{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T21:46:15Z","timestamp":1776980775582,"version":"3.51.4"},"reference-count":67,"publisher":"AIP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T00:00:00Z","timestamp":1688947200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"crossref","award":["DP190102100"],"award-info":[{"award-number":["DP190102100"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,14]]},"abstract":"<jats:p>We develop a machine-learning method for coarse-graining condensed-phase molecular systems using anisotropic particles. The method extends currently available high-dimensional neural network potentials by addressing molecular anisotropy. We demonstrate the flexibility of the method by parametrizing single-site coarse-grained models of a rigid small molecule (benzene) and a semi-flexible organic semiconductor (sexithiophene), attaining structural accuracy close to the all-atom models for both molecules at a considerably lower computational expense. The machine-learning method of constructing the coarse-grained potential is shown to be straightforward and sufficiently robust to capture anisotropic interactions and many-body effects. The method is validated through its ability to reproduce the structural properties of the small molecule\u2019s liquid phase and the phase transitions of the semi-flexible molecule over a wide temperature range.<\/jats:p>","DOI":"10.1063\/5.0143724","type":"journal-article","created":{"date-parts":[[2023,7,10]],"date-time":"2023-07-10T13:37:00Z","timestamp":1688996220000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":16,"title":["Anisotropic molecular coarse-graining by force and torque matching with neural networks"],"prefix":"10.1063","volume":"159","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0143-3476","authenticated-orcid":false,"given":"Marltan O.","family":"Wilson","sequence":"first","affiliation":[{"name":"Department of Chemistry, School of Physics, Chemistry and Earth Sciences, The University of Adelaide , Adelaide, South Australia 5005, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2048-4500","authenticated-orcid":false,"given":"David M.","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Chemistry, School of Physics, Chemistry and Earth Sciences, The University of Adelaide , Adelaide, South Australia 5005, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"317","published-online":{"date-parts":[[2023,7,10]]},"reference":[{"key":"2023071012530146300_c1","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/s41586-018-0337-2","article-title":"Machine learning for molecular and materials science","volume":"559","year":"2018","journal-title":"Nature"},{"key":"2023071012530146300_c2","doi-asserted-by":"publisher","first-page":"20273","DOI":"10.1021\/jacs.0c09105","article-title":"The role of machine learning in the understanding and design of materials","volume":"142","year":"2020","journal-title":"J. Am. Chem. Soc."},{"key":"2023071012530146300_c3","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1038\/s41586-021-03828-1","article-title":"Highly accurate protein structure prediction for the human proteome","volume":"596","year":"2021","journal-title":"Nature"},{"key":"2023071012530146300_c4","doi-asserted-by":"publisher","first-page":"034702","DOI":"10.1063\/5.0005084","article-title":"An accurate and transferable machine learning potential for carbon","volume":"153","year":"2020","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c5","doi-asserted-by":"publisher","first-page":"045010","DOI":"10.1088\/2632-2153\/ac9955","article-title":"How robust are modern graph neural network potentials in long and hot molecular dynamics simulations?","volume":"3","year":"2022","journal-title":"Mach. Learn.: Sci. Tech."},{"key":"2023071012530146300_c6","doi-asserted-by":"publisher","first-page":"750","DOI":"10.1038\/s41563-020-0777-6","article-title":"Machine-learned potentials for next-generation matter simulations","volume":"20","year":"2021","journal-title":"Nat. Mater."},{"key":"2023071012530146300_c7","doi-asserted-by":"publisher","first-page":"361","DOI":"10.1146\/annurev-physchem-042018-052331","article-title":"Machine learning for molecular simulation","volume":"71","year":"2020","journal-title":"Annu. Rev. Phys. Chem."},{"key":"2023071012530146300_c8","first-page":"205","article-title":"Extending the limit of molecular dynamics with ab\u00a0initio accuracy to 10 billion atoms","year":"2022"},{"key":"2023071012530146300_c9","volume-title":"Ab Initio Molecular Dynamics: Basic Theory and Advanced Methods","year":"2009"},{"key":"2023071012530146300_c10","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1016\/j.cpc.2018.03.016","article-title":"DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics","volume":"228","year":"2018","journal-title":"Comput. Phys. Commun."},{"key":"2023071012530146300_c11","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","article-title":"Machine learning force fields","volume":"121","year":"2021","journal-title":"Chem. Rev."},{"key":"2023071012530146300_c12","doi-asserted-by":"publisher","first-page":"5759","DOI":"10.1021\/acs.jctc.2c00643","article-title":"Bottom-up coarse-graining: Principles and perspectives","volume":"18","year":"2022","journal-title":"J. Chem. Theory Comput."},{"key":"2023071012530146300_c13","doi-asserted-by":"publisher","first-page":"6801","DOI":"10.1039\/c3cs60093a","article-title":"Perspective on the Martini model","volume":"42","year":"2013","journal-title":"Chem. Soc. Rev."},{"key":"2023071012530146300_c14","doi-asserted-by":"publisher","first-page":"034101","DOI":"10.1063\/1.5027645","article-title":"DeePCG: Constructing coarse-grained models via deep neural networks","volume":"149","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c15","doi-asserted-by":"publisher","first-page":"755","DOI":"10.1021\/acscentsci.8b00913","article-title":"Machine learning of coarse-grained molecular dynamics force fields","volume":"5","year":"2019","journal-title":"ACS Cent. Sci."},{"key":"2023071012530146300_c16","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1063\/1.441483","article-title":"Modification of the overlap potential to mimic a linear site\u2013site potential","volume":"74","year":"1981","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c17","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/0009-2614(95)00212-m","article-title":"A generalized Gay\u2013Berne intermolecular potential for biaxial particles","volume":"236","year":"1995","journal-title":"Chem. Phys. Lett."},{"key":"2023071012530146300_c18","doi-asserted-by":"publisher","first-page":"423001","DOI":"10.1088\/1361-648x\/ab2ac2","article-title":"The interplay of interfaces, supramolecular assembly, and electronics in organic semiconductors","volume":"31","year":"2019","journal-title":"J. Phys.: Condens. Matter"},{"key":"2023071012530146300_c19","doi-asserted-by":"publisher","first-page":"074106","DOI":"10.1063\/1.3553717","article-title":"Atom-centered symmetry functions for constructing high-dimensional neural network potentials","volume":"134","year":"2011","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c20","doi-asserted-by":"publisher","first-page":"024902","DOI":"10.1063\/5.0091319","article-title":"Machine-learning effective many-body potentials for anisotropic particles using orientation-dependent symmetry functions","volume":"157","year":"2022","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c21","doi-asserted-by":"publisher","first-page":"184118","DOI":"10.1063\/5.0085006","article-title":"Systematic bottom-up molecular coarse-graining via force and torque matching using anisotropic particles","volume":"156","year":"2022","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c22","doi-asserted-by":"publisher","first-page":"244114","DOI":"10.1063\/1.2938860","article-title":"The multiscale coarse-graining method. I. A rigorous bridge between atomistic and coarse-grained models","volume":"128","year":"2008","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c23","doi-asserted-by":"publisher","first-page":"164106","DOI":"10.1063\/1.3394862","article-title":"The multiscale coarse-graining method. V. Isothermal\u2013isobaric ensemble","volume":"132","year":"2010","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c24","volume-title":"Classical Mechanics","year":"2002"},{"key":"2023071012530146300_c25","doi-asserted-by":"publisher","first-page":"184115","DOI":"10.1103\/physrevb.87.184115","article-title":"On representing chemical environments","volume":"87","year":"2013","journal-title":"Phys. Rev. B"},{"key":"2023071012530146300_c26","doi-asserted-by":"publisher","first-page":"629","DOI":"10.4208\/cicp.oa-2017-0213","article-title":"Deep Potential: A general representation of a many-body potential energy surface","volume":"23","year":"2018","journal-title":"Commun. Comput. Phys."},{"key":"2023071012530146300_c27","first-page":"5738","article-title":"On the continuity of rotation representations in neural networks","year":"2019"},{"key":"2023071012530146300_c28","doi-asserted-by":"publisher","first-page":"241709","DOI":"10.1063\/1.5019667","article-title":"wACSF\u2014Weighted atom-centered symmetry functions as descriptors in machine learning potentials","volume":"148","year":"2018","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c29","doi-asserted-by":"publisher","first-page":"1809","DOI":"10.1002\/cphc.200400669","article-title":"Blue moon sampling, vectorial reaction coordinates, and unbiased constrained dynamics","volume":"6","year":"2005","journal-title":"ChemPhysChem"},{"key":"2023071012530146300_c30","doi-asserted-by":"publisher","first-page":"15742","DOI":"10.1021\/jp805039u","article-title":"Efficient and direct generation of multidimensional free energy surfaces via adiabatic dynamics without coordinate transformations","volume":"112","year":"2008","journal-title":"J. Phys. Chem. B"},{"key":"2023071012530146300_c31","unstructured":"D. P.\n            Kingma\n           and J.Ba, \u201cAdam: A method for stochastic optimization,\u201d arXiv:1412.6980 (2014)."},{"key":"2023071012530146300_c32","first-page":"265","article-title":"TensorFlow: A system for large-scale machine learning","year":"2016"},{"key":"2023071012530146300_c33","volume-title":"Keras","year":"2015"},{"key":"2023071012530146300_c34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1006\/jcph.1995.1039","article-title":"Fast parallel algorithms for short-range molecular dynamics","volume":"117","year":"1995","journal-title":"J. Comput. Phys."},{"key":"2023071012530146300_c35","doi-asserted-by":"publisher","first-page":"898","DOI":"10.1016\/j.cpc.2010.12.021","article-title":"Implementing molecular dynamics on hybrid high performance computers\u2014Short range forces","volume":"182","year":"2011","journal-title":"Comput. Phys. Commun."},{"key":"2023071012530146300_c36","doi-asserted-by":"publisher","first-page":"449","DOI":"10.1016\/j.cpc.2011.10.012","article-title":"Implementing molecular dynamics on hybrid high performance computers\u2014Particle\u2013particle particle\u2013mesh","volume":"183","year":"2012","journal-title":"Comput. Phys. Commun."},{"key":"2023071012530146300_c37","doi-asserted-by":"publisher","first-page":"11225","DOI":"10.1021\/ja9621760","article-title":"Development and testing of the OPLS all-atom force field on conformational energetics and properties of organic liquids","volume":"118","year":"1996","journal-title":"J. Am. Chem. Soc."},{"key":"2023071012530146300_c38","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1016\/s0166-1280(97)00237-6","article-title":"Development of an all-atom force field for heterocycles. Properties of liquid pyridine and diazenes","volume":"424","year":"1998","journal-title":"J. Mol. Struct.: THEOCHEM"},{"key":"2023071012530146300_c39","doi-asserted-by":"publisher","first-page":"4827","DOI":"10.1021\/ja984106u","article-title":"OPLS all-atom model for amines: Resolution of the amine hydration problem","volume":"121","year":"1999","journal-title":"J. Am. Chem. Soc."},{"key":"2023071012530146300_c40","doi-asserted-by":"publisher","first-page":"1340","DOI":"10.1002\/jcc.1092","article-title":"Gas-phase and liquid-state properties of esters, nitriles, and nitro compounds with the OPLS-AA force field","volume":"22","year":"2001","journal-title":"J. Comput. Chem."},{"key":"2023071012530146300_c41","doi-asserted-by":"publisher","first-page":"3864","DOI":"10.1021\/acs.jpcb.7b00272","article-title":"1.14\u2217CM1A-LBCC: Localized bond-charge corrected CM1A charges for condensed-phase simulations","volume":"121","year":"2017","journal-title":"J. Phys. Chem. B"},{"key":"2023071012530146300_c42","doi-asserted-by":"publisher","first-page":"W331","DOI":"10.1093\/nar\/gkx312","article-title":"LigParGen web server: An automatic OPLS-AA parameter generator for organic ligands","volume":"45","year":"2017","journal-title":"Nucleic Acids Res."},{"key":"2023071012530146300_c43","volume-title":"Computer Simulation Using Particles","year":"1988"},{"key":"2023071012530146300_c44","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/0021-9991(77)90098-5","article-title":"Numerical integration of the Cartesian equations of motion of a system with constraints: Molecular dynamics of n-alkanes","volume":"23","year":"1977","journal-title":"J. Comput. Phys."},{"key":"2023071012530146300_c45","doi-asserted-by":"publisher","first-page":"1695","DOI":"10.1103\/physreva.31.1695","article-title":"Canonical dynamics: Equilibrium phase-space distributions","volume":"31","year":"1985","journal-title":"Phys. Rev. A"},{"key":"2023071012530146300_c46","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1080\/00268978400101201","article-title":"A molecular dynamics method for simulations in the canonical ensemble","volume":"52","year":"1984","journal-title":"Mol. Phys."},{"key":"2023071012530146300_c47","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1007\/s00180-020-00999-9","article-title":"What is an optimal value of k in k-fold cross-validation in discrete Bayesian network analysis?","volume":"36","year":"2021","journal-title":"Comput. Stat."},{"key":"2023071012530146300_c48","first-page":"513","article-title":"No unbiased estimator of the variance of k-fold cross-validation","year":"2004"},{"key":"2023071012530146300_c49","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1063\/1.457480","article-title":"Error estimates on averages of correlated data","volume":"91","year":"1989","journal-title":"J. Chem. Phys."},{"key":"2023071012530146300_c50","doi-asserted-by":"publisher","first-page":"369","DOI":"10.1039\/a605274f","article-title":"Organic molecular solids as thin film transistor semiconductors","volume":"7","year":"1997","journal-title":"J. Mater. Chem."},{"key":"2023071012530146300_c51","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1039\/a908312j","article-title":"Structural order in conjugated oligothiophenes and its implications on opto-electronic devices","volume":"10","year":"2000","journal-title":"J. Mater. Chem."},{"key":"2023071012530146300_c52","doi-asserted-by":"publisher","first-page":"4617","DOI":"10.1038\/s41467-020-18439-z","article-title":"Orientation dependent molecular electrostatics drives efficient charge generation in homojunction organic solar cells","volume":"11","year":"2020","journal-title":"Nat. Commun."},{"key":"2023071012530146300_c53","first-page":"25","article-title":"Extrapolation limitations of multilayer feedforward neural networks","year":"1992"},{"key":"2023071012530146300_c54","doi-asserted-by":"publisher","first-page":"1300","DOI":"10.1039\/d1cp04450h","article-title":"Nonlinearity encoding to improve extrapolation capabilities for unobserved physical states","volume":"24","year":"2022","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2023071012530146300_c55","first-page":"728","article-title":"Generalizable and interpretable learning for configuration extrapolation","year":"2021"},{"key":"2023071012530146300_c56","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1080\/13658810110038951","article-title":"Artificial neural networks as a tool for spatial interpolation","volume":"15","year":"2001","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"2023071012530146300_c57","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1016\/j.phpro.2015.07.115","article-title":"Probing the effect of density on the aggregation temperature of semi-flexible polymers in spherical confinement","volume":"68","year":"2015","journal-title":"Phys. Procedia"},{"key":"2023071012530146300_c58","doi-asserted-by":"publisher","first-page":"623","DOI":"10.1590\/s0103-97332006000500006","article-title":"Monte Carlo simulations of a semi-flexible polymer chain: A first glance","volume":"36","year":"2006","journal-title":"Braz. J. Phys."},{"key":"2023071012530146300_c59","doi-asserted-by":"publisher","first-page":"8363","DOI":"10.1021\/jp2108895","article-title":"Optimal number of coarse-grained sites in different components of large biomolecular complexes","volume":"116","year":"2012","journal-title":"J. Phys. Chem. B"},{"key":"2023071012530146300_c60","doi-asserted-by":"publisher","first-page":"2043","DOI":"10.1002\/cphc.201600149","article-title":"Neutron scattering of aromatic and aliphatic liquids","volume":"17","year":"2016","journal-title":"ChemPhysChem"},{"key":"2023071012530146300_c61","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1039\/c0jm01284j","article-title":"An atomistic simulation of the liquid-crystalline phases of sexithiophene","volume":"21","year":"2011","journal-title":"J. Mater. Chem."},{"key":"2023071012530146300_c62","doi-asserted-by":"publisher","first-page":"765","DOI":"10.1021\/ja00315a051","article-title":"A new force field for molecular mechanical simulation of nucleic acids and proteins","volume":"106","year":"1984","journal-title":"J. Am. Chem. Soc."},{"key":"2023071012530146300_c63","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1002\/jcc.540070216","article-title":"An all atom force field for simulations of proteins and nucleic acids","volume":"7","year":"1986","journal-title":"J. Comput. Chem."},{"key":"2023071012530146300_c64","doi-asserted-by":"publisher","first-page":"5179","DOI":"10.1021\/ja00124a002","article-title":"A second generation force field for the simulation of proteins, nucleic acids, and organic molecules","volume":"117","year":"1995","journal-title":"J. Am. Chem. Soc."},{"key":"2023071012530146300_c65","doi-asserted-by":"publisher","first-page":"8406","DOI":"10.1021\/acs.macromol.8b01344","article-title":"Monte Carlo algorithm based on internal bridging moves for the atomistic simulation of thiophene oligomers and polymers","volume":"51","year":"2018","journal-title":"Macromolecules"},{"key":"2023071012530146300_c66","doi-asserted-by":"publisher","first-page":"eaav4683","DOI":"10.1126\/sciadv.aav4683","article-title":"Energy renormalization for coarse-graining polymers having different segmental structures","volume":"5","year":"2019","journal-title":"Sci. Adv."},{"key":"2023071012530146300_c67","doi-asserted-by":"publisher","first-page":"2239","DOI":"10.1140\/epjst\/e2015-02410-3","article-title":"Coarse-graining polymer solutions: A critical appraisal of single-and multi-site models","volume":"224","year":"2015","journal-title":"Eur. Phys. J. Spec. Top."}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0143724\/18036786\/024110_1_5.0143724.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0143724\/18036786\/024110_1_5.0143724.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0143724\/18036786\/024110_1_5.0143724.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,27]],"date-time":"2025-05-27T20:20:42Z","timestamp":1748377242000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/159\/2\/024110\/2901764\/Anisotropic-molecular-coarse-graining-by-force-and"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,10]]},"references-count":67,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2023,7,14]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0143724","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"value":"0021-9606","type":"print"},{"value":"1089-7690","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,7,14]]},"published":{"date-parts":[[2023,7,10]]},"article-number":"024110"}}