Genomic data analysis using a two stage expectation propagation algorithm for analysis of sparse Bayesian high-dimensional instrumental variables regression

Simultaneous analysis of gene expression data and genetic variants is highly interest, especially when the number expressions are both greater than sample size. Association causal genes effective SNPs makes use sparse modeling such sets, important. The high-dimensional instrumental variables models one useful association models, which simultaneous relation with complex traits. From a Bayesian viewpoint, sparsity can be favored using sparsity-enforcing priors as spike-and-slab priors. A two-stage modification expectation propagation (EP) algorithm proposed examined for approximate inference in This method an adoption classical least squares method, to used Bayes context. simulation study performed examine performance methods. applied mouse obesity data.