Figure 5
From: Bayesian neural networks for detecting epistasis in genetic association studies
![Figure 5](http://media.springernature.com/full/springer-static/image/art%3A10.1186%2Fs12859-014-0368-0/MediaObjects/12859_2014_Article_368_Fig5_HTML.jpg)
Purely epistatic model with 10% heritability. Estimated power to detect both disease SNPs of Bayesian neural networks (BNN), BEAM, χ 2 test (CHI) with 2 d.f., gradient boosted trees (GBM), and MDR. The results are stratified by minor allele frequency (MAF).