Machine learning for molecular simulation

Frank Noé, Alexandre Tkatchenko, Klaus Robert Müller, Cecilia Clementi

Research output: Contribution to journalReview article

11 Citations (Scopus)

Abstract

Machine learning (ML) is transforming all areas of science. The complex and time-consuming calculations in molecular simulations are particularly suitable for an ML revolution and have already been profoundly affected by the application of existing ML methods. Here we review recent ML methods for molecular simulation, with particular focus on (deep) neural networks for the prediction of quantum-mechanical energies and forces, on coarse-grained molecular dynamics, on the extraction of free energy surfaces and kinetics, and on generative network approaches to sample molecular equilibrium structures and compute thermodynamics. To explain these methods and illustrate open methodological problems, we review some important principles of molecular physics and describe how they can be incorporated into ML structures. Finally, we identify and describe a list of open challenges for the interface between ML and molecular simulation.

Original languageEnglish
Pages (from-to)361-390
Number of pages30
JournalAnnual Review of Physical Chemistry
Volume71
DOIs
Publication statusPublished - 2020 Apr 20

Keywords

  • coarse graining
  • kinetics
  • machine learning
  • molecular simulation
  • neural networks
  • quantum mechanics

ASJC Scopus subject areas

  • Physical and Theoretical Chemistry

Fingerprint Dive into the research topics of 'Machine learning for molecular simulation'. Together they form a unique fingerprint.

  • Cite this