from transformers import AutoModelForMaskedLM, AutoTokenizer
import torch

model = AutoModelForMaskedLM.from_pretrained("kojima-lab/molcrawl-protein-sequence-esm2-medium")
tokenizer = AutoTokenizer.from_pretrained("kojima-lab/molcrawl-protein-sequence-esm2-medium")

# Predict masked amino acid
# Use tokenizer.mask_token instead of hardcoded "[MASK]":
# BERT-style tokenizers vary ("[MASK]", "<mask>", etc.)
if tokenizer.mask_token is None:
    raise ValueError("This tokenizer has no mask_token; masked LM inference is not supported.")
prompt = "MKTAYIAK{MASK}RQISFVKSHFSRQ".replace("{MASK}", tokenizer.mask_token)
inputs = tokenizer(prompt, return_tensors="pt")
inputs.pop("token_type_ids", None)  # ESM2 does not use token_type_ids
mask_index = (inputs["input_ids"] == tokenizer.mask_token_id).nonzero(as_tuple=True)[1]

with torch.no_grad():
    outputs = model(**inputs)
logits = outputs.logits

predicted_token_id = logits[0, mask_index].argmax(dim=-1)
predicted_token = tokenizer.decode(predicted_token_id)
result = prompt.replace(tokenizer.mask_token, predicted_token)
print(f"Predicted: {result}")

Source Code

Model Type: esm2
Data Type: Protein
Training Date: 2026-04-24

Training pipeline, configuration files, and data preparation scripts are available in the MolCrawl GitHub repository: https://github.com/mmai-framework-lab/MolCrawl

License

This model is released under the APACHE-2.0 license.

Citation

If you use this model, please cite:

bibtex

@misc{molcrawl_protein_sequence_esm2_medium,
  title={molcrawl-protein-sequence-esm2-medium},
  author={{RIKEN}},
  year={2026},
  publisher={{Hugging Face}},
  url={{https://huggingface.co/kojima-lab/molcrawl-protein-sequence-esm2-medium}}
}