JayLau123/Machine-learning-for-Materials

CGCNN for inorganic solid materials

30
/ 100
Emerging

This project helps materials scientists and chemists reconstruct complex molecular structures when only their spectroscopic properties are known. It takes a 1D or 2D spectrum (like from Raman spectroscopy) and iteratively builds candidate molecular graphs, representing atoms and chemical bonds. The outcome is a proposed molecular structure that best matches the observed spectrum, making it useful for researchers analyzing unknown compounds.

No commits in the last 6 months.

Use this if you need to determine the precise atomic and bond structure of a material based solely on its spectroscopic data.

Not ideal if you already know the molecular structure and simply want to predict its properties, or if your data is not spectroscopic in nature.

materials-science spectroscopy molecular-structure chemistry materials-discovery
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 5 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

10

Forks

1

Language

Jupyter Notebook

License

MIT

Last pushed

Sep 07, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/JayLau123/Machine-learning-for-Materials"

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