microsoft/Graphormer

Graphormer is a general-purpose deep learning backbone for molecular modeling.

49
/ 100
Emerging

Applies transformer architecture to graph-structured molecular data, using spectral features and spatial encodings to capture atomic interactions and 3D geometry. Integrates with PyG, DGL, OGB, and OCP datasets while supporting fairseq as its training backbone, with pre-trained models available on quantum property prediction (PCQM4M) and catalysis tasks (Open Catalyst Project).

2,427 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

2,427

Forks

376

Language

Python

License

MIT

Last pushed

Jun 07, 2024

Commits (30d)

0

Get this data via API

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

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