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

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 classica...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Thölke, Philipp, De Fabritiis, Gianni
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 23.04.2022
Subjects
Accuracy
Computational efficiency
Computing time
Machine learning
Mechanical properties
Molecular dynamics
Neural networks
Quantum mechanics
Transformers
Weight analysis
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422