@article {Stein-O{\textquoteright}Brien083717, author = {Genevieve L Stein-O{\textquoteright}Brien and Jacob L Carey and Wai-shing Lee and Michael Considine and Alexander V Favorov and Emily Flam and Theresa Guo and Sijia Li and Luigi Marchionni and Thomas Sherman and Shawn Sivy and Daria A Gaykalova and Ronald D McKay and Michael F Ochs and Carlo Colantuoni and Elana J Fertig}, title = {PatternMarkers \& GWCoGAPS for novel data-driven biomarkers via whole transcriptome NMF}, elocation-id = {083717}, year = {2016}, doi = {10.1101/083717}, publisher = {Cold Spring Harbor Laboratory}, abstract = {Summary Non-negative Matrix Factorization (NMF) algorithms associate gene expression with biological processes (e.g., time-course dynamics or disease subtypes). Compared with univariate associations, the relative weights of NMF solutions can obscure biomarkers. Therefore, we developed a novel PatternMarkers statistic to extract genes for biological validation and enhanced visualization of NMF results. Finding novel and unbiased gene markers with PatternMarkers requires whole-genome data. However, NMF algorithms typically do not converge for the tens of thousands of genes in genome-wide profiling. Therefore, we also developed Genome-Wide CoGAPS Analysis in Parallel Sets (GWCoGAPS), the first robust whole genome Bayesian NMF using the sparse, MCMC algorithm, CoGAPS. This software contains analytic and visualization tools including a Shiny web application, patternMatcher, which are generalized for any NMF. Using these tools, we find granular brain-region and cell-type specific signatures with corresponding biomarkers in GTex data, illustrating GWCoGAPS and patternMarkers ascertainment of data-driven biomarkers from whole-genome data.Availability PatternMarkers \& GWCoGAPS are in the CoGAPS Bioconductor package (3.5) under the GPL license.Contact gsteinobrien{at}jhmi.edu; ccolantu{at}jhmi.edu; ejfertig{at}jhmi.edu}, URL = {https://www.biorxiv.org/content/early/2016/10/28/083717}, eprint = {https://www.biorxiv.org/content/early/2016/10/28/083717.full.pdf}, journal = {bioRxiv} }