Zero-shot named-entity recognition for cancer genetics in English text
Zero-shot NER (your own labels)Cancer and oncologyEnglishMedium · 220Mapache-2.0
What it does
This model detects 16 cancer-related entity types, including genes, cells, and tissues, in English biomedical literature and clinical notes. It reports an F1 score of 0.817 on the BioNLP 2013 Cancer Genetics test set.
Best for
- Cancer pathway curation from literature
- Driver gene analysis in oncology
- 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 | 0.817 |
| Precision | 0.811 |
| Recall | 0.823 |
| Accuracy | 0.946 |
| 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-Base-220M")
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.