The analysis of microarray data

Abstract

This article describes issues, techniques and algorithms for analyzing data from microarray experiments. Each such experiment generates a large amount of data, only a fraction of which comprises significant differentially expressed genes. The precise identification of these interesting genes is heavily dependent not only on the statistical data analysis techniques used but also on the accuracy of the previous oligonucleotide probe design and image analysis steps as well. Indeed, wrong decisions in these steps can multiply the number of false positives by many-fold, thus necessitating a careful choice of algorithms in all three steps. These steps are described here and placed in the context of commercial and public tools available for the analysis of microarray data.