Cartesian message passing neural networks for directional properties: Fast and transferable atomic multipoles
- 9 June 2021
- journal article
- research article
- Published by AIP Publishing in The Journal of Chemical Physics
- Vol. 154 (22), 224103
- https://doi.org/10.1063/5.0050444
Abstract
The message passing neural network (MPNN) framework is a promising tool for modeling atomic properties but is, until recently, incompatible with directional properties, such as Cartesian tensors. We propose a modified Cartesian MPNN (CMPNN) suitable for predicting atom-centered multipoles, an essential component of ab initio force fields. The efficacy of this model is demonstrated on a newly developed dataset consisting of 46 623 chemical structures and corresponding high-quality atomic multipoles, which was deposited into the publicly available Molecular Sciences Software Institute QCArchive server. We show that the CMPNN accurately predicts atom-centered charges, dipoles, and quadrupoles and that errors in the predicted atomic multipoles have a negligible effect on multipole–multipole electrostatic energies. The CMPNN is accurate enough to model conformational dependencies of a molecule’s electronic structure. This opens up the possibility of recomputing atomic multipoles on the fly throughout a simulation in which they might exhibit strong conformational dependence.Funding Information
- National Science Foundation (CHE-1955940, MRI-1828187)
- U.S. Department of Energy (AL-18-380-057)
This publication has 49 references indexed in Scilit:
- Assessment of the Performance of DFT and DFT-D Methods for Describing Distance Dependence of Hydrogen-Bonded InteractionsJournal of Chemical Theory and Computation, 2010
- Current Status of the AMOEBA Polarizable Force FieldThe Journal of Physical Chemistry B, 2010
- CHARMM: The biomolecular simulation programJournal of Computational Chemistry, 2009
- Beyond Point Charges: Dynamic Polarization from Neural Net Predicted Multipole MomentsJournal of Chemical Theory and Computation, 2008
- Generalized Neural-Network Representation of High-Dimensional Potential-Energy SurfacesPhysical Review Letters, 2007
- “Learn on the Fly”: A Hybrid Classical and Quantum-Mechanical Molecular Dynamics SimulationPhysical Review Letters, 2004
- Experimental and computational approaches to estimate solubility and permeability in drug discovery and development settingsAdvanced Drug Delivery Reviews, 2001
- The Effective Fragment Potential Method: A QM-Based MM Approach to Modeling Environmental Effects in ChemistryThe Journal of Physical Chemistry A, 2000
- Conformational dependence of the molecular charge distribution and its influence on intermolecular interactionsJournal of the Chemical Society, Faraday Transactions, 1996
- Distributed multipole analysisMolecular Physics, 1985