Machine Learning for Molecular Simulation

• Published in: Annual review of physical chemistry Vol. 71; no. 1; pp. 361 - 390
• Main Authors: Noé, Frank, Tkatchenko, Alexandre, Müller, Klaus-Robert, Clementi, Cecilia
• Format: Journal Article
• Language: English
• Published: United States Annual Reviews 20.04.2020; Annual Reviews, Inc
• Subjects: coarse graining; Computer simulation; Free energy; kinetics; Machine learning; Molecular dynamics; Molecular physics; molecular simulation; Neural networks; quantum mechanics; Simulation; Thermodynamic equilibrium; coarse graining; quantum mechanics; kinetics; machine learning; molecular simulation; neural networks
• ISSN: 0066-426X; 1545-1593
• DOI: 10.1146/annurev-physchem-042018-052331

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.