Analysis of variance for gene expression microarray data

Spotted cDNA microarrays are emerging as a powerful and cost-effective tool for large-scale analysis of gene expression, Microarrays can be used to me asure the relative quantities of specific mRNAs in two or more tissue sampl es for thousands of genes simultaneously. While the power of this technolog y has been recognized, many open questions remain about appropriate analysi s of microarray data. One question is how to make valid estimates of the re lative expression for genes that are not biased by ancillary sources of var iation. Recognizing that there is inherent "noise'' in microarray data, how does one estimate the error variation associated with an estimated change in expression, i.e., how does one construct the error bars? We demonstrate that ANOVA methods can be used to normalize microarray data and provide est imates of changes in gene expression that are corrected for potential confo unding effects. This approach establishes a framework for the general analy sis and interpretation of microarray data.