Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Sparse multitask regression for identifying common mechanism of response to therapeutic targets

Journal Article · · Bioinformatics
 [1];  [2];  [2]
  1. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Life Sciences Division; DOE/OSTI
  2. Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). Life Sciences Division
+ Show Author Affiliations
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 multitask 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.
Research Organization:
Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States)
Sponsoring Organization:
USDOE Office of Science (SC), Biological and Environmental Research (BER). Biological Systems Science Division
Grant/Contract Number:
AC02-05CH11231
OSTI ID:
1625267
Journal Information:
Bioinformatics, Journal Name: Bioinformatics Journal Issue: 12 Vol. 26; ISSN 1367-4803
Publisher:
Oxford University PressCopyright Statement
Country of Publication:
United States
Language:
English

References (29)

A collection of breast cancer cell lines for the study of functionally distinct cancer subtypes journal December 2006
Abrogated Response to Cellular Stress Identifies DCIS Associated with Subsequent Tumor Events and Defines Basal-like Breast Tumors journal November 2007
CLCA2 tumour suppressor gene in 1p31 is epigenetically regulated in breast cancer journal February 2004
PAN1/NALP2/PYPAF2, an Inducible Inflammatory Mediator That Regulates NF-κB and Caspase-1 Activation in Macrophages journal December 2004
Direct Clustering of a Data Matrix journal March 1972
Discovering statistically significant biclusters in gene expression data journal July 2002
Unsupervised feature selection via two-way ordering in gene expression analysis journal July 2003
Spectral Biclustering of Microarray Data: Coclustering Genes and Conditions journal April 2003
Geometric approach to segmentation and protein localization in cell culture assays journal January 2007
Integrated Genomic and Proteomic Analyses of a Systematically Perturbed Metabolic Network journal May 2001
hCLCA2 Is a p53-Inducible Inhibitor of Breast Cancer Cell Proliferation journal August 2009
Response projected clustering for direct association with physiological and clinical response data journal January 2008
Multitask Learning journal January 1997
Reverse engineering gene networks: Integrating genetic perturbations with dynamical modeling journal May 2003
Gene-based approach to human gene-phenotype correlations journal October 1997
Structure and Transcriptional Regulation of the Human Cystatin A Gene journal July 1998
PAN1/NALP2/PYPAF2, an Inducible Inflammatory Mediator That Regulates NF-κB and Caspase-1 Activation in Macrophages journal December 2004
Discovering statistically significant biclusters in gene expression data journal July 2002
An Interior-Point Method for Large-Scale -Regularized Least Squares journal December 2007
Multidimensional Profiling of Cell Surface Proteins and Nuclear Markers journal January 2010
Compressed sensing journal April 2006
Causal Protein-Signaling Networks Derived from Multiparameter Single-Cell Data journal April 2005
Probabilistic Joint Feature Selection for Multi-task Learning conference April 2007
Atomic Decomposition by Basis Pursuit journal January 2001
Learning a meta-level prior for feature relevance from multiple related tasks conference June 2007
Co-clustering documents and words using bipartite spectral graph partitioning conference January 2001
hCLCA2 Is a p53-Inducible Inhibitor of Breast Cancer Cell Proliferation journal August 2009
Molecular Predictors of 3D Morphogenesis by Breast Cancer Cell Lines in 3D Culture journal February 2010
Direct Clustering of a Data Matrix journal March 1972

Cited By (8)

A Survey on Multi-Task Learning journal January 2021
Using multitask classification methods to investigate the kinase-specific phosphorylation sites journal June 2012
Pattern Classification of Large-Scale Functional Brain Networks: Identification of Informative Neuroimaging Markers for Epilepsy journal May 2012
An ensemble method approach to investigate kinase-specific phosphorylation sites journal May 2014
Integrative analysis of multiple diverse omics datasets by sparse group multitask regression journal October 2014
Multi-task diagnosis for autism spectrum disorders using multi-modality features: A multi-center study: Multi-Modality Multi-Center Diagnosis for ASD journal March 2017
Deep multi-task learning for individuals origin–destination matrices estimation from census data journal November 2019
An overview of multi-task learning journal September 2017

Similar Records

Learning perturbation-inducible cell states from observability analysis of transcriptome dynamics
Journal Article · Tue May 30 20:00:00 EDT 2023 · Nature Communications · OSTI ID:1975887

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY
59 BASIC BIOLOGICAL SCIENCES
97 MATHEMATICS AND COMPUTING
Biochemistry & Molecular Biology
Biotechnology & Applied Microbiology
Computer Science
Mathematical & Computational Biology
Mathematics