hERG toxicity prediction in early drug discovery using extreme gradient boosting and isometric stratified ensemble mapping.

Blockade of the human Ether-à-go-go Related Gene (hERG) potassium channel by small molecules can prolong the QT interval, leading to fatal cardiotoxicity. Numerous drugs have been withdrawn from the market due to cardiac side effects, underscoring the need for early identification of hERG toxicity. Despite several classification machine learning (ML) models having been developed to this end, robustness, class imbalance, and interpretability are still challenges. Using the largest public database of hERG inhibition, this work integrates eXtreme Gradient Boosting (XGBoost) with Isometric Stratified Ensemble (ISE) mapping (XGB + ISE map) to enhance hERG prediction. An XGBoost consensus model was developed using balanced training sets and diverse variable subsets, resulting in robust models less affected by class imbalance. The model demonstrated competitive predictive performance, achieving a balance between sensitivity (SE = 0.83) and specificity (SP = 0.90) through exhaustive validation. ISE mapping estimated the model applicability domain and improved prediction confidence evaluation and compound selection by stratifying data. Refined variable selection procedures enhanced model interpretability. Variable importance analysis highlights key molecular determinants (peoe_VSA8, ESOL, SdssC, MaxssO, nRNR2, MATS1i, nRNHR, nRNH2) associated with hERG inhibition. The XGB + ISE map strategy provides an effective approach to identifying promising molecules in drug discovery campaigns with reduced hERG inhibition risk.