XieResearchGroup/Physics-aware-Multiplex-GNN

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

torch-molecule is a deep learning package for molecular discovery, designed with an sklearn-style interface for property prediction, inverse design and representation learning.

SchNetPack - Deep Neural Networks for Atomistic Systems

Keras layers for end-to-end learning with rdkit and pymatgen

Implementation of Alphafold 3 from Google Deepmind in Pytorch

Implementations of different GNNs from scratch for chemists

Learning Universal Representations of Intermolecular Interactions with ATOMICA

An open-source deep learning framework for data mining of protein-protein interfaces or single-residue variants.

KERMT is a pretrained graph neural network model for molecular property prediction.