Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles
Abstract
The molecular dipole moment (μ) is a central quantity in chemistry. It is essential in predicting infrared and sum-frequency generation spectra as well as induction and long-range electrostatic interactions. Furthermore, it can be extracted directly—via the ground state electron density—from high-level quantum mechanical calculations, making it an ideal target for machine learning (ML). Here, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression framework which assigns a (vector) dipole moment to each atom, while the movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom. The resulting “MuML” models are fitted together to reproduce molecular μ computed using high-level coupled-cluster theory and density functional theory (DFT) on the QM7b dataset, achieving more accurate results due to the physics-based combination of these complementary terms. The combined model shows excellent transferability when applied to a showcase dataset of larger and more complex molecules, approaching the accuracy of DFT at a small fraction of the computational cost. We also demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model.more »
- Authors:
-
- Ecole Polytechnique Federale Lausanne (Switzlerland). Lab. of Computational Science and Modeling, IMX
- Cornell Univ., Ithaca, NY (United States). Dept. of Chemistry and Chemical Biology
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Laboratory (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
- Sponsoring Org.:
- USDOE Office of Science (SC); European Research Council (ERC)
- OSTI Identifier:
- 1681219
- Alternate Identifier(s):
- OSTI ID: 1637990
- Grant/Contract Number:
- AC02-05CH11231; 677013-HBMAP
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Physics
- Additional Journal Information:
- Journal Volume: 153; Journal Issue: 2; Journal ID: ISSN 0021-9606
- Publisher:
- American Institute of Physics (AIP)
- Country of Publication:
- United States
- Language:
- English
- Subject:
- 37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY; Gaussian processes; machine learning; polarization; electrostatics; polypeptide; density functional theory; coupled-cluster methods; molecular dipole moments; infrared spectroscopy; sum-frequency generation
Citation Formats
Veit, Max, Wilkins, David M., Yang, Yang, DiStasio, Robert A., and Ceriotti, Michele. Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles. United States: N. p., 2020.
Web. doi:10.1063/5.0009106.
Veit, Max, Wilkins, David M., Yang, Yang, DiStasio, Robert A., & Ceriotti, Michele. Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles. United States. https://doi.org/10.1063/5.0009106
Veit, Max, Wilkins, David M., Yang, Yang, DiStasio, Robert A., and Ceriotti, Michele. Thu .
"Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles". United States. https://doi.org/10.1063/5.0009106. https://www.osti.gov/servlets/purl/1681219.
@article{osti_1681219,
title = {Predicting molecular dipole moments by combining atomic partial charges and atomic dipoles},
author = {Veit, Max and Wilkins, David M. and Yang, Yang and DiStasio, Robert A. and Ceriotti, Michele},
abstractNote = {The molecular dipole moment (μ) is a central quantity in chemistry. It is essential in predicting infrared and sum-frequency generation spectra as well as induction and long-range electrostatic interactions. Furthermore, it can be extracted directly—via the ground state electron density—from high-level quantum mechanical calculations, making it an ideal target for machine learning (ML). Here, we choose to represent this quantity with a physically inspired ML model that captures two distinct physical effects: local atomic polarization is captured within the symmetry-adapted Gaussian process regression framework which assigns a (vector) dipole moment to each atom, while the movement of charge across the entire molecule is captured by assigning a partial (scalar) charge to each atom. The resulting “MuML” models are fitted together to reproduce molecular μ computed using high-level coupled-cluster theory and density functional theory (DFT) on the QM7b dataset, achieving more accurate results due to the physics-based combination of these complementary terms. The combined model shows excellent transferability when applied to a showcase dataset of larger and more complex molecules, approaching the accuracy of DFT at a small fraction of the computational cost. We also demonstrate that the uncertainty in the predictions can be estimated reliably using a calibrated committee model. The ultimate performance of the models—and the optimal weighting of their combination—depends, however, on the details of the system at hand, with the scalar model being clearly superior when describing large molecules whose dipole is almost entirely generated by charge separation. These observations point to the importance of simultaneously accounting for the local and non-local effects that contribute to μ; furthermore, they define a challenging task to benchmark future models, particularly those aimed at the description of condensed phases.},
doi = {10.1063/5.0009106},
journal = {Journal of Chemical Physics},
number = 2,
volume = 153,
place = {United States},
year = {Thu Jul 09 00:00:00 EDT 2020},
month = {Thu Jul 09 00:00:00 EDT 2020}
}
Web of Science
Works referenced in this record:
Nonlinear Light Scattering and Spectroscopy of Particles and Droplets in Liquids
journal, May 2012
- Roke, Sylvie; Gonella, Grazia
- Annual Review of Physical Chemistry, Vol. 63, Issue 1
Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials
journal, June 2018
- Imbalzano, Giulio; Anelli, Andrea; Giofré, Daniele
- The Journal of Chemical Physics, Vol. 148, Issue 24
Dynamically Polarizable Water Potential Based on Multipole Moments Trained by Machine Learning
journal, May 2009
- Handley, Chris M.; Popelier, Paul L. A.
- Journal of Chemical Theory and Computation, Vol. 5, Issue 6
Coupled cluster response functions
journal, September 1990
- Koch, Henrik; Jo/rgensen, Poul
- The Journal of Chemical Physics, Vol. 93, Issue 5
An approach to computing electrostatic charges for molecules
journal, April 1984
- Singh, U. Chandra; Kollman, Peter A.
- Journal of Computational Chemistry, Vol. 5, Issue 2
Comparison of atomic charges derived via different procedures
journal, December 1993
- Wiberg, Kenneth B.; Rablen, Paul R.
- Journal of Computational Chemistry, Vol. 14, Issue 12
Distributed multipole analysis, or how to describe a molecular charge distribution
journal, October 1981
- Stone, A. J.
- Chemical Physics Letters, Vol. 83, Issue 2
Permutationally invariant potential energy surfaces in high dimensionality
journal, October 2009
- Braams, Bastiaan J.; Bowman, Joel M.
- International Reviews in Physical Chemistry, Vol. 28, Issue 4
Inexpensive modeling of quantum dynamics using path integral generalized Langevin equation thermostats
journal, March 2020
- Kapil, Venkat; Wilkins, David M.; Lan, Jinggang
- The Journal of Chemical Physics, Vol. 152, Issue 12
Polarization in Kohn-Sham density-functional theory
journal, June 2018
- Resta, Raffaele
- The European Physical Journal B, Vol. 91, Issue 6
Determination of partial atomic charges from ab initio molecular electrostatic potentials. Application to formamide, methanol, and formic acid
journal, March 1978
- Momany, Frank A.
- The Journal of Physical Chemistry, Vol. 82, Issue 5
How Accurate Is Density Functional Theory at Predicting Dipole Moments? An Assessment Using a New Database of 200 Benchmark Values
journal, March 2018
- Hait, Diptarka; Head-Gordon, Martin
- Journal of Chemical Theory and Computation, Vol. 14, Issue 4
Machine learning of molecular electronic properties in chemical compound space
journal, September 2013
- Montavon, Grégoire; Rupp, Matthias; Gobre, Vivekanand
- New Journal of Physics, Vol. 15, Issue 9
Equation of State of Fluid Methane from First Principles with Machine Learning Potentials
journal, February 2019
- Veit, Max; Jain, Sandeep Kumar; Bonakala, Satyanarayana
- Journal of Chemical Theory and Computation, Vol. 15, Issue 4
Incorporating long-range physics in atomic-scale machine learning
journal, November 2019
- Grisafi, Andrea; Ceriotti, Michele
- The Journal of Chemical Physics, Vol. 151, Issue 20
Critical analysis and extension of the Hirshfeld atoms in molecules
journal, April 2007
- Bultinck, Patrick; Van Alsenoy, Christian; Ayers, Paul W.
- The Journal of Chemical Physics, Vol. 126, Issue 14
SchNet – A deep learning architecture for molecules and materials
journal, June 2018
- Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J.
- The Journal of Chemical Physics, Vol. 148, Issue 24
Fast and Accurate Uncertainty Estimation in Chemical Machine Learning
journal, November 2018
- Musil, Félix; Willatt, Michael J.; Langovoy, Mikhail A.
- Journal of Chemical Theory and Computation, Vol. 15, Issue 2
Using Gaussian process regression to simulate the vibrational Raman spectra of molecular crystals
journal, October 2019
- Raimbault, Nathaniel; Grisafi, Andrea; Ceriotti, Michele
- New Journal of Physics, Vol. 21, Issue 10
Benchmarking Quantum Chemical Methods for the Calculation of Molecular Dipole Moments and Polarizabilities
journal, May 2014
- Hickey, A. Leif; Rowley, Christopher N.
- The Journal of Physical Chemistry A, Vol. 118, Issue 20
Minimal Basis Iterative Stockholder: Atoms in Molecules for Force-Field Development
journal, July 2016
- Verstraelen, Toon; Vandenbrande, Steven; Heidar-Zadeh, Farnaz
- Journal of Chemical Theory and Computation, Vol. 12, Issue 8
PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments, and Partial Charges
journal, April 2019
- Unke, Oliver T.; Meuwly, Markus
- Journal of Chemical Theory and Computation, Vol. 15, Issue 6
Non-covalent interactions across organic and biological subsets of chemical space: Physics-based potentials parametrized from machine learning
journal, June 2018
- Bereau, Tristan; DiStasio, Robert A.; Tkatchenko, Alexandre
- The Journal of Chemical Physics, Vol. 148, Issue 24
Determining atom-centered monopoles from molecular electrostatic potentials. The need for high sampling density in formamide conformational analysis
journal, April 1990
- Breneman, Curt M.; Wiberg, Kenneth B.
- Journal of Computational Chemistry, Vol. 11, Issue 3
Electronic Population Analysis on LCAO–MO Molecular Wave Functions. I
journal, October 1955
- Mulliken, R. S.
- The Journal of Chemical Physics, Vol. 23, Issue 10
Gaussian basis sets for use in correlated molecular calculations. IV. Calculation of static electrical response properties
journal, February 1994
- Woon, David E.; Dunning, Thom H.
- The Journal of Chemical Physics, Vol. 100, Issue 4
Discovering a Transferable Charge Assignment Model Using Machine Learning
journal, July 2018
- Sifain, Andrew E.; Lubbers, Nicholas; Nebgen, Benjamin T.
- The Journal of Physical Chemistry Letters, Vol. 9, Issue 16
Density‐functional thermochemistry. III. The role of exact exchange
journal, April 1993
- Becke, Axel D.
- The Journal of Chemical Physics, Vol. 98, Issue 7, p. 5648-5652
Performance and basis set dependence of density functional theory dipole and quadrupole moments
journal, July 2000
- De Proft, F.; Tielens, F.; Geerlings, P.
- Journal of Molecular Structure: THEOCHEM, Vol. 506, Issue 1-3
Use of the complete basis set limit for computing highly accurate ab initio dipole moments
journal, January 2020
- Conway, Eamon K.; Gordon, Iouli E.; Polyansky, Oleg L.
- The Journal of Chemical Physics, Vol. 152, Issue 2
Alchemical and structural distribution based representation for universal quantum machine learning
journal, June 2018
- Faber, Felix A.; Christensen, Anders S.; Huang, Bing
- The Journal of Chemical Physics, Vol. 148, Issue 24
Gaussian approximation potentials: A brief tutorial introduction
journal, April 2015
- Bartók, Albert P.; Csányi, Gábor
- International Journal of Quantum Chemistry, Vol. 115, Issue 16
A beginner's guide to the modern theory of polarization
journal, November 2012
- Spaldin, Nicola A.
- Journal of Solid State Chemistry, Vol. 195
How van der Waals interactions determine the unique properties of water
journal, July 2016
- Morawietz, Tobias; Singraber, Andreas; Dellago, Christoph
- Proceedings of the National Academy of Sciences, Vol. 113, Issue 30
Machine learning unifies the modeling of materials and molecules
journal, December 2017
- Bartók, Albert P.; De, Sandip; Poelking, Carl
- Science Advances, Vol. 3, Issue 12
Distributed Multipole Analysis: Stability for Large Basis Sets
journal, September 2005
- Stone, Anthony J.
- Journal of Chemical Theory and Computation, Vol. 1, Issue 6
FOHI-D: An iterative Hirshfeld procedure including atomic dipoles
journal, April 2014
- Geldof, D.; Krishtal, A.; Blockhuys, F.
- The Journal of Chemical Physics, Vol. 140, Issue 14
Visualization and analysis of atomistic simulation data with OVITO–the Open Visualization Tool
journal, December 2009
- Stukowski, Alexander
- Modelling and Simulation in Materials Science and Engineering, Vol. 18, Issue 1
Polarizable QM/MM Approach with Fluctuating Charges and Fluctuating Dipoles: The QM/FQFμ Model
journal, March 2019
- Giovannini, Tommaso; Puglisi, Alessandra; Ambrosetti, Matteo
- Journal of Chemical Theory and Computation, Vol. 15, Issue 4
Accurate molecular polarizabilities with coupled cluster theory and machine learning
journal, February 2019
- Wilkins, David M.; Grisafi, Andrea; Yang, Yang
- Proceedings of the National Academy of Sciences, Vol. 116, Issue 9
Chemical shifts in molecular solids by machine learning
journal, October 2018
- Paruzzo, Federico M.; Hofstetter, Albert; Musil, Félix
- Nature Communications, Vol. 9, Issue 1
Comparison of Density Functional and MP2 Calculations on the Water Monomer and Dimer
journal, October 1994
- Kim, K.; Jordan, K. D.
- The Journal of Physical Chemistry, Vol. 98, Issue 40
Improved Atoms-in-Molecule Charge Partitioning Functional for Simultaneously Reproducing the Electrostatic Potential and Chemical States in Periodic and Nonperiodic Materials
journal, July 2012
- Manz, Thomas A.; Sholl, David S.
- Journal of Chemical Theory and Computation, Vol. 8, Issue 8
Representation of the molecular electrostatic potential by a net atomic charge model
journal, October 1981
- Cox, S. R.; Williams, D. E.
- Journal of Computational Chemistry, Vol. 2, Issue 3
Quantum mechanical static dipole polarizabilities in the QM7b and AlphaML showcase databases
journal, August 2019
- Yang, Yang; Lao, Ka Un; Wilkins, David M.
- Scientific Data, Vol. 6, Issue 1
Machine learning molecular dynamics for the simulation of infrared spectra
journal, January 2017
- Gastegger, Michael; Behler, Jörg; Marquetand, Philipp
- Chemical Science, Vol. 8, Issue 10
Redefining the atom: atomic charge densities produced by an iterative stockholder approach
journal, January 2008
- Lillestolen, Timothy C.; Wheatley, Richard J.
- Chemical Communications, Issue 45
Quantum chemistry structures and properties of 134 kilo molecules
journal, August 2014
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- Scientific Data, Vol. 1, Issue 1
Beyond Point Charges: Dynamic Polarization from Neural Net Predicted Multipole Moments
journal, July 2008
- Darley, Michael G.; Handley, Chris M.; Popelier, Paul L. A.
- Journal of Chemical Theory and Computation, Vol. 4, Issue 9
Hirshfeld-E Partitioning: AIM Charges with an Improved Trade-off between Robustness and Accurate Electrostatics
journal, April 2013
- Verstraelen, T.; Ayers, P. W.; Van Speybroeck, V.
- Journal of Chemical Theory and Computation, Vol. 9, Issue 5
Formulation in terms of normalized propagators of a charge-dipole model enabling the calculation of the polarization properties of fullerenes and carbon nanotubes
journal, January 2007
- Mayer, A.
- Physical Review B, Vol. 75, Issue 4
On the Non‐Orthogonality Problem Connected with the Use of Atomic Wave Functions in the Theory of Molecules and Crystals
journal, March 1950
- Löwdin, Per‐Olov
- The Journal of Chemical Physics, Vol. 18, Issue 3
Operators in quantum machine learning: Response properties in chemical space
journal, February 2019
- Christensen, Anders S.; Faber, Felix A.; von Lilienfeld, O. Anatole
- The Journal of Chemical Physics, Vol. 150, Issue 6
SchNet – A deep learning architecture for molecules and materials
journal, June 2018
- Schütt, K. T.; Sauceda, H. E.; Kindermans, P. -J.
- The Journal of Chemical Physics, Vol. 148, Issue 24