Unified Multitask Model for Aquatic Toxicity Prediction across Organism Groups and Effect End Points: A Comparison of Molecular Representations
Journal of Chemical Information and Modeling · 2026
DOI: 10.1021/acs.jcim.6c02487 ↗Kurz gefasst
Vergleichsstudie in der Zeitschrift Journal of Chemical Information and Modeling, 2026. Verfasst von Xiushan Wu und 4 weiteren Autor:innen. Beteiligte Einrichtung: Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Sy…. Hauptthemen laut MEDLINE: Aquatic Organisms, Water Pollutants, Chemical. Die Arbeit nennt 56 Literaturangaben. Gefördert von: Agricultural Science and Technology Major Project.
Abstract (Originalsprache)
Computational prediction of aquatic toxicity provides a rapid and cost-efficient alternative to resource-intensive in vivo ecotoxicological testing. However, most existing models adopt a fragmented modeling strategy, developing separate models for each organism group and toxicity end point. Such task-specific models restrict knowledge transfer across related biological contexts and fail to account for the biological ordering between multiple effect concentrations (EC50/EC10). Here, we propose a unified multitask framework to simultaneously predict effect concentrations for three aquatic organism groups (fish, crustaceans, algae) and two end points (EC50/EC10) within a single model. This framework integrates a molecular encoder with a Multigate Mixture-of-Experts (MMoE) network, a soft end point-ordering term that encourages the biological relation EC50 ≥ EC10, and a heteroscedastic regression output that provides per-prediction uncertainty estimates. We evaluated a multirepresentation fusion encoder combining physicochemical descriptors, molecular fingerprints, and a 2D molecular graph neural network (GNN), together with 3D-pretrained Uni-Mol and TRIDENT baselines. Under a common global scaffold/acyclic-cluster 5-fold pooled out-of-fold (OOF) protocol, the multirepresentation fusion model demonstrated robust predictive performance across all six organism–end point tasks, with lower prediction errors than TRIDENT across all six tasks and Uni-Mol in four tasks. Attention-based interpretation further highlighted chemically meaningful atoms and substructures that were consistent with plausible toxicity-relevant structural motifs. Together, these findings demonstrate that integrating multitask learning, biologically informed end point constraints, and complementary molecular representations provides a promising foundation for broadly applicable and uncertainty-aware models of aquatic toxicity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Shanghai Engineering Research Center of Molecular Therapeutics and New Drug Development, Shanghai Frontiers Science Center of Molecule Intelligent Syntheses, School of Chemistry and Molecular Engineering, East China Nor…
- Anhui Provincial Key Laboratory of Advanced Catalysis and Energy Materials, Anhui Ultra High Molecular Weight Polyethylene Fiber Engineering Research Center, School of Chemistry and Chemical Engineering, Anqing Normal U…
- New York University-East China Normal University Center for Computational Chemistry, New York University Shanghai, Shanghai, 200062, China.
ORCID-Profile: Jinrong Yang, Xiao He
Förderung
- Agricultural Science and Technology Major Project
Zitieren
APA
Wu, X., Hu, B., Chen, D., Yang, J., & He, X. (2026). Unified Multitask Model for Aquatic Toxicity Prediction across Organism Groups and Effect End Points: A Comparison of Molecular Representations. Journal of Chemical Information and Modeling. https://doi.org/10.1021/acs.jcim.6c02487
Vancouver
Wu X, Hu B, Chen D, Yang J, He X. Unified Multitask Model for Aquatic Toxicity Prediction across Organism Groups and Effect End Points: A Comparison of Molecular Representations. Journal of Chemical Information and Modeling. 2026. doi:10.1021/acs.jcim.6c02487
BibTeX
@article{Wu2026,
author = {Wu, Xiushan and Hu, Baochuan and Chen, Dongliang and Yang, Jinrong and He, Xiao},
title = {Unified Multitask Model for Aquatic Toxicity Prediction across Organism Groups and Effect End Points: A Comparison of Molecular Representations},
journal = {Journal of Chemical Information and Modeling},
year = {2026},
doi = {10.1021/acs.jcim.6c02487}
}
EUVIMED