Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms
Journal article, 2024
Environmental hazard assessments are reliant on toxicity data that cover multiple organism groups. Generating experimental toxicity data is, however, resource-intensive and time-consuming. Computational methods are fast and cost-efficient alternatives, but the low accuracy and narrow applicability domains have made their adaptation slow. Here, we present a AI-based model for predicting chemical toxicity. The model uses transformers to capture toxicity-specific features directly from the chemical structures and deep neural networks to predict effect concentrations. The model showed high predictive performance for all tested organism groups—algae, aquatic invertebrates and fish—and has, in comparison to commonly used QSAR methods, a larger applicability domain and a considerably lower error. When the model was trained on data with multiple effect concentrations (EC50/EC10), the performance was further improved. We conclude that deep learning and transformers have the potential to markedly advance computational prediction of chemical toxicity.
Author
Mikael Gustavsson
University of Gothenburg
Styrbjörn Käll
Chalmers, Mathematical Sciences, Applied Mathematics and Statistics
University of Gothenburg
Patrik Svedberg
University of Gothenburg
Juan Salvador Inda Diaz
Chalmers, Mathematical Sciences, Applied Mathematics and Statistics
University of Gothenburg
Sverker Molander
Chalmers, Technology Management and Economics, Environmental Systems Analysis
Jessica Coria
University of Gothenburg
Thomas Backhaus
University of Gothenburg
Erik Kristiansson
University of Gothenburg
Chalmers, Mathematical Sciences, Applied Mathematics and Statistics
Science advances
2375-2548 (eISSN)
Vol. 10 10 eadk6669Driving Forces
Sustainable development
Subject Categories
Pharmacology and Toxicology
Environmental Sciences
DOI
10.1126/sciadv.adk6669
PubMed
38446886