Added JOSS paper

1 files changed, 36 insertions, 0 deletions

diff --git a/doc/joss/2016/paper.bib b/doc/joss/2016/paper.bib
new file mode 100644
index 00000000..73a88227
--- /dev/null
+++ b/doc/joss/2016/paper.bib
@@ -0,0 +1,36 @@
+@article{WGCNA:2008,
+  author       = {Langfelder, P. and Horvath, S.},
+  title        = {{WGCNA: an R package for weighted correlation network analysis}},
+  journal      = {BMC Bioinformatics},
+  year         = {2008},
+  volume       = {9},
+  pages        = {559},
+  doi          = {10.1186/1471-2105-9-559},
+  url          = {http://www.ncbi.nlm.nih.gov/pubmed/19114008},
+  abstract     = {BACKGROUND: Correlation networks are increasingly being used in bioinformatics applications. For example, weighted gene co-expression network analysis is a systems biology method for describing the correlation patterns among genes across microarray samples. Weighted correlation network analysis (WGCNA) can be used for finding clusters (modules) of highly correlated genes, for summarizing such clusters using the module eigengene or an intramodular hub gene, for relating modules to one another and to external sample traits (using eigengene network methodology), and for calculating module membership measures. Correlation networks facilitate network based gene screening methods that can be used to identify candidate biomarkers or therapeutic targets. These methods have been successfully applied in various biological contexts, e.g. cancer, mouse genetics, yeast genetics, and analysis of brain imaging data. While parts of the correlation network methodology have been described in separate publications, there is a need to provide a user-friendly, comprehensive, and consistent software implementation and an accompanying tutorial. RESULTS: The WGCNA R software package is a comprehensive collection of R functions for performing various aspects of weighted correlation network analysis. The package includes functions for network construction, module detection, gene selection, calculations of topological properties, data simulation, visualization, and interfacing with external software. Along with the R package we also present R software tutorials. While the methods development was motivated by gene expression data, the underlying data mining approach can be applied to a variety of different settings. CONCLUSION: The WGCNA package provides R functions for weighted correlation network analysis, e.g. co-expression network analysis of gene expression data. The R package along with its source code and additional material are freely available at http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA.}
+}
+
+@article{Wang:2016,
+  author       = {Wang, X. and Pandey, A. K. and Mulligan, M. K. and Williams, E. G. and Mozhui, K. and Li, Z. and Jovaisaite, V. and Quarles, L. D. and Xiao, Z. and Huang, J. and Capra, J. A. and Chen, Z. and Taylor, W. L. and Bastarache, L. and Niu, X. and Pollard, K. S. and Ciobanu, D. C. and Reznik, A. O. and Tishkov, A. V. and Zhulin, I. B. and Peng, J. and Nelson, S. F. and Denny, J. C. and Auwerx, J. and Lu, L. and Williams, R. W.},
+  title        = {{Joint mouse-human phenome-wide association to test gene function and disease risk}},
+  journal      = {Nat Commun},
+  year         = {2016},
+  volume       = {7},
+  pages        = {10464},
+  doi          = {10.1038/ncomms10464},
+  url          = {http://www.ncbi.nlm.nih.gov/pubmed/26833085},
+  abstract     = {Phenome-wide association is a novel reverse genetic strategy to analyze genome-to-phenome relations in human clinical cohorts. Here we test this approach using a large murine population segregating for approximately 5 million sequence variants, and we compare our results to those extracted from a matched analysis of gene variants in a large human cohort. For the mouse cohort, we amassed a deep and broad open-access phenome consisting of approximately 4,500 metabolic, physiological, pharmacological and behavioural traits, and more than 90 independent expression quantitative trait locus (QTL), transcriptome, proteome, metagenome and metabolome data sets--by far the largest coherent phenome for any experimental cohort (www.genenetwork.org). We tested downstream effects of subsets of variants and discovered several novel associations, including a missense mutation in fumarate hydratase that controls variation in the mitochondrial unfolded protein response in both mouse and Caenorhabditis elegans, and missense mutations in Col6a5 that underlies variation in bone mineral density in both mouse and human.}
+}
+
+@article{Lippert:2011,
+  author       = {Lippert, C. and Listgarten, J. and Liu, Y. and Kadie, C. M. and Davidson, R. I. and Heckerman, D.},
+  title        = {{FaST linear mixed models for genome-wide association studies}},
+  journal      = {Nat Methods},
+  year         = {2011},
+  volume       = {8},
+  number       = {10},
+  pages        = {833-835},
+  doi          = {10.1038/nmeth.1681},
+  url          = {http://www.ncbi.nlm.nih.gov/pubmed/21892150},
+  abstract     = {We describe factored spectrally transformed linear mixed models (FaST-LMM), an algorithm for genome-wide association studies (GWAS) that scales linearly with cohort size in both run time and memory use. On Wellcome Trust data for 15,000 individuals, FaST-LMM ran an order of magnitude faster than current efficient algorithms. Our algorithm can analyze data for 120,000 individuals in just a few hours, whereas current algorithms fail on data for even 20,000 individuals (http://mscompbio.codeplex.com/).}
+}