Applying gradient tree boosting to QTL mapping with Shapley additive explanations

Mapping quantitative trait loci (QTLs) is one of the major goals of quantitative genetics; however, identifying the interactions between QTLs (i.e., epistasis) remains challenging. Recently developed machine learning methods, such as deep learning and gradient boosting, are transforming the real world. These methods could advance QTL mapping methodologies because of their high capability for capturing complex relationships among features. One problem with applying such complex models to QTL mapping is the evaluation of feature importance. In this study, XGBoost, a popular gradient tree boosting algorithm, was applied for QTL mapping in biparental populations with Shapley additive explanations (SHAPs). SHAP is a local (i.e., in‍stance-wise) importance index with the desired properties as feature importance indices. The SHAP-assisted XGBoost (SHAP-XGB) was compared with conventional methods, including composite interval mapping (CIM), multiple interval mapping (MIM), inclusive CIM (ICIM), and BayesC, using simulations and rice heading date data. SHAP-XGB performed comparably to CIM, MIM, ICIM, and BayesC in mapping main QTL effects and was superior to MIM, ICIM, and BayesC in mapping QTL interaction effects. As SHAP can evaluate local importance, interactions between markers can be visualized by plotting SHAP interaction values for each instance (plant/line). These results illustrated the strength of SHAP-XGB in detecting and interpreting epistatic QTLs and suggest the possibility that SHAP-XGB complements conventional methods.