Self-organizing maps in mining gene expression data

Modern DNA microarray technology provides means of measuring gene expressio n patterns of the whole genome of simple organisms at once. Exploratory ana lysis of these large-scale expression datasets is becoming vital to extract ing functional information from the measurements. We demonstrate how self-o rganizing maps (SOM) can be applied to exploratory analysis of gene express ion data from a yeast DNA microarray database in order to very rapidly find gene families with similar expression patterns. SOM not only enabled quick ly selecting the gene families identified in previous work, but it facilita ted identifying additional genes with similar expression patterns. Identify ing new families of genes also appears to be possible as demonstrated by ad ditional clusters of genes discovered from the data. Moreover, further insi ght into the primary pattern variations that discriminate between the famil ies became explicit. (C) 2001 Elsevier Science Inc. All rights reserved.