A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules
Abstract
We address the degree to which machine learning (ML) can be used to accurately and transferably predict post-Hartree-Fock correlation energies. Refined strategies for feature design and selection are presented, and the molecular-orbital-based machine learning (MOB-ML) method is applied to several test systems. Strikingly, for the second-order Møller-Plessett perturbation theory, coupled cluster with singles and doubles (CCSD), and CCSD with perturbative triples levels of theory, it is shown that the thermally accessible (350 K) potential energy surface for a single water molecule can be described to within 1 mhartree using a model that is trained from only a single reference calculation at a randomized geometry. To explore the breadth of chemical diversity that can be described, MOB-ML is also applied to a new dataset of thermalized (350 K) geometries of 7211 organic models with up to seven heavy atoms. In comparison with the previously reported Δ-ML method, MOB-ML is shown to reach chemical accuracy with threefold fewer training geometries. Finally, a transferability test in which models trained for seven-heavy-atom systems are used to predict energies for thirteen-heavy-atom systems reveals that MOB-ML reaches chemical accuracy with 36-fold fewer training calculations than Δ-ML (140 vs 5000 training calculations).
- Authors:
-
- California Inst. of Technology (CalTech), Pasadena, CA (United States)
- Univ. of Basel (Switzerland)
- Publication Date:
- Research Org.:
- Lawrence Berkeley National Lab. (LBNL), Berkeley, CA (United States). National Energy Research Scientific Computing Center (NERSC)
- Sponsoring Org.:
- USDOE Office of Science (SC)
- OSTI Identifier:
- 1529903
- Alternate Identifier(s):
- OSTI ID: 1505017
- Grant/Contract Number:
- AC02-05CH11231
- Resource Type:
- Accepted Manuscript
- Journal Name:
- Journal of Chemical Physics
- Additional Journal Information:
- Journal Volume: 150; Journal Issue: 13; 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
Citation Formats
Cheng, Lixue, Welborn, Matthew, Christensen, Anders S., and Miller, Thomas F. A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules. United States: N. p., 2019.
Web. doi:10.1063/1.5088393.
Cheng, Lixue, Welborn, Matthew, Christensen, Anders S., & Miller, Thomas F. A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules. United States. https://doi.org/10.1063/1.5088393
Cheng, Lixue, Welborn, Matthew, Christensen, Anders S., and Miller, Thomas F. Thu .
"A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules". United States. https://doi.org/10.1063/1.5088393. https://www.osti.gov/servlets/purl/1529903.
@article{osti_1529903,
title = {A universal density matrix functional from molecular orbital-based machine learning: Transferability across organic molecules},
author = {Cheng, Lixue and Welborn, Matthew and Christensen, Anders S. and Miller, Thomas F.},
abstractNote = {We address the degree to which machine learning (ML) can be used to accurately and transferably predict post-Hartree-Fock correlation energies. Refined strategies for feature design and selection are presented, and the molecular-orbital-based machine learning (MOB-ML) method is applied to several test systems. Strikingly, for the second-order Møller-Plessett perturbation theory, coupled cluster with singles and doubles (CCSD), and CCSD with perturbative triples levels of theory, it is shown that the thermally accessible (350 K) potential energy surface for a single water molecule can be described to within 1 mhartree using a model that is trained from only a single reference calculation at a randomized geometry. To explore the breadth of chemical diversity that can be described, MOB-ML is also applied to a new dataset of thermalized (350 K) geometries of 7211 organic models with up to seven heavy atoms. In comparison with the previously reported Δ-ML method, MOB-ML is shown to reach chemical accuracy with threefold fewer training geometries. Finally, a transferability test in which models trained for seven-heavy-atom systems are used to predict energies for thirteen-heavy-atom systems reveals that MOB-ML reaches chemical accuracy with 36-fold fewer training calculations than Δ-ML (140 vs 5000 training calculations).},
doi = {10.1063/1.5088393},
journal = {Journal of Chemical Physics},
number = 13,
volume = 150,
place = {United States},
year = {2019},
month = {4}
}
Web of Science
Works referenced in this record:
Machine-learning approaches in drug discovery: methods and applications
journal, March 2015
- Lavecchia, Antonio
- Drug Discovery Today, Vol. 20, Issue 3
Deep Learning in Drug Discovery
journal, December 2015
- Gawehn, Erik; Hiss, Jan A.; Schneider, Gisbert
- Molecular Informatics, Vol. 35, Issue 1
Deep reinforcement learning for de novo drug design
journal, July 2018
- Popova, Mariya; Isayev, Olexandr; Tropsha, Alexander
- Science Advances, Vol. 4, Issue 7
Virtual screening of inorganic materials synthesis parameters with deep learning
journal, December 2017
- Kim, Edward; Huang, Kevin; Jegelka, Stefanie
- npj Computational Materials, Vol. 3, Issue 1
Accelerated discovery of metallic glasses through iteration of machine learning and high-throughput experiments
journal, April 2018
- Ren, Fang; Ward, Logan; Williams, Travis
- Science Advances, Vol. 4, Issue 4
Machine learning for molecular and materials science
journal, July 2018
- Butler, Keith T.; Davies, Daniel W.; Cartwright, Hugh
- Nature, Vol. 559, Issue 7715
Inverse molecular design using machine learning: Generative models for matter engineering
journal, July 2018
- Sanchez-Lengeling, Benjamin; Aspuru-Guzik, Alán
- Science, Vol. 361, Issue 6400
Neural Networks for the Prediction of Organic Chemistry Reactions
journal, October 2016
- Wei, Jennifer N.; Duvenaud, David; Aspuru-Guzik, Alán
- ACS Central Science, Vol. 2, Issue 10
Machine-learning-assisted materials discovery using failed experiments
journal, May 2016
- Raccuglia, Paul; Elbert, Katherine C.; Adler, Philip D. F.
- Nature, Vol. 533, Issue 7601
To address surface reaction network complexity using scaling relations machine learning and DFT calculations
journal, March 2017
- Ulissi, Zachary W.; Medford, Andrew J.; Bligaard, Thomas
- Nature Communications, Vol. 8, Issue 1
Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction
journal, February 2017
- Segler, Marwin H. S.; Waller, Mark P.
- Chemistry - A European Journal, Vol. 23, Issue 25
Planning chemical syntheses with deep neural networks and symbolic AI
journal, March 2018
- Segler, Marwin H. S.; Preuss, Mike; Waller, Mark P.
- Nature, Vol. 555, Issue 7698
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
journal, January 2017
- Smith, J. S.; Isayev, O.; Roitberg, A. E.
- Chemical Science, Vol. 8, Issue 4
Hierarchical modeling of molecular energies using a deep neural network
journal, June 2018
- Lubbers, Nicholas; Smith, Justin S.; Barros, Kipton
- The Journal of Chemical Physics, Vol. 148, Issue 24
Gaussian Approximation Potentials: The Accuracy of Quantum Mechanics, without the Electrons
journal, April 2010
- Bartók, Albert P.; Payne, Mike C.; Kondor, Risi
- Physical Review Letters, Vol. 104, Issue 13
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning
journal, January 2012
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- Physical Review Letters, Vol. 108, Issue 5
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
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies
journal, July 2013
- Hansen, Katja; Montavon, Grégoire; Biegler, Franziska
- Journal of Chemical Theory and Computation, Vol. 9, Issue 8
Recognizing molecular patterns by machine learning: An agnostic structural definition of the hydrogen bond
journal, November 2014
- Gasparotto, Piero; Ceriotti, Michele
- The Journal of Chemical Physics, Vol. 141, Issue 17
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach
journal, April 2015
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- Journal of Chemical Theory and Computation, Vol. 11, Issue 5
Perspective: Machine learning potentials for atomistic simulations
journal, November 2016
- Behler, Jörg
- The Journal of Chemical Physics, Vol. 145, Issue 17
Molecular graph convolutions: moving beyond fingerprints
journal, August 2016
- Kearnes, Steven; McCloskey, Kevin; Berndl, Marc
- Journal of Computer-Aided Molecular Design, Vol. 30, Issue 8
Getting the Right Answers for the Right Reasons: Toward Predictive Molecular Simulations of Water with Many-Body Potential Energy Functions
journal, August 2016
- Paesani, Francesco
- Accounts of Chemical Research, Vol. 49, Issue 9
Quantum-chemical insights from deep tensor neural networks
journal, January 2017
- Schütt, Kristof T.; Arbabzadah, Farhad; Chmiela, Stefan
- Nature Communications, Vol. 8, Issue 1
Bypassing the Kohn-Sham equations with machine learning
journal, October 2017
- Brockherde, Felix; Vogt, Leslie; Li, Li
- Nature Communications, Vol. 8, Issue 1
MoleculeNet: a benchmark for molecular machine learning
journal, January 2018
- Wu, Zhenqin; Ramsundar, Bharath; Feinberg, Evan N.
- Chemical Science, Vol. 9, Issue 2
Comparison of permutationally invariant polynomials, neural networks, and Gaussian approximation potentials in representing water interactions through many-body expansions
journal, June 2018
- Nguyen, Thuong T.; Székely, Eszter; Imbalzano, Giulio
- The Journal of Chemical Physics, Vol. 148, Issue 24
The TensorMol-0.1 model chemistry: a neural network augmented with long-range physics
journal, January 2018
- Yao, Kun; Herr, John E.; Toth, David W.
- Chemical Science, Vol. 9, Issue 8
Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures
journal, June 2018
- Fujikake, So; Deringer, Volker L.; Lee, Tae Hoon
- The Journal of Chemical Physics, Vol. 148, Issue 24
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians
journal, October 2018
- Li, Haichen; Collins, Christopher; Tanha, Matteus
- Journal of Chemical Theory and Computation, Vol. 14, Issue 11
Transferable Machine-Learning Model of the Electron Density
journal, December 2018
- Grisafi, Andrea; Fabrizio, Alberto; Meyer, Benjamin
- ACS Central Science, Vol. 5, Issue 1
Deep Potential Molecular Dynamics: A Scalable Model with the Accuracy of Quantum Mechanics
journal, April 2018
- Zhang, Linfeng; Han, Jiequn; Wang, Han
- Physical Review Letters, Vol. 120, Issue 14
Improving the accuracy of Møller-Plesset perturbation theory with neural networks
journal, October 2017
- McGibbon, Robert T.; Taube, Andrew G.; Donchev, Alexander G.
- The Journal of Chemical Physics, Vol. 147, Issue 16
Transferability in Machine Learning for Electronic Structure via the Molecular Orbital Basis
journal, July 2018
- Welborn, Matthew; Cheng, Lixue; Miller, Thomas F.
- Journal of Chemical Theory and Computation, Vol. 14, Issue 9
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
970 Million Druglike Small Molecules for Virtual Screening in the Chemical Universe Database GDB-13
journal, July 2009
- Blum, Lorenz C.; Reymond, Jean-Louis
- Journal of the American Chemical Society, Vol. 131, Issue 25
Brueckner's Theory and the Method of Superposition of Configurations
journal, March 1958
- Nesbet, R. K.
- Physical Review, Vol. 109, Issue 5
Note on an Approximation Treatment for Many-Electron Systems
journal, October 1934
- Møller, Chr.; Plesset, M. S.
- Physical Review, Vol. 46, Issue 7
Intrinsic Atomic Orbitals: An Unbiased Bridge between Quantum Theory and Chemical Concepts
journal, October 2013
- Knizia, Gerald
- Journal of Chemical Theory and Computation, Vol. 9, Issue 11
Generalized Neural-Network Representation of High-Dimensional Potential-Energy Surfaces
journal, April 2007
- Behler, Jörg; Parrinello, Michele
- Physical Review Letters, Vol. 98, Issue 14
Construction of Some Molecular Orbitals to Be Approximately Invariant for Changes from One Molecule to Another
journal, April 1960
- Boys, S. F.
- Reviews of Modern Physics, Vol. 32, Issue 2
Localized Orbitals for NH 3 , C 2 H 4 , and C 2 H 2
journal, March 1967
- Kaldor, Uzi
- The Journal of Chemical Physics, Vol. 46, Issue 5
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
journal, August 2001
- Breiman, Leo
- Statistical Science, Vol. 16, Issue 3
Gaussian processes with built-in dimensionality reduction: Applications to high-dimensional uncertainty propagation
journal, September 2016
- Tripathy, Rohit; Bilionis, Ilias; Gonzalez, Marcial
- Journal of Computational Physics, Vol. 321
Advances in molecular quantum chemistry contained in the Q-Chem 4 program package
journal, September 2014
- Shao, Yihan; Gan, Zhengting; Epifanovsky, Evgeny
- Molecular Physics, Vol. 113, Issue 2
Accurate spin-dependent electron liquid correlation energies for local spin density calculations: a critical analysis
journal, August 1980
- Vosko, S. H.; Wilk, L.; Nusair, M.
- Canadian Journal of Physics, Vol. 58, Issue 8
Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density
journal, January 1988
- Lee, Chengteh; Yang, Weitao; Parr, Robert G.
- Physical Review B, Vol. 37, Issue 2
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
Ab Initio Calculation of Vibrational Absorption and Circular Dichroism Spectra Using Density Functional Force Fields
journal, November 1994
- Stephens, P. J.; Devlin, F. J.; Chabalowski, C. F.
- The Journal of Physical Chemistry, Vol. 98, Issue 45, p. 11623-11627
The influence of polarization functions on molecular orbital hydrogenation energies
journal, January 1973
- Hariharan, P. C.; Pople, J. A.
- Theoretica Chimica Acta, Vol. 28, Issue 3
Accurate sampling using Langevin dynamics
journal, May 2007
- Bussi, Giovanni; Parrinello, Michele
- Physical Review E, Vol. 75, Issue 5
Gaussian basis sets for use in correlated molecular calculations. I. The atoms boron through neon and hydrogen
journal, January 1989
- Dunning, Thom H.
- The Journal of Chemical Physics, Vol. 90, Issue 2
Local Treatment of Electron Correlation
journal, January 1993
- Saebo, S.
- Annual Review of Physical Chemistry, Vol. 44, Issue 1
On the Correlation Problem in Atomic and Molecular Systems. Calculation of Wavefunction Components in Ursell‐Type Expansion Using Quantum‐Field Theoretical Methods
journal, December 1966
- Čížek, Jiří
- The Journal of Chemical Physics, Vol. 45, Issue 11
Local treatment of electron correlation in coupled cluster theory
journal, April 1996
- Hampel, Claudia; Werner, Hans‐Joachim
- The Journal of Chemical Physics, Vol. 104, Issue 16
Non-iterative fifth-order triple and quadruple excitation energy corrections in correlated methods
journal, February 1990
- Bartlett, Rodney J.; Watts, J. D.; Kucharski, S. A.
- Chemical Physics Letters, Vol. 165, Issue 6
Low-order scaling local electron correlation methods. III. Linear scaling local perturbative triples correction ( T )
journal, December 2000
- Schütz, Martin
- The Journal of Chemical Physics, Vol. 113, Issue 22
Fast Hartree–Fock theory using local density fitting approximations
journal, November 2004
- Polly, Robert; Werner *, Hans-Joachim; Manby, Frederick R.
- Molecular Physics, Vol. 102, Issue 21-22
Mathematical Contributions to the Theory of Evolution. III. Regression, Heredity, and Panmixia
journal, January 1896
- Pearson, K.
- Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 187, Issue 0
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
Localization: theory and experiment
journal, December 1993
- Kramer, B.; MacKinnon, A.
- Reports on Progress in Physics, Vol. 56, Issue 12
miRNALoc: predicting miRNA subcellular localizations based on principal component scores of physico-chemical properties and pseudo compositions of di-nucleotides
journal, September 2020
- Meher, Prabina Kumar; Satpathy, Subhrajit; Rao, Atmakuri Ramakrishna
- Scientific Reports, Vol. 10, Issue 1
ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost
text, January 2017
- ,
- The University of North Carolina at Chapel Hill University Libraries
Gaussian approximation potential modeling of lithium intercalation in carbon nanostructures.
text, January 2018
- Fujikake, So; Deringer, Volker; Lee, Taehoon
- Apollo - University of Cambridge Repository
Machine learning of molecular electronic properties in chemical compound space
text, January 2013
- Montavon, Grégoire; Rupp, Matthias; Gobre, Vivekanand
- ETH Zurich
Development of the Colle-Salvetti correlation-energy formula into a functional of the electron density
text, January 1988
- Robert, Parr,; Chengteh, Lee,; Weitao, Yang,
- The University of North Carolina at Chapel Hill University Libraries
Fast and accurate modeling of molecular atomization energies with machine learning
text, January 2012
- Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert
- American Physical Society
Accelerated Discovery of Metallic Glasses through Iteration of Machine Learning and High-Throughput Experiments
dataset, January 2018
- Fang, Ren; Ward, Logan; Williams, Travis
- Materials Data Facility
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach
text, January 2015
- Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias
- American Chemical Society
Works referencing / citing this record:
Unifying machine learning and quantum chemistry with a deep neural network for molecular wavefunctions
journal, November 2019
- Schütt, K. T.; Gastegger, M.; Tkatchenko, A.
- Nature Communications, Vol. 10, Issue 1
Deep learning for molecular design—a review of the state of the art
journal, January 2019
- Elton, Daniel C.; Boukouvalas, Zois; Fuge, Mark D.
- Molecular Systems Design & Engineering, Vol. 4, Issue 4
Machine-learned electron correlation model based on correlation energy density at complete basis set limit
journal, July 2019
- Nudejima, Takuro; Ikabata, Yasuhiro; Seino, Junji
- The Journal of Chemical Physics, Vol. 151, Issue 2
FCHL revisited: Faster and more accurate quantum machine learning
journal, January 2020
- Christensen, Anders S.; Bratholm, Lars A.; Faber, Felix A.
- The Journal of Chemical Physics, Vol. 152, Issue 4
Dataset’s chemical diversity limits the generalizability of machine learning predictions
journal, November 2019
- Glavatskikh, Marta; Leguy, Jules; Hunault, Gilles
- Journal of Cheminformatics, Vol. 11, Issue 1
Synergistic Approach of Ultrafast Spectroscopy and Molecular Simulations in the Characterization of Intramolecular Charge Transfer in Push-Pull Molecules
journal, January 2020
- Patrizi, Barbara; Cozza, Concetta; Pietropaolo, Adriana
- Molecules, Vol. 25, Issue 2