---
language:
- en
pipeline_tag: token-classification
---

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](http://varnomen.hgvs.org/). 

[PubMedBERT](https://huggingface.co/microsoft/BiomedNLP-PubMedBERT-base-uncased-abstract-fulltext) fine-tuned on the following datasets:
- [tmVar](https://www.ncbi.nlm.nih.gov/research/bionlp/Data/): entity types "DNAMutation", "ProteinMutation", "SNP"
- [PGxCorpus](https://www.nature.com/articles/s41597-019-0342-9): entity type "Limited_variation"
- [SNPPhenA](https://figshare.com/s/f19191317056d6835b38): entity type "SNP"