Skip to main content
OSTI.GOVU.S. Department of Energy Office of Scientific and Technical Information
U.S. Department of Energy
Office of Scientific and Technical Information
 

Machine Learning of Parameters for Accurate Semiempirical Quantum Chemical Calculations

Journal Article · · Journal of Chemical Theory and Computation
; ;
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.
Research Organization:
Argonne National Laboratory (ANL)
Sponsoring Organization:
Swiss National Science Foundation (SNSF); Argonne National Laboratory - Argonne Leadership Computing Facility
DOE Contract Number:
AC02-06CH11357
OSTI ID:
1392016
Journal Information:
Journal of Chemical Theory and Computation, Journal Name: Journal of Chemical Theory and Computation Journal Issue: 5 Vol. 11; ISSN 1549-9618
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English

References (30)

High-Throughput Virtual Screening Using Quantum Mechanical Probes: Discovery of Selective Kinase Inhibitors journal June 2010
An Algorithm for Least-Squares Estimation of Nonlinear Parameters journal June 1963
Identification and design principles of low hole effective mass p-type transparent conducting oxides journal August 2013
“Learn on the Fly”: A Hybrid Classical and Quantum-Mechanical Molecular Dynamics Simulation journal October 2004
Comment on “Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning” journal August 2012
Data-mined similarity function between material compositions journal December 2013
Quantum chemistry structures and properties of 134 kilo molecules journal August 2014
MNDO-Like Semiempirical Molecular Orbital Theory and Its Application to Large Systems book July 2011
Commentary: The Materials Project: A materials genome approach to accelerating materials innovation journal July 2013
A method for the solution of certain non-linear problems in least squares journal January 1944
Challenges for Density Functional Theory journal December 2011
Direct dynamics calculations with NDDO (neglect of diatomic differential overlap) molecular orbital theory with specific reaction parameters journal June 1991
First principles view on chemical compound space: Gaining rigorous atomistic control of molecular properties journal February 2013
Towards the computational design of solid catalysts journal April 2009
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
Orthogonalization corrections for semiempirical methods journal April 2000
Benchmarking Semiempirical Methods for Thermochemistry, Kinetics, and Noncovalent Interactions: OMx Methods Are Almost As Accurate and Robust As DFT-GGA Methods for Organic Molecules journal August 2011
Rupp et al. Reply: journal August 2012
Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies journal July 2013
Virtual screening: an endless staircase? journal April 2010
The Many Roles of Computation in Drug Discovery journal March 2004
Gaussian-4 theory using reduced order perturbation theory journal September 2007
A MNDO study of carbon clusters with specifically fitted parameters journal November 1995
Fast and Accurate Modeling of Molecular Atomization Energies with Machine Learning journal January 2012
The Harvard Clean Energy Project: Large-Scale Computational Screening and Design of Organic Photovoltaics on the World Community Grid journal August 2011
Quantum chemistry structures and properties of 134 kilo molecules text January 2014
“Learn on the Fly”: A Hybrid Classical and Quantum-Mechanical Molecular Dynamics Simulation journal October 2004
Specific Reaction Path Hamiltonian for Proton Transfer in Water: Reparameterized Semiempirical Models journal May 2013
Quantifying and Assessing the Effect of Chemical Symmetry in Metabolic Pathways journal September 2012
Enumeration of 166 Billion Organic Small Molecules in the Chemical Universe Database GDB-17 journal November 2012

Cited By (19)

Deep learning for computational chemistry journal March 2017
Machine Learning a General-Purpose Interatomic Potential for Silicon journal December 2018
Semiempirical Quantum-Chemical Methods with Orthogonalization and Dispersion Corrections journal January 2019
Machine Learning, Quantum Chemistry, and Chemical Space book January 2017
Structure-based sampling and self-correcting machine learning for accurate calculations of potential energy surfaces and vibrational levels journal June 2017
Machine Learning a General-Purpose Interatomic Potential for Silicon text January 2018
A Density Functional Tight Binding Layer for Deep Learning of Chemical Hamiltonians preprint January 2018
Quantitative Analysis of Quantum Mechanics/Molecular Mechanics Boundary Artifacts and the correction in Adaptive QM/MM Methods posted_content March 2019
Semiempirical molecular orbital models based on the neglect of diatomic differential overlap approximation journal October 2018
Semiempirical Molecular Orbital Models based on the Neglect of Diatomic Differential Overlap Approximation text January 2018
Read between the Molecules: Computational Insights into Organic Semiconductors journal November 2018
From DFT to machine learning: recent approaches to materials science–a review journal May 2019
Deep Learning for Deep Chemistry: Optimizing the Prediction of Chemical Patterns journal November 2019
Deep Learning for Computational Chemistry preprint January 2017
MLatom : A program package for quantum chemical research assisted by machine learning journal June 2019
Endothelin-1 and cell Proliferation in lung Organ Cultures journal November 1996
A new approach for the prediction of partition functions using machine learning techniques journal July 2018
Deterministic and Statistical Approaches to Quantum Chemistry text January 2020
Machine learning prediction of interaction energies in rigid water clusters journal January 2018

Similar Records

Machine learning of parameters for accurate semiempirical quantum chemical calculations
Journal Article · Mon Apr 13 20:00:00 EDT 2015 · Journal of Chemical Theory and Computation · OSTI ID:1214088

Related Subjects