GLAD: a mixed-membership model for heterogeneous tumor subtype classification

• DOI: 10.1093/bioinformatics/btu618
• Publication Date: 2014-09-30T05:52:55Z
• Authors: Hachem Saddiki; Jon McAuliffe; Patrick Flaherty
• Keywords: Python

Abstract Motivation: Genomic analyses of many solid cancers have demonstrated extensive genetic heterogeneity between as well within individual tumors. However, statistical methods for classifying tumors by subtype based on genomic biomarkers generally entail an all-or-none decision, which may be misleading clinical samples containing a mixture subtypes and/or normal cell contamination. Results: We developed mixed-membership classification model, called glad , that simultaneously learns sparse biomarker signature each distribution over sample. demonstrate the accuracy this model simulated data, in-vitro experiments, and from Cancer Genome Atlas (TCGA) project. show TCGA are likely multiple subtypes. Availability: A python module implementing our algorithm is available http://genomics.wpi.edu/glad/ Contact: [e-mail] Supplementary information: data at Bioinformatics online.