pruas/BENT-PubMEdBERT-NER-Variant

Named Entity Recognition (NER) model to recognize variant entities. Here variant entity is a DNA-level or protein-level mutation as defined by the Human Genome Variation Society nomenclature.

Please cite our work:

@article{NILNKER2022,
  title = {NILINKER: Attention-based approach to NIL Entity Linking},
  journal = {Journal of Biomedical Informatics},
  volume = {132},
  pages = {104137},
  year = {2022},
  issn = {1532-0464},
  doi = {https://doi.org/10.1016/j.jbi.2022.104137},
  url = {https://www.sciencedirect.com/science/article/pii/S1532046422001526},
  author = {Pedro Ruas and Francisco M. Couto},
}

PubMedBERT fine-tuned on the following datasets:

• tmVar: entity types "DNAMutation", "ProteinMutation", "SNP"
• PGxCorpus: entity type "Limited_variation"
• SNPPhenA: entity type "SNP"