Abstract
Genome-wide association studies usually involve several hundred thousand of single-nucleotide polymorphisms (SNPs). Conventional approaches face challenges when there are enormous number of SNPs but a relatively small number of samples and, in some cases, are not feasible. We introduce here an iterative Bayesian variable selection method that provides a unique tool for association studies with a large number of SNPs (p) but a relatively small sample size (n). We applied this method to the simulated case-control sample provided by the Genetic Analysis Workshop 15 and compared its performance with stepwise variable selection method. We demonstrated that the results of iterative Bayesian variable selection applied to when p t n are as comparable as those of stepwise variable selection implemented to when n t p. When n > p, the iterative Bayesian variable selection performs better than stepwise variable selection does.
Highlights
IntroductionA large number of single-nucleotide polymorphisms (SNPs) are engaged in a genome-wide association study
Advances in genotyping technology have made genomewide association studies feasible
We found a peak corresponding to the genomic region where loci DR and C are located for all three panels, demonstrating that iterative Bayesian variable selection (IBVS) properly identified two trait loci (DR and C)
Summary
A large number of single-nucleotide polymorphisms (SNPs) are engaged in a genome-wide association study. Many statistical approaches have been used to analyze the genome-wide association data. Conventional statistical approaches, face many challenges for analyzing the data in which a relatively small number of samples that are realistic to recruit for a research study contain hundreds of thousands of markers densely spaced over the genome. Various statistical approaches that can be utilized when p » n have been applied to reduce dimension. West et al [1] utilized singular value decomposition in the design matrices of Bayesian regression analysis with binary responses. Sha et al [2] applied stochastic search variable selection, which is a Bayesian variable selection (BVS) approach proposed by George and McCulloch [3], to identify molecular signatures of disease stage
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
