Detecting Differentially Expressed Genes in Microarray Data by Split-and-Recombine

• Activity Number: 426
• Type: Contributed
• Date/Time: Tuesday, August 3, 2010 : 2:00 PM to 3:50 PM
• Sponsor: International Chinese Statistical Association
• Author(s): Dongseok Choi*+ and Zhixin Kang and George Tiao
• Companies: Oregon Health & Science University and The University of North Carolina at Pembroke and The University of Chicago
• Keywords: microarray ; gene expression ; p-value ; outlier ; cluster

Abstract

Microarrays have been widely used in biomedical researches and have been in the center stage of statistical methodology development during the past decades. One of the common goals in microarray data analysis has been testing differentially expressed genes between different experimental conditions. Several modified t-tests have been widely used commonly with the false discovery rate. However, p-value adjustment is becoming less straightforward as experimental designs become more complex. In this talk, we will present a novel application of Split-and-Recombine (SAR) to identify differentially expressed genes while simultaneously form clusters among them. SAR was originally developed for outlier detection assuming a mixture of normal distributions and has been also applied for cluster analysis.