jonathanking/sidechainnet

An all-atom protein structure dataset for machine learning.

58
/ 100
Established

Extends ProteinNet with complete all-atom structure data (sidechain coordinates and torsion angles) rather than backbone-only annotations. Provides PyTorch DataLoaders for efficient batching, angle-to-coordinate conversion via `fastbuild()`, and OpenMM integration for computing protein energy and atomic forces. Supports structure visualization in PDB, 3Dmol, and glTF formats, plus gradient-friendly hydrogen addition for molecular dynamics workflows.

360 stars and 561 monthly downloads. No commits in the last 6 months. Available on PyPI.

Stale 6m
Maintenance 0 / 25
Adoption 16 / 25
Maturity 25 / 25
Community 17 / 25

How are scores calculated?

Stars

360

Forks

40

Language

Python

License

BSD-3-Clause

Last pushed

Mar 16, 2024

Monthly downloads

561

Commits (30d)

0

Dependencies

10

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jonathanking/sidechainnet"

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