mims-harvard/ProCyon
ProCyon: A multimodal foundation model for protein phenotypes
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.
Stars
56
Forks
13
Language
Python
License
MIT
Category
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.
Higher-rated alternatives
microsoft/mattergen
Official implementation of MatterGen -- a generative model for inorganic materials design across...
MolecularAI/REINVENT4
AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker...
MorganCThomas/MolScore
An automated scoring function to facilitate and standardize the evaluation of goal-directed...
AspirinCode/papers-for-molecular-design-using-DL
List of Molecular and Material design using Generative AI and Deep Learning
pregHosh/MolCraftDiffusion
A generative AI framework for 3D molecular generation and data-driven molecular design in...