BioinfoMachineLearning/DeepInteract
A geometric deep learning framework (Geometric Transformers) for predicting protein interface contacts. (ICLR 2022)
Implements geometric transformer blocks that jointly encode both sequence and 3D structural context via graph neural networks, leveraging HH-suite sequence alignments and PSAIA structural features. Supports multiple protein complex datasets (DIPS, DB5, CASP-CAPRI) with PyTorch Lightning training pipelines and provides Docker containerization with GPU acceleration for reproducible inference on new protein pairs.
No commits in the last 6 months. Available on PyPI.
Stars
64
Forks
12
Language
Python
License
GPL-3.0
Category
Last pushed
Jun 20, 2022
Monthly downloads
18
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.
Higher-rated alternatives
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...