Open Access
September 2015 The Gibbs-plaid biclustering model
Thierry Chekouo, Alejandro Murua, Wolfgang Raffelsberger
Ann. Appl. Stat. 9(3): 1643-1670 (September 2015). DOI: 10.1214/15-AOAS854


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.


Download Citation

Thierry Chekouo. Alejandro Murua. Wolfgang Raffelsberger. "The Gibbs-plaid biclustering model." Ann. Appl. Stat. 9 (3) 1643 - 1670, September 2015.


Received: 1 January 2014; Revised: 1 March 2015; Published: September 2015
First available in Project Euclid: 2 November 2015

zbMATH: 06526002
MathSciNet: MR3418739
Digital Object Identifier: 10.1214/15-AOAS854

Keywords: Autologistic model , clustering , gene expression , gene ontology , plaid model , relational graph , retinal detachment , Wang–Landau algorithm

Rights: Copyright © 2015 Institute of Mathematical Statistics

Vol.9 • No. 3 • September 2015
Back to Top