Zero-shot named-entity recognition for cancer genetics in English biomedical text
What it does
This model detects 16 cancer-related entity types, including genes, cells, tissues, and pathological formations, in English biomedical text. It reports an F1 score of 0.875 on the BioNLP 2013 Cancer Genetics benchmark, with user-supplied labels at inference time.
Best for
- Cancer pathway curation from literature
- Driver gene analysis in tumor biology
- Precision oncology literature mining
What it detects (16 labels)
Trained on the label below; you can pass any other label names at inference time.
- Amino acid
- Anatomical system
- Cancer
- Cell
- Cellular component
- Developing anatomical structure
- Gene or gene product
- Immaterial anatomical entity
- Multi-tissue structure
- Organ
- Organism
- Organism subdivision
- Organism substance
- Pathological formation
- Simple chemical
- Tissue
Quality
| Benchmark | BioNLP 2013 Cancer Genetics · all models on this benchmark |
|---|---|
| F1 | 0.875 |
| Precision | 0.867 |
| Recall | 0.883 |
| Accuracy | 0.963 |
| Source | Reported by the authors (test_results.json in the repository) |
Cancer Genetics - Cancer-related genetic entities
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Oncology-XLarge-770M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))All model information shown here is public and belongs to its authors: use and download it freely under each model’s license. The selection, organization, search design and presentation of this catalog are © 2026 Clinical Corpus. Please link to these pages rather than copy them.