@article{da797d41b0bd466f8600c28aafb338d9,
title = "OpenMM 8: Molecular Dynamics Simulation with Machine Learning Potentials",
abstract = "Machine learning plays an important and growing role in molecular simulation. The newest version of the OpenMM molecular dynamics toolkit introduces new features to support the use of machine learning potentials. Arbitrary PyTorch models can be added to a simulation and used to compute forces and energy. A higher-level interface allows users to easily model their molecules of interest with general purpose, pretrained potential functions. A collection of optimized CUDA kernels and custom PyTorch operations greatly improves the speed of simulations. We demonstrate these features in simulations of cyclin-dependent kinase 8 (CDK8) and the green fluorescent protein chromophore in water. Taken together, these features make it practical to use machine learning to improve the accuracy of simulations with only a modest increase in cost.",
author = "Peter Eastman and Raimondas Galvelis and Pel{\'a}ez, {Ra{\'u}l P.} and Abreu, {Charlles R.A.} and Farr, {Stephen E.} and Emilio Gallicchio and Anton Gorenko and Henry, {Michael M.} and Frank Hu and Jing Huang and Andreas Kr{\"a}mer and Julien Michel and Mitchell, {Joshua A.} and Pande, {Vijay S.} and Rodrigues, {Jo{\~a}o PGLM} and Jaime Rodriguez-Guerra and Simmonett, {Andrew C.} and Sukrit Singh and Jason Swails and Philip Turner and Yuanqing Wang and Ivy Zhang and Chodera, {John D.} and {De Fabritiis}, Gianni and Markland, {Thomas E.}",
note = "Funding Information: Research reported in this publication was supported by the National Institute of General Medical Sciences (NIGMS) of the National Institutes of Health under award number GM140090 (P.E., T.E.M., J.D.C., G.D.F.). The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health. P.E. and T.E.M. acknowledge support from the Chan Zuckerberg Initiative{\textquoteright}s Essential Open Source Software for Science program grant EOSS2-0000000172. J.D.C. acknowledges support from NIH grant P30 CA008748, NIH grant R01 GM140090, and the Sloan Kettering Institute. S.F. and J.M. acknowledge support from the Engineering and Physical Sciences Research Council under grant award EP/W030276/1. G.D.F. acknowledges support from the project PID2020-116564GB-I00 that has been funded by MCIN/AEI/10.13039/501100011033. I.Z. acknowledges support from Vir Biotechnology, Inc., a Molecular Sciences Software Institute Seed Fellowship, and the Tri-Institutional Program in Computational Biology and Medicine. ACS acknowledges support from the intramural research program of the National Heart, Lung and Blood Institute. J.P.R. acknowledges support from NIH NIGMS grant R35GM122543. E.G. acknowledges support from the NSF CAREER award 1750511. Y.W. acknowledges support from the Schmidt Science Fellowship, in partnership with the Rhodes Trust, and the Simons Center for Computational Physical Chemistry at New York University. S.S. is a Damon Runyon Quantitative Biology Fellow supported by the Damon Runyon Cancer Research Foundation (DRQ-14-22). Publisher Copyright: {\textcopyright} 2023 American Chemical Society.",
year = "2023",
month = dec,
day = "28",
doi = "10.1021/acs.jpcb.3c06662",
language = "English",
volume = "128",
pages = "109--116",
journal = "Journal of Physical Chemistry B",
issn = "1520-6106",
publisher = "American Chemical Society",
number = "1",
}