Finds cell line names in English biomedical and clinical text
Extract biomedical entitiesGenes, proteins and cellsEnglishMedium · 396Mapache-2.0
What it does
This model detects cell line names in English clinical texts, research papers, and healthcare documents. It reports an F1 score of 0.981 on the Gelius benchmark, with 0.987 precision and 0.975 recall, and is based on ModernBERT-large with 396M parameters.
Best for
- Cell line mentions in medical records
- Entity extraction from research literature
- Biomedical knowledge graph construction
What it detects (1 labels)
- Cell line
Quality
| Benchmark | Gellus (cell lines) · all models on this benchmark |
|---|---|
| F1 | 0.981 |
| Precision | 0.987 |
| Recall | 0.975 |
| Accuracy | 0.998 |
| Source | Reported by the authors (test_results.json in the repository) |
Gene Entity Recognition - Gene-related entities
Use it
pip install transformers torch
from transformers import pipeline
ner = pipeline("token-classification", model="OpenMed/OpenMed-NER-GenomicDetect-ModernMed-395M", aggregation_strategy="simple")
print(ner("Patient prescribed 10 mg aspirin for hypertension."))Android, browser, CPU (ONNX) build
pip install --upgrade "openmed[onnx-runtime]"
from openmed import OnnxModel
model = OnnxModel.from_pretrained("OpenMed/OpenMed-NER-GenomicDetect-ModernMed-395M-v1-onnx-android")
for entity in model("The patient started imatinib after the consultation."):
print(entity.to_dict())All model information shown here is public and belongs to its authors: use and download it freely under each model’s license. The selection, organization, search design and presentation of this catalog are © 2026 Clinical Corpus. Please link to these pages rather than copy them.