Spectral Map Analysis of Microarray Data

Specific aspects of analyzing microarray data are described, which include size and shape of gene expression profiles, taking logarithms, and the biplot graphic for visualizing associations between genes and cells. Three methods of factor analysis are presented that find application to microarray data: principal component analysis, correspondence analysis, and spectral map analysis. It is shown that these three methods differ only in the way the data are preprocessed and that spectral map analysis has advantages over the other two methods. Two graphical devices that are helpful in exploring and interpreting microarray data are also described.