aimat-lab/gcnn_keras

Graph convolutions in Keras with TensorFlow, PyTorch or Jax.

46
/ 100
Emerging

This is a framework for materials scientists and chemists to build and apply graph neural networks for molecules and crystalline materials. It takes in structured data representing chemical graphs (nodes as atoms, edges as bonds) with their properties. It outputs predictions or insights about material characteristics, enabling researchers to leverage advanced machine learning without deep low-level coding.

118 stars. No commits in the last 6 months.

Use this if you are a researcher in chemistry or materials science needing to apply graph neural networks to predict properties of molecules or crystals and prefer using Keras.

Not ideal if your primary domain is not molecules or materials, or if you need to work with highly dynamic graph structures that don't fit into batched or disjoint tensor representations.

materials-science computational-chemistry drug-discovery molecular-modeling crystal-structure-prediction
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 20 / 25

How are scores calculated?

Stars

118

Forks

30

Language

Jupyter Notebook

License

MIT

Last pushed

Jan 08, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/aimat-lab/gcnn_keras"

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