mims-harvard/ProCyon

ProCyon: A multimodal foundation model for protein phenotypes

48
/ 100
Emerging

ProCyon helps researchers understand protein behavior and characteristics by predicting their phenotypes across various biological scales. You input protein sequences or structures, and it outputs detailed descriptions of their functions, binding properties, or other observable traits. This tool is designed for biologists, biochemists, and drug discovery scientists who need to analyze and interpret protein data.

Use this if you need to predict a wide range of protein characteristics, identify drug-binding domains, or understand protein-peptide interactions from sequence or structural data.

Not ideal if you lack access to a GPU with CUDA capabilities or are not comfortable with command-line installation and managing model dependencies.

protein-phenotype-prediction drug-discovery bioinformatics protein-binding molecular-biology
No Package No Dependents
Maintenance 6 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 18 / 25

How are scores calculated?

Stars

56

Forks

13

Language

Python

License

MIT

Last pushed

Nov 25, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/generative-ai/mims-harvard/ProCyon"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.