X-DILiver: an ensemble learning framework for predicting drug-induced liver injury
- 1Department of Biomedical Engineering, Chung-Ang University
- 2Department of Medicinal and Pharmaceutical Chemistry, University of Science and Technology
- 3Data Convergence Drug Research Center, Korea Research Institute of Chemical Technology
Abstract
Drug-induced liver injury (DILI) is a primary cause of drug attrition, associated with over 1000 medications and accounting for 32% of marketed drugs withdrawn due to toxicity. This has created an urgent demand for high-accuracy computational methods predicting DILI risk early in the drug development pipeline. We developed X-DILiver, a predictive framework built on the largest DILI-annotated dataset to date. We used data augmentation to improve model robustness and address class imbalance. A library of 312 machine learning models was created using various algorithms and molecular features, and then an optimized ensemble strategy was applied. The final model is an ensemble of two extreme gradient boosting models and seven recurrent neural networks. It achieved an accuracy (ACC) of 0.64 and a Matthew’s correlation coefficient (MCC) of 0.33 on the Tanimoto-filtered external test dataset, and an ACC of 0.64 and an MCC of 0.38 on the scaffold-unique external test dataset, outperforming all other publicly available DILI prediction models. While this performance improvement is significant, this accuracy reflects ongoing challenges in DILI prediction. X-DILiver represents a valuable advancement that can assist in DILI risk assessment during drug discovery, serving as a reliable tool to predict DILI potential, thereby accelerating and improving drug discovery safety. To facilitate broad access, X-DILiver is accessible via http://xdiliver.lile.bio .
Related
- An ensemble machine learning approach for predicting colorectal polyps using novel inflammatory markers.
- Multi-task deep learning framework for brain tumor classification and segmentation using ensemble feature extraction
- An integrated evolutionary optimization and machine learning framework for predicting pharmacokinetics of nanocarrier-encapsulated drugs
- Deep learning and metaheuristic optimization for predicting drug release from nanocarrier systems: a data-driven framework for formulation development
- A hybrid deep feature extraction and ensemble learning framework for robust multi-class ECG image classification
BibTeX
@article{lee2026xdiliver,
title = {{X-DILiver: an ensemble learning framework for predicting drug-induced liver injury}},
author = {Jingyu Lee and Myeong-Sang Yu and Yunhyeok Lee and Hyun Jung Nam and Kwang-Seok Oh and Jidon Jang and Hyang-Mi Lee and Dokyun Na},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-59299-9},
url = {https://doi.org/10.1038/s41598-026-59299-9},
note = {CC BY},
}
RIS
TY - JOUR
TI - X-DILiver: an ensemble learning framework for predicting drug-induced liver injury
AU - Jingyu Lee
AU - Myeong-Sang Yu
AU - Yunhyeok Lee
AU - Hyun Jung Nam
AU - Kwang-Seok Oh
AU - Jidon Jang
AU - Hyang-Mi Lee
AU - Dokyun Na
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-59299-9
UR - https://doi.org/10.1038/s41598-026-59299-9
AB - Drug-induced liver injury (DILI) is a primary cause of drug attrition, associated with over 1000 medications and accounting for 32% of marketed drugs withdrawn due to toxicity. This has created an urgent demand for high-accuracy computational methods predicting DILI risk early in the drug development pipeline. We developed X-DILiver, a predictive framework built on the largest DILI-annotated dataset to date. We used data augmentation to improve model robustness and address class imbalance. A library of 312 machine learning models was created using various algorithms and molecular features, and then an optimized ensemble strategy was applied. The final model is an ensemble of two extreme gradient boosting models and seven recurrent neural networks. It achieved an accuracy (ACC) of 0.64 and a Matthew’s correlation coefficient (MCC) of 0.33 on the Tanimoto-filtered external test dataset, and an ACC of 0.64 and an MCC of 0.38 on the scaffold-unique external test dataset, outperforming all other publicly available DILI prediction models. While this performance improvement is significant, this accuracy reflects ongoing challenges in DILI prediction. X-DILiver represents a valuable advancement that can assist in DILI risk assessment during drug discovery, serving as a reliable tool to predict DILI potential, thereby accelerating and improving drug discovery safety. To facilitate broad access, X-DILiver is accessible via http://xdiliver.lile.bio .
SN - 2045-2322
ER -