Clustering gene expression data using self-organizing maps and k-means clustering

We present a method of combining a self-organizing map (SOM) and k-means clustering for analyzing and categorizing gene expression data. Some studies have addressed about visualizing cluster structures in an easily understandable manner using a U-matrix or Sammon´s mapping. However, it is difficult to find obvious clustering boundaries in the SOM results. We show that the method is effective for categorizing the published data of yeast gene expression.