skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Abstract

Chemically accurate and comprehensive studies of the virtual space of all possible molecules are severely limited by the computational cost of quantum chemistry. We introduce a composite strategy that adds machine learning corrections to computationally inexpensive approximate legacy quantum methods. After training, highly accurate predictions of enthalpies, free energies, entropies, and electron correlation energies are possible, for significantly larger molecular sets than used for training. For thermochemical properties of up to 16k isomers of C7H10O2 we present numerical evidence that chemical accuracy can be reached. We also predict electron correlation energy in post Hartree-Fock methods, at the computational cost of HartreeFock, and we establish a qualitative relationship between molecular entropy and electron correlation. The transferability of our approach is demonstrated, using semiempirical quantum chemistry and machine learning models trained on 1 and 10% of 134k organic molecules, to reproduce enthalpies of all remaining molecules at density functional theory level of accuracy.

Authors:
; ; ;
Publication Date:
Research Org.:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org.:
Argonne National Laboratory - Argonne Leadership Computing Facility
OSTI Identifier:
1392925
DOE Contract Number:  
AC02-06CH11357
Resource Type:
Journal Article
Journal Name:
Journal of Chemical Theory and Computation
Additional Journal Information:
Journal Volume: 11; Journal Issue: 5; Journal ID: ISSN 1549-9618
Publisher:
American Chemical Society
Country of Publication:
United States
Language:
English

Citation Formats

Ramakrishnan, Raghunathan, Dral, Pavlo O., Rupp, Matthias, and von Lilienfeld, O. Anatole. Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. United States: N. p., 2015. Web. doi:10.1021/acs.jctc.5b00099.
Ramakrishnan, Raghunathan, Dral, Pavlo O., Rupp, Matthias, & von Lilienfeld, O. Anatole. Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach. United States. doi:10.1021/acs.jctc.5b00099.
Ramakrishnan, Raghunathan, Dral, Pavlo O., Rupp, Matthias, and von Lilienfeld, O. Anatole. Tue . "Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach". United States. doi:10.1021/acs.jctc.5b00099.
@article{osti_1392925,
title = {Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach},
author = {Ramakrishnan, Raghunathan and Dral, Pavlo O. and Rupp, Matthias and von Lilienfeld, O. Anatole},
abstractNote = {Chemically accurate and comprehensive studies of the virtual space of all possible molecules are severely limited by the computational cost of quantum chemistry. We introduce a composite strategy that adds machine learning corrections to computationally inexpensive approximate legacy quantum methods. After training, highly accurate predictions of enthalpies, free energies, entropies, and electron correlation energies are possible, for significantly larger molecular sets than used for training. For thermochemical properties of up to 16k isomers of C7H10O2 we present numerical evidence that chemical accuracy can be reached. We also predict electron correlation energy in post Hartree-Fock methods, at the computational cost of HartreeFock, and we establish a qualitative relationship between molecular entropy and electron correlation. The transferability of our approach is demonstrated, using semiempirical quantum chemistry and machine learning models trained on 1 and 10% of 134k organic molecules, to reproduce enthalpies of all remaining molecules at density functional theory level of accuracy.},
doi = {10.1021/acs.jctc.5b00099},
journal = {Journal of Chemical Theory and Computation},
issn = {1549-9618},
number = 5,
volume = 11,
place = {United States},
year = {2015},
month = {5}
}