1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
|
{
"question": [
"What is the age range in mouse for the onset of diabetes?",
"Do we find significant quantitative trait loci in the studies for diabetes?",
"What environmental factors effect mice that also influence diabetes?",
"List mouse studies that involve insulin.",
"Are there phenotypes or genotypes associated with early onset diabetes in mouse?"
],
"answer": [
"The onset of diabetes in mice can occur as early as 3 to 4 weeks of age, with blood sugar concentrations often elevating between 5 and 8 weeks. However, in some cases, hyperglycemia can develop at approximately 20 weeks of age.",
"Yes, the studies identified significant quantitative trait loci associated with both type 1 and type 2 diabetes. These include loci such as TCF7L2, DNER, SRR, HNF1A, KCNQ1, CDKN2A/CDKN2B, JAZF1, CDC123, CAMK1D, TSPAN8, LGR5, THADA, ADAMTS9, NOTCH2, and others. However, the significance of some loci varied across different populations and studies.",
"Several environmental factors can affect mice and influence diabetes. These include the stress response, which can be greater in male mice and can confound feeding behavior, the unique gut microbiota of rodents from different production facilities, cage position, single versus group housing, the skill level of the researcher, ambient room temperature, and the type of cage bedding. Diet, particularly high-fat feeding, can also induce obesity and diabetes. Additionally, the intrauterine environment can impact the subsequent development of diabetes amongst offspring.",
"1. Diabetes incidence study where mice were tested for diabetes monthly by blood glucose and weekly by urine assessment. 2. Studies involving transgenic/knockout animal models of type 2 diabetes to study the role of genes and their effects on peripheral insulin action. 3. Study involving male type-2 diabetic db/db mice and genetic control non-diabetic db/ mice. 4. Study involving young adult mice fed a high-fat or Western diet to elicit DIO and insulin resistance. 5. Study involving Akita mouse genotyping. 6. Study involving 12-week-old male type 2 diabetic db/db mice and contemporary control wild-type mice. 7. Study involving transgenic mice to create specific models of type 1 and type 2 diabetes. 8. Study involving AKITA mice derived from a C57BL/6NSlc mouse with a spontaneous mutation in the insulin 2 gene. 9. Study monitoring mice for the development of diabetes.",
"Yes, there are phenotypes and genotypes associated with early onset diabetes in mice. The db/db mouse strain, which carries the diabetes (db) mutation, is one such genotype. These mice develop an abnormal and characteristic deposition of fat beginning at 3 to 4 weeks of age, which is an associated phenotype. The C57BL/Ks strain also exhibits early onset diabetes. The severity of the diabetes condition in these mice depends on the interaction of the mutant gene with the inbred background."
],
"contexts": [
[
"Diabetes incidence study. Mice were kept for 20-28 weeks and tested for diabetes monthly by blood glucose and weekly by urine assessment, with a positive indication being followed by twice-weekly blood testing.Mice were diagnosed as diabetic when the blood glucose concentration was over 260 mg/dl (14.4 mM) after 2-3 h of fasting for two sequential tests.Glucose and insulin tolerance tests were performed by injecting glucose (2 g/kg body weight) or insulin (1 U/kg body weight) intraperitoneally in mice fasted for 6-7 h.Tail vein blood was tested by a Contour glucometer.Assessments of plasma insulin, proinsulin and C-peptide levels were performed using commercial ELISA kits, according to the manufacturer's instructions (insulin, proinsulin and C-peptide mouse ELISA kits, R&D Systems Quantikine).Assays were performed with blinding, with mice coded by number until experimental end.",
"Subsequently, genetic dissection of the diabetes-associated traits in the male BC1 progeny obtained from a cross between (normal B6 female \u03eb diabetic TH male)F1 female and diabetic TH male mice (B6 cross) was carried out.Because of the sexual dimorphism, with respect to NIDDM onset, we used diabetic TH male mice as breeders to ensure the presence of a mutant allele(s) and targeted our genetic dissection using only male BC1 progeny.In male BC1 mice hyperglycemia developed at approximately 20 weeks of age and was sustained through a 30-week period studied.Based on these data, we measured plasma glucose levels three times in biweekly intervals (to minimize phenotyping error) between 20 and 26 weeks of age, and the mean of the three measurements was used for genetic analysis.Body weights were measured at 20 weeks.At the end of the study (26 weeks), plasma insulin levels and nasal-anal lengths were measured, and the five regional fat pads were dissected and weighed from a subset of 133 mice.In total, 206 male BC1 mice were collected, and individual mice were genotyped with 92 SSLP markers at approximately 20-cM intervals (covering \u03f396% of the genome).",
"The Diabetes (db) .Mouse (Chromosome 4).Diabetes (db), an autosomal recessive mutation, occurred in the C57BL/KsJ (BL/Ks) inbred strain and on this background is characterized by obesity, hyperphagia, and a severe diabetes with marked hyperglycaemia [7,22].Increased plasma insulin concentration is observed as early as 10 days of age [10].The concentration of insulin peaks at 6 to 10 times normal by 2 to 3 months of age then drops precipitously to near normal levels.Prior to the fall in plasma insulin concentration, the most consistent morphological feature of the islets of Langerhans appears to be hyperplasia and hypertrophy of the beta cells in an attempt to produce sufficient insulin to control blood glucose concentration at physiological levels.The drop in plasma insulin concentration is concomitant with islet atrophy and rapidly rising blood glucose concentrations that remain over 400 mg per 100 ml until death at 5 to 8 months [7].Compared with other obesity mutants the diabetic condition is more severe and the lifespan is markedly decreased.",
"The animal models available for diabetes research (Table 1) are most often more like maturityonset diabetes in man.Obesity is a consistent factor and insulinopaenia is rare.However, the time of gene expression at about two weeks of age is within the time period of juvenile expression.The severity and clinical course of the diabetes produced depends on the interaction of the mutant gene with the inbred background rather than the action of the gene itself.Thus on one inbred background a well-compensated, maturity onset type diabetes, compatible with near normal life is observed whereas on another inbred background the syndrome presents as a juvenile-type diabetes with insulinopaenia, islet cell degeneration, marked hyperglycaemia, some ketosis and a much shortened lifespan.Unfortunately, vascular, retinal and the other complications of diabetes are not seen consistently in these rodent syndromes.It seems that the severely diabetic animal either does not live long enough to develop these complications or that rodents are particularly resistant to those complications that commonly afflict human diabetics.Several comprehensive bibliographies and excellent reviews of the various studies carried out with each of these syndromes in animals have been published [2,3,19,30,31,32].This presentation will be restricted primarily to the research undertaken by my colleagues and myself with the two mouse mutations; diabetes (db), and obese (ob).Both mutations have been extensively studied by numerous investigators in attempts to define the primary lesion causing the syndrome.As yet, the primary defect remains illusive, although several possibilities are becoming increasingly plausible in the light of current research.Although the metabolic abnormalities associated with both obese and diabetes have many similarities with regard to the overall progression of the obesity-diabetes state, the documentation of two single genes on separate chromosomes makes it unlikely that the two syndromes are caused by the same primary lesion.However, the marked similarity between the two mutants when maintained on the same genetic background implies that the defects may occur in the same metabolic pathway.",
"Diabetes-obesity syndromes in rodents",
"Diabetes-related clinical traits for 275 B6XBTBR-ob/ ob F2 male mice at 10 weeks of age.",
"However, in other contexts, B6 mice are more likely than D2 to spontaneously develop diabetic syndromes, Aging Clin Exp Res indicating that risk factors exist on both genetic backgrounds [29]. QTL mapping studies indicate that these murine metabolic traits have a complex genetic architecture that is not dominated by any single allele [29\u201331], much like humans [32, 33]. Prior work identified candidate genes on Chr 13 that might underlie diabetes-related traits, including RASA1, Nnt, and PSK1. RASA1 show strong sequence differences between B6 and D2 strains [34]. Rasche et al.",
"In total, about 360 male mice (10 for each strain) were fed with either a regular chow diet (CD) or a high-fat diet (HFD) to induce obesity and associated metabolic stress. At 20 weeks of age, a test meal bolus was administered orally, and postprandial BAs and blood glucose levels were analyzed at three different time points (before and 30 or 60 min after gavage). Nine weeks later, the mice were sacrificed 4 h after feeding, a time point in which the main metabolic adaptive processes in response to BA-mediated food intake are captured.",
"BB rats usually develop diabetes just after puberty and have similar incidence in males and females.Around 90% of rats develop diabetes between 8 and 16 weeks of age.The diabetic phenotype is quite severe, and the rats require insulin therapy for survival.Although the animals have insulitis with the presence of T cells, B cells, macrophages and NK cells, the animals are lymphopenic with a severe reduction in CD4 + T cells and a near absence of CD8 + T cells (Mordes et al., 2004).Lymphopenia is not a characteristic of type 1 diabetes in humans or NOD mice (Mordes et al., 2004) and is seen to be a disadvantage in using the BB as a model of type 1 diabetes in humans.Also, in contrast to NOD mice, the insulitis is not preceded by peri-insulitis.However, the model has been valuable in elucidating more about the genetics of type 1 diabetes (Wallis et al., 2009), and it has been suggested that it may be the preferable small animal model for islet transplantation tolerance induction (Mordes et al., 2004).In addition, BB rats have been used in intervention studies (Hartoft-Nielsen et al., 2009;Holmberg et al., 2011) and studies of diabetic neuropathy (Zhang et al., 2007).",
"Ageing likewise affects metabolic parameters in rodents.Analogous to what occurs in humans, the body weight of the C57BL/6J mouse, the most commonly used mouse strain for metabolic studies, increases with age, peaking at ~9 months 133 , and older C57BL/6J mice (22 months) have reduced lean mass and increased fat mass compared with young 3-month-old mice 134 .In both rats and mice, fasting glucose levels are mostly stable throughout life, but whereas glucose tolerance generally worsens with age in rats, mice are less affected [135][136][137][138][139][140] .In fact, 2-year-old male C57BL/6J mice were significantly more glucose tolerant than their 5-month-old counterparts 138 .Consistent with these findings, glucosestimulated insulin release from the pancreas decreases with age in rats, but not in mice 137,138 .",
"All mice h o m o z y g o u s for t h e d i a b e t e s gene (db/db) b e c o m e diabetic, t h e first d i s t i n g u i s h i n g f e a t u r e being a m a r k e d t e n d e n c y to o b e s i t y w i t h large f a t d e p o s i t i o n s o b s e r v e d in t h e a x i l l a r y a n d i n g u i n a l regions a t a b o u t 3 t o 4 weeks of age.",
"In many of these diabetic mice blood sugar concentration tends to increase gradually between 5 and 12 weeks of age, after which it may rise sharply to over 500 rag/100 ml of blood almost overnight. The diabetic condition, thus, appears to develop in two phases, an early one when there is some regulation of blood sugar concentration, and a later stage characterized by a marked increase in hyperglycemia and a complete loss of metabolic control. A few exceptional diabetics, usually females, exhibit a pattern similar to that shown in Fig. 3. Although 16 240 D.L. COLEMANand K.P.",
"Results All mice homozygous for the trait, diabetes (db), develop an abnormal and characteristic deposition of fat beginning at 3 to 4 weeks of age, making their early identification possible. The difference in size and appearance of litter-mate 6-week old mice, one normal and one diabetic, is shown in Fig. 1. Weight increases Fig. 1. C57BL/Ks-db litter-mates a t 6 weeks.",
"of age; m o r e o f t e n this e l e v a t i o n occurs b e t w e e n 5 a n d 8 weeks. I n older d i a b e t i c mice b l o o d sugar c o n c e n t r a t i o n s g r e a t e r t h a n 600 m g / 1 0 0 m l are n o t u n c o m m o n .",
"I n older mice with blood sugar concentrations over 250 rag/100 ml, injections of up t o 100 units / 100 g were completely ineffective in reducing blood sugar to normal levels. Continued treatment of young diabetic mice with daily injections of insulin, although controlling Mood sugar concentrations initially, did not prevent or delay either the obesity or the uncontrollable high blood sugar concentrations, which usually develop at about 6 to 8 weeks of age.",
"Although the early onset of diabetes in db mice coincides with t h a t in juvenile diabetes in man, the symptoms of obesity and elevated serum insulin are more suggestive of the pattern of development observed in the maturity-onset type of diabetes. As yet, none of the lesions associated with advanced diabetes in humans such as retinopathies, cardiovascular and kidney lesions have been observed, possibly because of the early onset of the diabetes and the relatively rapid deterioration and death of these mice.",
"To screen for genes that show correlation with different phenotypic outcome in diabetic mouse models, we used the cross-sectional design and performed microarray analysis on 24-wk-old STZ-treated and db/db mice with established renal pathology.In parallel with the functional genomics characterization, each individual mouse underwent a detailed renal phenotype analysis.Mice that were treated with low doses of STZ developed diabetes and moderately severe albuminuria (twice the control).In mice with C57B6/J background, the mesangial changes were mild or absent.Mice with 129SvJ genetic background developed significant glomerular changes.However, these were not significantly different from the agematched controls (K.Sharma, K. Susztak, and E.P. Bo \u00a8ttinger, unpublished observations).The db/db mice became insulin resistant and developed diabetes at approximately 8 wk of age.Albuminuria was detected as early as 3 to 4 wk after the development of hyperglycemia.The glomerular histology was characterized by severe diffuse mesangial expansion, as previously reported (49).",
"Renal lesions in diabetic mouse models Db/db mice, which have a recessive mutation in the hypothalamic leptin receptor, develop obesity at 4 wk of age and type 2 diabetes at approximately 8 wk of age.In C57BL/6J background, the diabetes and the obesity are usually less severe than in the C57BL/KsJ background (44).Kidneys are generally enlarged in this mouse strain, and structural glomerular changes (e.g., diffuse glomerulosclerosis, GBM thickening) occur without evidence of tubulointerstitial disease (40).Glomerular lesions of the KK mice are characterized by diffuse and nodular mesangial sclerosis without evidence of tubular disease (45).The lack of reliable mouse models prompted the National Institute of Diabetes and Digestive and Kidney Diseases to fund a consortium for the development and phenotyping of new diabetic mouse models that would resemble closely human DNP.",
"In total, about 360 male mice (10 for each strain) were fed with either a regular chow diet (CD) or a high-fat diet (HFD) to induce obesity and associated metabolic stress. At 20 weeks of age, a test meal bolus was administered orally, and postprandial BAs and blood glucose levels were analyzed at three different time points (before and 30 or 60 min after gavage). Nine weeks later, the mice were sacrificed 4 h after feeding, a time point in which the main metabolic adaptive processes in response to BA-mediated food intake are captured.",
"Assessment of Diabetes Mice were monitored for the development of diabetes as described previously (Wicker et al. 1994)."
],
[
"Additional large-scale meta-analysis predicated upon increased sample size, were carried out on existing datasets from the WTCCC [18] and the Genetics of Kidneys in Diabetes (GoKinD) study [69][70][71] plus control data derived from the National Institute of Mental Health.These investigators observed significant association of previously observed loci.Importantly, they did not observe evidence of new T1D loci reaching the threshold for genome-wide significance.Instead they re-analyzed the most nominally significant associated SNP in an independent British cohort of approximately 6000 cases, 7000 controls and in 2800 families, where they uncovered four additional loci, BACH2 (previously reported [67]), 10p15 harboring protein kinase C theta (PRKCQ), 15q24 harboring nine genes including the cathepsin H (CTSH), complement 1q (C1q), tumor necrosis factor related protein 6 (C1QTNF6) and somatostatin receptor 3 (SSTR3) genes.Table 1 summarizes the 16 T1D loci reported to date.An example of a tag-SNP that captures the association with T1D in each instance is highlighted together with its relative minor allele frequency in controls and what magnitude of risk or protection it confers.Key references regarding the role of each locus in the context of the disease are included and along with the chromosomal band where each locus resides, the main candidate gene (symbol and full name) is highlighted.",
"Detection of established loci We explored the extent to which previously reported type 2 diabetes association signals could be detected in African-descent individuals.Based on the previously reported effect sizes and the effect allele frequency and sample size from our African meta-analysis, we had sufficient power (80%) to detect three signals (TCF7L2, DNER and SRR) at genome-wide significance (p < 2.5 \u00d7 10 \u22128 ) (ESM Table 2).Only the TCF7L2 variant reached genome-wide significance in our study, whereas both variants in DNER (rs1861612) and SRR (rs391300), originally discovered in Pima Indians and East Asians, respectively, had p > 0.1 (ESM Table 2).",
"On the basis of the combined stage 1-3 analyses, we found that six signals reached compelling levels of evidence (P \u00bc 5.0 \u00c2 10 -8 or better) for association with T2D (Table 2).As in all linkage disequilibrium (LD)-mapping approaches, characterization of the causal variants responsible, their effect sizes and the genes through which they act will require extensive resequencing and fine-mapping.However, on the basis of current evidence, we found that the most associated variants in each of these signals map to intron 1 of JAZF1, between CDC123 and CAMK1D, between TSPAN8 and LGR5, in exon 24 of THADA, near ADAMTS9 and in intron 5 of NOTCH2.",
"Replication study of newly identified type 1 diabetes risk loci",
"Although these are considered to be loci convincingly associated with susceptibility to type 2 diabetes in populations of European descent, other genes related to susceptibility to the disease are probably still unidentified, particularly those for populations of other ancestries.In order to uncover genetic variants that increase the risk of type 2 diabetes, we conducted a genome-wide association study in Japanese individuals with type 2 diabetes and unrelated controls.We first genotyped 268,068 SNPs, which covered approximately 56% of common SNPs in the Japanese, in 194 individuals with type 2 diabetes and diabetic retinopathy (case 1) and in 1,558 controls (control 1) collected in the BioBank Japan.We compared the allele frequencies of 207,097 successfully genotyped SNPs and selected the 8,323 SNPs showing the lowest P values.We then attempted to genotype these 8,323 SNPs in 1,367 individuals with type 2 diabetes and diabetic retinopathy (case 2) and for 1,266 controls (control 2) (stage 2), and successfully obtained data for 6,731 SNPs (the P value distribution in the second test is shown in Supplementary Fig. 1a online).The results of principal component analysis 8 in the stage 1 and 2 samples and HapMap samples revealed that there was no evidence for population stratification between the case and control groups throughout the present tests (Supplementary Fig. 1b,c).We selected the 9 SNP loci showing P values o0.0001 (additive model in stage 2, Table 1) and genotyped a third set of cases and controls comprising 3,557 Japanese individuals with type 2 diabetes (cases 3,4,5) and 1,352 controls (controls 3,4).We evaluated the differences in the population structure among these three sets of case and two sets of control groups by Wright's F test.As the results indicated that there was no difference in the population structure among these groups (Supplementary Table 1b online), we combined these populations for the third test of case-control study.The third set of analysis identified the significant associations for six SNPs (Table 1), including the CDKAL1 locus at 6p22.3 (rs4712524, rs9295475 and rs9460546), the IGF2BP2 locus at 3q27.2 (rs6769511 and rs4376068) and the KCNQ1 locus at 11p15.5 (rs2283228).The remaining three SNPs (rs13259803, rs612774 and rs10836097) had P values of 40.05 in the third test and were not further examined.CDKAL1 and IGF2BP2 were previously reported as susceptibility genes for type 2 diabetes in the Japanese population 9 .Therefore, we focused on the KCNQ1 locus, which was highly associated with type 2 diabetes.",
"We consider these data as an interesting preliminary result that surely requires additional independent studies including a higher number of patients in order to confirm and clarify the possible contribution of this locus to the development of T2DM complications.",
"DISCUSSION Taken together, our full second-stage approach and combined meta-analysis have revealed additional loci associated with type 1 diabetes.Clearly the risks are relatively modest compared with previously described associations, and it was only with this sample size at our disposal that we could we detect and establish these signals as true positives through an independent validation effort.",
"Identification of susceptibility loci The degree of evidence for all reported T2D loci was quantified as follows: a locus with a logarithm of odds ratio (LOD) score of 3 or more was considered significant, a LOD score between 2.2 and 3 was considered suggestive and a LOD score between 1 and 2.2 was considered nominal.For T2D, only those loci were included that were significant at least once, or were suggestive in at least one study and at least nominal in two or more studies.The inclusion of the second category of loci was based on a study by Wiltshire et al. [72], in which it was postulated that locus counting is a useful additional tool for the evaluation of genome scan data for complex trait loci.We used the same two criteria to determine the loci from the five papers published on obesity since 2004 and combined these loci with those from Bell et al. [7].As obesity phenotypes, BMI, serum leptin levels, abdominal subcutaneous and visceral fat, and percentage body fat were included.All of these phenotypes were used as continuous quantitative traits, as well as with various cut-off levels.",
"Today, more than 100 loci for type 2 diabetes and glycemic traits have been identified through numerous GWA studies of common and rare variation in populations of diverse ancestral origins [31]; however, to date, very few GWA studies have been published in cohorts of Mexican ancestry.The first GWA study performed in a non-European cohort was published in 2007 and comprised 561 Mexican American type 2 diabetes cases and controls drawn from the Starr County Health Studies [32].Although no loci reached genome-wide significance, several loci identified in prior GWA studies in Europeans were replicated [32].This analysis was subsequently expanded (N = 1273) and meta-analyzed with a cohort from Mexico City (N = 1310) in 2011 [33,34].The most significant variants observed in this meta-analysis included known regions near HNF1A and KCNQ1.Top association signals were then meta-analyzed with the DIAGRAM and DIAGRAM+ datasets of European ancestry individuals, resulting in two regions reaching genome-wide significance: HNF1A and CDKN2A/CDKN2B (Table 1).Top association signals in both studies were annotated to explore their roles as expression quantitative trait loci (eQTL) in both adipose and muscle tissues, revealing a marked excess of transacting eQTL in top signals in both tissue types.",
"75\u00b179 The main conclusion is that there is no major locus for T2D (analogous to HLA in type 1 diabetes).This is not surprising given the modest l s for T2D (approximately 3.5 in Europeans), imposing a limit on the magnitude of any single gene eect. 4Many scans have consequently been signi\u00aecantly underpowered to detect the modest gene eects anticipated.Certainly, few T2D scans have reported linkages meeting the established criteria for genomewide signi\u00aecance. 80This modest power, combined with the diversity of the pedigrees sampled and the analytical techniques used, means that the replication of positive \u00aendings between data sets has been the exception rather than the rule.",
"Quantitative Trait Analysis Exploration of putative T2DM variants with quantitative glycemic traits in a subset of African-American samples (n = 671 from the IRAS and IRASFS control samples, Table S5) revealed limited insight into the biological mechanism associated with T2DM risk.In addition, the five putative African-American T2DM susceptibility loci were tested for association with quantitative measures of glucose homeostasis in the European Caucasian population, in silico, by the Meta-Analyses of Glucose and Insulin-related traits Consortium (MAGIC; [16]).These results did not provide further insight into the probable role these variants may have in disease susceptibility (Table S6).The most significantly associated SNP in African Americans, rs7560163, failed quality controls filters and was not included in analysis likely due to being monomorphic as seen in a representative Caucasian population from the HapMap project (Table S4).",
"Discovery of novel loci for T2D susceptibility.We tested for T2D association with ~27 million variants passing quality-control filters, ~21 million of which had a minor allele frequency (MAF) < 5%.Our meta-analysis identified variants at 231 loci reaching genomewide significance (P < 5 \u00d7 10 \u22128 ) in the BMI-unadjusted analysis (N eff 231,436) and 152 in the smaller (N eff 157,401) BMI-adjusted analysis.Of the 243 loci identified across these two analyses, 135 mapped outside regions previously implicated in T2D risk (Methods, Fig. 1 and Supplementary Table 2).",
"Genetic 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 \u00d7 10 \u22128 ) (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.",
"Finally, 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 \u03fd10 \u03ea4 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.",
"Surprisingly, data about previous published loci associated with type 2 diabetes were not sufficiently powerful to reach a significant P value in individual scans.For example, variants at SLC30A8 and PPARG were significantly associated with type 2 diabetes only when pooling all the GWAs data, whereas in a single genome scan (DGI), no gene showed a positive signal (P value: 0.92 and 0.83, respectively).Thus, this may suggest that GWAs are still underpowered to find SNPs with small effect size.",
"Background: The two genome-wide association studies published by us and by the Wellcome Trust Case-Control Consortium (WTCCC) revealed a number of novel loci, but neither had the statistical power to elucidate all of the genetic components of type 1 diabetes risk, a task for which larger effective sample sizes are needed.Methods: We analysed data from two sources: (1) The previously published second stage of our study, with a total sample size of the two stages consisting of 1046 Canadian case-parent trios and 538 multiplex families with 929 affected offspring from the Type 1 Diabetes Genetics Consortium (T1DGC); (2) the Rapid Response 2 (RR2) project of the T1DGC, which genotyped 4417 individuals from 1062 non-overlapping families, including 2059 affected individuals (mostly sibling pairs) for the 1536 markers with the highest statistical significance for type 1 diabetes in the WTCCC results.Results: One locus, mapping to a linkage disequilibrium (LD) block at chr15q14, reached statistical significance by combining results from two markers (rs17574546 and rs7171171) in perfect LD with each other (r 2 = 1).We obtained a joint p value of 1.3610 26 , which exceeds by an order of magnitude the conservative threshold of 3.26610 25 obtained by correcting for the 1536 single nucleotide polymorphisms (SNPs) tested in our study.Meta-analysis with the original WTCCC genome-wide data produced a p value of 5.83610 29 .Conclusions: A novel type 1 diabetes locus was discovered.It involves RASGRP1, a gene known to play a crucial role in thymocyte differentiation and T cell receptor (TCR) signalling by activating the Ras signalling pathway.",
"Finally, we examined whether genes identified using our association studies were enriched within diabetes-related pathways.We collated a list of 42 genes to which 53 CpG sites associated with T2D traits (CS score \u22651.77, combined P < 0.017) mapped.Even in this small dataset, pathway analysis (Supplementary Material, Table S12) indicated significant enrichment in 31 pathways (Fisher's exact P < 0.05), including those related to circadian clock (P = 0.005), adipocytokine signaling (P = 0.009), leptin pathway (P = 0.023), HDL-mediated lipid transport (P = 0.031) and insulin signaling (P = 0.033).",
"In recent years, progress has been made in following up mechanistic studies of GWAS type 2 diabetes-association signals [6,7,9,[25][26][27][28][29][30], but challenges remain in sifting through the many associated variants at a locus to identify those influencing disease.We hypothesized that a common variant with modest effect underlies the association at the CDC123/CAMK1D locus and evaluated the location of high LD variants (r 2 $.7; n = 11) at the locus relative to known transcripts and to putative DNA regulatory elements.We identified two variants that overlapped putative islet and/or liver regulatory regions and none located in exons.We did not assess variants in lower LD (r 2 ,.7), and additional functional SNPs may exist at this locus acting through alternate functional mechanisms untested in the current study.",
"Meta-analysis results for T2D SNPs for insulin and glucose-related traits.",
"A r t i c l e s By combining genome-wide association data from 8,130 individuals with type 2 diabetes (T2D) and 38,987 controls of European descent and following up previously unidentified meta-analysis signals in a further 34,412 cases and 59,925 controls, we identified 12 new T2D association signals with combined P < 5 \u00d7 10 \u22128 .These include a second independent signal at the KCNQ1 locus; the first report, to our knowledge, of an X-chromosomal association (near DUSP9); and a further instance of overlap between loci implicated in monogenic and multifactorial forms of diabetes (at HNF1A).The identified loci affect both beta-cell function and insulin action, and, overall, T2D association signals show evidence of enrichment for genes involved in cell cycle regulation.We also show that a high proportion of T2D susceptibility loci harbor independent association signals influencing apparently unrelated complex traits."
],
[
"Methods Mouse models of diabetes.All animal studies were conducted according to a protocol approved by the Institutional Animal Care and Use Committee at the Beckman Research Institute of City of Hope.Male type-2 diabetic db/db mice (T2D leptin receptor deficient; Strain BKS.Cg-m \u00fe / \u00fe lepr db/J) and genetic control non-diabetic db/ \u00fe mice (10-12 weeks old), were obtained from The Jackson Laboratory (Bar Harbor, ME) 11,17 .Male C57BL/6 mice (10 week old, The Jackson Laboratory) were injected with 50 mg kg \u00c0 1 of STZ intraperitoneally on 5 consecutive days.Mice injected with diluent served as controls.Diabetes was confirmed by tail vein blood glucose levels (fasting glucose 4300 mg dl \u00c0 1 ).Each group was composed of five to six mice.Mice were sacrificed at 4-5 or 22 (ref.17) weeks post-induction of diabetes.Glomeruli were isolated from freshly harvested kidneys by a sieving technique 11,17 in which renal capsules were removed, and the cortical tissue of each kidney separated by dissection.The cortical tissue was then carefully strained through a stainless sieve with a pore size of 150 mm by applying gentle pressure.Enriched glomerular tissue below the sieve was collected and transferred to another sieve with a pore size of 75 mm.After several washes with cold PBS, the glomerular tissue remaining on top of the sieve was collected.Pooled glomeruli were centrifuged, and the pellet was collected for RNA, protein extraction or for preparing MMCs 11,17 .Male Chop-KO mice were also obtained from the Jackson Laboratory (B6.129S(Cg)-Ddit3 tm2.1Dron /J).Based on our previous experience, sample size was determined to have enough power to detect an estimated difference between two groups.With minimum sample size of 5 in each group, the study can provide at least 80% power to detect an effect size of 2 between diabetic and non-diabetic groups or treated and untreated groups at the 0.05 significant level using two-sided t-test.Since we expected larger variation between groups especially for the mice with oligo-injection, we used more than 5 mice in each group (with 6 mice in each group, we have 80% power to detect an effect size of 1.8 at the 0.05 confidence level).Our actual results with current sample size did show statistical significance for majority of the miRNAs in the cluster.Histopathological and biochemical analysis of tissues or cells derived from animal models were performed by investigators masked to the genotypes or treatments of the animals.",
"In these models, adult offspring of diabetic animals were noted to have normal development of the endocrine pancreas (Aerts et al., 1997;Ma et al., 2012).However, they develop glucose intolerance and impaired insulin response to glucose challenge, and display insulin resistance, mainly in the liver and muscle, highlighting the presence of both insulin resistance and b-cell dysfunction (Aerts et al., 1988;Holemans et al., 1991a,b).The key role of the intrauterine environment was demonstrated by a series of embryo transfer experiments, which showed that the diabetes risk in a low genetic risk strain can be substantially increased by the hyperglycaemic environment of a dam with a high genetic risk of diabetes (Gill-Randall et al., 2004).",
"Diabetes-obesity syndromes in rodents",
"However, in other contexts, B6 mice are more likely than D2 to spontaneously develop diabetic syndromes, Aging Clin Exp Res indicating that risk factors exist on both genetic backgrounds [29]. QTL mapping studies indicate that these murine metabolic traits have a complex genetic architecture that is not dominated by any single allele [29\u201331], much like humans [32, 33]. Prior work identified candidate genes on Chr 13 that might underlie diabetes-related traits, including RASA1, Nnt, and PSK1. RASA1 show strong sequence differences between B6 and D2 strains [34]. Rasche et al.",
"Other diet-induced rodent models of type 2 diabetes.Although rats and mice are the most commonly used models for studies of type 2 diabetes, other rodents have also been identified as useful models.These include the desert gerbil and the newly described Nile grass rat, both of which tend to develop obesity in captivity.",
"Summary of rodent models of type 2 diabetes",
"Since the obesity is induced by environmental manipulation rather than genes, it is thought to model the human situation more accurately than genetic models of obesityinduced diabetes.High fat feeding is often used in transgenic or knock-out models, which may not show an overt diabetic phenotype under normal conditions, but when the beta cells are 'pushed', the gene may be shown to be of importance.It should be noted that the background strain of the mice can determine the susceptibility to diet-induced metabolic changes, and thus, effects could be missed if a more resistant strain is used (Surwit et al., 1995;Bachmanov et al., 2001;Almind and Kahn, 2004).It has also been reported that there is heterogeneity of the response to high fat feeding within the inbred C57BL/6 strain, indicating that differential responses to a high-fat diet are not purely genetic (Burcelin et al., 2002).",
"Other considerations and limitations A myriad of factors affect animal experiments.Men elicit a greater stress response in mice than women 292 , likely confounding feeding behaviour.Rodents from different production facilities (for example, Jackson Laboratory and Taconic) have unique gut microbiotas 293 , perhaps contributing to differences in their susceptibility to DIO and related diabetic complications 293 .Similarly, cage position within a rack of cages, single versus group housing, the skill level of the researcher, ambient room temperature or the type of cage bedding can all affect experimental outcomes.",
"We believe there are several factors that researchers should consider when conducting obesity and diabetes mellitus research in rodents (FIG.2).Although our list is by no means an exhaustive, it demonstrates the complexity and interconnectedness of the myriad of factors that can confound experimental outcomes.Although it is impossible to control for everything, researchers should accurately detail all experimental conditions and methods to allow for better interpretation of the results and, importantly, for better reproducibility.",
"Figure2| Important experimental parameters and potential confounders of experimental outcomes in obesity and diabetes research and their interrelatedness.Countless factors influence experimental outcomes when using animal models, and what is enumerated here is by no means a complete list.This figure is one depiction of the multifactorial and interconnected genetic and environmental matrix that makes it virtually impossible to design the perfect experiment.For example, single-housing mice to obtain more accurate food intake data introduces a stress that in turn affects food intake.The severity of this stress response is both strain-specific and sex-dependent.What is important is to be aware of these challenges and to control for them in the most optimal manner.It is equally, if not more, important to accurately and comprehensively detail all experimental conditions in research papers, as these have bearing on the interpretation and reproducibility of the published results.DIO, diet-induced obesity.",
"Another concern pertains to control mice.Compared with free-living mice in the wild, laboratory control mice with ad libitum access to food are sedentary, overweight, glucose intolerant and tend to die at a younger age 297 .Comparisons between mice with DIO and control mice might be analogous to investigating the genetic cause of obesity-resistance by comparing humans who are overweight or obese.This potential problem with control mice could explain why the use of DIO diets that have 40% to 60% of total energy from fat is so prevalent, as this might be necessary to achieve divergent weight gains.With free access to running wheels, C57BL/6J mice voluntarily run 5-10 km per day 298,299 .As is the case with humans 300 , mice get health benefits from regular physical activity including weight loss, decreased adiposity and improved insulin sensitivity 301,302 .Physical activity might also affect the epigenome over several generations 303 .An enriched physical and social cage environment alone improves leptin sensitivity and energy expenditure in mice, independent of physical activity 304,305 .Overall, these data suggest that with standard mouse husbandry, chow-fed laboratory mice are not the ideal healthy and lean control group for meaningful obesity research.",
"To better address these points, various animal models have been developed.For example, using HFD-T2DM male rats, the F1 female offspring showed reduced \u03b2 cell area and insulin secretion, together with glucose intolerance, without changes in body weight [145].The islets of the F1 female offspring showed differential expression of many genes involved in Ca 2+ , mitogen-activated protein kinase and Wnt signaling, apoptosis and cell cycle regulation [145].Similarly, in pregnant C57BL6J mice, food deprivation resulted in \u03b2 cell mass reduction and an increased risk of \u03b2 cell failure in offspring [146].",
"They are probably typical of those few mice that develop diabetes more slowly and do not tax the pancreatic insulin supply as severely early in the course of the disease. Attempts at therapy. Attempts to keep the weight of diabetic mice within normal limits by total or partial food restriction resulted in premature deaths. After it was discovered that gluconeogenesis is greatly increased in diabetic mice, attempts were made to regulate blood sugar levels and also weight gain by feeding rations devoid of carbohydrate.",
"The degree of dependence of adiposity, hyperglycemia, and islet hypertrophy on food consumption varies among these mice, but in all, the increase in islet volume and consequent fi-eell hyperplasia appears to be an effective 247 means of maintaining blood sugar concentrations at near normal levels. I n contrast, neither the diabetic sand rat [5] nor the diabetic mouse has hypertrophied islets and neither effectively controls blood sugar levels.",
"HV~MEI,: Studies with the Mutation, Diabetes almost undetectable. Similarly, the activities of citrate lyase and glucose-6-phosphate dehydrogenase were greatly decreased in these older diabetic as compared Diabetologia the diabetic mice have attained m a x i m u m weight, after which no further accumulation of adipose tissue is noted. Fig. 8.",
"Rodent models of monogenic obesity and diabetes Obesity and the consequent insulin resistance is a major harbinger of Type 2 diabetes mellitus in humans.Consequently, animal models of obesity have been used in an attempt to gain insights into the human condition.Some strains maintain euglycaemia by mounting a robust and persistent compensatory \u03b2 -cell response, matching the insulin resistance with hyperinsulinaemia.The ob / ob mouse and fa / fa rats are good examples of this phenomenon.Others, such as the db / db mouse and Psammomys obesus (discussed later) rapidly develop hyperglycaemia as their \u03b2 -cells are unable to maintain the high levels of insulin secretion required throughout life.Investigation of these different animal models may help explain why some humans with morbid obesity never develop Type 2 diabetes whilst others become hyperglycaemic at relatively modest levels of insulin resistance and obesity.",
"As with the KK mouse, the Israeli sand rat model is particularly useful when studying the effects of diet and exercise [120] on the development of Type 2 diabetes.",
"Animal models of diabetes in pregnancy and the role of intrauterine environment Another important field of diabetes research that has relied heavily on animal experimentation is the study of diabetes in pregnancy and the role of the intrauterine environment on the subsequent development of diabetes amongst offspring.",
"Animal models of Type 2 diabetes mellitus",
"Assessment of Diabetes Mice were monitored for the development of diabetes as described previously (Wicker et al. 1994)."
],
[
"Methods Mouse models of diabetes.All animal studies were conducted according to a protocol approved by the Institutional Animal Care and Use Committee at the Beckman Research Institute of City of Hope.Male type-2 diabetic db/db mice (T2D leptin receptor deficient; Strain BKS.Cg-m \u00fe / \u00fe lepr db/J) and genetic control non-diabetic db/ \u00fe mice (10-12 weeks old), were obtained from The Jackson Laboratory (Bar Harbor, ME) 11,17 .Male C57BL/6 mice (10 week old, The Jackson Laboratory) were injected with 50 mg kg \u00c0 1 of STZ intraperitoneally on 5 consecutive days.Mice injected with diluent served as controls.Diabetes was confirmed by tail vein blood glucose levels (fasting glucose 4300 mg dl \u00c0 1 ).Each group was composed of five to six mice.Mice were sacrificed at 4-5 or 22 (ref.17) weeks post-induction of diabetes.Glomeruli were isolated from freshly harvested kidneys by a sieving technique 11,17 in which renal capsules were removed, and the cortical tissue of each kidney separated by dissection.The cortical tissue was then carefully strained through a stainless sieve with a pore size of 150 mm by applying gentle pressure.Enriched glomerular tissue below the sieve was collected and transferred to another sieve with a pore size of 75 mm.After several washes with cold PBS, the glomerular tissue remaining on top of the sieve was collected.Pooled glomeruli were centrifuged, and the pellet was collected for RNA, protein extraction or for preparing MMCs 11,17 .Male Chop-KO mice were also obtained from the Jackson Laboratory (B6.129S(Cg)-Ddit3 tm2.1Dron /J).Based on our previous experience, sample size was determined to have enough power to detect an estimated difference between two groups.With minimum sample size of 5 in each group, the study can provide at least 80% power to detect an effect size of 2 between diabetic and non-diabetic groups or treated and untreated groups at the 0.05 significant level using two-sided t-test.Since we expected larger variation between groups especially for the mice with oligo-injection, we used more than 5 mice in each group (with 6 mice in each group, we have 80% power to detect an effect size of 1.8 at the 0.05 confidence level).Our actual results with current sample size did show statistical significance for majority of the miRNAs in the cluster.Histopathological and biochemical analysis of tissues or cells derived from animal models were performed by investigators masked to the genotypes or treatments of the animals.",
"Diabetes incidence study. Mice were kept for 20-28 weeks and tested for diabetes monthly by blood glucose and weekly by urine assessment, with a positive indication being followed by twice-weekly blood testing.Mice were diagnosed as diabetic when the blood glucose concentration was over 260 mg/dl (14.4 mM) after 2-3 h of fasting for two sequential tests.Glucose and insulin tolerance tests were performed by injecting glucose (2 g/kg body weight) or insulin (1 U/kg body weight) intraperitoneally in mice fasted for 6-7 h.Tail vein blood was tested by a Contour glucometer.Assessments of plasma insulin, proinsulin and C-peptide levels were performed using commercial ELISA kits, according to the manufacturer's instructions (insulin, proinsulin and C-peptide mouse ELISA kits, R&D Systems Quantikine).Assays were performed with blinding, with mice coded by number until experimental end.",
"Animal group and study design First, one set of animals comprising 12-week-old male type 2 diabetic db/db (C57BL/KsJ-db\u2212/db\u2212, n = 8) and contemporary control wild-type (C57BL/KsJ-db+/db\u2212, n = 8) mice (Jackson Laboratories) were included in this study.Their weights and blood glucose levels were analysed to eliminate variation.Erectile functions of the animals were evaluated by the apomorphine-induced penile erection test, according to a previously described protocol (Pan et al. 2014).Afterwards, intracavernous pressure (ICP) investigations and histological measurements were applied to further confirm the results of the function tests.Then, all mice were sacrificed and the corpus cavernosum (CC) was collected from each mouse.Because the tissue of the CC is difficult to crush, we randomly collected the CCs from two mice and mixed them into one subgroup.As a result, four diabetic subgroups (DB groups) and four normal control subgroups (NC groups) were used for molecular measurements.Second, another set of animals, including three T2DMED and three normal control mice that were independent from the original set of animals, were included in the validation experiments using qRT-PCR.Third, another separate set of animals, including five T2DMED and five control mice, were used to verify one of the predicted targets, IGF-1, using ELISA.A luciferase reporter assay was performed to verify the binding of the differentially expressed miRNAs to the target gene IGF-1.All procedures were approved by the Institutional Animal Care and Use committee at Nanjing Medical University.",
"Summary of rodent models of type 2 diabetes",
"Summary of rodent models of type 1 diabetes",
"Knock-out and transgenic mice in diabetes research Transgenic mice have been used to create specific models of type 1 and type 2 diabetes, including hIAPP mice, humanized mice with aspects of the human immune system and mice allowing conditional ablation of beta cells, as outlined above.Beta cells expressing fluorescent proteins can also provide elegant methods of tracking beta cells for use in diabetes research (Hara et al., 2003).",
"Genetically induced insulin-dependent diabetes AKITA mice.The AKITA mouse was derived in Akita, Japan from a C57BL/6NSlc mouse with a spontaneous mutation in the insulin 2 gene preventing correct processing of proinsulin.This causes an overload of misfolded proteins and subsequent ER stress.This results in a severe insulindependent diabetes starting from 3 to 4 weeks of age, which is characterized by hyperglycaemia, hypoinsulinaemia, polyuria and polydipsia.Untreated homozygotes rarely survive longer than 12 weeks.The lack of beta cell mass in this model makes it an alternative to streptozotocin-treated mice in transplantation studies (Mathews et al., 2002).It has also been used as a model of type 1 diabetic macrovascular disease (Zhou et al., 2011) and neuropathy (Drel et al., 2011).In addition, this model is commonly used to study potential alleviators of ER stress in the islets and in this respect models some of the pathology of type 2 diabetes (Chen et al., 2011).",
"To achieve a slow pathogenesis of T2DM, young adult mice 284 or rats 285 are fed a high-fat or Western diet to elicit DIO and insulin resistance.Single or multiple injections with low-dose streptozotocin (~30-40 mg/kg intraperitoneally) then elicit partial loss of \u03b2-cells, which results in hypoinsulinaemia and hyperglycaemia.Protocols are being continuously refined and likely differ between species and even strains 283 .The HFD streptozotocin rat is sensitive to metformin, further demonstrating the utility of this model 285 .Downsides of streptozotocin treatment include liver and kidney toxicity and mild carcinogenic adverse effects (TABLE 1).",
"Materials and methods 2.1 Mouse models 2.1.1 Mouse strains 2.1.2 Induction of type 1 diabetes 8 2.1.3 Insulin treatment on diabetic mice 2.1.4 Akita mouse genotyping 2.2 Characterization of diabetic nephropathy in mice 2.2.1 Proteinuria measurement 2.2.2 Glomerular cells quantification 2.2.3 Methenamine silver staining quantification 3. 4. 5. 6.",
"ii) Rodent models of diabetic retinopathy",
"There are some good reviews available in the literatures describing the transgenic/knockout animal models of type 2 diabetes [114][115][116][117][118] .The transgenic and knockout models are developed for studying the role of genes and their effects on peripheral insulin action such as insulin receptor, IRS-1, IRS-2, glucose transporter (GLUT 4), peroxisome proliferator activated receptor-g (PPAR-g) and tumour necrosis factor-a (TNF-a) as well as in insulin secretion such as GLUT-2, glucokinase (GK), islet amyloid polypeptide (IAPP) and GLP-1 and in hepatic glucose production (expression of PEPCK) associated with development of type 2 diabetes.Further, combination or double knockout mouse models including defect in insulin action and insulin secretion (e.g., IRS-1 +/-/GK +/-double knockout) have been produced which clearly illustrate the mechanisms associated with development of insulin resistance and beta cell dysfunction leading to overt hyperglycaemic state in human type 2 diabetes.These above genetically modified animals exhibit various phenotypic features of type 2 diabetes varying from mild to severe hyperglycaemia, insulin resistance, hyperinsulinaemia, impaired glucose tolerance and others as explained in detail elsewhere 6,9,[114][115][116][117][118] .Very recently, tissue specific knockout mouse models have been achieved, allowing further insight into the insulin action with respect to particular target tissues (muscle, adipose tissue and liver) associated with insulin resistance and type 2 diabetes 115,117,118 .The transgenic/knockout animals are currently used mostly for the mechanistic study in diabetes research and not usually recommended for screening programme as they are more complicated and costly.",
"Functional deficits refs Non-Alzheimer-disease mouse [71][72][73][74]76,78,81,85,87 and rat 59,75,77 ,79,95,97 Mouse [81][82][83][84][85] and rat 79,111 Cerebral effects of inducing diabetes or insulin resistance in normal rodents (that is, non-Alzheimer-disease rodent models) and in rodents genetically modified to accumulate amyloid\u03b2 in the brain (that is, rodent models of Alzheimer disease). Common intervetions to induce diabetic conditions in rodents included recessive mutations in the leptin gene (Lep; also known as Ob), defects in the leptin receptor (LEPR; also known as OB-R), diet and administration of streptozotocin. Rodents with pancratic overexpression of human amylin spontaneously develop both type 2 diabetes mellitus and dementia-like pathology.",
"Animal models have been used extensively in diabetes research.Early studies used pancreatectomised dogs to confirm the central role of the pancreas in glucose homeostasis, culminating in the discovery and purification of insulin.Today, animal experimentation is contentious and subject to legal and ethical restrictions that vary throughout the world.Most experiments are carried out on rodents, although some studies are still performed on larger animals.Several toxins, including streptozotocin and alloxan, induce hyperglycaemia in rats and mice.Selective inbreeding has produced several strains of animal that are considered reasonable models of Type 1 diabetes, Type 2 diabetes and related phenotypes such as obesity and insulin resistance.Apart from their use in studying the pathogenesis of the disease and its complications, all new treatments for diabetes, including islet cell transplantation and preventative strategies, are initially investigated in animals.In recent years, molecular biological techniques have produced a large number of new animal models for the study of diabetes, including knock-in, generalized knock-out and tissue-specific knockout mice.",
"Animal models of Type 2 diabetes mellitus",
"As with the KK mouse, the Israeli sand rat model is particularly useful when studying the effects of diet and exercise [120] on the development of Type 2 diabetes.",
"Animal models of Type 1 diabetes",
"Animal models have been used extensively in diabetes research.Early studies used pancreatectomised dogs to confirm the central role of the pancreas in glucose homeostasis, culminating in the discovery and purification of insulin.Today, animal experimentation is contentious and subject to legal and ethical restrictions that vary throughout the world.Most experiments are carried out on rodents, although some studies are still performed on larger animals.Several toxins, including streptozotocin and alloxan, induce hyperglycaemia in rats and mice.Selective inbreeding has produced several strains of animal that are considered reasonable models of Type 1 diabetes, Type 2 diabetes and related phenotypes such as obesity and insulin resistance.Apart from their use in studying the pathogenesis of the disease and its complications, all new treatments for diabetes, including islet cell transplantation and preventative strategies, are initially investigated in animals.In recent years, molecular biological techniques have produced a large number of new animal models for the study of diabetes, including knock-in, generalized knock-out and tissue-specific knockout mice.",
"Rodent models of monogenic obesity and diabetes Obesity and the consequent insulin resistance is a major harbinger of Type 2 diabetes mellitus in humans.Consequently, animal models of obesity have been used in an attempt to gain insights into the human condition.Some strains maintain euglycaemia by mounting a robust and persistent compensatory \u03b2 -cell response, matching the insulin resistance with hyperinsulinaemia.The ob / ob mouse and fa / fa rats are good examples of this phenomenon.Others, such as the db / db mouse and Psammomys obesus (discussed later) rapidly develop hyperglycaemia as their \u03b2 -cells are unable to maintain the high levels of insulin secretion required throughout life.Investigation of these different animal models may help explain why some humans with morbid obesity never develop Type 2 diabetes whilst others become hyperglycaemic at relatively modest levels of insulin resistance and obesity.",
"Introduction Animal experimentation has a long history in the field of diabetes research.The aim of this article is to review the commonly used animal models and discuss the recent technological advances that are being employed in the discipline.The review is based on an extensive literature search using the terms rodent, mouse, rat, animal model, transgenics, knockout, diabetes and pathogenesis, in scientific journal databases such as MEDLINE \u00ae.In addition, abstracts presented at meetings of Diabetes UK, the European Association for the Study of Diabetes and the American Diabetes Association over the last 5 years were examined in order to gain an appreciation of recent and ongoing research projects.",
"Assessment of Diabetes Mice were monitored for the development of diabetes as described previously (Wicker et al. 1994)."
],
[
"Subsequently, genetic dissection of the diabetes-associated traits in the male BC1 progeny obtained from a cross between (normal B6 female \u03eb diabetic TH male)F1 female and diabetic TH male mice (B6 cross) was carried out.Because of the sexual dimorphism, with respect to NIDDM onset, we used diabetic TH male mice as breeders to ensure the presence of a mutant allele(s) and targeted our genetic dissection using only male BC1 progeny.In male BC1 mice hyperglycemia developed at approximately 20 weeks of age and was sustained through a 30-week period studied.Based on these data, we measured plasma glucose levels three times in biweekly intervals (to minimize phenotyping error) between 20 and 26 weeks of age, and the mean of the three measurements was used for genetic analysis.Body weights were measured at 20 weeks.At the end of the study (26 weeks), plasma insulin levels and nasal-anal lengths were measured, and the five regional fat pads were dissected and weighed from a subset of 133 mice.In total, 206 male BC1 mice were collected, and individual mice were genotyped with 92 SSLP markers at approximately 20-cM intervals (covering \u03f396% of the genome).",
"Effects of Inbred Background (Table 2).The syndrome produced in BL/Ks diabetes (db) mice, while similar in early development to that of BL/6 obese (ob) mice, has a more severe diabetes-like condition and a less pronounced obesity.However, both mutations when maintained on the same inbred background exhibit identical syndromes from 3 weeks of age on [9,21].Both diabetes and obese mice of the BL/Ks strain have the severe diabetes characterized by insulinopaenia and islet atrophy, whereas both mutations maintained on the BL/6 strain have mild diabetes characterized by islet hypertrophy and hyperplasia of the beta cells.Islet hypertrophy is either sustained or followed by atrophy depending on modifiers in the genetic background rather than the specific action of the mutant gene.The markedly different obesity-diabetes states exhibited when obese and diabetes mice are on different backgrounds points out the importance of strict genetic control in studies with all types of obese-hyperglycaemic mutants.Genetic studies [11] have shown that the modifiers leading to islet hypertrophy and well-compensated diabetes compatible with a near normal lifespan are dominant to those factors causing severe diabetes.Two other mutations, yellow and fat, cause similar diabetes-syndromes and yet have identical symptoms on both inbred backgrounds (Table 2).This may suggest that the primary insult caused by these mutations is not as severe as that for obese and diabetes and that this more gradual initiation of obesity permits the host genome to make a response (islet hypertrophy) compatible with life rather than islet atrophy, insulinopaenia, and life-shortening diabetes.",
"The animal models available for diabetes research (Table 1) are most often more like maturityonset diabetes in man.Obesity is a consistent factor and insulinopaenia is rare.However, the time of gene expression at about two weeks of age is within the time period of juvenile expression.The severity and clinical course of the diabetes produced depends on the interaction of the mutant gene with the inbred background rather than the action of the gene itself.Thus on one inbred background a well-compensated, maturity onset type diabetes, compatible with near normal life is observed whereas on another inbred background the syndrome presents as a juvenile-type diabetes with insulinopaenia, islet cell degeneration, marked hyperglycaemia, some ketosis and a much shortened lifespan.Unfortunately, vascular, retinal and the other complications of diabetes are not seen consistently in these rodent syndromes.It seems that the severely diabetic animal either does not live long enough to develop these complications or that rodents are particularly resistant to those complications that commonly afflict human diabetics.Several comprehensive bibliographies and excellent reviews of the various studies carried out with each of these syndromes in animals have been published [2,3,19,30,31,32].This presentation will be restricted primarily to the research undertaken by my colleagues and myself with the two mouse mutations; diabetes (db), and obese (ob).Both mutations have been extensively studied by numerous investigators in attempts to define the primary lesion causing the syndrome.As yet, the primary defect remains illusive, although several possibilities are becoming increasingly plausible in the light of current research.Although the metabolic abnormalities associated with both obese and diabetes have many similarities with regard to the overall progression of the obesity-diabetes state, the documentation of two single genes on separate chromosomes makes it unlikely that the two syndromes are caused by the same primary lesion.However, the marked similarity between the two mutants when maintained on the same genetic background implies that the defects may occur in the same metabolic pathway.",
"Diabetes-obesity syndromes in rodents",
"The Diabetes (db) .Mouse (Chromosome 4).Diabetes (db), an autosomal recessive mutation, occurred in the C57BL/KsJ (BL/Ks) inbred strain and on this background is characterized by obesity, hyperphagia, and a severe diabetes with marked hyperglycaemia [7,22].Increased plasma insulin concentration is observed as early as 10 days of age [10].The concentration of insulin peaks at 6 to 10 times normal by 2 to 3 months of age then drops precipitously to near normal levels.Prior to the fall in plasma insulin concentration, the most consistent morphological feature of the islets of Langerhans appears to be hyperplasia and hypertrophy of the beta cells in an attempt to produce sufficient insulin to control blood glucose concentration at physiological levels.The drop in plasma insulin concentration is concomitant with islet atrophy and rapidly rising blood glucose concentrations that remain over 400 mg per 100 ml until death at 5 to 8 months [7].Compared with other obesity mutants the diabetic condition is more severe and the lifespan is markedly decreased.",
"Diabetes-related clinical traits for 275 B6XBTBR-ob/ ob F2 male mice at 10 weeks of age.",
"Results We generated an F2 inter-cross between diabetes-resistant (B6) and diabetes-susceptible (BTBR) mouse strains, made genetically obese in response to the Lep ob mutation [24].The cross consisted of .500mice, evenly split between males and females.A comprehensive set of ,5000 genotype markers were used to genotype each F2 mouse (,2000 informative SNPs were used for analysis), and the expression levels of ,40 K transcripts (corresponding to 25,901 unique genes) were monitored in five tissues (adipose, liver, pancreatic islets, hypothalamus, and gastroc (gastrocnemius muscle)) that were harvested from each mouse at 10 weeks of age.In addition to gene expression, several key T2D-related traits were determined for each mouse.The medians, and 1st and 3rd quartiles for the following traits: body weight, the number of islets harvested per pancreas, HOMA, plasma insulin, glucose, triglyceride, and C-peptide are listed in Table 1.",
"However, in other contexts, B6 mice are more likely than D2 to spontaneously develop diabetic syndromes, Aging Clin Exp Res indicating that risk factors exist on both genetic backgrounds [29]. QTL mapping studies indicate that these murine metabolic traits have a complex genetic architecture that is not dominated by any single allele [29\u201331], much like humans [32, 33]. Prior work identified candidate genes on Chr 13 that might underlie diabetes-related traits, including RASA1, Nnt, and PSK1. RASA1 show strong sequence differences between B6 and D2 strains [34]. Rasche et al.",
"Thus, there is a rich literature indicating strong genetic effects on glucose metabolism in the B6 and D2 genetic background, and a male-specific form of diabetes is known to spontaneously occur in hybrids of this strain. Dental traits The reported link between a Chr 13 locus and dental malocclusions [46] might provide an alternative or additional explanation of the associations we observe. Dental malocclusions were the only major male-specific cause of death we observed in this mouse population (20 % of males that died before the 750-day phenotyping tests, 0 % of females).",
"Obesity-associated diabetes (''diabesity'') in mouse strains is characterized by severe insulin resistance, hyperglycaemia and progressive failure, and loss of beta cells.This condition is observed in inbred obese mouse strains such as the New Zealand Obese (NZO/HlLt and NZO/HlBomDife) or the TALLYHO/JngJ mouse.In lean strains such as C57BLKS/J, BTBR T?tf/J or DBA/2 J carrying diabetes susceptibility genes (''diabetes susceptible'' background), it can be induced by introgression of the obesity-causing mutations Lep \\ob[ (ob) or Lepr \\db[ (db).Outcross populations of these models have been employed in the genome-wide search for mouse diabetes genes, and have led to positional cloning of the strong candidates Pctp, Tbc1d1, Zfp69, and Ifi202b (NZO-derived obesity) and Sorcs1, Lisch-like, Tomosyn-2, App, Tsc2, and Ube2l6 (obesity caused by the ob or db mutation).Some of these genes have been shown to play a role in the regulation of the human glucose or lipid metabolism.Thus, dissection of the genetic basis of obesity and diabetes in mouse models can identify regulatory mechanisms that are relevant for the human disease.",
"Polygenic basis of ''diabesity'' in mice: the interaction of obesity and diabetes genes Obesity-associated diabetes (''diabesity'') is due to interaction of genes causing obesity with diabetes genes.This conclusion is based on findings indicating that obesity is a necessary but not sufficient condition for the type 2 diabetes-like hyperglycaemia: Obese mice are insulin resistant and therefore more or less glucose intolerant, but in some strains such as C57BL/6J-ob/ob, insulin resistance is compensated by hyperinsulinemia and beta cell hyperplasia, and plasma glucose is only moderately elevated.Other models such as C57BLKS/J-db/db and NZO present overt diabetes mellitus as defined by a threshold of 16.6 mM (300 mg/dl) plasma glucose (Leiter et al. 1998); mice crossing this threshold usually exhibit progressive failure and subsequent apoptosis of beta cells.This type 2 diabetes-like condition is not due to the obesity-causing gene variants but to other genes in the genetic background of the strain, which cause obesity-associated diabetes.The severe and early onsetting diabetes of the C57BLKS/J-db/ db strain is due to the C57BLKS/J background, since mice carrying the db mutation on the C57BL/6J background are not diabetic (Stoehr et al. 2000).Conversely, C57BL/6Job/ob mice are normoglycemic, whereas introgression of the ob mutation into the C57BLKS/J background produced a severely diabetic strain (Coleman 1978).Furthermore, it has been shown that in crosses of lean, normoglycaemic strains with diabetic strains the lean strain can introduce variants that markedly aggravate the diabetic phenotype (Leiter et al. 1998;Plum et al. 2000).",
"Obesity-associated diabetes (''diabesity'') in mouse strains is characterized by severe insulin resistance, hyperglycaemia and progressive failure, and loss of beta cells.This condition is observed in inbred obese mouse strains such as the New Zealand Obese (NZO/HlLt and NZO/HlBomDife) or the TALLYHO/JngJ mouse.In lean strains such as C57BLKS/J, BTBR T?tf/J or DBA/2 J carrying diabetes susceptibility genes (''diabetes susceptible'' background), it can be induced by introgression of the obesity-causing mutations Lep \\ob[ (ob) or Lepr \\db[ (db).Outcross populations of these models have been employed in the genome-wide search for mouse diabetes genes, and have led to positional cloning of the strong candidates Pctp, Tbc1d1, Zfp69, and Ifi202b (NZO-derived obesity) and Sorcs1, Lisch-like, Tomosyn-2, App, Tsc2, and Ube2l6 (obesity caused by the ob or db mutation).Some of these genes have been shown to play a role in the regulation of the human glucose or lipid metabolism.Thus, dissection of the genetic basis of obesity and diabetes in mouse models can identify regulatory mechanisms that are relevant for the human disease.",
"Spontaneous type 2 diabetic models Spontaneously diabetic animals of type 2 diabetes may be obtained from the animals with one or several genetic mutations transmitted from generation to generation (e.g., ob/ob, db/db mice) or by selected from non-diabetic outbred animals by repeated breeding over several generation [e.g., (GK) rat, Tsumara Suzuki Obese Diabetes (TSOD) mouse].These animals generally inherited diabetes either as single or multigene defects.The metabolic peculiarities result from single gene defect (monogenic) which may be due to dominant gene (e.g., Yellow obese or KK/A y mouse) or recessive gene (diabetic or db/db mouse, Zucker fatty rat) or it can be of polygenic origin [e.g., Kuo Kondo (KK) mouse, New Zealand obese (NZO) mouse] 13 .Type 2 diabetes occurring in majority of human being is a result of interaction between environmental and multiple gene defects though certain subtype of diabetes do also exist with well defined cause [i.e., maturity onset diabetes of youth (MODY) due to defect in glucokinase gene] and this single gene defects may cause type 2 diabetes only in few cases.",
"Mice of the KK strain exhibit a multigenic syndrome of hyperphagia, moderate obesity, hyperinsulinemia, and hyperglycemia (Ikeda 1994;Nakamura andYamada 1963, 1967;Reddi and Camerini-Davalos 1988).Most KK males develop non-insulindependent diabetes after 4 months of age (Leiter and Herberg 1997).While KK females are much less diabetes prone, they do become obese.Previous analyses indicate that the inheritance of obesity and diabetes phenotypes in KK mice is multigenic (Nakamura and Yamada 1963;Reddi and Camerini-Davalos 1988).In the present study, we have searched for QTLs affecting male and female adiposity and related traits in an intercross between strains KK and B6.",
"We have previously shown that diabetes traits show strong heritability in an F2 intercross between the diabetes-resistant C57BL/6 leptinob/ob and the diabetes-susceptible BTBR leptinob/ob mouse strains. We assume that the disease phenotype is brought about by a complex pattern of gene expression changes in key tissues [21,22]. However, we also recognize the complexity inherent in discriminating the gene expression changes that cause diabetes from those that occur as a consequence of the disease. For example, many genes are known to be responsive to elevated blood glucose levels [43].",
"Although the early onset of diabetes in db mice coincides with t h a t in juvenile diabetes in man, the symptoms of obesity and elevated serum insulin are more suggestive of the pattern of development observed in the maturity-onset type of diabetes. As yet, none of the lesions associated with advanced diabetes in humans such as retinopathies, cardiovascular and kidney lesions have been observed, possibly because of the early onset of the diabetes and the relatively rapid deterioration and death of these mice.",
"Key-words: Spontaneous Diabetes, Genotype : C57BL/ K5-db, Diabetes in mice, Mutation: diabetes, Obesity, Prediabetes, Insulin in plasma, Insulin in pancreas.",
"Results All mice homozygous for the trait, diabetes (db), develop an abnormal and characteristic deposition of fat beginning at 3 to 4 weeks of age, making their early identification possible. The difference in size and appearance of litter-mate 6-week old mice, one normal and one diabetic, is shown in Fig. 1. Weight increases Fig. 1. C57BL/Ks-db litter-mates a t 6 weeks.",
"Diabetologia 3, 238-248 (1967) Studies with the Mutation, Diabetes, in the Mouse* D . L . COT.EMA~ a n d I ~ T H A a I ~ P. t I u M ~ L The Jackson Laboratory, Bar Harbor, Maine Summary. The mutation, diabetes:,(db), t h a t occurred in the C57BL/Ks strain of mice is a unit autosomal recessive gene with full penetrance, and causes metabolic disturbances in homozygous mice resembling diabetes mellitus in man.",
"To screen for genes that show correlation with different phenotypic outcome in diabetic mouse models, we used the cross-sectional design and performed microarray analysis on 24-wk-old STZ-treated and db/db mice with established renal pathology.In parallel with the functional genomics characterization, each individual mouse underwent a detailed renal phenotype analysis.Mice that were treated with low doses of STZ developed diabetes and moderately severe albuminuria (twice the control).In mice with C57B6/J background, the mesangial changes were mild or absent.Mice with 129SvJ genetic background developed significant glomerular changes.However, these were not significantly different from the agematched controls (K.Sharma, K. Susztak, and E.P. Bo \u00a8ttinger, unpublished observations).The db/db mice became insulin resistant and developed diabetes at approximately 8 wk of age.Albuminuria was detected as early as 3 to 4 wk after the development of hyperglycemia.The glomerular histology was characterized by severe diffuse mesangial expansion, as previously reported (49)."
]
]
}
|
