BioinfoMachineLearning/DeepInteract
A geometric deep learning framework (Geometric Transformers) for predicting protein interface contacts. (ICLR 2022)
This tool helps computational biologists and drug discovery researchers predict where two proteins are likely to physically touch when they bind together. By inputting protein sequence and structural information, it identifies specific amino acid residues that form contact points at the protein-protein interface. This is crucial for understanding molecular interactions and designing new drugs or therapies.
No commits in the last 6 months. Available on PyPI.
Use this if you need to accurately identify potential contact sites between interacting proteins to understand their binding mechanisms or to inform protein engineering and drug design efforts.
Not ideal if you are looking for a tool to predict the overall 3D structure of a single protein or the complete docking orientation of two proteins, rather than just the interface contacts.
Stars
64
Forks
12
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 20, 2022
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/BioinfoMachineLearning/DeepInteract"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related models
lucidrains/alphagenome
Implementation of AlphaGenome, Deepmind's updated genomic attention model
BiomedSciAI/biomed-multi-omic
Build foundation model for RNA or DNA data
Gleghorn-Lab/Protify
Low code molecular property prediction
raimondilab/precogx
A predictor of GPCR couplings with G-proteins/B-arrs using Transformers
ziegler-ingo/cleavage_benchmark
[BIBM 2025] Code and resources for the paper "Enhancing Multi-Epitope Vaccine Effectiveness...