⚠ Archived — the upstream repository is no longer receiving updates.
megnet
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals.
README
Deprecation This repository has been deprecated in favor of a new PyTorch + Deep Graph Library implementation in the matgl repository. It will no longer be updated and is retained purely as a reference implementation in the original Tensorflow. Table of Contents Introduction MEGNet Framework Installation Usage Datasets Implementation details Computing requirements Known limitations Contributors References Introduction This repository represents the efforts of the Materials Virtual Lab in…
- Repository
- github.com/materialsvirtuallab/megnet
Source attribution
- Awesome Python Chemistry — github.com/materialsvirtuallab/megnet
- GitHub — github.com/materialsvirtuallab/megnet
Related resources
Deep learning library for Chemistry based on Tensorflow
E(3)-equivariant neural network interatomic potentials achieving DFT accuracy with up to 1000× less training data than invariant models, foundational architecture behind MACE and Allegro (Harvard, MIT, Nature Communications 2022)
Cross-platform library for differentiable programming of quantum computers with automatic differentiation, enabling hybrid quantum-classical machine learning for quantum chemistry, quantum physics, and NISQ algorithm research (Xanadu, 3k+ stars)
Open-source framework for building physics-ML models at scale (renamed from Modulus, 2025)
Provides functionality for producing geometric representations of protein and RNA structures, and biological interaction networks.
OpenChem is a deep learning toolkit for Computational Chemistry with PyTorch backend.