Equivariant Graph Neural Network for Atomic Multipoles

Description

Repository for the Model used in the publication 'Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks'. The model was trained on the following publicly available Dataset.

How to Use

Check out the jupyter notebook for exemplary usecases. Versions used:

• Tensorflow: 2.6.2
• Numpy: 1.21.2
• Graph-Nets: 1.1.0