OpenMed-NER-ProteinDetect-ModernMed-395M

What it does

This model detects five types of protein-related entities, including proteins, protein complexes, and protein variants, in English biomedical and clinical text. It reports an F1 score of 0.904 on the FSU-PRGE benchmark, with a maximum sequence length of 8192 tokens.

Best for

• Extracting protein names from research papers
• Identifying protein complexes in clinical notes
• Annotating protein variants in biomedical literature

What it detects (5 labels)

• Protein
• Protein complex
• Protein (enumeration)
• Protein family or group
• Protein variant

Quality

Biomedical Entity Recognition - Various biomedical entities

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-ProteinDetect-ModernMed-395M", 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-ProteinDetect-ModernMed-395M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
    print(entity.to_dict())