The Gibbs-plaid biclustering model

TL;DR

This paper introduces the Gibbs-plaid biclustering model, a Bayesian approach that incorporates biological prior knowledge via a relational graph to improve gene expression data analysis.

Contribution

It develops a novel Bayesian biclustering model using a Gibbs random field and a stochastic algorithm for posterior inference, integrating biological knowledge into gene clustering.

Findings

Identifies subnetworks associated with retinal detachment.

Confirms known gene associations with the disorder.

Suggests potential novel protein subnetworks.

Abstract

We propose and develop a Bayesian plaid model for biclustering that accounts for the prior dependency between genes (and/or conditions) through a stochastic relational graph. This work is motivated by the need for improved understanding of the molecular mechanisms of human diseases for which effective drugs are lacking, and based on the extensive raw data available through gene expression profiling. We model the prior dependency information from biological knowledge gathered from gene ontologies. Our model, the Gibbs-plaid model, assumes that the relational graph is governed by a Gibbs random field. To estimate the posterior distribution of the bicluster membership labels, we develop a stochastic algorithm that is partly based on the Wang-Landau flat-histogram algorithm. We apply our method to a gene expression database created from the study of retinal detachment, with the aim of confirming known or finding novel subnetworks of proteins associated with this disorder.