Bayesian model search and multilevel inference for SNP association studies

TL;DR

This paper introduces MISA, a Bayesian method for SNP association studies that improves detection power by accounting for multiple comparisons, correlations, and missing data, demonstrated through simulations and real data analysis.

Contribution

The paper presents MISA, a novel Bayesian multilevel inference method that searches over genetic markers and parametrizations, providing intrinsic multiplicity correction and enhanced detection power.

Findings

MISA outperforms standard methods in simulated data.

MISA identifies novel variants in NCOCS data validated externally.

Results are sensitive to prior choices and missing data imputation methods.

Abstract

Technological advances in genotyping have given rise to hypothesis-based association studies of increasing scope. As a result, the scientific hypotheses addressed by these studies have become more complex and more difficult to address using existing analytic methodologies. Obstacles to analysis include inference in the face of multiple comparisons, complications arising from correlations among the SNPs (single nucleotide polymorphisms), choice of their genetic parametrization and missing data. In this paper we present an efficient Bayesian model search strategy that searches over the space of genetic markers and their genetic parametrization. The resulting method for Multilevel Inference of SNP Associations, MISA, allows computation of multilevel posterior probabilities and Bayes factors at the global, gene and SNP level, with the prior distribution on SNP inclusion in the model providing an intrinsic multiplicity correction. We use simulated data sets to characterize MISA's statistical power, and show that MISA has higher power to detect association than standard procedures. Using data from the North Carolina Ovarian Cancer Study (NCOCS), MISA identifies variants that were not identified by standard methods and have been externally ``validated'' in independent studies. We examine sensitivity of the NCOCS results to prior choice and method for imputing missing data. MISA is available in an R package on CRAN.