OpenMed-NER-DNADetect-PubMed-335M

What it does

This model identifies DNA, RNA, protein, cell line, and cell type entities in English clinical and research documents. It reports an F1 score of 0.806 on the JNLPBA benchmark, with 334 million parameters and a maximum sequence length of 512 tokens.

Best for

• Entity extraction from medical records
• Mining scientific literature for entities
• Identifying proteins and cells in research papers

What it detects (5 labels)

• DNA
• RNA
• Cell line
• Cell type
• Protein

Quality

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

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-DNADetect-PubMed-335M", aggregation_strategy="simple")
print(ner("Patient prescribed 10 mg aspirin for hypertension."))

pip install --upgrade "openmed[onnx-runtime]"

from openmed import OnnxModel
model = OnnxModel.from_pretrained("OpenMed/OpenMed-NER-DNADetect-PubMed-335M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())

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-NER-DNADetect-PubMed-335M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)