Molecular Simulations with a Pretrained Neural Network and Universal Pairwise Force Fields
Authors:
- Adil KabyldaAKAdil Kabylda
- J. Thorben FrankJFJ. Thorben Frank
- Sergio Suarez DouSDSergio Suarez Dou
- Almaz KhabibrakhmanovAKAlmaz Khabibrakhmanov
- Leonardo Medrano SandonasLSLeonardo Medrano Sandonas
- Oliver T. UnkeOUOliver T. Unke
- Stefan ChmielaSCStefan Chmiela
- Klaus-Robert MullerKMKlaus-Robert Muller
- Alexandre TkatchenkoATAlexandre Tkatchenko
Preprint
- 8 October 2024
- preprint
- Published by American Chemical Society (ACS) in ChemRxiv
Abstract
Machine Learning Force Fields (MLFFs) promise to enable general molecular simulations that can simultaneously achieve efficiency, accuracy, transferability, and scalability for diverse molecules, materials, and hybrid interfaces. A key step toward this goal has been made with the GEMS approach to biomolecular dynamics [Sci. Adv. 10, eadn4397 (2024)]. This work introduces the SO3LR method that integrates the fast and stable SO3krates neural network for semi-local interactions with universal pairwise force fields designed for short-range repulsion, long-range electrostatics, and dispersion interactions. SO3LR is trained on a diverse set of 4 million neutral and charged molecular complexes computed at the PBE0+MBD level of quantum mechanics, ensuring a comprehensive coverage of covalent and non-covalent interactions. Our approach is characterized by computational and data efficiency, scalability to 200 thousand atoms on a single GPU, and reasonable to high accuracy across the chemical space of organic (bio)molecules. SO3LR is applied to study units of four major biomolecule types, polypeptide folding, and nanosecond dynamics of larger systems such as a protein, a glycoprotein, and a lipid bilayer, all in explicit solvent. Finally, we discuss the future challenges toward truly general molecular simulations by combining MLFFs with traditional atomistic models.Keywords
All Related Versions
This publication has 93 references indexed in Scilit:
- Recent developments and applications of the CHARMM force fieldsWIREs Computational Molecular Science, 2011
- CHARMM general force field: A force field for drug‐like molecules compatible with the CHARMM all‐atom additive biological force fieldsJournal of Computational Chemistry, 2009
- CHARMM: The biomolecular simulation programJournal of Computational Chemistry, 2009
- Biomolecular Modeling: Goals, Problems, PerspectivesAngewandte Chemie International Edition, 2006
- The Amber biomolecular simulation programsJournal of Computational Chemistry, 2005
- A biomolecular force field based on the free enthalpy of hydration and solvation: The GROMOS force‐field parameter sets 53A5 and 53A6Journal of Computational Chemistry, 2004
- Empirical force fields for biological macromolecules: Overview and issuesJournal of Computational Chemistry, 2004
- Development and testing of a general amber force fieldJournal of Computational Chemistry, 2004
- Structure validation by Cα geometry: ϕ,ψ and Cβ deviationProteins: Structure, Function, and Bioinformatics, 2003
- Knowledge‐based protein secondary structure assignmentProteins: Structure, Function, and Bioinformatics, 1995