Grappa -- A Machine Learned Molecular Mechanics Force Field

arXiv:2404.00050v1 Announce Type: cross
Abstract: Simulating large molecular systems over long timescales requires force fields that are both accurate and efficient. In recent years, E(3) equivariant neural networks have lifted the tension between computational efficiency and accuracy of force fields, but they are still several orders of magnitude more expensive than classical molecular mechanics (MM) force fields.
Here, we propose a novel machine learning architecture to predict MM parameters from the molecular graph, employing a graph attentional neural network and …

abstract accuracy arxiv computational cs.lg efficiency fields machine networks neural networks orders physics.chem-ph physics.comp-ph systems type