Systematic analysis of hepatotoxicity: combining literature mining and AI language models
We demonstrated that automated text mining is able to successfully assess the toxicity of compounds. A text mining approach seems to be superior to word embeddings. However, the application of a large language model with prompt engineering showed the best performance.
Authors
- Twan van den Beucken (ORCID: https://orcid.org/0000-0002-2233-7558)
- Johannes Schuchhardt (ORCID: https://orcid.org/0009-0008-8896-4328)
- Ralf Herwig (ORCID: https://orcid.org/0000-0002-9335-1760)
- Chris Bauer
- L. Dang (ORCID: https://orcid.org/0009-0006-0098-1234)
Institutions
- Maastricht University (NL)
- MicroDiscovery (Germany) (DE)
- Max Planck Institute for Molecular Genetics (DE)
Publication Details
- Journal
- Frontiers in Artificial Intelligence
- Published
- 2025-07-21
- DOI
- https://doi.org/10.3389/frai.2025.1561292
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Bundesministerium für Bildung und Forschung