Non-negative matrix factorization of gene expression profiles: a plug-in for BRB-ArrayTools.

Abstract

Non-negative matrix factorization (NMF) is an increasingly used algorithm for the analysis of complex high-dimensional data. BRB-ArrayTools is a widely used software system for the analysis of gene expression data with almost 9000 registered users in over 65 countries. We have developed a NMF analysis plug-in in BRB-ArrayTools for unsupervised sample clustering of microarray gene expression data. Our analysis tool also incorporates an algorithm for Semi-NMF which can handle both positive and negative elements for log-ratio data. Output includes a heat map of sample clusters and differentially expressed genes with extensive biological annotation. For comparison, output also includes the results of K-means clustering. The NMF analysis plug-in is freely available in BRB-ArrayTools for non-commercial users. BRB-ArrayTools can be downloaded at http://linus.nci.nih.gov/BRB-ArrayTools.html. The algorithms used for NMF and Semi-NMF are available at ftp://linus.nci.nih.gov/pub/NMF.