Stable and accurate atomistic simulations of flexible molecules using conformationally generalisable machine learned potentials
Open Access
- 8 July 2024
- journal article
- research article
- Published by Royal Society of Chemistry (RSC) in Chemical Science
- Vol. 15 (32) , 12780-12795
Abstract
Computational simulation methods based on machine learned potentials (MLPs) promise to revolutionise shape prediction of flexible molecules in solution, but their widespread adoption has been limited by the way in which training data is generated. Here, we present an approach which allows the key conformational degrees of freedom to be properly represented in reference molecular datasets. MLPs trained on these datasets using a global descriptor scheme are generalisable in conformational space, providing quantum chemical accuracy for all conformers. These MLPs are capable of propagating long, stable molecular dynamics trajectories, an attribute that has remained a challenge. We deploy the MLPs in obtaining converged conformational free energy surfaces for flexible molecules via well-tempered metadynamics simulations; this approach provides a hitherto inaccessible route to accurately computing the structural, dynamical and thermodynamical properties of a wide variety of flexible molecular systems. It is further demonstrated that MLPs must be trained on reference datasets with complete coverage of conformational space, including in barrier regions, to achieve stable molecular dynamics trajectories.Keywords
All Related Versions
Funding Information
- Engineering and Physical Sciences Research Council (T022205/1)
- Leverhulme Trust (RPG-2020-059)
This publication has 92 references indexed in Scilit:
- Modeling pyranose ring pucker in carbohydrates using machine learning and semi‐empirical quantum chemical methodsJournal of Computational Chemistry, 2022
- Machine learning of atomic forces from quantum mechanics: An approach based on pairwise interatomic forcesInternational Journal of Quantum Chemistry, 2022
- Assessing conformer energies using electronic structure and machine learning methodsInternational Journal of Quantum Chemistry, 2020
- Machine Learning Interatomic Potentials as Emerging Tools for Materials ScienceAdvanced Materials, 2019
- A sobering assessment of small‐molecule force field methods for low energy conformer predictionsInternational Journal of Quantum Chemistry, 2017
- Polarisable multipolar electrostatics from the machine learning method Kriging: an application to alanineTheoretical Chemistry Accounts, 2012
- Empirical force fields for biological macromolecules: Overview and issuesJournal of Computational Chemistry, 2004
- How well does a restrained electrostatic potential (RESP) model perform in calculating conformational energies of organic and biological molecules?Journal of Computational Chemistry, 2000
- Local elevation: A method for improving the searching properties of molecular dynamics simulationJournal of Computer-Aided Molecular Design, 1994
- The influence of polarization functions on molecular orbital hydrogenation energiesTheoretical Chemistry Accounts, 1973