PredHLM: quantitative and interpretable prediction of metabolic half-life in human liver microsomes
- 1Korea Research Institute of Chemical Technology
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 (T1/2) 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 R2 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.
Related
- Interpretable computational SHG microscopy enables quantitative tissue phenotyping of cardiac remodeling in nonischemic heart failure
- Extracting interpretable single-cell metabolic states with graph-guided representation learning
- An interpretable open platform for sequence-based antibody developability prediction
- Lung cancer risk prediction using interpretable ensemble models on lifestyle and clinical data
- irAEGIS: Pathway-guided interpretable prediction of immune-related adverse events
BibTeX
@misc{jang2026predhlm,
title = {{PredHLM: quantitative and interpretable prediction of metabolic half-life in human liver microsomes}},
author = {J. Jang and N.-C. Cho and J. Y. Ryu and K.-S. Oh},
howpublished = {bioRxiv},
year = {2026},
month = jul,
doi = {10.64898/2026.07.02.736062},
url = {https://www.biorxiv.org/content/10.64898/2026.07.02.736062v2},
note = {CC BY},
}
RIS
TY - UNPB
TI - PredHLM: quantitative and interpretable prediction of metabolic half-life in human liver microsomes
AU - J. Jang
AU - N.-C. Cho
AU - J. Y. Ryu
AU - K.-S. Oh
PY - 2026
DA - 2026/07/02
PB - bioRxiv
DO - 10.64898/2026.07.02.736062
UR - https://www.biorxiv.org/content/10.64898/2026.07.02.736062v2
AB - 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 (T1/2) 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 R2 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.
ER -