Statistical analysis of microarray data

Microarrays promise dynamic snapshots of cell activity, but microarray results are unfortunately not straightforward to interpret. This article aims to distill the most useful practical results from the vast body of literature available on microarray data analysis. Topics covered include: experimental design issues, normalization, quality control, exploratory analysis, and tests for differential expression. Special attention is paid to the peculiarities of low-level analysis of Affymetrix chips, and the multiple testing problem in determining differential expression. The aim of this article is to provide useful answers to the most common practical issues in microarray data analysis. The main topics are pre-processing (normalization), and detecting differential expression. Subsidiary topics include experimental design, and exploratory analysis. Further discussion is found at the author's web page (http://discover.nci.nih.gov --> Notes on Microarray Data Analysis).