Bayesian Models for Variable Selection That Incorporate Biological Information

• Activity Number: 637
• Type: Invited
• Date/Time: Thursday, August 4, 2011 : 10:30 AM to 12:20 PM
• Sponsor: International Society of Bayesian Analysis
• Author(s): Marina Vannucci*+ and Francesco Stingo
• Companies: Rice University and Rice University
• Keywords: Bayesian variable selection ; MRF prior ; DNA microarrays ; Pathway and gene selection

Abstract

This talk will start with a brief review of Bayesian methods for variable selection in linear models that use mixture priors. Models and inferential algorithms are quite flexible and allow to incorporate additional information, such as data substructure and/or knowledge on relationships among the variables. Specific interest will be towards high-dimensional genomic data, and in particular DNA microarrays. The vast amount of biological knowledge accumulated over the years has allowed researchers to define different families of pathways. There is now an increased interest in identifying pathways and pathway elements involved in particular biological processes. We propose Bayesian models that address this question by incorporating information on pathways and gene networks in the analysis of genomic data. Our approach makes use of Markov Random Field priors, i.e., undirected graphical models, that incorporate biological information into the models. In addition to identifying markers that would have been missed otherwise and improving prediction accuracy, the integration of existing biological knowledge into the analysis provides a better understanding of underlying molecular processes