BioBERT for K. marxianus Survival Gene NER

Fine-tuned BioBERT-Large v1.1 for Named Entity Recognition in Kluyveromyces marxianus literature.

Model Description

Identifies biological entities in yeast genomics:

  • GENE: Gene names (PMA1, HOG1, MSN2)
  • PROTEIN: Protein types (ATPase, kinase)
  • STRESS: Environmental stress (acid, heat, osmotic)
  • PATHWAY: Metabolic/signaling pathways
  • PHENOTYPE: Phenotypic traits
  • METABOLITE: Biochemical compounds

Usage

from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("Milad96/km-biobert-survival-genes")
model = AutoModelForTokenClassification.from_pretrained("Milad96/km-biobert-survival-genes")

text = "The PMA1 gene encodes H+-ATPase for acid stress tolerance"
inputs = tokenizer(text, return_tensors="pt")
outputs = model(**inputs)

PhD Research

Author: Milad Shaghaghi Ranjbar (میلاد شقاقی رنجبر)
Institution: Islamic Azad University, Kish International Campus

License

MIT License

Downloads last month
50
Safetensors
Model size
0.4B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Dataset used to train Milad96/km-biobert-survival-genes