Machine learning of parameters for accurate semiempirical quantum chemical calculations

Dral, Pavlo O.; von Lilienfeld, O. Anatole; Thiel, Walter

doi:10.1021/acs.jctc.5b00141

Title: Machine learning of parameters for accurate semiempirical quantum chemical calculations

Journal Article · Tue Apr 14 00:00:00 EDT 2015 · Journal of Chemical Theory and Computation

DOI:https://doi.org/10.1021/acs.jctc.5b00141· OSTI ID:1214088

Dral, Pavlo O. ^[1]; von Lilienfeld, O. Anatole ^[2]; Thiel, Walter ^[3]

Max-Planck Institute fur Kohlenforschung, Mulheim an der Ruhr (Germany)
Univ. of Basel, Basel (Switzerland); Argonne National Lab. (ANL), Argonne, IL (United States)
Max-Planck Institute for Kohlenforschung, Mulheim an der Ruhr (Germany)

We investigate possible improvements in the accuracy of semiempirical quantum chemistry (SQC) methods through the use of machine learning (ML) models for the parameters. For a given class of compounds, ML techniques require sufficiently large training sets to develop ML models that can be used for adapting SQC parameters to reflect changes in molecular composition and geometry. The ML-SQC approach allows the automatic tuning of SQC parameters for individual molecules, thereby improving the accuracy without deteriorating transferability to molecules with molecular descriptors very different from those in the training set. The performance of this approach is demonstrated for the semiempirical OM2 method using a set of 6095 constitutional isomers C₇H₁₀O₂, for which accurate ab initio atomization enthalpies are available. The ML-OM2 results show improved average accuracy and a much reduced error range compared with those of standard OM2 results, with mean absolute errors in atomization enthalpies dropping from 6.3 to 1.7 kcal/mol. They are also found to be superior to the results from specific OM2 reparameterizations (rOM2) for the same set of isomers. The ML-SQC approach thus holds promise for fast and reasonably accurate high-throughput screening of materials and molecules.

View Accepted Manuscript (DOE)

Cite

Export

Save

Research Organization:: Argonne National Laboratory (ANL), Argonne, IL (United States)

Sponsoring Organization:: USDOE Office of Science (SC)

Grant/Contract Number:: AC02-06CH11357

OSTI ID:: 1214088

Journal Information:: Journal of Chemical Theory and Computation, Vol. 11, Issue 5; ISSN 1549-9618

Publisher:: American Chemical SocietyCopyright Statement

Country of Publication:: United States

Language:: English

Citation Metrics:

Cited by: 73 works

Citation information provided by
Web of Science

References (28)

The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid Hachmann, Johannes; Olivares-Amaya, Roberto; Atahan-Evrenk, Sule The Journal of Physical Chemistry Letters, Vol. 2, Issue 17 https://doi.org/10.1021/jz200866s	journal	August 2011
Data-mined similarity function between material compositions Yang, Lusann; Ceder, Gerbrand Physical Review B, Vol. 88, Issue 22 https://doi.org/10.1103/PhysRevB.88.224107	journal	December 2013
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy APL Materials, Vol. 1, Issue 1 https://doi.org/10.1063/1.4812323	journal	July 2013
The Many Roles of Computation in Drug Discovery Jorgensen, W. L. Science, Vol. 303, Issue 5665 https://doi.org/10.1126/science.1096361	journal	March 2004
Towards the computational design of solid catalysts Nørskov, J.; Bligaard, T.; Rossmeisl, J. Nature Chemistry, Vol. 1, Issue 1, p. 37-46 https://doi.org/10.1038/nchem.121	journal	April 2009
Virtual screening: an endless staircase? Schneider, Gisbert Nature Reviews Drug Discovery, Vol. 9, Issue 4 https://doi.org/10.1038/nrd3139	journal	April 2010
Identification and design principles of low hole effective mass p-type transparent conducting oxides Hautier, Geoffroy; Miglio, Anna; Ceder, Gerbrand Nature Communications, Vol. 4, Issue 1 https://doi.org/10.1038/ncomms3292	journal	August 2013
High-Throughput Virtual Screening Using Quantum Mechanical Probes: Discovery of Selective Kinase Inhibitors Zhou, Ting; Caflisch, Amedeo ChemMedChem, Vol. 5, Issue 7 https://doi.org/10.1002/cmdc.201000085	journal	June 2010
MNDO-Like Semiempirical Molecular Orbital Theory and Its Application to Large Systems Clark, Timothy; Stewart, James J. P. Computational Methods for Large Systems: Electronic Structure Approaches for Biotechnology and Nanotechnology https://doi.org/10.1002/9780470930779.ch8	book	July 2011
Benchmarking Semiempirical Methods for Thermochemistry, Kinetics, and Noncovalent Interactions: OMx Methods Are Almost As Accurate and Robust As DFT-GGA Methods for Organic Molecules Korth, Martin; Thiel, Walter Journal of Chemical Theory and Computation, Vol. 7, Issue 9 https://doi.org/10.1021/ct200434a	journal	August 2011
A MNDO study of carbon clusters with specifically fitted parameters Tseng, Shiuh-ping; Shen, Min-yi; Yu, Chin-hui Theoretica Chimica Acta, Vol. 92, Issue 5 https://doi.org/10.1007/BF01113867	journal	November 1995
Direct dynamics calculations with NDDO (neglect of diatomic differential overlap) molecular orbital theory with specific reaction parameters Gonzalez-Lafont, Angels; Truong, Thanh N.; Truhlar, Donald G. The Journal of Physical Chemistry, Vol. 95, Issue 12 https://doi.org/10.1021/j100165a009	journal	June 1991
Specific Reaction Path Hamiltonian for Proton Transfer in Water: Reparameterized Semiempirical Models Wu, Xin; Thiel, Walter; Pezeshki, Soroosh Journal of Chemical Theory and Computation, Vol. 9, Issue 6 https://doi.org/10.1021/ct400224n	journal	May 2013
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 108, Issue 5 https://doi.org/10.1103/PhysRevLett.108.058301	journal	January 2012
First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties von Lilienfeld, O. Anatole International Journal of Quantum Chemistry, Vol. 113, Issue 12 https://doi.org/10.1002/qua.24375	journal	February 2013
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies Hansen, Katja; Montavon, Grégoire; Biegler, Franziska Journal of Chemical Theory and Computation, Vol. 9, Issue 8 https://doi.org/10.1021/ct400195d	journal	July 2013
Comment on “Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning” Moussa, Jonathan E. Physical Review Letters, Vol. 109, Issue 5 https://doi.org/10.1103/PhysRevLett.109.059801	journal	August 2012
Rupp et al. Reply: Rupp, Matthias; Tkatchenko, Alexandre; Müller, Klaus-Robert Physical Review Letters, Vol. 109, Issue 5 https://doi.org/10.1103/PhysRevLett.109.059802	journal	August 2012
Gaussian-4 theory using reduced order perturbation theory Curtiss, Larry A.; Redfern, Paul C.; Raghavachari, Krishnan The Journal of Chemical Physics, Vol. 127, Issue 12 https://doi.org/10.1063/1.2770701	journal	September 2007
Quantum chemistry structures and properties of 134 kilo molecules Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias Scientific Data, Vol. 1, Issue 1 https://doi.org/10.1038/sdata.2014.22	journal	August 2014
Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17 Ruddigkeit, Lars; van Deursen, Ruud; Blum, Lorenz C. Journal of Chemical Information and Modeling, Vol. 52, Issue 11 https://doi.org/10.1021/ci300415d	journal	November 2012
Orthogonalization corrections for semiempirical methods Weber, Wolfgang; Thiel, Walter Theoretical Chemistry Accounts: Theory, Computation, and Modeling (Theoretica Chimica Acta), Vol. 103, Issue 6 https://doi.org/10.1007/s002149900083	journal	April 2000
A method for the solution of certain non-linear problems in least squares Levenberg, Kenneth Quarterly of Applied Mathematics, Vol. 2, Issue 2 https://doi.org/10.1090/qam/10666	journal	January 1944
An Algorithm for Least-Squares Estimation of Nonlinear Parameters Marquardt, Donald W. Journal of the Society for Industrial and Applied Mathematics, Vol. 11, Issue 2 https://doi.org/10.1137/0111030	journal	June 1963
Challenges for Density Functional Theory Cohen, Aron J.; Mori-Sánchez, Paula; Yang, Weitao Chemical Reviews, Vol. 112, Issue 1 https://doi.org/10.1021/cr200107z	journal	December 2011
Quantifying and Assessing the Effect of Chemical Symmetry in Metabolic Pathways Zhou, Wanding; Nakhleh, Luay Journal of Chemical Information and Modeling, Vol. 52, Issue 10 https://doi.org/10.1021/ci300259u	journal	September 2012
“Learn on the Fly”: A Hybrid Classical and Quantum-Mechanical Molecular Dynamics Simulation Csányi, Gabor; Albaret, T.; Payne, M. C. Physical Review Letters, Vol. 93, Issue 17 https://doi.org/10.1103/physrevlett.93.175503	journal	October 2004
Quantum chemistry structures and properties of 134 kilo molecules Raghunathan, Ramakrishnan,; O., Dral, Pavlo; Matthias, Rupp, Springer Nature https://doi.org/10.5451/unibas-ep43357	text	January 2014

Cited By (18)

Machine learning prediction of interaction energies in rigid water clusters Bose, Samik; Dhawan, Diksha; Nandi, Sutanu Physical Chemistry Chemical Physics, Vol. 20, Issue 35 https://doi.org/10.1039/c8cp03138j	journal	January 2018
Structure-based sampling and self-correcting machine learning for accurate calculations of potential energy surfaces and vibrational levels Dral, Pavlo O.; Owens, Alec; Yurchenko, Sergei N. The Journal of Chemical Physics, Vol. 146, Issue 24 https://doi.org/10.1063/1.4989536	journal	June 2017
Machine Learning, Quantum Chemistry, and Chemical Space Ramakrishnan, Raghunathan; von Lilienfeld, O. Anatole Reviews in Computational Chemistry, Vol. 30 https://doi.org/10.1002/9781119356059.ch5	book	January 2017
A new approach for the prediction of partition functions using machine learning techniques Desgranges, Caroline; Delhommelle, Jerome The Journal of Chemical Physics, Vol. 149, Issue 4 https://doi.org/10.1063/1.5037098	journal	July 2018
MLatom : A program package for quantum chemical research assisted by machine learning Dral, Pavlo O. Journal of Computational Chemistry, Vol. 40, Issue 26 https://doi.org/10.1002/jcc.26004	journal	June 2019
Semiempirical molecular orbital models based on the neglect of diatomic differential overlap approximation Husch, Tamara; Vaucher, Alain C.; Reiher, Markus International Journal of Quantum Chemistry, Vol. 118, Issue 24 https://doi.org/10.1002/qua.25799	journal	October 2018
Deep learning for computational chemistry Goh, Garrett B.; Hodas, Nathan O.; Vishnu, Abhinav Journal of Computational Chemistry, Vol. 38, Issue 16 https://doi.org/10.1002/jcc.24764	journal	March 2017
From DFT to machine learning: recent approaches to materials science–a review Schleder, Gabriel R.; Padilha, Antonio C. M.; Acosta, Carlos Mera Journal of Physics: Materials, Vol. 2, Issue 3 https://doi.org/10.1088/2515-7639/ab084b	journal	May 2019
Machine Learning a General-Purpose Interatomic Potential for Silicon Bartók, Ap; Kermode, J.; Bernstein, N. Apollo - University of Cambridge Repository https://doi.org/10.17863/cam.34909	text	January 2018
Deep Learning for Computational Chemistry Goh, Garrett B.; Hodas, Nathan O.; Vishnu, Abhinav arXiv https://doi.org/10.48550/arxiv.1701.04503	preprint	January 2017
Semiempirical Molecular Orbital Models based on the Neglect of Diatomic Differential Overlap Approximation Husch, Tamara; Vaucher, Alain C.; Reiher, Markus arXiv https://doi.org/10.48550/arxiv.1806.06147	text	January 2018
Semiempirical Quantum-Chemical Methods with Orthogonalization and Dispersion Corrections Dral, Pavlo O.; Wu, Xin; Thiel, Walter Journal of Chemical Theory and Computation, Vol. 15, Issue 3 https://doi.org/10.1021/acs.jctc.8b01265	journal	January 2019
Read between the Molecules: Computational Insights into Organic Semiconductors Gryn’ova, Ganna; Lin, Kun-Han; Corminboeuf, Clémence Journal of the American Chemical Society, Vol. 140, Issue 48 https://doi.org/10.1021/jacs.8b07985	journal	November 2018
Endothelin-1 and cell Proliferation in lung Organ Cultures Ricagna, Fabio; Miller, Virginia M.; Tazelaar, Henry D. Transplantation, Vol. 62, Issue 10 https://doi.org/10.1097/00007890-199611270-00018	journal	November 1996
Quantitative Analysis of Quantum Mechanics/Molecular Mechanics Boundary Artifacts and the correction in Adaptive QM/MM Methods Watanabe, Hiroshi C.; Cui, Qiang ChemRxiv https://doi.org/10.26434/chemrxiv.7744103.v2	posted_content	March 2019
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns Cova, Tânia F. G. G.; Pais, Alberto A. C. C. Frontiers in Chemistry, Vol. 7 https://doi.org/10.3389/fchem.2019.00809	journal	November 2019
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians Li, Haichen; Collins, Christopher; Tanha, Matteus arXiv https://doi.org/10.48550/arxiv.1808.04526	preprint	January 2018
Deterministic and Statistical Approaches to Quantum Chemistry Alberto, Fabrizio, Lausanne, EPFL https://doi.org/10.5075/epfl-thesis-7808	text	January 2020

Similar Records

Machine Learning of Parameters for Accurate Semiempirical Quantum Chemical Calculations

Journal Article · Tue May 12 00:00:00 EDT 2015 · Journal of Chemical Theory and Computation · OSTI ID:1214088

Dral, Pavlo O.; von Lilienfeld, O. Anatole; Thiel, Walter

Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach

Journal Article · Fri Apr 10 00:00:00 EDT 2015 · Journal of Chemical Theory and Computation · OSTI ID:1214088

Ramakrishnan, Raghunathan; Dral, Pavlo O.; Rupp, Matthias; +1 more

Deep learning of dynamically responsive chemical Hamiltonians with semiempirical quantum mechanics

Journal Article · Tue Jul 05 00:00:00 EDT 2022 · Proceedings of the National Academy of Sciences of the United States of America · OSTI ID:1214088

Zhou, Guoqing; Lubbers, Nicholas; Barros, Kipton; +2 more

Related Subjects

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CHEMISTRY

Title: Machine learning of parameters for accurate semiempirical quantum chemical calculations

Citation Formats

References (28)

Cited By (18)

Similar Records

Related Subjects