EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Interpretable multi-species QSAR modeling for ecotoxicological hazard prediction of aquatic pollutants

Ze-Jun Wang, Rui Sun, Xiao-Wen Han, Ting-Ting Ding, Peng Huang, Jin Yan, Qiu-Hui Qian, Chang Wu, Hui-Li Wang, Kai Li, Shu-Shen Liu

Environment International · 2026-02 · 208 · 110122

DOI: 10.1016/j.envint.2026.110122 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Environment International, 2026-02. Verfasst von Ze-Jun Wang und 10 weiteren Autor:innen. Beteiligte Einrichtung: National and Local Joint Engineering Laboratory of Municipal Sewage Resource Utilization Technology, School of Environmental Science and Engineering,…. Hauptthemen laut MEDLINE: Quantitative Structure-Activity Relationship, Water Pollutants, Chemical, Ecotoxicology. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

As global industrialization accelerates, the variety of emerging aquatic pollutants is increasing, posing complex toxic effects and regional ecological risks. However, toxicity data for native aquatic species remain limited, hindering effective pollutant identification and risk management. Traditional individual species QSAR models lack cross-species generalization, sample efficiency, and mechanistic interpretability. To address these limitations under small-sample conditions, this study developed two biologically interpretable linear multi-species QSAR models based on multi-task learning: a multi-species multiple linear regression model (MS_MLR) and a multi-species stepwise regression model (MS_SR). These models predict acute toxicity across five representative native species: Carassius auratus, Leuciscus idus, Oryzias latipes, Culex quinquefasciatus, and Lemna minor. Compared to individual species models, these cross-species models exhibit an expected performance trade-off in terms of robustness and generalizability, despite a slight decrease in some evaluation metrics. Five key sharing molecular descriptors (P_VSA_LogP_5, R8s, ATS4m, Eta_betaS_A, BLTA96) related to structural features such as hydrophobicity, topology, symmetry, and baseline toxicity were identified. Additionally, six high-risk pollutants (e.g., TCDD, Chlorpyrifos) were consistently detected, with literature-supported mechanisms including AhR activation, AChE inhibition, and oxidative stress. This interpretable multi-task QSAR framework enhances structural sharing and mechanistic understanding, supporting early screening, prioritization, ecological risk assessment and green chemistry design of emerging pollutants under data-limited scenarios. Future extensions may further improve this framework by expanding species coverage, increasing data availability, and integrating advanced multi-task learning strategies.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Quantitative Structure-Activity RelationshipWater Pollutants, ChemicalEcotoxicologyAnimalsCulexOryziasAraceaeLinear ModelsCyprinidae

Stichwörter der Autor:innen

Aquatic pollutantsMulti-speciesMulti-taskPollutant prioritizationQuantitative Structure-Activity Relationship (QSAR)

Substanzen

Water Pollutants, Chemical

Autor:innen und Institutionen

  • National and Local Joint Engineering Laboratory of Municipal Sewage Resource Utilization Technology, School of Environmental Science and Engineering, Suzhou University of Science and Technology, Suzhou 215009, China; Ke…
  • National and Local Joint Engineering Laboratory of Municipal Sewage Resource Utilization Technology, School of Environmental Science and Engineering, Suzhou University of Science and Technology, Suzhou 215009, China.
  • Key Laboratory of Yangtze River Water Environment, Ministry of Education, College of Environmental Science and Engineering, Tongji University, Shanghai 200092, China; State Key Laboratory of Pollution Control and Resour…
  • Yangtze Delta Region Institute of Tsinghua University, Zhejiang, Jiaxing 314000, China. Electronic address: likai@tsinghua-zj.edu.cn.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Wang, Z. J., Sun, R., Han, X. W., Ding, T. T., Huang, P., Yan, J., Qian, Q. H., Wu, C., Wang, H. L., Li, K., & Liu, S. S. (2026). Interpretable multi-species QSAR modeling for ecotoxicological hazard prediction of aquatic pollutants. Environment International, 208, 110122. https://doi.org/10.1016/j.envint.2026.110122

Vancouver

Wang ZJ, Sun R, Han XW, Ding TT, Huang P, Yan J, et al. Interpretable multi-species QSAR modeling for ecotoxicological hazard prediction of aquatic pollutants. Environment International. 2026;208:110122. doi:10.1016/j.envint.2026.110122

BibTeX
@article{Wang2026,
  author = {Wang, Ze-Jun and Sun, Rui and Han, Xiao-Wen and Ding, Ting-Ting and Huang, Peng and Yan, Jin and Qian, Qiu-Hui and Wu, Chang and Wang, Hui-Li and Li, Kai and Liu, Shu-Shen},
  title = {Interpretable multi-species QSAR modeling for ecotoxicological hazard prediction of aquatic pollutants},
  journal = {Environment International},
  year = {2026},
  volume = {208},
  pages = {110122},
  doi = {10.1016/j.envint.2026.110122}
}
Kostenlos starten →