TorchMD-NET: Equivariant Transformers for Neural Network based Molecular Potentials

Abstract

The prediction of quantum mechanical properties is historically plagued by a trade-off between accuracy and speed. Machine learning potentials have previously shown great success in this domain, reaching increasingly better accuracy while maintaining computational efficiency comparable with classical force fields. In this work we propose TorchMD-NET, a novel equivariant transformer (ET) architecture, outperforming state-of-the-art on MD17, ANI-1, and many QM9 targets in both accuracy and computational efficiency. Through an extensive attention weight analysis, we gain valuable insights into the black box predictor and show differences in the learned representation of conformers versus conformations sampled from molecular dynamics or normal modes. Furthermore, we highlight the importance of datasets including off-equilibrium conformations for the evaluation of molecular potentials.

Cited by in corpus (8)

• On the design space between molecular mechanics and machine learning force fields
• Denoise Pretraining on Nonequilibrium Molecules for Accurate and Transferable Neural Potentials
• Scaling Graph Neural Networks to Large Proteins
• Refining Coarse-Grained Molecular Topologies: A Bayesian Optimization Approach
• Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective
• Considerations in the use of ML interaction potentials for free energy calculations
• Artificial Intelligence for Direct Prediction of Molecular Dynamics Across Chemical Space
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model