EUVIMEDEUVIMED entdecken
Übersichtsarbeit

Deep learning advances high-throughput toxicity screening of chemicals at multi-biological levels

Xinyue Wu, Ya Zhu, Jie Hou, Jianying Zhang, Jiang Xu, Daohui Lin

Journal of Environmental Sciences · 2026

DOI: 10.1016/j.jes.2025.09.045 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Journal of Environmental Sciences, 2026. Verfasst von Xinyue Wu und 5 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Provincial Key Laboratory of Organic Pollution Process and Control, College of Environmental and Resource Sciences, Zhejiang University, Han…. Hauptthemen laut MEDLINE: Deep Learning, Toxicity Tests, High-Throughput Screening Assays. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 149 Literaturangaben. Gefördert von: Key Research and Development Program of Zhejiang Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Deep learning (DL) has emerged as a powerful tool for modeling unstructured data, thereby improving prediction accuracy and expanding the application of machine learning (ML) in toxicity assessment. However, selecting suitable DL architectures and training methods for toxicity prediction remains challenging due to the lack of systematic comparisons regarding data types and modeling tasks across biological levels, which hinders the development of optimal models. To address these challenges, we review the current DL applications for predicting toxic events at four stages within the adverse outcome pathway framework: toxicophore-induced effects at the chemical exposure stage, activation of toxic pathways at the macro-molecular level (molecular initiating events), toxicogenomic responses at the cellular level (key events), and observable toxic effects (adverse outcomes) at the tissue/organ/individual levels. We compare the technical aspects of various DL methods for toxicity prediction and discuss how interpretability analyses can reveal the underlying molecular mechanisms and modes of toxic action. We also summarize current solutions to the challenges of increased data requirements and reduced interpretability of DL compared to traditional ML, and propose the development of a general environmental toxicological model. We hope that the interdisciplinary insights provided in this review can accelerate the development and application of new DL models in high-throughput toxicity screening, thereby advancing risk management strategies based on modes of toxic action.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Deep LearningToxicity TestsHigh-Throughput Screening AssaysPredictive Learning Models

Stichwörter der Autor:innen

Adverse outcome pathwayDeep learningHigh-throughput screeningToxicity prediction

Autor:innen und Institutionen

  • Zhejiang Provincial Key Laboratory of Organic Pollution Process and Control, College of Environmental and Resource Sciences, Zhejiang University, Hangzhou 310058, China; State Key Laboratory of Soil Pollution Control an…
  • School of Medicine, Taizhou University, Taizhou, Zhejiang 318000, China.

Förderung

  • Key Research and Development Program of Zhejiang Province
  • National Natural Science Foundation of China

Zitieren

APA

Wu, X., Zhu, Y., Hou, J., Zhang, J., Xu, J., & Lin, D. (2026). Deep learning advances high-throughput toxicity screening of chemicals at multi-biological levels. Journal of Environmental Sciences. https://doi.org/10.1016/j.jes.2025.09.045

Vancouver

Wu X, Zhu Y, Hou J, Zhang J, Xu J, Lin D. Deep learning advances high-throughput toxicity screening of chemicals at multi-biological levels. Journal of Environmental Sciences. 2026. doi:10.1016/j.jes.2025.09.045

BibTeX
@article{Wu2026,
  author = {Wu, Xinyue and Zhu, Ya and Hou, Jie and Zhang, Jianying and Xu, Jiang and Lin, Daohui},
  title = {Deep learning advances high-throughput toxicity screening of chemicals at multi-biological levels},
  journal = {Journal of Environmental Sciences},
  year = {2026},
  doi = {10.1016/j.jes.2025.09.045}
}
Kostenlos starten →