Integrating curation into scientific publishing to train AI models
Trained models are available at https://huggingface.co/EMBO. The SourceData-NLP dataset and code are available at https://github.com/source-data/soda-data, https://github.com/source-data/soda-model, and https://github.com/source-data/soda_image_segmentation.
Authors
- Cassie S. Mitchell
- Thomas Lemberger (ORCID: https://orcid.org/0000-0002-2499-4025)
- Hannah Sonntag (ORCID: https://orcid.org/0000-0001-5461-3265)
- J. Abreu-Vicente (ORCID: https://orcid.org/0000-0002-0211-6416)
- Thomas Eidens
Institutions
- European Molecular Biology Organization (DE)
- Georgia Institute of Technology (US)
- Emory University (US)
Publication Details
- Journal
- Bioinformatics
- Published
- 2025-12-27
- DOI
- https://doi.org/10.1093/bioinformatics/btaf685
- Primary Topic
- Biomedical Text Mining and Ontologies
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Georgia Institute of Technology