PredHLM: quantitative and interpretable prediction of metabolic half-life in human liver microsomes
Year: 2026
Type: preprint
Abstract: Human liver microsome (HLM)-based metabolic stability assays are fundamental in early drug discovery, shaping pharmacokinetic profiles and oral bioavailability. However, these experimental assays are labor-intensive and time-consuming, limiting their application in large-scale virtual screening. Computational models can prioritize compounds at scale, yet most are classification-based, leaving quantitative and interpretable prediction of HLM half-life limited. In this study, we developed a quantitative machine learning model for the direct prediction of HLM half-life (T 1/2 ) by integrating 11,790 compounds combining in-house and curated public data. Among various combinations of molecular features and learning algorithms, the XGBoost model with RDKit 2D descriptors achieved the best predictive performance, with an RMSE of 0.507 and an R 2 of 0.431 on an independent test set. Shapley Additive Explanations (SHAP) analysis identified lipophilicity and known metabolic soft-spot features as the primary contributors to the predictions. These results suggest that this quantitative approach provides a practical framework for defining metabolic stability margins, thereby supporting rapid Go/No-go decisions in preclinical drug discovery. The source code, data, and trained model are available at https://github.com/joshua-416/PredHLM . Scientific Contribution This study integrates in-house and curated public data for 11,790 compounds to enable quantitative HLM half-life prediction beyond classification-based metabolic stability assessment. Comparative evaluation of molecular representations and learning algorithms identifies XGBoost with RDKit 2D descriptors as the best-performing configuration among those tested. SHAP analysis links predictions to lipophilicity and known metabolic soft-spot features, while an applicability domain based on the sum of distance-weighted contributions (SDC) supports compound-specific assessment of prediction reliability and compound prioritization. Graphical Abstract
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7167685020