Biological evaluation of biclustering algorithms using Gene Ontology and chIP-chip data

In this paper, we propose a new framework for assessing the biological significance of the outputs of any biclustering algorithm. The framework relies on the p-value computed by a Fisher's exact test on a 2x2 contingency table derived from gene ontology (GO) enrichment level and chromatin immunoprecipitation (ChIP) data enrichment level. We illustrate the framework using our published robust biclustering algorithm (RoBA), the Cheng and Church (CC) algorithm, and a well-defined set of yeast cell cycle gene expression data and chip-chip data. Our evaluation also shows that the biclusters identified by RoBA are biologically more homogeneous than the ones identified by the Cheng and Church (CC) algorithm.