BioinfoMachineLearning/DeepInteract

A geometric deep learning framework (Geometric Transformers) for predicting protein interface contacts. (ICLR 2022)

46
/ 100
Emerging

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.

Stale 6m No Dependents
Maintenance 0 / 25
Adoption 11 / 25
Maturity 18 / 25
Community 17 / 25

How are scores calculated?

Stars

64

Forks

12

Language

Python

License

GPL-3.0

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.