Combining Force Fields and Neural Networks for an Accurate Representation of Chemically Diverse Molecular Interactions
Open Access
- 19 October 2023
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of the American Chemical Society
- Vol. 145 (43) , 23620-23629
Abstract
A key goal of molecular modeling is the accurate reproduction of the true quantum mechanical potential energy of arbitrary molecular ensembles with a tractable classical approximation. The challenges are that analytical expressions found in general purpose force fields struggle to faithfully represent the intermolecular quantum potential energy surface at close distances and in strong interaction regimes; that the more accurate neural network approximations do not capture crucial physics concepts, e.g., nonadditive inductive contributions and application of electric fields; and that the ultra-accurate narrowly targeted models have difficulty generalizing to the entire chemical space. We therefore designed a hybrid wide-coverage intermolecular interaction model consisting of an analytically polarizable force field combined with a short-range neural network correction for the total intermolecular interaction energy. Here, we describe the methodology and apply the model to accurately determine the properties of water, the free energy of solvation of neutral and charged molecules, and the binding free energy of ligands to proteins. The correction is subtyped for distinct chemical species to match the underlying force field, to segment and reduce the amount of quantum training data, and to increase accuracy and computational speed. For the systems considered, the hybrid ab initio parametrized Hamiltonian reproduces the two-body dimer quantum mechanics (QM) energies to within 0.03 kcal/mol and the nonadditive many-molecule contributions to within 2%. Simulations of molecular systems using this interaction model run at speeds of several nanoseconds per day.Keywords
Funding Information
- NSF (MCB-1818213)
- NeoTX, InterX
- U.S. DOE, Office of Basic Energy Sciences (DE-AC02-06CH11357)
- NIH (R01NS083660)
This publication has 68 references indexed in Scilit:
- Current Status of the AMOEBA Polarizable Force FieldThe Journal of Physical Chemistry B, 2010
- 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
- Anisotropic, Polarizable Molecular Mechanics Studies of Inter- and Intramolecular Interactions and Ligand−Macromolecule Complexes. A Bottom-Up StrategyJournal of Chemical Theory and Computation, 2007
- Accurate and Efficient Corrections for Missing Dispersion Interactions in Molecular SimulationsThe Journal of Physical Chemistry B, 2007
- Development and testing of a general amber force fieldJournal of Computational Chemistry, 2004
- Convergence of the Electrostatic Interaction Based on Topological AtomsThe Journal of Physical Chemistry A, 2001
- Molecular dynamics of native proteinJournal of Molecular Biology, 1983
- CHARMM: A program for macromolecular energy, minimization, and dynamics calculationsJournal of Computational Chemistry, 1983
- Refinement of protein conformations using a macromolecular energy minimization procedureJournal of Molecular Biology, 1969
- Self-Consistent Equations Including Exchange and Correlation EffectsPhysical Review B, 1965