A new method for exploring gene-gene and gene-environment interactions in GWAS with tree ensemble methods and SHAP values.

Pål Vegard JohnsenSigne Riemer-SørensenAndrew Thomas DeWanMegan E CahillMette Langaas

Published in: BMC bioinformatics (2021)

The new method identifies interaction candidates otherwise not detected with parametric regression models. However, further research is needed to evaluate the uncertainties of these candidates. The method can be applied to large-scale biobanks with high-dimensional data.

Keyphrases

genome wide
copy number
genome wide identification
dna methylation
gene expression
transcription factor
machine learning
genome wide association study