The Stochastic QT–Clust Algorithm: Evaluation of Stability and Variance on Time–Course Microarray Data∗

Clustering time–course microarray data is an important tool to find co–regulated genes and groups of genes with similar temporal or spacial expression patterns. Depending on the distance measure and cluster algorithm used different kinds of clusters will be found. In a simulation study on a publicly available dataset from yeast the quality–based cluster algorithm QT–Clust is compared to a stochastic variant of the original algorithm using different distance measures. For that purpose the stability and sum of within cluster distances are evaluated. Finally stochastic QT–Clust is compared to the well–known k–means algorithm.