Workshop on the Analysis of Microarray Data
Sunday afternoon, July, 8Katie Pollard, University of California, Davis
This workshop will cover statistical and computational problems in the analysis of microarray data. We will review the biological basis of microarrays and pre-processing issues such as background correction and array normalization. Then we will focus on multiple testing procedures, including choices of error rate, test statistics, null distribution and error control. Multiple hypothesis testing problems arise naturally in high dimensional genomic experiments such as microarray studies. Identifying differently expressed genes in two or more populations is a typical example. Other testing problems include analyses of significantly correlated gene expression profiles and identification of genes whose expression patterns are associated with an outcome of interest, such as a clinical measurement. We will discuss currently available methods for addressing these questions with an emphasis on procedures implemented in the R multtest package.
Katie Pollard received her Ph.D. from UC Berkeley Division of Biostatistics under the supervision of Mark van der Laan. Her research at Berkeley included developing computationally intensive statistical methods for analysis of microarray data with applications in cancer biology. She has developed Bioconductor packages for clustering and multiple hypothesis testing. In November 2003, she began an NIH Postdoctoral Fellowship in the labs of David Haussler and Todd Lowe in the Center for Biomolecular Science & Engineering at UC Santa Cruz. Her projects involved comparative genomics, population genetics, and transcriptomics approaches to studying human and microbial genome sequences. In November 2005, she became an Assistant Professor at UC Davis. She is affiliated with the Davis Genome Center and Department of Statistics. (Personal Website: http://docpollard.com/katie.html)