Stars
Implementation of the So3krates model in pytorch
Proteina is a new large-scale flow-based protein backbone generator that utilizes hierarchical fold class labels for conditioning and relies on a tailored scalable transformer architecture.
Official implementation of All Atom Diffusion Transformers (ICML 2025)
GEOM: Energy-annotated molecular conformations
Minimalistic 4D-parallelism distributed training framework for education purpose
Run OpenMM with forces provided by any Python program
NeuralPLexer: State-specific protein-ligand complex structure prediction with a multi-scale deep generative model
A repository for implementing graph network models based on atomic structures.
Official implementation of HEGNN, a novel high-degree equivariant graph neural network proposed in the NeurIPS 2024 paper 'Are High-Degree Representations Really Unnecessary in Equivariant Graph Ne…
SO3krates and Universal Pairwise Force Field for Molecular Simulation
Source code of "Improving Equivariant Graph Neural Networks on Large Geometric Graphs via Virtual Nodes Learning"
Official code repository of paper Equivariance via Minimal Frame Averaging for More Symmetries and Efficiency.
An interface to various automatic differentiation backends in Julia.
Force-field-enhanced Neural Networks optimized library
A library to generate LaTeX expression from Python code.
Classical Monte Carlo simulations for lattice spin systems
A collection of QM data for training potential functions
Build neural networks for machine learning force fields with JAX
E3x is a JAX library for constructing efficient E(3)-equivariant deep learning architectures built on top of Flax.
[TMLR 2023] Training and simulating MD with ML force fields
GradDFT is a JAX-based library enabling the differentiable design and experimentation of exchange-correlation functionals using machine learning techniques.
Hardware accelerated, batchable and differentiable optimizers in JAX.
🏆 A ranked list of awesome atomistic machine learning projects ⚛️🧬💎.
Reference implementation of "Ewald-based Long-Range Message Passing for Molecular Graphs" (ICML 2023)
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more