Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space

Katja Hansen, Franziska Biegler, Raghunathan Ramakrishnan, Wiktor Pronobis, O. Anatole Von Lilienfeld, Klaus Muller, Alexandre Tkatchenko

Research output: Contribution to journalArticle

163 Citations (Scopus)

Abstract

Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the "holy grail" of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.

Original languageEnglish
Pages (from-to)2326-2331
Number of pages6
JournalJournal of Physical Chemistry Letters
Volume6
Issue number12
DOIs
Publication statusPublished - 2015 Jun 18

Fingerprint

Learning systems
Chemical Industry
Benchmarking
Molecules
Drug Industry
Atoms
Chemical compounds
Geometry
Atomization
Molecular orbitals
Electronic properties
Drug products
Density functional theory
Pharmaceutical Preparations
Machine Learning
Industry

Keywords

  • atomization energies
  • chemical compound space
  • machine learning
  • many-body potentials
  • molecular properties

ASJC Scopus subject areas

  • Materials Science(all)

Cite this

Hansen, K., Biegler, F., Ramakrishnan, R., Pronobis, W., Von Lilienfeld, O. A., Muller, K., & Tkatchenko, A. (2015). Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space. Journal of Physical Chemistry Letters, 6(12), 2326-2331. https://doi.org/10.1021/acs.jpclett.5b00831

Machine learning predictions of molecular properties : Accurate many-body potentials and nonlocality in chemical space. / Hansen, Katja; Biegler, Franziska; Ramakrishnan, Raghunathan; Pronobis, Wiktor; Von Lilienfeld, O. Anatole; Muller, Klaus; Tkatchenko, Alexandre.

In: Journal of Physical Chemistry Letters, Vol. 6, No. 12, 18.06.2015, p. 2326-2331.

Research output: Contribution to journalArticle

Hansen, K, Biegler, F, Ramakrishnan, R, Pronobis, W, Von Lilienfeld, OA, Muller, K & Tkatchenko, A 2015, 'Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space', Journal of Physical Chemistry Letters, vol. 6, no. 12, pp. 2326-2331. https://doi.org/10.1021/acs.jpclett.5b00831
Hansen, Katja ; Biegler, Franziska ; Ramakrishnan, Raghunathan ; Pronobis, Wiktor ; Von Lilienfeld, O. Anatole ; Muller, Klaus ; Tkatchenko, Alexandre. / Machine learning predictions of molecular properties : Accurate many-body potentials and nonlocality in chemical space. In: Journal of Physical Chemistry Letters. 2015 ; Vol. 6, No. 12. pp. 2326-2331.
@article{4b539e22e47a4652ac4f2202e4fefbe2,
title = "Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space",
abstract = "Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the {"}holy grail{"} of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.",
keywords = "atomization energies, chemical compound space, machine learning, many-body potentials, molecular properties",
author = "Katja Hansen and Franziska Biegler and Raghunathan Ramakrishnan and Wiktor Pronobis and {Von Lilienfeld}, {O. Anatole} and Klaus Muller and Alexandre Tkatchenko",
year = "2015",
month = "6",
day = "18",
doi = "10.1021/acs.jpclett.5b00831",
language = "English",
volume = "6",
pages = "2326--2331",
journal = "Journal of Physical Chemistry Letters",
issn = "1948-7185",
publisher = "American Chemical Society",
number = "12",

}

TY - JOUR

T1 - Machine learning predictions of molecular properties

T2 - Accurate many-body potentials and nonlocality in chemical space

AU - Hansen, Katja

AU - Biegler, Franziska

AU - Ramakrishnan, Raghunathan

AU - Pronobis, Wiktor

AU - Von Lilienfeld, O. Anatole

AU - Muller, Klaus

AU - Tkatchenko, Alexandre

PY - 2015/6/18

Y1 - 2015/6/18

N2 - Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the "holy grail" of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.

AB - Simultaneously accurate and efficient prediction of molecular properties throughout chemical compound space is a critical ingredient toward rational compound design in chemical and pharmaceutical industries. Aiming toward this goal, we develop and apply a systematic hierarchy of efficient empirical methods to estimate atomization and total energies of molecules. These methods range from a simple sum over atoms, to addition of bond energies, to pairwise interatomic force fields, reaching to the more sophisticated machine learning approaches that are capable of describing collective interactions between many atoms or bonds. In the case of equilibrium molecular geometries, even simple pairwise force fields demonstrate prediction accuracy comparable to benchmark energies calculated using density functional theory with hybrid exchange-correlation functionals; however, accounting for the collective many-body interactions proves to be essential for approaching the "holy grail" of chemical accuracy of 1 kcal/mol for both equilibrium and out-of-equilibrium geometries. This remarkable accuracy is achieved by a vectorized representation of molecules (so-called Bag of Bonds model) that exhibits strong nonlocality in chemical space. In addition, the same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.

KW - atomization energies

KW - chemical compound space

KW - machine learning

KW - many-body potentials

KW - molecular properties

UR - http://www.scopus.com/inward/record.url?scp=84935014439&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84935014439&partnerID=8YFLogxK

U2 - 10.1021/acs.jpclett.5b00831

DO - 10.1021/acs.jpclett.5b00831

M3 - Article

C2 - 26113956

AN - SCOPUS:84935014439

VL - 6

SP - 2326

EP - 2331

JO - Journal of Physical Chemistry Letters

JF - Journal of Physical Chemistry Letters

SN - 1948-7185

IS - 12

ER -