Statistical intelligence: effective analysis of high-density microarray data

Microarrays enable researchers to interrogate thousands of genes simultaneously. A crucial step in data analysis is the selection of subsets of interesting genes from the initial set of genes. In many cases, especially when comparing genes expressed in a specific condition to a reference condition, the genes of interest are those which are differentially regulated. This review focusses on the methods currently available for the selection of such genes. Fold change, unusual ratio, univariate testing with correction for multiple experiments, ANOVA and noise sampling methods are reviewed and compared.