Integrative QSAR modelling of multi-species pesticide baseline (narcosis) toxicity
Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology · 2026-10 · 308 · 110603
DOI: 10.1016/j.cbpc.2026.110603 ↗Kurz gefasst
Fachartikel in der Zeitschrift Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology, 2026-10. Verfasst von Suyu Mei. Beteiligte Einrichtung: College of Artificial Intelligence, Shenyang Normal University, Shenyang, 110034, China. Electronic address: meisygle@outlook.com. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Pesticides. Die Arbeit nennt 57 Literaturangaben.
Abstract (Originalsprache)
Baseline toxicity modelling aims at estimating the lowest dose of pesticides leading to non-polar narcosis. Existing logKow linear regression models often exhibit less resistance to outliers and noise. In this work, from the viewpoint of quantitative structure-activity relationship (QSAR), we propose an integrative extreme gradient boosting model (XGBoost) model to combine multimodal features, comprising Mordred descriptors, PubChem fingerprints and species one-hot encodings, for in silico modelling of pesticide baseline (narcosis) toxicity. The integrative XGBoost model facilitates transferring knowledge across species at different trophic levels, including four fishes (Danio rerio, Bluegill, Fathead minnow, and Rainbow trout), invertebrate crustacean Daphnia magna, alga Pseudokirchneriella subcapitata, and bacterium Vibrio fischeri. K-fold stratified cross validation (k = 10) shows that the integrative XGBoost model achieves competitive performance, with overall 0.96 R2, and per species R2 ranging from 0.71 (Danio rerio) to 0.96 (Bluegill), significantly outperforming logKow linear regression, non-linear support vector regression (SVR), and individual XGBoost models. SHapley Additive exPlanations (SHAP) show that SLogP contributes most to baseline toxicity, confirming the significance of hydrophobicity SLogP/logKow in determining baseline toxicity. Lastly, the case studies on Daphnia magna and Pimephales promela show that the derived logTR values exhibit agreements with the known MoAs of control pesticides, indicating the potentials of the integrative XGBoost model to predict baseline and excess toxicities, from which to further infer polar-narcosis, reactive and specifically-acting MoAs.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- College of Artificial Intelligence, Shenyang Normal University, Shenyang, 110034, China. Electronic address: meisygle@outlook.com.
Zitieren
APA
Mei, S. (2026). Integrative QSAR modelling of multi-species pesticide baseline (narcosis) toxicity. Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology, 308, 110603. https://doi.org/10.1016/j.cbpc.2026.110603
Vancouver
Mei S. Integrative QSAR modelling of multi-species pesticide baseline (narcosis) toxicity. Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology. 2026;308:110603. doi:10.1016/j.cbpc.2026.110603
BibTeX
@article{Mei2026,
author = {Mei, Suyu},
title = {Integrative QSAR modelling of multi-species pesticide baseline (narcosis) toxicity},
journal = {Comparative Biochemistry and Physiology Part C: Toxicology & Pharmacology},
year = {2026},
volume = {308},
pages = {110603},
doi = {10.1016/j.cbpc.2026.110603}
}
EUVIMED