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

Background: The identification of gene-gene and gene-environment interactions in genome-wide association studies is challenging due to the unknown nature of the interactions and the overwhelmingly large number of possible combinations. Classical logistic regression models are suitable to look for pre-defined interactions while more complex models, such as tree ensemble models, with the ability to detect any interactions have previously been difficult to interpret. However, with the development of methods for model explainability, it is now possible to interpret tree ensemble models with a strong theoretical ground and efficiently. Results: We propose a tree ensemble- and SHAP-based method for identifying as well as interpreting both gene-gene and gene-environment interactions on large-scale biobank data. A set of independent cross-validation runs are used to implicitly investigate the whole genome. We apply and evaluate the method using data from the UK Biobank with obesity as the phenotype. The results are in line with previous research on obesity as we identify top SNPs previously associate with obesity. We further demonstrate how to interpret and visualize interactions. The analysis suggests that the new method finds interactions between features that logistic regression models have difficulties in detecting. Conclusions: The new method robustly detects interesting interactions, and can be applied to large-scale biobanks with high-dimensional data.