Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms
Science Advances · 08.03.2024 · 10 (10)
DOI: 10.1126/sciadv.adk6669 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 08.03.2024. Verfasst von Mikael Gustavsson und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Economics, University of Gothenburg, Gothenburg, Sweden. Hauptthemen laut MEDLINE: Aquatic Organisms, Electric Power Supplies. Die Arbeit wurde bisher 83-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
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 (EC 50 /EC 10 ), the performance was further improved. We conclude that deep learning and transformers have the potential to markedly advance computational prediction of chemical toxicity.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Economics, University of Gothenburg, Gothenburg, Sweden.
- Department of Mathematical Sciences, Chalmers University of Technology/University of Gothenburg, Gothenburg, Sweden.
- Department of Biological and Environmental Sciences, University of Gothenburg, Gothenburg, Sweden.
- Division of Environmental Systems Analysis, Department of Technology Management and Economics, Chalmers University of Technology, Gothenburg, Sweden.
ORCID-Profile: Mikael Gustavsson, Styrbjörn Käll, Patrik Svedberg, Juan S Inda-Diaz, Jessica Coria, Thomas Backhaus, Erik Kristiansson
Zitieren
APA
Gustavsson, M., Käll, S., Svedberg, P., Inda-Diaz, J. S., Molander, S., Coria, J., Backhaus, T., & Kristiansson, E. (2024). Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms. Science Advances, 10(10). https://doi.org/10.1126/sciadv.adk6669
Vancouver
Gustavsson M, Käll S, Svedberg P, Inda-Diaz JS, Molander S, Coria J, et al. Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms. Science Advances. 2024;10(10). doi:10.1126/sciadv.adk6669
BibTeX
@article{Gustavsson2024,
author = {Gustavsson, Mikael and Käll, Styrbjörn and Svedberg, Patrik and Inda-Diaz, Juan S and Molander, Sverker and Coria, Jessica and Backhaus, Thomas and Kristiansson, Erik},
title = {Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms},
journal = {Science Advances},
year = {2024},
volume = {10},
number = {10},
doi = {10.1126/sciadv.adk6669}
}
EUVIMED