Identifies protein-related entities in English biomedical text
What it does
This model performs zero-shot named-entity recognition for protein-related entities such as proteins, complexes, and variants in English biomedical text, with labels supplied at inference. It reports an F1 score of 0.781 on the FSU-PRGE benchmark, using a GLiNER backbone with 209M parameters.
Best for
- Protein-protein interaction mining
- Pathway modeling from literature
- Custom entity extraction in research
What it detects (5 labels)
Trained on the label below; you can pass any other label names at inference time.
- Protein
- Protein complex
- Protein (enumeration)
- Protein family or group
- Protein variant
Quality
| Benchmark | FSU-PRGE · all models on this benchmark |
|---|---|
| F1 | 0.781 |
| Precision | 0.748 |
| Recall | 0.817 |
| Accuracy | 0.954 |
| Source | Reported by the authors (test_results.json in the repository) |
Biomedical Entity Recognition - Various biomedical entities
Use it
pip install gliner
from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Protein-Multi-209M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))Apple Silicon (MLX) build
pip install "openmed[mlx]"
from openmed import analyze_text
from openmed.core.config import OpenMedConfig
result = analyze_text("Patient started imatinib in March.", model_name="OpenMed/OpenMed-ZeroShot-NER-Protein-Multi-209M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
print(e.label, e.text)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.