README.md

metadata

license: llama3
datasets:
  - mims-harvard/ProCyon-Instruct
language:
  - en
base_model:
  - mims-harvard/ProCyon-Full
tags:
  - biology
  - protein

ProCyon-Bind

ProCyon-Bind is a multimodal foundation model for protein phenotypes, which combines a large language model with protein encoders to support inputs of interleaved free text and proteins. This model is a further fine-tuned version of the ProCyon-Full model, specifically fine-tuned for understanding interactions between proteins and peptides. Fine-tuning was performed using 1097 examples of protein-peptide complexes curated from PDBBind.

For more information on the model design, training, and validation, please see the overview page.

Additional versions of the model are available as ProCyon-Split and ProCyon-Full.