Reference : Machine learning predictions of molecular properties: Accurate many-body potentials a...
Scientific journals : Article
Physical, chemical, mathematical & earth Sciences : Physics
http://hdl.handle.net/10993/25682
Machine learning predictions of molecular properties: Accurate many-body potentials and nonlocality in chemical space
English
Hansen, K. [Fritz-Haber-Institut der Max-Planck-Gesellschaft, Faradayweg 4-6, Berlin, Germany]
Biegler, F. [Machine Learning Group, Technical University of Berlin, Marchstr. 23, Berlin, Germany]
Ramakrishnan, R. [Department of Chemistry, National Center for Computational Design and Discovery of Novel Materials, University of Basel, Klingelbergstrasse 80, Basel, Switzerland]
Pronobis, W. [Machine Learning Group, Technical University of Berlin, Marchstr. 23, Berlin, Germany]
Von Lilienfeld, O. A. [Department of Chemistry, National Center for Computational Design and Discovery of Novel Materials, University of Basel, Klingelbergstrasse 80, Basel, Switzerland, Argonne Leadership Computing Facility, Argonne National Laboratory, 9700 South Cass Avenue, Argonne, IL, United States]
Müller, K.-R. [Machine Learning Group, Technical University of Berlin, Marchstr. 23, Berlin, Germany, Department of Brain and Cognitive Engineering, Korea University, Anam-dong, Seongbuk-ku, Seoul, South Korea]
Tkatchenko, Alexandre mailto [Fritz-Haber-Institut der Max-Planck-Gesellschaft, Faradayweg 4-6, Berlin, Germany]
2015
Journal of Physical Chemistry Letters
American Chemical Society
6
12
2326-2331
Yes (verified by ORBilu)
International
1948-7185
[en] Artificial intelligence ; Atomization ; Chemical compounds ; Density functional theory ; Electronic properties ; Forecasting ; Learning systems ; Molecules ; Atomization energies ; Frontier orbital energies ; Many-body interactions ; Many-body potentials ; Molecular properties ; Pharmaceutical industry ; Rational compound designs ; Sophisticated machines ; Chemical bonds
[en] 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. © 2015 American Chemical Society.
MU 987/20, DFG, Natural Sciences and Engineering Research Council of Canada; ERC, Natural Sciences and Engineering Research Council of Canada; NSERC, Natural Sciences and Engineering Research Council of Canada; PP00P2-138932, SNSF, Natural Sciences and Engineering Research Council of Canada
http://hdl.handle.net/10993/25682
10.1021/acs.jpclett.5b00831

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Open access
Interaction Potentials in Molecules and Non-Local Information in Chemical Space.pdfAuthor postprint411.98 kBView/Open

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.