skip to main content


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

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. The same representation allows us to predict accurate electronic properties of molecules, such as their polarizability and molecular frontier orbital energies.
 [1] ;  [2] ;  [3] ;  [2] ;  [4] ;  [5] ;  [1]
  1. Max-Planck-Gesellschaft, Berlin (Germany)
  2. Techincal Univ. of Berlin, Berlin (Germany)
  3. Univ. of Basel, Basel (Switzerland)
  4. Univ. of Basel, Basel (Switzerland); Argonne National Lab. (ANL), Argonne, IL (United States)
  5. Techincal Univ. of Berlin, Berlin (Germany); Korea Univ., Seoul (Korea)
Publication Date:
Grant/Contract Number:
AC02-06CH11357; NSF PP00P2_138932
Accepted Manuscript
Journal Name:
Journal of Physical Chemistry Letters
Additional Journal Information:
Journal Volume: 6; Journal Issue: 12; Journal ID: ISSN 1948-7185
American Chemical Society
Research Org:
Argonne National Lab. (ANL), Argonne, IL (United States)
Sponsoring Org:
USDOE Office of Science (SC)
Country of Publication:
United States
74 ATOMIC AND MOLECULAR PHYSICS; chemical compound space; machine learning; atomization energies; molecular properties; many-body potentials
OSTI Identifier: