|
Activity Number:
|
497
|
|
Type:
|
Topic Contributed
|
|
Date/Time:
|
Thursday, August 2, 2007 : 8:30 AM to 10:20 AM
|
|
Sponsor:
|
Section on Bayesian Statistical Science
|
| Abstract - #309114 |
|
Title:
|
Bayesian Pathways Studies Using Microarray Data
|
|
Author(s):
|
Lynn Kuo*+ and Wangang Xie and Dong-Guk Shin and Fang Yu and Yifang Zhao and Ming-Hui Chen
|
|
Companies:
|
University of Connecticut and University of Connecticut and University of Connecticut and University of Connecticut and University of Connecticut and University of Connecticut
|
|
Address:
|
215 Glenbrook Rd, Storrs, CT, 06269-4120,
|
|
Keywords:
|
model selection ; Bayes factor ; MCMC ; microarray data ; Bayesian network ; molecular pathways
|
|
Abstract:
|
Identifying molecular pathways that are most activated in a defined stage of cell differentiation or when cells are exposed to environmental stimuli provides more insights on the functional information about genes. We propose novel methods to evaluate a set of possible pathways obtained from KEGG or BioCarta data bases on their activations from the microarray and proteomic data. These high-throughput data are further supplemented by prior information that is constructed from literature search on the gene-to-gene promotion or inhibition knowledge. The Bayes factor approach is used to evaluate the evidence for each activated pathway. Essentially, we develop Markov chain Monte Carlo methods and Bayesian model selection methods to identify a set of pathways that are most activated by observing the high-throughput data.
|
