Authors
Yining Zhang, Sijie Xing, Jiawei Li, Yue Zheng, Tongfei Shi
Published in
Journal of hazardous materials. Volume 518. Pages 144056. Nov 05, 2026. Epub Nov 05, 2026.
Abstract
We investigated mouse intraperitoneal acute-toxicity prediction using source-traceable public records, residual diagnostics, and evaluation stratified by structural similarity. Rule-based curation and compound aggregation of TOXRIC and PubChem LD50 records produced a 34,959-compound development pool and a reserved 1068-compound PubChem-only holdout. The studied 20× OOF discrepancy criterion excluded 448 compounds and retained 34,511 for ECFP4-count/RDKit-2D modeling with multi-seed XGBoost averaging. Database checks reproduced all 448 TOXRIC source values and modeling targets, establishing record traceability without identifying label error. Random and scaffold-based nested evaluations did not show improved R2, RMSE, or MAE from exclusion on fixed outer-test populations. The final ensemble achieved a holdout R2 of 0.7440, RMSE of 0.4703, and MAE of 0.2445 on the -log10(LD50,mol/kg) scale. Structural decomposition showed R2 = 0.9794 for 641 compounds with fingerprint-identical development-set neighbors and R2 = 0.4290 for the remaining 427 fingerprint-nonidentical compounds. Upstream-record overlap was identified within the fingerprint-identical group. The combined in-domain R2 of 0.9136 included all 641 fingerprint-identical compounds and 92 similar but nonidentical compounds. These findings distinguish source-record traceability from model agreement and characterize prediction accuracy in relation to structural and provenance support. The released compound-level data, predictions, source checks, and code support reproducible endpoint-specific modeling and examination of its prediction limits.
PMID:
43000007
Bibliographic data and abstract were imported from PubMed on 09 Nov 2026.
Read full publication at:
Please sign in
to see all details.
Advertisement
Stats
- Recommendations n/a n/a positive of 0 vote(s)
- Views 11
- Comments 0