ABSTRACT

A cluster operator takes a set of data points and partitions the points into clusters (subsets). Clustering has become a popular data-analysis technique in genomic studies using gene-expression microarrays. Time-series clustering groups together genes whose expression levels exhibit similar behavior through time. Similarity indicates possible co-regulation. Another way to use expression data is to take expression profiles over various tissue samples, and then cluster these samples based on the expression levels for each sample. This approach offers the potential to discriminate pathologies based on their differential patterns of gene expression.