel disease mechanisms and biological pathways that will fuel subsequent functional and clinical translation studies.This is important, because diabetes medicine may rely increasingly on genomic stratification of patient populations and disease phenotype, for which gene-environment interaction studies might prove highly informative.\tThe Rationale for Studying Gene-Environment Interactions\n\nIt is often said that T2D is the consequence of geneenvironment interactions [17].Indeed, both the environment and the genome are involved in diabetes etiology, and there are many genetic and environmental risk factors for which very robust evidence of association exists.But when epidemiologists and statisticians discuss gene-environment interactions, they are usually referring to the synergistic relationship between the two exposures, and there is limited empirical evidence for such effects in the etiology of cardiometabolic disease.Indeed, in non-monogenic human obesity, a condition widely believed to result from a genetic predisposition triggered by exposure to adverse lifestyle factors, of the >200 human gene-lifestyle interaction studies reported since 1995, only a few examples of gene-environment interactions have been adequately replicated [18], and because these results are derived primarily from cross-sectional studies with little or no experimental validation, even those that have been robustly replicated may not represent causal interaction effects.The evidence base for T2D is thinner still.Nevertheless, other data support the existence of gene-environment interactions in complex disease, thus motivating the search for empirically defined interactions in T2D.",
+      "\t\n\nGenome-wide interaction studies have potential to identify gene variants that influence diabetes risk that might not be detected using hypothesis-driven approaches.However, the statistical power limitations of such studies when applying conventional tests of interaction, combined with the challenges of identifying large cohort collections with appropriately characterized environmental, genetic, and phenotypic data, pose challenges that conventional genetic association studies do not face.Several methods have been developed to mitigate these challenges; among the most promising is the joint meta-analysis approach, which is derived from the model with two degrees of freedom popularized by Kraft et al. (45) and developed further by Manning et al. (46).Manning et al. (47) went on to apply the joint meta-analysis approach in a genome-wide study of 52 cohorts in which they tested for SNP main effects and interactions (with BMI) on fasting glucose and insulin levels.The analysis yielded novel experiment-wide association signals for main effects, but none was discovered for interactions.",
+      "\t\nGenome wide association studies (GWAS) have transformed the study of heritable factors influencing complex diseases such as type 2 diabetes (T2D), with the current tally of established risk loci approaching 70.Each of these loci has the potential to offer novel insights into the biology of this disease, and opportunities for clinical exploitation.However, the complexity of this condition has often frustrated efforts to achieve these functional and translational advances.This review describes progress made over the past year to expand genome wide association studies, to characterize the mechanisms through which diabetes risk loci operate, and to define the processes involved in diabetes predisposition.",
+      "\t\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.\t\n\nA new generation of genetic studies of diabetes is underway.Following from initial genome-wide association (GWA) studies, more recent approaches have used genotyping arrays of more densely spaced markers, imputation of ungenotyped variants based on improved reference haplotype panels, and sequencing of protein-coding exomes and whole genomes.Experimental and statistical advances make possible the identification of novel variants and loci contributing to trait variation and disease risk.Integration of sequence variants with functional analysis is critical to interpreting the consequences of identified variants.We briefly review these methods and technologies and describe how they will continue to expand our understanding of the genetic risk factors and underlying biology of diabetes.",
+      "\t\n\nIn summary, the present findings demonstrate that analysis of physiologically defined genome-wide interactions with variants strongly associated with insulin secretion is a potentially powerful approach for discovery of novel T2D loci and for expanding the knowledge base of disease etiology.A similar approach examining interactions with variants associated with key biomarkers may be of wider relevance in other complex human diseases.Results highlight the need for further study of genetic variation underlying T2D risk in African Americans as a means to improve our overall understanding of this disease.",
+      "\t\nIn this review, we briefly outlined salient features of pathophysiology and results of the genetic association studies hitherto conducted on type 2 diabetes.Primarily focusing on the current status of genomic research, we briefly discussed the limited progress made during the post-genomic era and tried to identify the limitations of the post-genomic research strategies.We suggested reanalysis of the existing genomic data through advanced statistical and computational methods and recommended integrated genomics-metabolomics approaches for future studies to facilitate understanding of the gene-environment interactions in the manifestation of the disease.We also propose a framework for research that may be apt for determining the effects of urbanization and changing lifestyles in the manifestation of complex genetic disorders like type 2 diabetes in the Indian populations and offset the confounding effects of both genetic and environmental factors in the natural way.\t\n\nIn this review, we briefly outlined salient features of pathophysiology and results of the genetic association studies hitherto conducted on type 2 diabetes.Primarily focusing on the current status of genomic research, we briefly discussed the limited progress made during the post-genomic era and tried to identify the limitations of the post-genomic research strategies.We suggested reanalysis of the existing genomic data through advanced statistical and computational methods and recommended integrated genomics-metabolomics approaches for future studies to facilitate understanding of the gene-environment interactions in the manifestation of the disease.We also propose a framework for research that may be apt for determining the effects of urbanization and changing lifestyles in the manifestation of complex genetic disorders like type 2 diabetes in the Indian populations and offset the confounding effects of both genetic and environmental factors in the natural way.",
+      "\tGenomics and gene-environment interactions\n\nEven though many cases of T2DM could be prevented by maintaining a healthy body weight and adhering to a healthy lifestyle, some individuals with prediabetes mellitus are more susceptible to T2DM than others, which suggests that individual differences in response to lifestyle interventions exist 76 .Substantial evidence from twin and family studies has suggested a genetic basis of T2DM 77 .Over the past decade, successive waves of T2DM genome-wide association studies have identified >100 robust association signals, demonstrating the complex polygenic nature of T2DM 5 .Most of these loci affect T2DM risk through primary effects on insulin secretion, and a minority act through reducing insulin action 78 .Individually, the common variants (minor allele frequency >5%) identified in these studies have only a modest effect on T2DM risk and collectively explain only a small portion (~20%) of observed T2DM heritability 5 .It has been hypothesized that lower-frequency variants could explain much of the remaining heritability 79 .However, results of a large-scale sequencing study from the GoT2D and T2D-GENES consortia, published in 2016, do not support such a hypothesis 5 .Genetic variants might help reveal possible aetiological mechanisms underlying T2DM development; however, the variants identified thus far have not enabled clinical prediction beyond that achieved with common clinical measurements, including age, BMI, fasting levels of glucose and dyslipidaemia.A study published in 2014 linked susceptibility variants to quantitative glycaemic traits and grouped these variants on the basis of their potential intermediate mechanisms in T2DM pathophysiology: four variants fitted a clear insulin resistance pattern; two reduced insulin secretion with fasting hyperglycaemia; nine reduced insulin secretion with normal fasting glycaemia; and one altered insulin processing 80 .Considering such evidence, the genetic architecture of T2DM is highly polygenic, and thus, substantially larger association studies are needed to identify most T2DM loci, which typically have small to modest effect sizes 81 .",
+      "\t\n\nThe public health genomics approach to type 2 diabetes.So, while exciting gene discoveries are being made, what can we do?The answer may lie in the relatively new field of public health genomics, \"a multidisciplinary field concerned with the effective and responsible translation of genome-based knowledge and technologies to improve population health\" (12).Researchers, policymakers, and practitioners in public health genomics use populationbased data on genetic variation and gene-environment interactions to develop, implement, and evaluate evidencebased tools for improving health and preventing disease.They also apply systematic evidence-based knowledge synthesis and appraisal of the clinical validity and utility of genomic applications in health practice.Validated genomic information is then integrated into disease control and prevention programs (13)."
+    ],
+    [
+      "Recent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.\t\n\nRecent advances in the understanding of the genetics of type 2 diabetes (T2D) susceptibility have focused attention on the regulation of transcriptional activity within the pancreatic beta-cell.MicroRNAs (miRNAs) represent an important component of regulatory control, and have proven roles in the development of human disease and control of glucose homeostasis.We set out to establish the miRNA profile of human pancreatic islets and of enriched beta-cell populations, and to explore their potential involvement in T2D susceptibility.We used Illumina small RNA sequencing to profile the miRNA fraction in three preparations each of primary human islets and of enriched beta-cells generated by fluorescenceactivated cell sorting.In total, 366 miRNAs were found to be expressed (i.e..100cumulative reads) in islets and 346 in betacells; of the total of 384 unique miRNAs, 328 were shared.A comparison of the islet-cell miRNA profile with those of 15 other human tissues identified 40 miRNAs predominantly expressed (i.e..50% of all reads seen across the tissues) in islets.Several highly-expressed islet miRNAs, such as miR-375, have established roles in the regulation of islet function, but others (e.g.miR-27b-3p, miR-192-5p)  have not previously been described in the context of islet biology.As a first step towards exploring the role of islet-expressed miRNAs and their predicted mRNA targets in T2D pathogenesis, we looked at published T2D association signals across these sites.We found evidence that predicted mRNA targets of islet-expressed miRNAs were globally enriched for signals of T2D association (p-values ,0.01, q-values ,0.1).At six loci with genome-wide evidence for T2D association (AP3S2, KCNK16, NOTCH2, SCL30A8, VPS26A, and WFS1) predicted mRNA target sites for islet-expressed miRNAs overlapped potentially causal variants.In conclusion, we have described the miRNA profile of human islets and beta-cells and provide evidence linking islet miRNAs to T2D pathogenesis.",
+      "PRECISE CELLULAR GENOMICS\n\nElucidating the molecular mechanisms that lead to beta cell dysfunction and T2D pathogenesis has been a major focus of diabetes research for decades.However, advances in single cell genomic profiling techniques have led to greater understanding of non-beta cell type transcriptional regulation and suggest that they may play important roles in hallmark features of beta cell insufficiency and failure linked to T2D genetic risk and pathophysiology.Single cell transcriptome analysis of human islet cells indicate that multiple monogenic diabetes genes are highly expressed in beta cells (e.g., PDX1, PAX4, INS, HNF1A, and GCK) [27].However, other non-beta cell types express genes mutated in monogenic diabetes (such as PAX6 and RFX6), congenital hyperinsulinemia (HADH, UCP2) and those implicated as T2D GWAS target/effector genes [28].Recent study of type 1 diabetic (T1D) human islets has provided surprising insights into alpha cell biology.In T1D islets, the alpha cell proportions remain relatively unchanged despite abnormal glucagon secretion [29].This dysregulated glucagon secretion is instead accompanied by decreased expression of important islet transcription factors including ARX, MAFB, and RFX6 and increased expression of stress response factors such as ATF4, ERN1, and HSPA5 [29] suggesting that changes in alpha cell identity may ultimately lead to their dysfunction.Analysis of normal and T2D islet single cells with simultaneous RNA-seq and patch clamping (patch-seq) also revealed subpopulations of alpha cells with varying enrichment for ER stress response genes (e.g., DDIT3, XBP1, PPP1R15A) [30].Interestingly, this transcriptomic heterogeneity was consistent in normal and T2D islets and associated with variability in alpha cell electrophysiological measures; ER stressed alpha cells had lower cellular size and Na  peak current.Prior single cell transcriptomic analyses have also noted subpopulations of ER-stressed beta cells [31,32] which implicates the dysfunction of both alpha and beta cells in diabetes pathogenesis.Similarly, the integrity of beta and alpha cell functions seem to be dependent on each other, as under hypoglycemic conditions, T2D islets show reduced insulin, C-peptide, and glucagon secretion [33].Additionally, during a glycemic clamp experiment, an increase in glucagon secretion was positively correlated with beta cell function suggesting that signaling between the two islet cell types is crucial for maintaining glucose homeostasis.Studies of delta cells in Sst-Cre transgenic mouse models [34e36] reveal that timely regulation of insulin secretion is controlled by various delta-cell specific pathways.Induction of the ghrelin receptor (Ghsr) in delta cells was correlated with enhanced somatostatin release and ultimately reduced insulin and glucagon secretion [35,36].Furthermore, the peptide hormone Ucn3 was shown to be co-released with insulin from beta cells to activate type 2 corticotropin-releasing hormone receptor (Crhr2) on delta cells in an alternate pathway that promotes somatostatin release and negatively regulates insulin levels [34].Delta cells are also notably enriched for G protein-coupled receptors (e.g., GLP1R, GIPR, GPR120) which exert careful control over metabolism [37].These receptors are also common therapeutic targets of T2D, suggesting that treatment and management of the disease should not neglect delta cell (dys)function and/or survival.Efforts to characterize the epigenomes of each islet cell type are emerging and revealing new insights of cellular fate and differentiation.Two groups have performed open chromatin profiling of purified beta and alpha cell fractions [10,12] and identified between 1850 and 3999 beta and 5316-27,000 alpha-specific peaks.These cell-specific regions were enriched for transcription factor motifs implicated in cell development and were enriched for diabetes-associated SNPs.Arda and colleagues also suggest that the beta cell epigenome is plastic and capable of being derived from other endocrine and exocrine precursor cells.Discrepancies in the numbers of cell-specific peaks determined by both groups are likely due to the cell surface markers used to enrich for each.CD26/DPP4, used by Arda et al., is a strong positive selector for alpha cells, which then enables negative selection for beta and other minor cell populations.However, this method of enrichment for beta cells will not remove contaminating delta and PP/gamma cells.Continued development of new tools and markers for islet cell enrichment, such as NTPDase3 [38] should continue to help us to understand changes elicited by genetic and environmental factors in each distinct cell type.Iterative proteomic screens in human islets are also proving useful for identifying putative cell-specific surface markers for isolation [39], wherein beta and delta cell populations were obtained by co-enrichment for CD9 and CD56.Challenges currently remain to exclusively enrich for the minor islet cell types (delta, gamma/PP), thus strategies that negatively select for these cells may be needed.Study of the rarer gamma/PP cells, which constitute roughly <1e5% of the total islet volume, remain limited due to the lack of known cell-surface markers for enrichment and purification (Figure 2).Whole islet analyses are unable to capture cell type-specific changes and therefore preclude analysis of their potential roles in T2D genetics and pathophysiology.Given the clear and extensive genotype effects on cis-RE usage [13,15] and gene expression [11,16,17] in islets, more extensive analysis of sorted cell types from multiple individuals is warranted to define a representative set of islet cell-specific REs and distinguish condition-specific from genotype-driven effects on their use and activity.\t\n\nunderstand each cell type's genomic architecture and better characterize their roles in islet resilience and failure.Experimental manipulation of the regulatory elements and/or the target genes identified by (epi)genomic approaches described above and modeling the putative pathways and processes they implicate in human islet cell lines (e.g., EndoC-bH1-H3) is essential to progress from correlation to causation.Similarly, transitioning from \"the\" mouse (C57BL/6) to multiple mouse models for insights into the effects of naturally occurring genetic variation on islet function and physiology [61] and for manipulation of key genomic elements should also help characterize the dynamic range of islet behavior and response.T2D is a heterogeneous, complex, and progressive disorder, as multiple subtypes have been identified and associated with different genetic risk and clinical outcome profiles.Future islet genomics studies that focus on identifying the distinct subgroups of individuals with distinct genes/pathways that are disrupted and/or contributing to islet (dys)function at basal and/or responsive states are needed.Furthermore, priority should be given to profiling more islets from pre-diabetic and T2D individuals to characterize the transition between basal to stressed to T2D state and determine if there are intermediate signatures for islet failure and T2D onset.Together, this multi-pronged approach toward studying T2D genetics and islet pathophysiology will help identify additional targets and opportunities for intervention that can be exploited for more precise and effective preventative, treatment, and management options for T2D.\t\n\nFigure2: Moving towards a more precise understanding of islet cellular genomics and responses.Proper elucidation of islet (dys)function and its association with T2D pathogenesis is confounded by individual genetic variation as well as islet cellular heterogeneity.To obtain a better understanding of both, future studies must prioritize strategies to obtain purified islet cell type populations (e.g., beta, alpha, delta, gamma/PP) via sorting with specific cell surface markers.Characterization of each cell type-specific genomic profile at baseline, stimulated, and diseased conditions will provide clearer understanding of key cellular and molecular processes that are altered and important in T2D development.Additionally, by sampling islets from multiple individuals and leveraging genotypes, it will be possible to identify cis-regulatory elements and genes that are influenced by genetics rather than disease state.SNP  single nucleotide polymorphism; QTL  quantitative trait locus; ER  endoplasmic reticulum.",
+      "Genetic and physiological studies have highlighted the singular importance of pancreatic islet dysfunction in type 2 diabetes, but epigenomic characterisation of this tissue has been limited in large-scale community projects such as ENCODE and GTEx.The present study seeks to address this deficit by describing, in unprecedented detail, genome-wide patterns of methylation and chromatin accessibility in human islet material.We have combined these data with existing islet epigenomic marks to generate a refined regulatory map which, based on the evidence of improved enrichment for T2D association signals, offers more granular annotation of functional impact.\t\n\nIn this study, we set out to expand upon previous studies of the islet regulome in several ways.First, we explored the human islet methylome in unprecedented depth using Whole-Genome Bisulphite Sequencing (WGBS) applied to a set of 10 human islet preparations.Second, we explored both basal and genotype-dependent variation in chromatin accessibility through ATAC-seq in 17 human islet samples.Third, we integrated these genome-wide data with existing islet regulatory annotations to generate a high-resolution, epigenome map of this key tissue.Finally, we used this detailed map to interpret GWAS signals for T2D (and the related trait of fasting glucose) and deduce the molecular mechanisms through which some of these loci operate.\t\n\nHuman genetic studies have emphasised the dominant contribution of pancreatic islet dysfunction to development of Type 2 Diabetes (T2D).However, limited annotation of the islet epigenome has constrained efforts to define the molecular mechanisms mediating the, largely regulatory, signals revealed by Genome-Wide Association Studies (GWAS).We characterised patterns of chromatin accessibility (ATAC-seq, n = 17) and DNA methylation (whole-genome bisulphite sequencing, n = 10) in human islets, generating high-resolution chromatin state maps through integration with established ChIP-seq marks.We found enrichment of GWAS signals for T2D and fasting glucose was concentrated in subsets of islet enhancers characterised by open chromatin and hypomethylation, with the former annotation predominant.At several loci (including CDC123, ADCY5, KLHDC5) the combination of fine-mapping genetic data and chromatin state enrichment maps, supplemented by allelic imbalance in chromatin accessibility pinpointed likely causal variants.The combination of increasingly-precise genetic and islet epigenomic information accelerates definition of causal mechanisms implicated in T2D pathogenesis.\t\nHuman genetic studies have emphasised the dominant contribution of pancreatic islet dysfunction to development of Type 2 Diabetes (T2D).However, limited annotation of the islet epigenome has constrained efforts to define the molecular mechanisms mediating the, largely regulatory, signals revealed by Genome-Wide Association Studies (GWAS).We characterised patterns of chromatin accessibility (ATAC-seq, n = 17) and DNA methylation (whole-genome bisulphite sequencing, n = 10) in human islets, generating high-resolution chromatin state maps through integration with established ChIP-seq marks.We found enrichment of GWAS signals for T2D and fasting glucose was concentrated in subsets of islet enhancers characterised by open chromatin and hypomethylation, with the former annotation predominant.At several loci (including CDC123, ADCY5, KLHDC5) the combination of fine-mapping genetic data and chromatin state enrichment maps, supplemented by allelic imbalance in chromatin accessibility pinpointed likely causal variants.The combination of increasingly-precise genetic and islet epigenomic information accelerates definition of causal mechanisms implicated in T2D pathogenesis.",
+      "It is worth mentioning that in [132], a meta-analysis study was conducted, where a collection of gene expression datasets of pancreatic beta-cells, conditioned in an environment resembling T1D induced apoptosis, such as exposure to proinflammatory cytokines, in order to identify relevant and differentially expressed genes.The specific genes were then characterized according to their function and prior literature-based information to build temporal regulatory networks.Moreover, biological experiments were carried out revealing that inhibition of two of the most relevant genes (RIPK2 and ELF3), previously unknown in T1D literature, have a certain impact on apoptosis.",
+      "Against this background, a genome-wide analysis to identify stable and well-expressed genes in human islets and beta cells represents an essential tool for accurate normalization.To achieve this goal, we used high-depth RNA-sequencing data from the human beta cell line EndoC-H1 and human islets exposed to pro-inflammatory cytokines or palmitate.Genes were validated as putative reference genes by qPCR in EndoC-H1 cells, human islets and induced pluripotent stem cell (iPSC)-derived islets.",
+      "Notably, single-cell transcriptome profiling has been utilized in the past few years to discern cellular heterogeneity within the islets of Langerhans (Fischer et al. 2019;Tritschler et al. 2019Tritschler et al. , 2017)), particularly for beta cells (Baron et al. 2016;Lawlor et al. 2017a;Segerstolpe et al. 2016;Teo et al. 2018;Xin et al. 2016).Segerstolpe et al. ( 2016) investigated cell-type specific gene expression in the pancreas of healthy and type 2 diabetic individuals and uncovered major gene expression differences (transcriptional signatures) between exocrine and endocrine cell types, including the less abundant cell types such as human delta, gamma and epsilon cells.Previously, these cells had been difficult to observe due to bulk characterization methods (Lawlor et al. 2017a), however, single-cell RNA sequencing has shed light on the novel roles for each rare cell type based on their activated signalling pathways and receptor proteins (Lawlor et al. 2017a;Segerstolpe et al. 2016).For example, insight into the transcriptome of the minority cell type, epsilon cells and its ghrelin-producing capability was provided (Segerstolpe et al. 2016), as well as the expression of the rare delta and gamma cell types that are prompted by hormonal cues from leptin, ghrelin and dopamine signalling pathways to facilitate metabolic signalling in the pancreas (Lawlor et al. 2017a).Further single-cell RNA investigations by Xin et al. (2016) showed a total of 245 genes to be affected by type 2 diabetes when compared to non-diabetic single-cell transcriptomes.Among the common transcript expression profiles found between the human islet cells, only 20 genes (for example, RBP4, DLK1, ADCYAP1, RGS16, SOX4, BMP5, TIMP2, TSPAN1, MAFB and TFF3) were specific to a certain cell type (Xin et al. 2016).Lastly, a few recent reviews have tracked the progress of genes linked to specific endocrine cell types in these studies (see Chiou et al. 2019;Tritschler et al. 2017), with some going as far as to re-analyse the single-cell transcriptome datasets using a machine learning approach (Ma and Zheng 2018).The in-depth analyses reported on oxidative stress being the perpetrator to enhance beta-cell dysfunction as a final result, together with the potential activation of pathways linked to beta-cell apoptosis that may be the resulting cause of an insulin gene expression deficit in type 2 diabetes (Ma and Zheng 2018).",
+      "The inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.\t\n\nThe inheritance of variants that lead to coding changes in, or the mis-expression of, genes critical to pancreatic beta cell function can lead to alterations in insulin secretion and increase the risk of both type 1 and type 2 diabetes.Recently developed clustered regularly interspaced short palindromic repeats (CRISPR/Cas9) gene editing tools provide a powerful means of understanding the impact of identified variants on cell function, growth, and survival and might ultimately provide a means, most likely after the transplantation of genetically \"corrected\" cells, of treating the disease.Here, we review some of the disease-associated genes and variants whose roles have been probed up to now.Next, we survey recent exciting developments in CRISPR/Cas9 technology and their possible exploitation for b cell functional genomics.Finally, we will provide a perspective as to how CRISPR/Cas9 technology may find clinical application in patients with diabetes.",
+      "Our primary intent was to employ an integrative genomics approach to identify mitogenic mechanisms with potential application for human beta cell expansion (Supplementary Fig. 1).This approach entails integrating whole-exome and RNAsequencing data into network analysis to computationally model insulinoma molecular events relative to normal adult and juvenile human beta cells.We reasoned that although some molecular events in insulinoma are likely relevant to the mechanisms of tumor formation, some may serve to uncover the genetic mechanisms that enforce beta cell quiescence, and are bypassed in such benign tumors.We further validated combinations of lead candidate genes derived from this approach as beta cell mitogenic mediators.Notably, we focused on insulinomas from subjects not known to be members of multiple endocrine neoplasia type 1 (MEN1) kindreds, as the MEN1 gene has been previously reported as one of the most frequently mutated genes in hereditary pancreatic neuroendocrine tumors (PNETs), although MEN1 mutations are uncommon in sporadic insulinomas [5][6][7] .Despite attempting to exclude MEN1 subjects, we nevertheless find widespread abnormalities in genes functionally related to MEN1, revealing a previously unsuspected unifying mechanism underlying insulinoma.\t\n\nAn integrative approach suggests proliferation drivers.Our integrative genomics approach led to the identification of ten coexpression modules (Fig. 2e) that may underlie insulinoma pathogenesis, many of which were linked to potential epigenetic dysregulation (Fig. 3b).Given our interest in beta cell regeneration, and seeking the mechanisms that may permit escape from beta cell quiescence in benign insulinomas, we elected to focus on the bisque4 co-expression module, the module in insulinomas that contained DEGs enriched for cell proliferation.Furthermore, the bisque4 cell cycle module was particularly enriched for betacell specific histone mark signature, including genes with bivalent marks, both H3K27me3 and H3K4me3 (Kaestner beta 28 : foldenrichment = 5.2, FDR = 4.0  10 6 ) (Fig. 3a,b).\t\nAlthough diabetes results in part from a deficiency of normal pancreatic beta cells, inducing human beta cells to regenerate is difficult.Reasoning that insulinomas hold the \"genomic recipe\" for beta cell expansion, we surveyed 38 human insulinomas to obtain insights into therapeutic pathways for beta cell regeneration.An integrative analysis of whole-exome and RNA-sequencing data was employed to extensively characterize the genomic and molecular landscape of insulinomas relative to normal beta cells.Here, we show at the pathway level that the majority of the insulinomas display mutations, copy number variants and/or dysregulation of epigenetic modifying genes, most prominently in the polycomb and trithorax families.Importantly, these processes are coupled to co-expression network modules associated with cell proliferation, revealing candidates for inducing beta cell regeneration.Validation of key computational predictions supports the concept that understanding the molecular complexity of insulinoma may be a valuable approach to diabetes drug discovery.",
+      "We built on recent work deriving glucose-responsive pancreatic beta-like cells from hESCs/iPSCs (Pagliuca et al., 2014;Rezania et al., 2014) and used isogenic hESC-derived glucose-responding cells to systematically examine the role of several GWAS-identified genes in pancreatic beta cell function and survival.Whereas the mutations do not affect the generation of insulin + cells, they impaired insulin secretion both in vitro and in vivo, coinciding with defective glucose homeostasis.CDKAL1 / insulin + cells also displayed hypersensitivity to glucolipotoxicity.A high-content chemical screen identified a candidate drug that rescued CDKAL1 / -specific defects by inhibiting the FOS/JUN pathway.These studies represent a proof of principle for the use of isogenic hESC-derived cells to define the precise role of genes associated with disease though GWASs in human pancreatic beta cells, as well as the leadcompound identification for pharmacological intervention of T2DM.\t\n\nIn summary, we established an isogenic hESC platform to systematically evaluate the role of disease-associated loci in the survival and function of human pancreatic beta-like cells in vitro and in vivo.The platform can be used to study other disease-associated loci/variants with respect to beta-like cell function.It is worth noting that the glucose-responding cells derived using the current reported protocols are not equivalent to primary human beta cells.Ca 2+ flux assays suggested that approximately 30%-40% of the insulin-GFP + cells show increased cytosolic Ca 2+ concentrations in response to glucose stimulation (Figure S7Q), whereas robust glucose-induced signaling was observed in more than 70% of human beta cells based on the previous report (Rezania et al., 2014).The restricted functionality of pancreatic beta-like cells derived using current protocols might limit their application for evaluating subtle contributions of genes to glucose metabolism and Ca 2+ signaling.Thus, additional work is needed to further improve the protocol to derive mature pancreatic beta-like cells.In addition, the platform established here can also be applied to study the role of disease-associated loci/variants in other diabetes-related cell types, such as hepatocytes, adipocytes, muscles, and/or intestinal neuroendocrine cells.Finally, the system may be used as a highthroughput/content chemical screening platform to identify candidate drugs correcting allele-specific defects for precision therapy of metabolic diseases.\tDISCUSSION\n\nWith more than 80 loci associated with T2DM identified by GWASs, a robust platform to evaluate the role of these loci using disease-relevant cells is urgently needed.Here, we report proof of principle for using isogenic hESC-derived glucose-responding cells to evaluate the role of these loci in the function and survival of human pancreatic beta cells under conditions mimicking both health and disease.The derived glucose-responding cells share the same genetic background, providing a unique resource to determine the precise role of genes or loci in human pancreatic beta cells independent of complications from genetic heterogeneity implied by other approaches, such as patient-derived iPSCs."
+    ]
+  ],
+  "task_id": [
+    {
+      "task_id": "5683950D08F6BDAB60BEA8BAC610A10B"
+    },
+    {
+      "task_id": "4261C4238D9943A6D54F8F140746169F"
+    },
+    {
+      "task_id": "2F912BE55930B6A50194B230FDF18693"
+    },
+    {
+      "task_id": "CC682B18ACF7B69EFDC2BE439BB2E059"
+    },
+    {
+      "task_id": "662BE235286FA528E8B3E9610248FB71"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_1.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_1.json
new file mode 100644
index 0000000..964fa74
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_1.json
@@ -0,0 +1,40 @@
+{
+  "question": [
+    "How are spatial transcriptomics approaches being integrated into GeneNetwork.org to enhance understanding of tissue architecture and function?",
+    "How do recent developments in quantitative trait locus (QTL) mapping refine our understanding of gene regulatory variants?",
+    "What are the implications of incorporating epigenomic data, such as histone modification maps, into the gene networks on GeneNetwork.org?",
+    "How do recent findings on 3D genome organization contribute to our understanding of functional genomic networks?",
+    "What are the potential applications of artificial intelligence in improving the annotation and interpretation of gene networks?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [],
+    [],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "8D1E141D648E5869E9231D1D816D3F0B"
+    },
+    {
+      "task_id": "F1CDC70335589DDE69AB182D3B7F19EE"
+    },
+    {
+      "task_id": "94563EE20767BE8C58226505DADC1A78"
+    },
+    {
+      "task_id": "4113FAD4A3D16D0E317AB7BBA08B8DDF"
+    },
+    {
+      "task_id": "00520BA174DCF1785E5A34048FEEB431"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_2.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_2.json
new file mode 100644
index 0000000..6abf5b0
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_2.json
@@ -0,0 +1,40 @@
+{
+  "question": [
+    "How has the study of genetic pleiotropy been advanced by data available on GeneNetwork.org?",
+    "What novel genetic pathways have been identified in GeneNetwork.org studies related to aging and lifespan?",
+    "How do polygenic risk scores (PRS) developed using GeneNetwork.org data enhance the prediction and prevention of complex diseases?",
+    "How do recent advancements in network-based integrative genomics alter our understanding of complex trait architectures?",
+    "What are the latest methodological improvements in evaluating gene-environment interactions using GeneNetwork.org?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [],
+    [],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "50467BE398D77655C6E26E7FA4B0DD75"
+    },
+    {
+      "task_id": "98A6AF486AC558307D3D62DCE3072801"
+    },
+    {
+      "task_id": "C258FC7AE58EB75FA86735D5648F56EB"
+    },
+    {
+      "task_id": "2854F2565410212047BF4E6FBB605344"
+    },
+    {
+      "task_id": "8131F0E7B26E93866105CBEA618A6559"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_3.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_3.json
new file mode 100644
index 0000000..fd79449
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_3.json
@@ -0,0 +1,76 @@
+{
+  "question": [
+    "How do multi-omics data integration techniques enhance the prediction accuracy of phenotypic traits in GeneNetwork datasets?",
+    "What are the computational challenges and solutions in analyzing large-scale transcriptomic data within GeneNetwork.org?",
+    "How has the inclusion of data from diverse populations impacted the generalizability of findings on GeneNetwork.org?",
+    "What novel insights have been obtained from GeneNetwork.org regarding the genetic basis of psychiatric disorders?",
+    "How do advancements in machine learning algorithms contribute to the deconvolution of gene expression data in complex tissues?"
+  ],
+  "answer": [
+    "Multi-omics data integration techniques enhance the prediction accuracy of phenotypic traits in GeneNetwork datasets by systematically integrating interactions of informational molecules, such as protein-protein interactions, protein-DNA interactions, protein-RNA interactions, RNA-RNA interactions, protein state information, methylation state, and interactions with metabolites. This comprehensive integration of data allows for a more accurate construction of genomics networks, leading to more reliable predictions of phenotypic traits. Additionally, the integration of genotype and gene-expression data in a single model can drastically reduce QTL candidate genes and infer the structure of networks from expression-regulatory polymorphisms to variation.",
+    "The computational challenges in analyzing large-scale transcriptomic data within GeneNetwork.org include handling the massive data sets, deciding how much confidence to place in QTL extracted from noisy array and proteomic platforms, and integrating multiple types of data across the biological scale. Solutions to these challenges involve the use of statistical tools to extract relevant patterns of covariation and causal relations, Bayesian and combinatorial network-analysis methods, and the integration of additional information such as SNP distributions. The GeneNetwork web service also provides workflows and methods to navigate massive multiscalar data sets and an extensive systems genetics toolkit for analysis and synthesis. Furthermore, machine-learning approaches like GANs can be used to generate larger expression datasets for network inference.",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [
+      "Until highly accurate genomics networks can beconstructed from more complete data, inferences drawnfrom biological networks should be considered as hypothesis that need to be further tested with experimental method, where the results can then illuminatethe representation of the biological system. The predictive power of the genomics networks could be enhancedby more systematically integrating interactions of informational molecules, such as protein-protein interactions, protein-DNA interactions, protein-RNA interactions, RNA-RNA interactions, protein state information, methylation state, and interactions with metabolites, as these types of data have become available(Schadt et al. 2009).",
+      "Until highly accurate genomics networks can beconstructed from more complete data, inferences drawnfrom biological networks should be considered as hypothesis that need to be further tested with experimental method, where the results can then illuminatethe representation of the biological system. The predictive power of the genomics networks could be enhancedby more systematically integrating interactions of informational molecules, such as protein-protein interactions, protein-DNA interactions, protein-RNA interactions, RNA-RNA interactions, protein state information, methylation state, and interactions with metabolites, as these types of data have become available(Schadt et al. 2009).",
+      "Tointegrate phenotypes in MKD with genomic datasets, wechose to include the Protein Family Database (Pfam) [17],Clusters of Orthologous Groups (COGs) [18,19], KyotoEncyclopedia of Genes and Genomes (KEGG) [20], andbiological concepts found in the Gene Ontology (GO)[21,22] which span multiple scales of biology. A key challenge of the post-genomic era is to conceive large-scalestudies of genomes and observable characteristics of organisms(phenotypes) and to interpret the data thus produced. The goal ofthis phenomic study is to improve our understanding of complexbiological systems in terms of their molecular underpinnings.Inaddition, the method has the potential to predict newcorrelations between phenotypes and biological systemsrepresented in GO as shown in the complete result datasetsat http://phenos.bsd.uchicago.edu/prok_phenotype. Whileprevious correlations studies had been completed on onlyfour phenotypes [5,6], we present an additional 38 phenotype-to-GO correlations. We propose that this methodpotentially enables a systems-biology approach to analyzegenomic datasets by providing a systematic view of themolecular mechanisms beneath phenotypes across differentclassications of genes (protein families, pathways, molecularfunctions, and biological processes).",
+      "Recent improvements toGeneNetwork have reinvigorated it, including the addition of data from 10 species, multi-omicsanalysis, updated code, and new tools. The new GeneNetwork is now an exciting resource forpredictive medicine and systems genetics, which is constantly being maintained and improved. Here, we give a brief overview of the process for carrying out some of the most commonfunctions on GeneNetwork, as a gateway to deeper analyses, demonstrating how a smallnumber of plausible candidate genes can be found for a typical immune phenotype.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).By integrating genotypeand gene-expression data in a single model, Kulp and Jagular (2006) have drastically reduced QTL candidate genes, and perhaps inferred the structure of networksfrom expression-regulatory polymorphisms to variation. Combinatorial algorithmsare applied to networks that are drawn by thresholding the gene-expression correlation matrix by high-pass filtering criteria. Edges in the graph represent highgenetic correlation, and the vertices or nodes represent traits. Maximal cliques, thelargest possible sets of completely connected (perfectly intercorrelated) traits, and16.5 SYSTEMS GENETIC ANALYSIS401other dense subgraphs are extracted and annotated from these gene sets (Baldwinet al. , 2005).",
+      "Other studies applied gene network modeling algorithms to identify thepotential regulators in complex diseases, for example cardiomyopathy [79], hepatic steatosis [80], as well ascoronary artery disease [81]. Finally, there are many other integrative approaches available for the analysis of multi-omics data, buthave not yet been applied in mouse systems genetics studies. Examples include the transcriptome-wideassociation study (TWAS) that integrates GWAS with expression datasets from other independent cohorts toprioritize candidate gene for phenotypic traits.We also developed a set of methods to analyze the different layers ofomics data that contribute to complex traits. In particular, intermediate phenotypes, including transcripts,proteins, and metabolites [22, 46, 73] were exploited to consolidate G2P and GXE connections. Despite theirpotential, transcriptome-/proteome-wide association studies (T/PWAS), which test the associations between aphenotype and all transcripts or proteins of a given tissue, have not been fully explored [74, 75], largelybecause of the limited availability of cohorts with such data (see above).",
+      "Recent improvements toGeneNetwork have reinvigorated it, including the addition of data from 10 species, multi-omicsanalysis, updated code, and new tools. The new GeneNetwork is now an exciting resource forpredictive medicine and systems genetics, which is constantly being maintained and improved. Here, we give a brief overview of the process for carrying out some of the most commonfunctions on GeneNetwork, as a gateway to deeper analyses, demonstrating how a smallnumber of plausible candidate genes can be found for a typical immune phenotype.",
+      "Theseresults do not rule out the possibility that for other tissues, conditions or organisms, utilizing thealternative methods as part of the third stage of the GEMOT algorithm may enhance its performance. We next aimed to characterize GEMOTs utility for a large biological network that included groupsof traits that share the same causal transcripts. Accordingly, each synthetic network included100 traits, 200 transcripts and 100 variants, featuring five co-mapped sub-networks. A singe datacollection consists of 100 networks, each containing five co-mapped sub-networks that carry the samenumber of traits (Materials and methods).",
+      "Here we provide open access and availability tothese data by integrating them into the GeneNetwork, aweb-based analytical tool that has been designed for multiscale integration of networks of genes, transcripts andtraits and optimized for on-line analysis of traits controlled by a combination of allelic variants and environmental factors. GeneNetwork with its central module WebQTLfacilitates the exploitation of permanent genetic referencepopulations that are accompanied by genotypic, phenotypic and mRNA abundance datasets.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).By integrating genotypeand gene-expression data in a single model, Kulp and Jagular (2006) have drastically reduced QTL candidate genes, and perhaps inferred the structure of networksfrom expression-regulatory polymorphisms to variation. Combinatorial algorithmsare applied to networks that are drawn by thresholding the gene-expression correlation matrix by high-pass filtering criteria. Edges in the graph represent highgenetic correlation, and the vertices or nodes represent traits. Maximal cliques, thelargest possible sets of completely connected (perfectly intercorrelated) traits, and16.5 SYSTEMS GENETIC ANALYSIS401other dense subgraphs are extracted and annotated from these gene sets (Baldwinet al. , 2005).",
+      "The integration of genotypic and expression and other data haverecently been shown, in a Bayesian network framework [76], to enhance the overallaccuracy of predictive networks [40, 5153]. We have also recently demonstratedhow this class of network can be used to inform associations identified in GWAstudies [40]. 9 SummaryThe significant challenge we face in the post-genome era is deciphering the biological function of individual genes, pathways, and networks that drive complexphenotypes like disease.",
+      "Data upload into open access databases (such asGeneNetwork) allows an integrated analysis of different resources,phenotypic, genomic, and proteomic traits as well as data derivedfrom different tissues and diseases. Fibrogenesis is a common pathway that is induced by injury in almost every tissue [34], whichimplies core fibrogenic pathways [35] and common systemic modifiers [2], but also tissue-specific mechanisms [36]. Hence, data integration enhances the chance to detect genuine modifiers acrossorgans. GeneNetwork is a valuable platform that can be used byresearchers without advanced skills of bioinformatics to performsystems genetics analyses.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).By integrating genotypeand gene-expression data in a single model, Kulp and Jagular (2006) have drastically reduced QTL candidate genes, and perhaps inferred the structure of networksfrom expression-regulatory polymorphisms to variation. Combinatorial algorithmsare applied to networks that are drawn by thresholding the gene-expression correlation matrix by high-pass filtering criteria. Edges in the graph represent highgenetic correlation, and the vertices or nodes represent traits. Maximal cliques, thelargest possible sets of completely connected (perfectly intercorrelated) traits, and16.5 SYSTEMS GENETIC ANALYSIS401other dense subgraphs are extracted and annotated from these gene sets (Baldwinet al. , 2005).",
+      "Integration ofthese data in a readily computable form is required for facileidentication of highly supported genephenotype, genegene and phenotypephenotype relations (Akil et al. 2011). Here we demonstrate the benet of data integration in theGeneWeaver software system that enabled us to identifya common biological basis for two phenotypic endpoints related to alcoholism. This convergent evidence enabled us toprioritize our search for a biological correlate of these behaviors for which we could then demonstrate functional andgenetic validity."
+    ],
+    [
+      "These programs have the capability to integrate large datasets ofgenetic and expression data from humans and animalstudies. Notably, the GeneNetwork program (www.genenetwork.org) can combine expression data gathered fromdifferent brain regions and tissues and map these withdescribed traits as a way to build gene networks [65]. Evolving developments in bioinformatics promise muchmore; it is now feasible to adopt a new modular approach,known as systems biology. Systems biology is a mathematical modeling technique applied to complex biologicalorganizations or processes for the purposes of generatingpredictive models that are more representative of biological situations [66,67].",
+      "This approach requires the accumulation and integration of many types of data,and also requires the use of many types of statistical tools to extract relevant patterns ofcovariation and causal relations as a function of genetics, environment, stage, and treatment. Inthis protocol we explain how to use the GeneNetwork web service, a powerful and free onlineresource for systems genetics. We provide workflows and methods to navigate massive multiscalardata sets and we explain how to use an extensive systems genetics toolkit for analysis andsynthesis.",
+      "Our work has been largely motivated by the computational demands ofsystems like GeneWeaver [82, 86], a web-based software platform for the integrationof functional genomics data. GeneWeaver includes a database containing lists ofgenes from diverse sources, along with descriptive metadata associated with theselists. Through gene homology, the lists can be combined across species such thatgenes on the lists are translated to a common reference. This enables theconstruction of a bipartite graph, with vertices representing individual genes.",
+      "Thismachine-learning approach could be readily extended to theCell 173, June 14, 2018 1589multi-omics datasets that drive network biology. A simpleexample would be using GANs to generate dramatically largerexpression datasets that can be used in the context ofnetwork inference to generate predictive models of transcriptional regulation. The black box nature of most next-generation machinelearning models presents an additional challenge for biologicalapplications.",
+      "This approach requires the accumulation and integration of many types of data,and also requires the use of many types of statistical tools to extract relevant patterns ofcovariation and causal relations as a function of genetics, environment, stage, and treatment. Inthis protocol we explain how to use the GeneNetwork web service, a powerful and free onlineresource for systems genetics. We provide workflows and methods to navigate massive multiscalardata sets and we explain how to use an extensive systems genetics toolkit for analysis andsynthesis.",
+      "Readersmay refer [42] for a comprehensive review on various availablesoftware tools. GeneNetWeaver (GNW) [43] is a Java-based reverse engineering tool for generating synthetic benchmark expression datasetsfrom gold standard DREAM challenge network. E. coli and Yeasttranscriptional regulatory networks are integrated as test case forbenchmark. Comparative assessment of inference algorithmsagainst DREAM challenge data can also be performed with thehelp GNW. Cytoscape [44] is a powerful tool most suitable forlarge-scale network analysis.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).",
+      "A large number of bioinformatics tools have been developed to predict genefunction based on sequence homology [143-145], protein structure [144-146], phylogenetic profiles [147-149],protein-protein interactions [150-152], genetic interactions [153-155], and co-expression [156-162]. With the development of transcriptome profiling technologies, thousands of high-throughput studies havegenerated a wealth of genome-wide data that has become a valuable resource for systems genetics analyses. A few web resources, including GEO [163], ArrayExpress [164], GeneNetwork [165], and Bgee [166] amongstothers, have created repositories of such expression data for curation, reuse, and integration.",
+      "Network effectsWith the technological developments that allow for samplingof genomic, transcriptomic and proteomic data for multiple targets in the same set of samples, it is now possible to performnetworking analyses. These techniques involve assessing the coexpression of transcripts or proteins and building maps of modulesof closely related proles. Within these network maps, verticesrepresent transcripts or proteins and the edges represent thesimilarity between expression proles of pairs of transcripts or proteins. The principle of this analysis is that genes involved in thesame functional pathway are linked via short paths within the coexpression network.",
+      "However, the accurate derivation of such high-throughput data andtheir analysis in terms of biological function has been critical to truly leveraging the postgenomicrevolution. This chapter will describe an approach that focuses on the use of gene networks to bothorganize and interpret genomic expression data. Such networks, derived from statistical analysisof large genomic datasets and the application of multiple bioinformatics data resources, potentially allow the identification of key control elements for networks associated with human disease,and thus may lead to derivation of novel therapeutic approaches., 2011; Rosen et al. , 2003, 2007). GeneNetwork alsoprovides links to the following external databases: NCBI Entrez Gene, Summary from onMendelian Inheritance in Man (OMIM), GenBank, HomoloGene, UCSC Genome Browser(UCSC), BioGPS, STRING, PANTHER, Gemma, the brain synapse database, and the AllenBrain Atlas. Int Rev Neurobiol. Author manuscript; available in PMC 2014 July 21. O'Brien et al. Page 134. BIOINFORMATICS APPROACHES IN BEHAVIORAL NEUROSCIENCENIH-PA Author ManuscriptDespite the various high-throughput technologies employed and plat-forms available toperform expression analysis, a unifying consequence is the generation of large-scaleexpression datasets.",
+      "One challenge facing investigators in the interpretation of the massive data sets on GeneNetworkand elsewhere is deciding how much confidence toplace in QTL extracted from still noisy array andproteomic platforms after having conducted manythousands of statistical tests with poorly understooddegrees of dependency. Statistical approaches toaddress these types of challenges have beendeveloped using either theoretically derived (Landerand Kruglyak 1995) or empirical (Churchill and Doerge 1994) p values as well as false discovery rates(Benjamini and Hochberg 1995; Benjamini and Yekutieli 2005; Storey and Tibshirani 2003).",
+      "Bioinformatics Data SourcesThe ability to identify bona fide candidate genes in any genetic study is limited by one's knowledge of the function of the genes that are determined to harbor the most risk of that disease.With more than 30,000 full-length genes and tens of thousands of transcript variants, micro-RNAs, and noncanonical open reading frames (ORFs), the human genome annotation is undergoing constant development and refinement.Much of this information is now publicly accessible in major database interfaces, including the Gene Ontology, InterPro, pFam, KEGG, UCSC, and NCBI sites.Additional information, of course, can be found in actual published accounts.One major challenge is to develop tools that can cross-reference the results of genetic and functional genomic studies with these massive data sources, to develop knowledge networks for inference testing.Through free software (such as Cytoscape) and commercial software (such as Ingenuity and Pathway Assist), this goal is now within reach.In fact, these software applications can even use natural language-based text mining algorithms to directly integrate author statements with experimental data.",
+      "Here we provide open access and availability tothese data by integrating them into the GeneNetwork, aweb-based analytical tool that has been designed for multiscale integration of networks of genes, transcripts andtraits and optimized for on-line analysis of traits controlled by a combination of allelic variants and environmental factors. GeneNetwork with its central module WebQTLfacilitates the exploitation of permanent genetic referencepopulations that are accompanied by genotypic, phenotypic and mRNA abundance datasets.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).",
+      "The integration of genotypic and expression and other data haverecently been shown, in a Bayesian network framework [76], to enhance the overallaccuracy of predictive networks [40, 5153]. We have also recently demonstratedhow this class of network can be used to inform associations identified in GWAstudies [40]. 9 SummaryThe significant challenge we face in the post-genome era is deciphering the biological function of individual genes, pathways, and networks that drive complexphenotypes like disease.",
+      "Computations can be as simple as sets of correlations andAnderson et al.  Open Source Web-Based ToolsJ.  Neurosci. , February 3, 2021  41(5):927936  933volume and neuron number (Fig. 5D). This type of information is important, forexample, when extrapolating from MRIvolume differences in humans to potentialvariations in cell number (Hibar et al. ,2015). One exciting area of research enabledby GeneNetwork.org is the reanalysis ofphenotypes generated before 2010, whichwould greatly benefit from recent computational methods and datasets.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006).",
+      "Coupling a large multispecies repository curated and empirical functionalgenomics data to fast computational tools allows for the rapid integrative analysis of heterogeneous datafor interpreting and extrapolating systems genetics results. Key words IT-tools for systems genetics, GeneWeaver data base, Data mining, QTL candidate gene1IntroductionSystems genetics studies generate large volumes of gene expressionnetworks, and positional candidate genes. Resolving and prioritizing these results requires refinement of the causal variants, functional role of genes and gene products and relationships of genecoexpression networks to mechanistic biology.",
+      "Several approaches have been developed to integrate multiple data typesacross the biological scale, particularly gene expression and genotype information. Both Bayesian (Li et al. , 2005, 2006) and combinatorial network-analysis methods(Baldwin et al. , 2005; Chesler et al. , 2005; Chesler and Langston, 2005) are beingapplied to genetical genomic data sets. The Bayesian approaches to microarray datamay allow a causal interpretation (Friedman et al. , 2000; Peer et al. , 2001). Thisis particularly true when additional information, such as SNP distributions, is incorporated directly in the modeling (Li et al. , 2005, 2006)."
+    ],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "0B24AD048D04D91C50DF2CF3D792F0A5"
+    },
+    {
+      "task_id": "87C90485F82B8FE83E20A2BFE13113C5"
+    },
+    {
+      "task_id": "607BFA90ED01542767EE86A202B27038"
+    },
+    {
+      "task_id": "690C8150471F6DDA0D8329DC88D2C27D"
+    },
+    {
+      "task_id": "1F35AC388AAF04FB9E8FB3806CE85510"
+    }
+  ]
+}
\ No newline at end of file
diff --git a/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_4.json b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_4.json
new file mode 100644
index 0000000..d605034
--- /dev/null
+++ b/gnqa/paper1_eval/src/data/datasets/gpt4o/dataset_domainexpert_gn_4.json
@@ -0,0 +1,40 @@
+{
+  "question": [
+    "What role do enhancer-promoter interactions play in the regulation of gene networks uncovered through GeneNetwork.org?",
+    "How can the integration of ATAC-seq data with RNA-seq data on GeneNetwork.org inform about chromatin accessibility and gene regulation?",
+    "What are the latest strategies for inferring causal relationships within gene networks using data from GeneNetwork.org?",
+    "How do advancements in single-nucleus RNA sequencing provide more granular insights into cell-type-specific gene expression networks?",
+    "What impact have recent discoveries in non-coding RNA regulation had on refining gene interaction maps on GeneNetwork.org?"
+  ],
+  "answer": [
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback",
+    "Please try to rephrase your question to receive feedback"
+  ],
+  "contexts": [
+    [],
+    [],
+    [],
+    [],
+    []
+  ],
+  "task_id": [
+    {
+      "task_id": "90A7674779E3320F5F7ADC4419DC7624"
+    },
+    {
+      "task_id": "CB7C63955ED2E239114B04F3EF36AADE"
+    },
+    {
+      "task_id": "5A7498A61427D762BF080934BBB87FA3"
+    },
+    {
+      "task_id": "139E439E73A0121BE95144BC656120D5"
+    },
+    {
+      "task_id": "74730F9F07A359644CD63AC5C1683E38"
+    }
+  ]
+}
\ No newline at end of file