OpenMed-ZeroShot-NER-Genomic-Large-459M

What it does

This zero-shot model detects genes, proteins, and cells in English biomedical literature, with users supplying entity labels at inference time. It reports an F1 of 0.978 on the Gelius cell-line benchmark, using a GLiNER backbone with 459M parameters.

Best for

• Genetic association study text mining
• Variant curation from literature
• Genomics informatics entity extraction

What it detects (1 labels)

Trained on the label below; you can pass any other label names at inference time.

• Cell line

Quality

Gene Entity Recognition - Gene-related entities

Use it

pip install gliner

from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-Genomic-Large-459M")
print(model.predict_entities("Patient with type 2 diabetes and hypertension.", ["disease"]))

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-Genomic-Large-459M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)