OpenMed-NER-ChemicalDetect-PubMed-v2-109M

What it does

This model identifies chemical compounds and drugs in English biomedical literature, including clinical texts and research papers. It reports an F1 score of 0.949 on the BC4CHEMD benchmark, using a BERT backbone with 109 million parameters.

Best for

• Drug interaction detection in research papers
• Medication extraction from patient records
• Adverse event monitoring in literature

What it detects (1 labels)

• Chemical or drug

Quality

Chemical Entity Recognition - Identifies chemical compounds and substances in biomedical literature

Use it

pip install transformers torch

from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-ChemicalDetect-PubMed-v2-109M", 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-ChemicalDetect-PubMed-v2-109M-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-ChemicalDetect-PubMed-v2-109M", config=OpenMedConfig(backend="mlx"))
for e in result.entities:
    print(e.label, e.text)