Frank Noé, Alexandre Tkatchenko, Klaus-Robert Müller, Cecilia Clementi
{"title":"分子模拟的机器学习。","authors":"Frank Noé, Alexandre Tkatchenko, Klaus-Robert Müller, Cecilia Clementi","doi":"10.1146/annurev-physchem-042018-052331","DOIUrl":null,"url":null,"abstract":"<p><p>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.</p>","PeriodicalId":7967,"journal":{"name":"Annual review of physical chemistry","volume":null,"pages":null},"PeriodicalIF":11.7000,"publicationDate":"2020-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1146/annurev-physchem-042018-052331","citationCount":"430","resultStr":"{\"title\":\"Machine Learning for Molecular Simulation.\",\"authors\":\"Frank Noé, Alexandre Tkatchenko, Klaus-Robert Müller, Cecilia Clementi\",\"doi\":\"10.1146/annurev-physchem-042018-052331\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>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.</p>\",\"PeriodicalId\":7967,\"journal\":{\"name\":\"Annual review of physical chemistry\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":11.7000,\"publicationDate\":\"2020-04-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://sci-hub-pdf.com/10.1146/annurev-physchem-042018-052331\",\"citationCount\":\"430\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Annual review of physical chemistry\",\"FirstCategoryId\":\"92\",\"ListUrlMain\":\"https://doi.org/10.1146/annurev-physchem-042018-052331\",\"RegionNum\":1,\"RegionCategory\":\"化学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2020/2/24 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"CHEMISTRY, PHYSICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Annual review of physical chemistry","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1146/annurev-physchem-042018-052331","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2020/2/24 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"CHEMISTRY, PHYSICAL","Score":null,"Total":0}
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.
期刊介绍:
The Annual Review of Physical Chemistry has been published since 1950 and is a comprehensive resource for significant advancements in the field. It encompasses various sub-disciplines such as biophysical chemistry, chemical kinetics, colloids, electrochemistry, geochemistry and cosmochemistry, chemistry of the atmosphere and climate, laser chemistry and ultrafast processes, the liquid state, magnetic resonance, physical organic chemistry, polymers and macromolecules, and others.