OpenMed-ZeroShot-NER-DNA-Large-459M

What it does

This zero-shot model detects DNA, RNA, cell lines, cell types, and proteins in English biomedical research text, with entity labels supplied by the user at inference. It reports an F1 of 0.822 on the JNLPBA benchmark, as stated by the author.

Best for

• Pathway curation from research articles
• Molecular interaction mining in literature
• Custom entity extraction from biomedical text

What it detects (5 labels)

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

• DNA
• RNA
• Cell line
• Cell tyle
• Protein

Quality

Biomedical Entity Recognition - Proteins, DNA, RNA, cell lines, and cell types

Use it

pip install gliner

from gliner import GLiNER
model = GLiNER.from_pretrained("OpenMed/OpenMed-ZeroShot-NER-DNA-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-DNA-Large-459M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)