Bayesian Neural Networks for Genetic Association Studies of Complex Disease
This addresses the challenge of computationally demanding genetic association analysis for researchers in genetics and bioinformatics, offering an incremental improvement over existing methods.
The authors tackled the problem of identifying causal genetic variants in complex disease studies by proposing a Bayesian neural network approach, which efficiently and accurately determined involved variants with computational speed improved by several orders of magnitude using GPUs.
Discovering causal genetic variants from large genetic association studies poses many difficult challenges. Assessing which genetic markers are involved in determining trait status is a computationally demanding task, especially in the presence of gene-gene interactions. A non-parametric Bayesian approach in the form of a Bayesian neural network is proposed for use in analyzing genetic association studies. Demonstrations on synthetic and real data reveal they are able to efficiently and accurately determine which variants are involved in determining case-control status. Using graphics processing units (GPUs) the time needed to build these models is decreased by several orders of magnitude. In comparison with commonly used approaches for detecting genetic interactions, Bayesian neural networks perform very well across a broad spectrum of possible genetic relationships while having the computational efficiency needed to handle large datasets.