Multiscale Force Field Model Based on a Graph Neural Network for Complex Chemical Systems
- 27 February 2025
- journal article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 21 (5) , 2501-2514
Abstract
Inspired by the QM/MM methodology, the ML/MM approach introduces a new opportunity for multiscale simulation, improving the balance between accuracy and computational efficiency. Benefited from the rapid advancements in molecular embedding methods, density functional theory level quantum mechanical (QM) calculations within the QM/MM framework can be accelerated by several orders of magnitude through the application of machine learning (ML) potential energy surfaces. As a problem inherited from the QM/MM methodology, challenges exist in designing the interactions between machine learning and molecular mechanics (MM) regions. In this study, electrostatic interactions between machine learning and MM atoms are treated by using a graphical neural network based on stationary perturbation theory. In this protocol, we process coordinates and MM charges to yield electrostatic energy and forces, resulting in a high-performance electrostatic embedding ML/MM architecture. The accuracy of the ML/MM energy was validated in aqueous solutions of alanine dipeptide and allyl vinyl ether (AVE). We investigated the transferability of parameters trained from AVE in a single solvent to various other solvents, including water, methanol, dimethyl sulfoxide, toluene, ionic liquids, and water-toluene interface environments. We then established a solvent-free protocol for data set preparation. Comparison of the free energy landscapes of the Claisen rearrangement of AVE in different solvation environments showed the catalytic effect of aqueous solutions, consistent with experiments.Keywords
Funding Information
- National Natural Science Foundation of China (21821004, 21927901, 22273061, 92053202, 92353304)
- National Science and Technology Major Project (2022ZD0115003)
- New Cornerstone Science Foundation (NCI202305)
This publication has 78 references indexed in Scilit:
- SPONGE: A GPU‐Accelerated Molecular Dynamics Package with Enhanced Sampling and AI‐Driven AlgorithmsChinese Journal of Chemistry, 2021
- A systematic study of minima in alanine dipeptideJournal of Computational Chemistry, 2018
- Multiscale modeling of enzymes: QM‐cluster, QM/MM, and QM/MM/MD: A tutorial reviewInternational Journal of Quantum Chemistry, 2018
- Accurate prediction of experimental free energy of activation barriers for the aliphatic-Claisen rearrangement through DFT calculationsComputational and Theoretical Chemistry, 2011
- Umbrella samplingWIREs Computational Molecular Science, 2011
- Accurate Kohn–Sham DFT with the speed of tight binding: Current techniques and future directions in materials modellingPhysica Status Solidi (b), 2010
- QM/MM Methods for Biomolecular SystemsAngewandte Chemie International Edition, 2009
- The implementation of a fast and accurate QM/MM potential method in AmberJournal of Computational Chemistry, 2007
- Molecular polarizabilities calculated with a modified dipole interactionChemical Physics, 1981
- Theoretical studies of enzymic reactions: Dielectric, electrostatic and steric stabilization of the carbonium ion in the reaction of lysozymeJournal of Molecular Biology, 1976