Sparse multitask regression for identifying common mechanism of response to therapeutic targets
Authors:
Open Access
- 1 June 2010
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 26 (12) , i97-i105
Abstract
Motivation: Molecular association of phenotypic responses is an important step in hypothesis generation and for initiating design of new experiments. Current practices for associating gene expression data with multidimensional phenotypic data are typically (i) performed one-to-one, i.e. each gene is examined independently with a phenotypic index and (ii) tested with one stress condition at a time, i.e. different perturbations are analyzed separately. As a result, the complex coordination among the genes responsible for a phenotypic profile is potentially lost. More importantly, univariate analysis can potentially hide new insights into common mechanism of response. Results: In this article, we propose a sparse, multitask regression model together with co-clustering analysis to explore the intrinsic grouping in associating the gene expression with phenotypic signatures. The global structure of association is captured by learning an intrinsic template that is shared among experimental conditions, with local perturbations introduced to integrate effects of therapeutic agents. We demonstrate the performance of our approach on both synthetic and experimental data. Synthetic data reveal that the multi-task regression has a superior reduction in the regression error when compared with traditional L1-and L2-regularized regression. On the other hand, experiments with cell cycle inhibitors over a panel of 14 breast cancer cell lines demonstrate the relevance of the computed molecular predictors with the cell cycle machinery, as well as the identification of hidden variables that are not captured by the baseline regression analysis. Accordingly, the system has identified CLCA2 as a hidden transcript and as a common mechanism of response for two therapeutic agents of CI-1040 and Iressa, which are currently in clinical use. Contact:b_parvin@lbl.govKeywords
This publication has 30 references indexed in Scilit:
- Molecular Predictors of 3D Morphogenesis by Breast Cancer Cell Lines in 3D CulturePLOS Computational Biology, 2010
- hCLCA2 Is a p53-Inducible Inhibitor of Breast Cancer Cell ProliferationCancer Research, 2009
- Response projected clustering for direct association with physiological and clinical response dataBMC Bioinformatics, 2008
- Abrogated Response to Cellular Stress Identifies DCIS Associated with Subsequent Tumor Events and Defines Basal-like Breast TumorsCancer Cell, 2007
- Geometric approach to segmentation and protein localization in cell culture assaysJournal of Microscopy, 2007
- A collection of breast cancer cell lines for the study of functionally distinct cancer subtypesCancer Cell, 2006
- A Novel Group of Genes Regulates Susceptibility to Antineoplastic Drugs in Highly Tumorigenic Breast Cancer CellsMolecular Pharmacology, 2005
- BioSig: an imaging bioinformatics system for phenotypic analysisIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 2003
- Structure and Transcriptional Regulation of the Human Cystatin A GeneJournal of Biological Chemistry, 1998
- Direct Clustering of a Data MatrixJournal of the American Statistical Association, 1972