Open Access
February 2020 Effects of gene–environment and gene–gene interactions in case-control studies: A novel Bayesian semiparametric approach
Durba Bhattacharya, Sourabh Bhattacharya
Braz. J. Probab. Stat. 34(1): 71-89 (February 2020). DOI: 10.1214/18-BJPS413

Abstract

Present day bio-medical research is pointing towards the fact that cognizance of gene–environment interactions along with genetic interactions may help prevent or detain the onset of many complex diseases like cardiovascular disease, cancer, type2 diabetes, autism or asthma by adjustments to lifestyle.

In this regard, we propose a Bayesian semiparametric model to detect not only the roles of genes and their interactions, but also the possible influence of environmental variables on the genes in case-control studies. Our model also accounts for the unknown number of genetic sub-populations via finite mixtures composed of Dirichlet processes. An effective parallel computing methodology, developed by us harnesses the power of parallel processing technology to increase the efficiencies of our conditionally independent Gibbs sampling and Transformation based MCMC (TMCMC) methods.

Applications of our model and methods to simulation studies with biologically realistic genotype datasets and a real, case-control based genotype dataset on early onset of myocardial infarction (MI) have yielded quite interesting results beside providing some insights into the differential effect of gender on MI.

Citation

Download Citation

Durba Bhattacharya. Sourabh Bhattacharya. "Effects of gene–environment and gene–gene interactions in case-control studies: A novel Bayesian semiparametric approach." Braz. J. Probab. Stat. 34 (1) 71 - 89, February 2020. https://doi.org/10.1214/18-BJPS413

Information

Received: 1 August 2017; Accepted: 1 August 2018; Published: February 2020
First available in Project Euclid: 3 February 2020

zbMATH: 07200392
MathSciNet: MR4058971
Digital Object Identifier: 10.1214/18-BJPS413

Keywords: case-control study , Dirichlet process , gene–gene and gene–environment interaction , matrix normal , parallel processing , transformation based MCMC

Rights: Copyright © 2020 Brazilian Statistical Association

Vol.34 • No. 1 • February 2020
Back to Top