SINGROUP/dscribe

DScribe is a python package for creating machine learning descriptors for atomistic systems.

52
/ 100
Established

DScribe helps materials scientists and computational chemists translate atomic structures into numerical 'fingerprints.' You input atomic configurations (like a molecule or crystal), and it outputs a fixed-size numerical vector that captures the structural essence. These fingerprints are then ready for tasks like training machine learning models to predict material properties, visualizing structural relationships, or analyzing similarity between different atomic systems.

463 stars. No commits in the last 6 months.

Use this if you need to convert atomic structures into standardized numerical representations for machine learning or other computational analysis in materials science.

Not ideal if your primary goal is quantum mechanical simulations or molecular dynamics without the need for machine learning-ready structural descriptors.

materials-science computational-chemistry materials-informatics molecular-modeling structural-analysis
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 24 / 25

How are scores calculated?

Stars

463

Forks

96

Language

C++

License

Apache-2.0

Last pushed

Sep 27, 2025

Commits (30d)

0

Get this data via API

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

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