EUVIMEDEUVIMED entdecken
Übersichtsarbeit

AmesFormer: State-of-the-Art Mutagenicity Prediction with Graph Transformers

Luke A Thompson, Josiah G Evans, Slade T Matthews iD

Chemical Research in Toxicology · 21.07.2025 · 38 (7) · 1167-1182

DOI: 10.1021/acs.chemrestox.4c00466 ↗

Kurz gefasst

Übersichtsarbeit in der Zeitschrift Chemical Research in Toxicology, online erschienen am 26.06.2025. Verfasst von Luke A Thompson und 2 weiteren Autor:innen. Beteiligte Einrichtung: Sydney Pharmacy School, The University of Sydney, Sydney 2006, Australia. Hauptthemen laut MEDLINE: Neural Networks, Computer, Mutagens. Die Arbeit wurde bisher 5-mal zitiert (Crossref) und nennt 95 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The Ames mutagenicity test is a gold standard assay for the safety assessment of new chemicals. However, many in silico models rely on challenging-to-interpret ensemble strategies and molecular fingerprint data, which neglects gestalt molecular structure. To improve upon these models, we propose AmesFormer, a graph transformer neural network that shows state-of-the-art performance when paired with our new Ames data set. We briefly review the current state of Ames modeling with a focus on graph neural networks. We then benchmark AmesFormer on a standardized test data set against 22 other Ames models, achieving state of the art (SOTA) performance. We uniquely report the calibration performance of our model and attempt to improve it using temperature scaling. We support our findings with reference to other models from the literature and with developments in machine learning (ML) and graph theory. Overall, we present a high-performance, accessible, and open-source computational model for Ames mutagenicity, with significant potential for regulatory and drug development applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Neural Networks, ComputerMutagensMutagenicity TestsMachine LearningHumans

Substanzen

Mutagens

Autor:innen und Institutionen

  • Sydney Pharmacy School, The University of Sydney, Sydney 2006, Australia.

ORCID-Profile: Slade T Matthews

Zitieren

APA

Thompson, L. A., Evans, J. G., & Matthews, S. T. (2025). AmesFormer: State-of-the-Art Mutagenicity Prediction with Graph Transformers. Chemical Research in Toxicology, 38(7), 1167-1182. https://doi.org/10.1021/acs.chemrestox.4c00466

Vancouver

Thompson LA, Evans JG, Matthews ST. AmesFormer: State-of-the-Art Mutagenicity Prediction with Graph Transformers. Chemical Research in Toxicology. 2025;38(7):1167-1182. doi:10.1021/acs.chemrestox.4c00466

BibTeX
@article{Thompson2025,
  author = {Thompson, Luke A and Evans, Josiah G and Matthews, Slade T},
  title = {AmesFormer: State-of-the-Art Mutagenicity Prediction with Graph Transformers},
  journal = {Chemical Research in Toxicology},
  year = {2025},
  volume = {38},
  number = {7},
  pages = {1167--1182},
  doi = {10.1021/acs.chemrestox.4c00466}
}
Kostenlos starten →