A Tight Clustering Method for Microarray Analysis

• Activity Number: 61
• Type: Contributed
• Date/Time: Sunday, August 3, 2003 : 4:00 PM to 5:50 PM
• Sponsor: Biopharmaceutical Section
• Author(s): George C. Tseng*+ and Wing Wong
• Companies: Harvard University and Harvard University
• Keywords: cluster analysis ; microarray ; tight clustering

Abstract

We propose a method for clustering that produces tight and stable clusters without forcing all points into clusters. The methodology is initially motivated from the cluster analysis of microarray experiments. Many existing clustering methods have been applied in microarray data to search for gene clusters with similar expression pattern. However, none have provided a way to deal with the nature of array data: many genes are sporadic and do not belong to any of the significant biological functions (clusters) that we are detecting. Most current algorithms aim to cluster all genes into clusters. However, for many biological studies we are interested mainly in the most informative, tight, and stable clusters at the size of, say, 20-60 genes to follow up. Tight clustering is developed to meet this need. The tightest and most stable clusters are identified in a sequential manner through an analysis of the tendency of genes to be grouped together under repeated resampling. We validated this method in simulated data and applied it to analyze expression profiles of Drosophila life cycle. The result of this new method is shown to better suit the biological needs in microarray analysis.