A Powerful Bayesian Meta-Analysis Method to Integrate Multiple Gene Set Enrichment Studies

• Activity Number: 38
• Type: Contributed
• Date/Time: Sunday, August 4, 2013 : 2:00 PM to 3:50 PM
• Sponsor: Section on Bayesian Statistical Science
• Author(s): Min Chen*+ and Miao Zang and Xinlei Wang and Guanghua Xiao
• Companies: The University of Texas Southwestern Medical Center at Dallas and PPD and SMU and UT Southwestern Medical Center
• Keywords: meta-analysis ; gene set enrichment ; Bayesian hierarchical model ; mcmc

Abstract

In gene set enrichment studies, identified gene sets are often found to be inconsistent among independent experiments, largely because of the noisy data of microarray experiments. Combining information from multiple studies is likely to improve the detection of truly enriched gene classes. We consider a Bayesian model that provides a coherent framework for joint modeling of both gene set information and gene expression data from multiple studies. One distinct feature of our method is that it directly models the gene expression data, instead of using summary statistics, when synthesizing studies. Besides, the model is flexible and offers an appropriate treatment of between-study heterogeneities. Simulation results show that the proposed method can improve the power of detecting enriched gene sets and it is pretty rebust to the violation of distributional assumptions. We illustrate the proposed method through an application of combining eight lung cancer datasets for gene set enrichment analysis, which demonstrates the usefulness of the method.