EUVIMEDEUVIMED entdecken
Open Access

Transformers enable accurate prediction of acute and chronic chemical toxicity in aquatic organisms

Mikael Gustavsson iD, Styrbjörn Käll iD, Patrik Svedberg iD, Juan S Inda-Diaz iD, Sverker Molander, Jessica Coria iD, Thomas Backhaus iD, Erik Kristiansson iD

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.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

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)

Aquatic OrganismsElectric Power SuppliesAnimalsNeural Networks, Computer

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}
}
Kostenlos starten →