We have made the code, weights, and training dataset freely available for the community.

#ComputationalChemistry #MolecularDynamics #MachineLearning #StructuralBiology #DFT #AI #NNP #MLIP

We showcase its scalability and accuracy across various benchmarks (>23 μs!), modeling solvation free energies, protein structural features, and free-energy profiles of enzymatically catalyzed reactions.

Trained on the new BMS25 dataset, featuring over 1.5 million DFT calculations, it can perform these simulations on a single GPU. We demonstrate efficient scaling for systems comprising tens of thousands of protein atoms and hundreds of thousands of water molecules.