{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T19:15:07Z","timestamp":1781896507267,"version":"3.54.5"},"reference-count":63,"publisher":"AIP Publishing","issue":"7","funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DMR-2309000"],"award-info":[{"award-number":["DMR-2309000"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Wisconsin Alumni Research Fund"},{"DOI":"10.13039\/501100000781","name":"European Research Council","doi-asserted-by":"publisher","award":["101001890-FIAMMA"],"award-info":[{"award-number":["101001890-FIAMMA"]}],"id":[{"id":"10.13039\/501100000781","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pubs.aip.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,21]]},"abstract":"<jats:p>Physics-based, atom-centered machine learning (ML) representations have been instrumental to the effective integration of ML within the atomistic simulation community. Many of these representations build off the idea of atoms as having spherical, or isotropic, interactions. In many communities, there is often a need to represent groups of atoms, either to increase the computational efficiency of simulation via coarse-graining or to understand molecular influences on system behavior. In such cases, atom-centered representations will have limited utility, as groups of atoms may not be well-approximated as spheres. In this work, we extend the popular Smooth Overlap of Atomic Positions (SOAP) ML representation for systems consisting of non-spherical anisotropic particles or clusters of atoms. We show the power of this anisotropic extension of SOAP, which we deem AniSOAP, in accurately characterizing liquid crystal systems and predicting the energetics of Gay\u2013Berne ellipsoids and coarse-grained benzene crystals. With our study of these prototypical anisotropic systems, we derive fundamental insights on how molecular shape influences mesoscale behavior and explain how to reincorporate important atom\u2013atom interactions typically not captured by coarse-grained models. Moving forward, we propose AniSOAP as a flexible, unified framework for coarse-graining in complex, multiscale simulation.<\/jats:p>","DOI":"10.1063\/5.0210910","type":"journal-article","created":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T09:43:29Z","timestamp":1724147009000},"update-policy":"https:\/\/doi.org\/10.1063\/aip-crossmark-policy-page","source":"Crossref","is-referenced-by-count":8,"title":["Expanding density-correlation machine learning representations for anisotropic coarse-grained particles"],"prefix":"10.1063","volume":"161","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7665-3767","authenticated-orcid":false,"given":"Arthur","family":"Lin","sequence":"first","affiliation":[{"name":"Department of Chemical and Biological Engineering, University of Wisconsin 1 , Madison, Wisconsin 53706, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0933-8417","authenticated-orcid":false,"given":"Kevin K.","family":"Huguenin-Dumittan","sequence":"additional","affiliation":[{"name":"Laboratory of Computational Science and Modeling, Institute of Materials, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne 2 , 1015 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6038-6764","authenticated-orcid":false,"given":"Yong-Cheol","family":"Cho","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, University of Wisconsin 1 , Madison, Wisconsin 53706, USA"},{"name":"Department of Computer Science and Engineering, University of Wisconsin 3 , Madison, Wisconsin 53706, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6857-4332","authenticated-orcid":false,"given":"Jigyasa","family":"Nigam","sequence":"additional","affiliation":[{"name":"Laboratory of Computational Science and Modeling, Institute of Materials, \u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne 2 , 1015 Lausanne, Switzerland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4515-3441","authenticated-orcid":false,"given":"Rose K.","family":"Cersonsky","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biological Engineering, University of Wisconsin 1 , Madison, Wisconsin 53706, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"317","published-online":{"date-parts":[[2024,8,20]]},"reference":[{"key":"2024082009432016400_c1","doi-asserted-by":"publisher","first-page":"3622","DOI":"10.1021\/acs.jctc.2c00110","article-title":"Learning efficient, collective Monte Carlo moves with variational autoencoders","volume":"18","year":"2022","journal-title":"J.\u00a0Chem. Theory Comput."},{"key":"2024082009432016400_c2","doi-asserted-by":"publisher","first-page":"094116","DOI":"10.1063\/5.0105120","article-title":"Systematic control of collective variables learned from variational autoencoders","volume":"157","year":"2022","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c3","unstructured":"A. d. S.\n            Costa\n          , I.Mitnikov, M.Geiger, M.Ponnapati, T.Smidt, and J.Jacobson, \u201cOphiuchus: Scalable modeling of protein structures through hierarchical coarse-graining SO(3)-equivariant autoencoders,\u201d arXiv:2310.02508 [cs] (2023)."},{"key":"2024082009432016400_c4","doi-asserted-by":"publisher","first-page":"5739","DOI":"10.1038\/s41467-023-41343-1","article-title":"Machine learning coarse-grained potentials of protein thermodynamics","volume":"14","year":"2023","journal-title":"Nat. Commun."},{"key":"2024082009432016400_c5","doi-asserted-by":"publisher","first-page":"164501","DOI":"10.1063\/5.0022431","article-title":"Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks","volume":"153","year":"2020","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c6","doi-asserted-by":"publisher","first-page":"194101","DOI":"10.1063\/5.0026133","article-title":"Coarse graining molecular dynamics with graph neural networks","volume":"153","year":"2020","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c7","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":"2024082009432016400_c8","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.\u00a0Chem. Phys."},{"key":"2024082009432016400_c9","doi-asserted-by":"publisher","first-page":"194106","DOI":"10.1063\/5.0007276","article-title":"Ensemble learning of coarse-grained molecular dynamics force fields with a kernel approach","volume":"152","year":"2020","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c10","doi-asserted-by":"publisher","first-page":"13754","DOI":"10.1039\/c6cp00415f","article-title":"Comparing molecules and solids across structural and alchemical space","volume":"18","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"2024082009432016400_c11","doi-asserted-by":"publisher","first-page":"10073","DOI":"10.1021\/acs.chemrev.1c00022","article-title":"Gaussian process regression for materials and molecules","volume":"121","year":"2021","journal-title":"Chem. Rev."},{"key":"2024082009432016400_c12","doi-asserted-by":"publisher","first-page":"9759","DOI":"10.1021\/acs.chemrev.1c00021","article-title":"Physics-inspired structural representations for molecules and materials","volume":"121","year":"2021","journal-title":"Chem. Rev."},{"key":"2024082009432016400_c13","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"SMILES, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","year":"1988","journal-title":"J.\u00a0Chem. Inf. Comput. Sci."},{"key":"2024082009432016400_c14","doi-asserted-by":"publisher","first-page":"045024","DOI":"10.1088\/2632-2153\/aba947","article-title":"Self-referencing embedded strings (SELFIES): A 100% robust molecular string representation","volume":"1","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2024082009432016400_c15","doi-asserted-by":"publisher","first-page":"e1603","DOI":"10.1002\/wcms.1603","article-title":"A review of molecular representation in the age of machine learning","volume":"12","year":"2022","journal-title":"Wiley Interdiscip. Rev.: Comput. Mol. Sci."},{"key":"2024082009432016400_c16","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.\u00a0Chem. Phys."},{"key":"2024082009432016400_c17","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":"2024082009432016400_c18","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1039\/c7sc02664a","article-title":"MoleculeNet: A benchmark for molecular machine learning","volume":"9","year":"2018","journal-title":"Chem. Sci."},{"key":"2024082009432016400_c19","doi-asserted-by":"publisher","first-page":"121101","DOI":"10.1063\/5.0021116","article-title":"Recursive evaluation and iterative contraction of N-body equivariant features","volume":"153","year":"2020","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c20","doi-asserted-by":"publisher","first-page":"204115","DOI":"10.1063\/5.0087042","article-title":"Unified theory of atom-centered representations and message-passing machine-learning schemes","volume":"156","year":"2022","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c21","first-page":"11423","article-title":"MACE: Higher order equivariant message passing neural networks for fast and accurate force fields","year":"2022"},{"key":"2024082009432016400_c22","doi-asserted-by":"publisher","first-page":"114109","DOI":"10.1063\/5.0044689","article-title":"Efficient implementation of atom-density representations","volume":"154","year":"2021","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c23","doi-asserted-by":"publisher","first-page":"234101","DOI":"10.1063\/5.0124363","article-title":"A smooth basis for atomistic machine learning","volume":"157","year":"2022","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c24","volume-title":"Gruppentheorie und ihre Anwendung auf die Quantenmechanik der Atomspektren","year":"1931"},{"key":"2024082009432016400_c25","first-page":"185","article-title":"On the nonorthogonality Problem**The work reported in this paper has been sponsored in part by the Swedish Natural Science Research Council, in part by the Air Force Office of Scientific Research (OSR) through the European Office of Aerospace Research (OAR), U.S. Air Force under Grant AF-EOAR 67-50 with Uppsala University, and in part by the National Science Foundation under Grant GP-5419 with the University of Florida","volume-title":"Advances in Quantum Chemistry","author":"L\u00f6wdin","year":"1970"},{"key":"2024082009432016400_c26","first-page":"9323","article-title":"E(n) equivariant graph neural networks","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Meila","year":"2021"},{"key":"2024082009432016400_c27","doi-asserted-by":"publisher","first-page":"11547","DOI":"10.1021\/la0513611","article-title":"Self-assembly of patchy particles into diamond structures through molecular mimicry","volume":"21","year":"2005","journal-title":"Langmuir"},{"key":"2024082009432016400_c28","doi-asserted-by":"publisher","first-page":"557","DOI":"10.1038\/nmat1949","article-title":"Anisotropy of building blocks and their assembly into complex structures","volume":"6","year":"2007","journal-title":"Nat. Mater."},{"key":"2024082009432016400_c29","doi-asserted-by":"publisher","first-page":"125201","DOI":"10.1103\/physrevmaterials.2.125201","article-title":"Pressure-tunable photonic band gaps in an entropic colloidal crystal","volume":"2","year":"2018","journal-title":"Phys. Rev. Mater."},{"key":"2024082009432016400_c30","doi-asserted-by":"publisher","first-page":"1439","DOI":"10.1073\/pnas.1720139115","article-title":"Relevance of packing to colloidal self-assembly","volume":"115","year":"2018","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"2024082009432016400_c31","doi-asserted-by":"publisher","first-page":"6438","DOI":"10.1016\/j.jcp.2011.04.017","article-title":"Characterizing complex particle morphologies through shape matching: Descriptors, applications, and algorithms","volume":"230","year":"2011","journal-title":"J.\u00a0Comput. Phys."},{"key":"2024082009432016400_c32","doi-asserted-by":"publisher","first-page":"E4812","DOI":"10.1073\/pnas.1418159111","article-title":"Understanding shape entropy through local dense packing","volume":"111","year":"2014","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"2024082009432016400_c33","volume-title":"Introduction to Soft Matter\u2014Revised Edition","year":"2007"},{"key":"2024082009432016400_c34","doi-asserted-by":"publisher","first-page":"107275","DOI":"10.1016\/j.cpc.2020.107275","article-title":"freud: A software suite for high throughput analysis of particle simulation data","volume":"254","year":"2020","journal-title":"Comput. Phys. Commun."},{"key":"2024082009432016400_c35","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1103\/physrevb.28.784","article-title":"Bond-orientational order in liquids and glasses","volume":"28","year":"1983","journal-title":"Phys. Rev. B"},{"key":"2024082009432016400_c36","doi-asserted-by":"publisher","first-page":"114707","DOI":"10.1063\/1.2977970","article-title":"Accurate determination of crystal structures based on averaged local bond order parameters","volume":"129","year":"2008","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c37","doi-asserted-by":"publisher","first-page":"11635","DOI":"10.1073\/pnas.0505436102","article-title":"Nearsightedness of electronic matter","volume":"102","year":"2005","journal-title":"Proc. Natl. Acad. Sci. U. S. A."},{"key":"2024082009432016400_c38","doi-asserted-by":"publisher","first-page":"025028","DOI":"10.1088\/2632-2153\/abdaf7","article-title":"The role of feature space in atomistic learning","volume":"2","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2024082009432016400_c39","doi-asserted-by":"publisher","first-page":"81","DOI":"10.12688\/openreseurope.15789.1","article-title":"scikit-matter: A suite of generalisable machine learning methods born out of chemistry and materials science","volume":"3","year":"2023","journal-title":"Open Res. Eur."},{"key":"2024082009432016400_c40","doi-asserted-by":"publisher","first-page":"041710","DOI":"10.1103\/physreve.67.041710","article-title":"Interaction potentials for soft and hard ellipsoids","volume":"67","year":"2003","journal-title":"Phys. Rev. E"},{"key":"2024082009432016400_c41","doi-asserted-by":"publisher","first-page":"462","DOI":"10.1016\/0009-2614(95)00212-m","article-title":"A generalized Gay-Berne intermolecular potential for biaxial particles","volume":"236","year":"1995","journal-title":"Chem. Phys. Lett."},{"key":"2024082009432016400_c42","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1016\/0021-9991(85)90171-8","article-title":"Statistical mechanics of hard ellipsoids. I. Overlap algorithm and the contact function","volume":"58","year":"1985","journal-title":"J.\u00a0Comput. Phys."},{"key":"2024082009432016400_c44","doi-asserted-by":"publisher","first-page":"015012","DOI":"10.1088\/0965-0393\/18\/1\/015012","article-title":"Visualization and analysis of atomistic simulation data with OVITO\u2013the Open Visualization Tool","volume":"18","year":"2009","journal-title":"Modell. Simul. Mater. Sci. Eng."},{"key":"2024082009432016400_c45","doi-asserted-by":"publisher","first-page":"107810","DOI":"10.1016\/j.cpc.2020.107810","article-title":"PyXtal: A Python library for crystal structure generation and symmetry analysis","volume":"261","year":"2021","journal-title":"Comput. Phys. Commun."},{"key":"2024082009432016400_c46","doi-asserted-by":"publisher","first-page":"395502","DOI":"10.1088\/0953-8984\/21\/39\/395502","article-title":"QUANTUM ESPRESSO: A modular and open-source software project for quantum simulations of materials","volume":"21","year":"2009","journal-title":"J.\u00a0Phys.: Condens. Matter"},{"key":"2024082009432016400_c47","doi-asserted-by":"publisher","first-page":"72","DOI":"10.1038\/s41524-018-0127-2","article-title":"Precision and efficiency in solid-state pseudopotential calculations","volume":"4","year":"2018","journal-title":"npj Comput. Mater."},{"key":"2024082009432016400_c48","doi-asserted-by":"publisher","first-page":"5105","DOI":"10.1021\/acs.chemrev.5b00533","article-title":"Dispersion-corrected mean-field electronic structure methods","volume":"116","year":"2016","journal-title":"Chem. Rev."},{"key":"2024082009432016400_c49","doi-asserted-by":"publisher","first-page":"5188","DOI":"10.1103\/physrevb.13.5188","article-title":"Special points for Brillouin-zone integrations","volume":"13","year":"1976","journal-title":"Phys. Rev. B"},{"key":"2024082009432016400_c50","first-page":"152","volume-title":"signac: A Python Framework for Data and Workflow Management","year":"2018"},{"key":"2024082009432016400_c51","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1016\/j.commatsci.2018.01.035","article-title":"Simple data and workflow management with the signac framework","volume":"146","year":"2018","journal-title":"Comput. Mater. Sci."},{"key":"2024082009432016400_c52","doi-asserted-by":"publisher","first-page":"273002","DOI":"10.1088\/1361-648x\/aa680e","article-title":"The atomic simulation environment\u2014A Python library for working with atoms","volume":"29","year":"2017","journal-title":"J.\u00a0Phys.: Condens. Matter"},{"key":"2024082009432016400_c53","doi-asserted-by":"publisher","first-page":"1981","DOI":"10.1021\/acs.accounts.0c00403","article-title":"Mapping materials and molecules","volume":"53","year":"2020","journal-title":"Acc. Chem. Res."},{"key":"2024082009432016400_c54","volume-title":"rascaline","year":"2023"},{"key":"2024082009432016400_c55","doi-asserted-by":"publisher","first-page":"166001","DOI":"10.1103\/physrevlett.125.166001","article-title":"Incompleteness of atomic structure representations","volume":"125","year":"2020","journal-title":"Phys. Rev. Lett."},{"key":"2024082009432016400_c59","doi-asserted-by":"publisher","first-page":"2117","DOI":"10.21105\/joss.02117","article-title":"Chemiscope: Interactive structure-property explorer for materials and molecules","volume":"5","year":"2020","journal-title":"J.\u00a0Open Source Softw."},{"key":"2024082009432016400_c60","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1038\/s41597-020-00637-5","article-title":"Materials Cloud, a platform for open computational science","volume":"7","year":"2020","journal-title":"Sci. Data"},{"key":"2024082009432016400_c61","article-title":"Case studies for `Expanding density-correlation machine learning representations for anisotropic coarse-grained particles","year":"2024"},{"key":"2024082009432016400_c62","doi-asserted-by":"publisher","first-page":"045021","DOI":"10.1088\/2632-2153\/aba9ef","article-title":"Structure-property maps with Kernel principal covariates regression","volume":"1","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"2024082009432016400_c63","doi-asserted-by":"publisher","first-page":"064802","DOI":"10.1063\/5.0156307","article-title":"Fast evaluation of spherical harmonics with sphericart","volume":"159","year":"2023","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c64","doi-asserted-by":"publisher","first-page":"104106","DOI":"10.1063\/5.0057229","article-title":"Optimal radial basis for density-based atomic representations","volume":"155","year":"2021","journal-title":"J.\u00a0Chem. Phys."},{"key":"2024082009432016400_c65","volume-title":"A Paging Experiment with the Multics System","year":"1969"},{"key":"2024082009432016400_c66","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1145\/2692956.2663188","article-title":"The rust language","volume":"34","year":"2014","journal-title":"ACM SIGAda Ada Lett."},{"issue":"1","key":"2024082009432016400_c67","doi-asserted-by":"publisher","first-page":"014104","DOI":"10.1103\/PhysRevB.99.014104","article-title":"Atomic cluster expansion for accurate and transferable interatomicpotentials","volume":"99","year":"2019","journal-title":"Phys. Rev. B"}],"container-title":["The Journal of Chemical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0210910\/20119273\/074112_1_5.0210910.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/pubs.aip.org\/aip\/jcp\/article-pdf\/doi\/10.1063\/5.0210910\/20119273\/074112_1_5.0210910.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,20]],"date-time":"2024-08-20T09:43:39Z","timestamp":1724147019000},"score":1,"resource":{"primary":{"URL":"https:\/\/pubs.aip.org\/jcp\/article\/161\/7\/074112\/3308992\/Expanding-density-correlation-machine-learning"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,20]]},"references-count":63,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,8,21]]}},"URL":"https:\/\/doi.org\/10.1063\/5.0210910","relation":{},"ISSN":["0021-9606","1089-7690"],"issn-type":[{"value":"0021-9606","type":"print"},{"value":"1089-7690","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,8,21]]},"published":{"date-parts":[[2024,8,20]]},"article-number":"074112"}}