{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T03:29:53Z","timestamp":1752550193084,"version":"3.37.3"},"reference-count":48,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T00:00:00Z","timestamp":1669334400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T00:00:00Z","timestamp":1669334400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2022,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Data-driven machine learning methods have the potential to dramatically accelerate the rate of materials design over conventional human-guided approaches. These methods would help identify or, in the case of generative models, even create novel crystal structures of materials with a set of specified functional properties to then be synthesized or isolated in the laboratory. For crystal structure generation, a key bottleneck lies in developing suitable atomic structure fingerprints or representations for the machine learning model, analogous to the graph-based or SMILES representations used in molecular generation. However, finding data-efficient representations that are invariant to translations, rotations, and permutations, while remaining invertible to the Cartesian atomic coordinates remains an ongoing challenge. Here, we propose an alternative approach to this problem by taking existing non-invertible representations with the desired invariances and developing an algorithm to reconstruct the atomic coordinates through gradient-based optimization using automatic differentiation. This can then be coupled to a generative machine learning model which generates new materials within the representation space, rather than in the data-inefficient Cartesian space. In this work, we implement this end-to-end structure generation approach using atom-centered symmetry functions as the representation and conditional variational autoencoders as the generative model. We are able to successfully generate novel and valid atomic structures of sub-nanometer Pt nanoparticles as a proof of concept. Furthermore, this method can be readily extended to any suitable structural representation, thereby providing a powerful, generalizable framework towards structure-based generation.<\/jats:p>","DOI":"10.1088\/2632-2153\/aca1f7","type":"journal-article","created":{"date-parts":[[2022,11,10]],"date-time":"2022-11-10T22:23:10Z","timestamp":1668118990000},"page":"045018","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":8,"title":["Atomic structure generation from reconstructing structural fingerprints"],"prefix":"10.1088","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3347-6983","authenticated-orcid":true,"given":"Victor","family":"Fung","sequence":"first","affiliation":[]},{"given":"Shuyi","family":"Jia","sequence":"additional","affiliation":[]},{"given":"Jiaxin","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Sirui","family":"Bi","sequence":"additional","affiliation":[]},{"given":"Junqi","family":"Yin","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7170-2902","authenticated-orcid":true,"given":"P","family":"Ganesh","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2022,11,25]]},"reference":[{"key":"mlstaca1f7bib1","doi-asserted-by":"publisher","first-page":"1099","DOI":"10.1126\/science.280.5366.1099","article-title":"Predicting properties from scratch","volume":"280","author":"Ceder","year":"1998","journal-title":"Science"},{"key":"mlstaca1f7bib2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/aad926","article-title":"The materials by design roadmap","volume":"2018","author":"Alberi","year":"2019","journal-title":"J. Appl. Phys."},{"key":"mlstaca1f7bib3","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1038\/s41524-019-0173-4","article-title":"New frontiers for the materials genome initiative","volume":"5","author":"de Pablo","year":"2019","journal-title":"npj Comput. Mater."},{"key":"mlstaca1f7bib4","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1021\/ar500432k","article-title":"The chemical space project","volume":"48","author":"Reymond","year":"2015","journal-title":"Acc. Chem. Res."},{"key":"mlstaca1f7bib5","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1146\/annurev-matsci-070214-020823","article-title":"What is high-throughput virtual screening? A perspective from organic materials discovery","volume":"45","author":"Pyzer-Knapp","year":"2015","journal-title":"Annu. Rev. Mater. Res."},{"key":"mlstaca1f7bib6","doi-asserted-by":"publisher","first-page":"0121","DOI":"10.1038\/s41570-018-0121","article-title":"Inverse design in search of materials with target functionalities","volume":"2","author":"Zunger","year":"2018","journal-title":"Nat. Rev. Chem."},{"key":"mlstaca1f7bib7","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1126\/science.aat2663","article-title":"Inverse molecular design using machine learning: generative models for matter engineering","volume":"361","author":"Sanchez-Lengeling","year":"2018","journal-title":"Science"},{"key":"mlstaca1f7bib8","doi-asserted-by":"publisher","first-page":"4871","DOI":"10.1039\/D0SC00594K","article-title":"Machine-enabled inverse design of inorganic solid materials: promises and challenges","volume":"11","author":"Noh","year":"2020","journal-title":"Chem. Sci."},{"key":"mlstaca1f7bib9","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1038\/s41578-020-00255-y","article-title":"Emerging materials intelligence ecosystems propelled by machine learning","volume":"6","author":"Batra","year":"2021","journal-title":"Nat. Rev. Mater."},{"key":"mlstaca1f7bib10","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1021\/ja01379a006","article-title":"The principles determining the structure of complex ionic crystals","volume":"51","author":"Pauling","year":"1929","journal-title":"J. Am. Chem. Soc."},{"key":"mlstaca1f7bib11","doi-asserted-by":"publisher","first-page":"6138","DOI":"10.1039\/C5CS00841G","article-title":"Computational materials design of crystalline solids","volume":"45","author":"Butler","year":"2016","journal-title":"Chem. Soc. Rev."},{"key":"mlstaca1f7bib12","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1038\/s41578-019-0101-8","article-title":"Structure prediction drives materials discovery","volume":"4","author":"Oganov","year":"2019","journal-title":"Nat. Rev. Mater."},{"key":"mlstaca1f7bib13","doi-asserted-by":"publisher","first-page":"2098","DOI":"10.1039\/C3CS60279F","article-title":"Predicting crystal structures of organic compounds","volume":"43","author":"Price","year":"2014","journal-title":"Chem. Soc. Rev."},{"key":"mlstaca1f7bib14","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevMaterials.2.013803","article-title":"Crystal structure prediction accelerated by Bayesian optimization","volume":"2","author":"Yamashita","year":"2018","journal-title":"Phys. Rev. Mater."},{"key":"mlstaca1f7bib15","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1021\/ar1001318","article-title":"How evolutionary crystal structure prediction works\u2014and why","volume":"44","author":"Oganov","year":"2011","journal-title":"Acc. Chem. Res."},{"key":"mlstaca1f7bib16","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1016\/j.cpc.2012.05.008","article-title":"CALYPSO: a method for crystal structure prediction","volume":"183","author":"Wang","year":"2012","journal-title":"Comput. Phys. Commun."},{"key":"mlstaca1f7bib17","doi-asserted-by":"publisher","first-page":"937","DOI":"10.1038\/nmat2321","article-title":"Crystal structure prediction from first principles","volume":"7","author":"Woodley","year":"2008","journal-title":"Nat. Mater."},{"key":"mlstaca1f7bib18","doi-asserted-by":"publisher","first-page":"200","DOI":"10.1038\/s41524-021-00670-x","article-title":"Inverse design of two-dimensional materials with invertible neural networks","volume":"7","author":"Fung","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstaca1f7bib19","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1038\/s42256-020-00271-1","article-title":"Inverse design of nanoporous crystalline reticular materials with deep generative models","volume":"3","author":"Yao","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstaca1f7bib20","doi-asserted-by":"publisher","first-page":"1370","DOI":"10.1016\/j.matt.2019.08.017","article-title":"Inverse design of solid-state materials via a continuous representation","volume":"1","author":"Noh","year":"2019","journal-title":"Matter"},{"key":"mlstaca1f7bib21","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","article-title":"Automatic chemical design using a data-driven continuous representation of molecules","volume":"4","author":"G\u00f3mez-Bombarelli","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"mlstaca1f7bib22","doi-asserted-by":"publisher","first-page":"e1608","DOI":"10.1002\/wcms.1608","article-title":"Generative models for molecular discovery: recent advances and challenges","volume":"12","author":"Bilodeau","year":"2022","journal-title":"Wiley Interdiscip. Rev.-Comput. Mol. Sci."},{"key":"mlstaca1f7bib23","doi-asserted-by":"publisher","first-page":"182","DOI":"10.3389\/fmats.2022.865270","article-title":"Deep generative models for materials discovery and machine learning-accelerated innovation","volume":"9","author":"Fuhr","year":"2022","journal-title":"Front. Mater."},{"key":"mlstaca1f7bib24","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","author":"Musil","year":"2021","journal-title":"Chem. Rev."},{"key":"mlstaca1f7bib25","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.104.144110","article-title":"Through the eyes of a descriptor: constructing complete, invertible descriptions of atomic environments","volume":"104","author":"Uhrin","year":"2021","journal-title":"Phys. Rev. B"},{"key":"mlstaca1f7bib26","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1038\/s41467-022-28526-y","article-title":"Inverse design of 3d molecular structures with conditional generative neural networks","volume":"13","author":"Gebauer","year":"2022","journal-title":"Nat. Commun."},{"article-title":"Symmetry-adapted generation of 3D point sets for the targeted discovery of molecules","year":"2019","author":"Gebauer","key":"mlstaca1f7bib27"},{"article-title":"Crystal diffusion variational autoencoder for periodic material generation","year":"2021","author":"Xie","key":"mlstaca1f7bib28"},{"key":"mlstaca1f7bib29","first-page":"5361","article-title":"Equivariant flows: exact likelihood generative learning for symmetric densities","volume":"vol 119","author":"K\u00f6hler","year":"2020"},{"key":"mlstaca1f7bib30","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac6b16","article-title":"Normalizing flows for atomic solids","volume":"3","author":"Wirnsberger","year":"2022","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstaca1f7bib31","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1016\/j.matt.2021.11.032","article-title":"An invertible crystallographic representation for general inverse design of inorganic crystals with targeted properties","volume":"5","author":"Ren","year":"2022","journal-title":"Matter"},{"key":"mlstaca1f7bib32","doi-asserted-by":"publisher","first-page":"eaax9324","DOI":"10.1126\/sciadv.aax9324","article-title":"Inverse design of porous materials using artificial neural networks","volume":"6","author":"Kim","year":"2020","journal-title":"Sci. Adv."},{"article-title":"Data-driven approach to encoding and decoding 3-D crystal structures","year":"2019","author":"Hoffmann","key":"mlstaca1f7bib33"},{"key":"mlstaca1f7bib34","doi-asserted-by":"publisher","first-page":"4468","DOI":"10.1038\/s41467-021-24525-7","article-title":"Machine learning based energy-free structure predictions of molecules, transition states, and solids","volume":"12","author":"Lemm","year":"2021","journal-title":"Nat. Commun."},{"key":"mlstaca1f7bib35","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2021.110436","article-title":"Crystal structure prediction in a continuous representative space","volume":"194","author":"Lee","year":"2021","journal-title":"Comput. Mater. Sci."},{"key":"mlstaca1f7bib36","doi-asserted-by":"publisher","DOI":"10.1063\/1.3553717","article-title":"Atom-centered symmetry functions for constructing high-dimensional neural network potentials","volume":"134","author":"Behler","year":"2011","journal-title":"J. Chem. Phys."},{"key":"mlstaca1f7bib37","doi-asserted-by":"publisher","first-page":"13754","DOI":"10.1039\/C6CP00415F","article-title":"Comparing molecules and solids across structural and alchemical space","volume":"18","author":"De","year":"2016","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstaca1f7bib38","doi-asserted-by":"publisher","first-page":"10142","DOI":"10.1021\/acs.chemrev.0c01111","article-title":"Machine learning force fields","volume":"121","author":"Unke","year":"2021","journal-title":"Chem. Rev."},{"key":"mlstaca1f7bib39","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.106.035402","article-title":"Local inversion of the chemical environment representations","volume":"106","author":"Cobelli","year":"2022","journal-title":"Phys. Rev. B"},{"article-title":"Pytorch: an imperative style, high-performance deep learning library","year":"2019","author":"Paszke","key":"mlstaca1f7bib40"},{"key":"mlstaca1f7bib41","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abc940","article-title":"PyXtal_FF: a python library for automated force field generation","volume":"2","author":"Yanxon","year":"2020","journal-title":"Mach. Learn.: Sci. Technol."},{"article-title":"Adam: a method for stochastic optimization","year":"2014","author":"Kingma","key":"mlstaca1f7bib42"},{"key":"mlstaca1f7bib43","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume":"vol 28","author":"Sohn","year":"2015"},{"article-title":"beta-vae: Learning basic visual concepts with a constrained variational framework","year":"2016","author":"Higgins","key":"mlstaca1f7bib44"},{"key":"mlstaca1f7bib45","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/0927-0256(96)00008-0","article-title":"Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set","volume":"6","author":"Kresse","year":"1996","journal-title":"Comput. Mater. Sci."},{"key":"mlstaca1f7bib46","doi-asserted-by":"publisher","first-page":"11169","DOI":"10.1103\/PhysRevB.54.11169","article-title":"Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set","volume":"54","author":"Kresse","year":"1996","journal-title":"Phys. Rev. B"},{"key":"mlstaca1f7bib47","doi-asserted-by":"publisher","first-page":"3865","DOI":"10.1103\/PhysRevLett.77.3865","article-title":"Generalized gradient approximation made simple","volume":"77","author":"Perdew","year":"1996","journal-title":"Phys. Rev. Lett."},{"key":"mlstaca1f7bib48","doi-asserted-by":"publisher","first-page":"17953","DOI":"10.1103\/PhysRevB.50.17953","article-title":"Projector augmented-wave method","volume":"50","author":"Bl\u00f6chl","year":"1994","journal-title":"Phys. Rev. B"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,25]],"date-time":"2022-11-25T11:04:34Z","timestamp":1669374274000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/aca1f7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,25]]},"references-count":48,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2022,11,25]]},"published-print":{"date-parts":[[2022,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/aca1f7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2022,11,25]]},"assertion":[{"value":"Atomic structure generation from reconstructing structural fingerprints","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2022 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-08-18","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-11-10","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2022-11-25","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}