A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Annotated implementations of equivariant (graph) neural networks in Jax: EGNN, SEGNN, NequIP.

3D pharmacophore-conditioned molecular diffusion with an E(3)-equivariant EGNN backbone. Generates shape-complementary, drug-like molecules conditioned on pharmacophore point clouds and PMI/SSD shape descriptors. Inspired by ShEPhERD (Adams et al., ICLR Oral 2025). PyTorch · e3nn · RDKit.

A phase-resolved geometric deep learning framework for disease-associated protein aggregation using Siamese EGNNs, FiLM phase tokens, structural graphs, ESM2 embeddings, and kinetic supervision.

Topology-aware EGNNs with persistent homology features for HOMO–LUMO gap prediction on QM9

Text-conditioned 3D molecule generation via E(3)-equivariant latent diffusion. A latent diffusion framework that generates physically consistent 3D molecular structures from natural language using an equivariant latent space and cross-attention conditioning.