| DNA microarrays are widely used research tools that allow the expression level of thousands of genes to be monitored simultaneously. A common interest is to determine whether a gene's expression level differs between two conditions. Differential expression anlaysis provides a means for addressing such interests, but several aspects of microarray data complicate the application of standard two-sample methods. The Limma software package utilizes a Bayesian linear model approach to differential expression analysis. In Chapter 1, the primary statistical challenges associated with differential expression analysis are reviewed, and the Bayesian linear model approach to these challenges is outlined. Chapter 2 presents a detailed application of the Limma procedure (and other methods) to microarray data generated from experiments performed with Arabidopsis thaliana. In particular, the heat shock transcription factor and protein network of Arabidopsis is profiled under a wide range of abiotic and biotic stress treatments in multiple cell types. |
