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…

• NS
  National Science Foundation

  Award: DE-AC02-06CH11357
• UD
  U.S. Department of Energy

  Awards: AC02-06CH11357, DE-AC02, 06CH11357, DE-AC02-06CH11357, DE-AC02-
• DF
  Deutsche Forschungsgemeinschaft

  Awards: DE-AC02-06CH11357, MU 987/20
• SN
  Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung

  Award: PP00P2_138932
• NR
  National Research Foundation of Korea
• ES
  Einstein Stiftung Berlin
• OO
  Office of Science

  Awards: DE-AC02-06CH11357, DE-AC02, 06CH11357, AC02-06CH11357
• NS
  Natural Sciences and Engineering Research Council of Canada

  Award: DE-AC02-06CH11357
• ER
  European Research Council
• AN
  Argonne National Laboratory

  Awards: DE-AC02, 06CH11357, AC02-06CH11357