Reliability-aware molecular screening for drug-induced liver injury in predictive toxicology under chemical scaffold shift
Frontiers in Pharmacology · 02.11.2026 · 17
DOI: 10.3389/fphar.2026.1976307 ↗Kurz gefasst
Fachartikel in der Zeitschrift Frontiers in Pharmacology, online erschienen am 02.11.2026. Verfasst von Zhi Jin und 3 weiteren Autor:innen. Die Arbeit nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Introduction
Drug-induced liver injury (DILI) remains a challenging endpoint in predictive toxicology because molecular datasets are limited, chemical scaffolds shift across data sources, and probability scores do not necessarily indicate prediction reliability. This study aimed to develop a reliability-aware molecular screening framework for DILI prediction under chemical scaffold shift.
Methods
We developed CC-SCAC-AFP, which combines an AttentiveFP ranking backbone with coverage-constrained split conformal prediction and adaptive novelty-conditioned calibration. The framework was evaluated on the Therapeutics Data Commons DILI task using leakage-audited Murcko-scaffold partitions, five seeds for model comparison, and 20 four-way scaffold splits for reliability analysis. DILIst and DILIrank 2.0 were reserved for strict external evaluation.
Results
AttentiveFP achieved an internal mean AUROC of 0.862 (standard deviation [SD], 0.023). Across 20 reliability splits at α = 0.10, CC-SCAC-AFP achieved empirical coverage of 0.949 (SD, 0.050), compared with 0.937 (SD, 0.054) for global split conformal prediction. The corresponding mean prediction-set sizes were 1.604 and 1.521, respectively, indicating that the additional coverage was largely attributable to increased conservatism rather than improved efficiency at matched set size. On external tests, AUROC was 0.598 for both DILIst and DILIrank 2.0. Coverage was 0.891 and 0.801, respectively, below the nominal 0.90 target. The DILIrank 2.0 Brier score of 0.348 was worse than that of a constant predictor based on the observed prevalence (0.249).
Discussion
CC-SCAC-AFP provides a chemically indexed, set-valued reliability screening framework for early DILI molecular prioritization and makes the coverage–efficiency trade-off explicit. Two-label prediction sets identify compounds requiring further review. Because source-domain calibration did not preserve the nominal coverage target on the external datasets, recalibration in the target domain is necessary before applying the framework to a new chemical library.
Zitieren
APA
Jin, Z., Sun, H., Zhou, Y., & Dong, Q. (2026). Reliability-aware molecular screening for drug-induced liver injury in predictive toxicology under chemical scaffold shift. Frontiers in Pharmacology, 17. https://doi.org/10.3389/fphar.2026.1976307
Vancouver
Jin Z, Sun H, Zhou Y, Dong Q. Reliability-aware molecular screening for drug-induced liver injury in predictive toxicology under chemical scaffold shift. Frontiers in Pharmacology. 2026;17. doi:10.3389/fphar.2026.1976307
BibTeX
@article{Jin2026,
author = {Jin, Zhi and Sun, Hua and Zhou, Yiting and Dong, Qiyu},
title = {Reliability-aware molecular screening for drug-induced liver injury in predictive toxicology under chemical scaffold shift},
journal = {Frontiers in Pharmacology},
year = {2026},
volume = {17},
doi = {10.3389/fphar.2026.1976307}
}
EUVIMED