{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T10:36:10Z","timestamp":1772793370513,"version":"3.50.1"},"reference-count":32,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"vor","delay-in-days":22,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:00:00Z","timestamp":1727049600000},"content-version":"tdm","delay-in-days":22,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"Austrian Science Fund","award":["SFB F81 TACO"],"award-info":[{"award-number":["SFB F81 TACO"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The efficient generation and filtering of candidate structures for new materials is becoming increasingly important as starting points for computational studies. In this work, we introduce an approach to Wasserstein generative adversarial networks for predicting unique crystal and molecular structures. Leveraging translation- and rotation-invariant atom-centered local descriptors addresses some of the major challenges faced by similar methods. Our models require only small sets of known structures as training data. Furthermore, the approach is able to generate both non-periodic and periodic structures based on local coordination. We showcase the data efficiency and versatility of the approach by recovering all stable C\n                    <jats:sub>5<\/jats:sub>\n                    H\n                    <jats:sub>12<\/jats:sub>\n                    O isomers using only 39 C\n                    <jats:sub>4<\/jats:sub>\n                    H\n                    <jats:sub>10<\/jats:sub>\n                    O and C\n                    <jats:sub>6<\/jats:sub>\n                    H\n                    <jats:sub>14<\/jats:sub>\n                    O training examples, as well as a few randomly selected known low-energy SiO\n                    <jats:sub>2<\/jats:sub>\n                    crystal structures utilizing only 167 training examples of other SiO\n                    <jats:sub>2<\/jats:sub>\n                    crystal structures. We also introduce a filtration technique to reduce the computational cost of subsequent characterization steps by selecting samples from unique basins on the potential energy surface, which allows to minimize the number of geometry relaxations needed after structure generation. The present method thus represents a new, versatile approach to generative modeling of crystal and molecular structures in the low-data regime, and is available as open-source.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/ad7a4d","type":"journal-article","created":{"date-parts":[[2024,9,12]],"date-time":"2024-09-12T19:31:26Z","timestamp":1726169486000},"page":"035079","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["LoGAN: local generative adversarial network for novel structure prediction"],"prefix":"10.1088","volume":"5","author":[{"given":"P\u00e9ter","family":"Kov\u00e1cs","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8404-6596","authenticated-orcid":true,"given":"Esther","family":"Heid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-5958-117X","authenticated-orcid":true,"given":"Jasper De","family":"Landsheere","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9844-9145","authenticated-orcid":true,"given":"Georg K H","family":"Madsen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2024,9,23]]},"reference":[{"key":"mlstad7a4dbib1","doi-asserted-by":"publisher","first-page":"1032","DOI":"10.1002\/qua.24890","volume":"115","author":"Behler","year":"2015","journal-title":"Int. J. Quantum Chem."},{"key":"mlstad7a4dbib2","doi-asserted-by":"publisher","DOI":"10.1088\/2515-7655\/abc7f3","volume":"3","author":"Watanabe","year":"2020","journal-title":"J. Phys. Energy"},{"key":"mlstad7a4dbib3","doi-asserted-by":"publisher","first-page":"3762","DOI":"10.1021\/cm100795d","volume":"22","author":"Hautier","year":"2010","journal-title":"Chem. Mater."},{"key":"mlstad7a4dbib4","first-page":"pp 103","article-title":"Predicting structures of compounds in the solid state by the global optimisation approach","author":"Sch\u00f6n","year":"1999"},{"key":"mlstad7a4dbib5","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1038\/346343a0","volume":"346","author":"Pannetier","year":"1990","journal-title":"Nature"},{"key":"mlstad7a4dbib6","doi-asserted-by":"publisher","first-page":"713","DOI":"10.1016\/j.cpc.2006.07.020","volume":"175","author":"Glass","year":"2006","journal-title":"Comput. Phys. Commun."},{"key":"mlstad7a4dbib7","doi-asserted-by":"publisher","first-page":"2063","DOI":"10.1016\/j.cpc.2012.05.008","volume":"183","author":"Wang","year":"2012","journal-title":"Comput. Phys. Commun."},{"key":"mlstad7a4dbib8","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41524-021-00537-1","volume":"7","author":"Arrigoni","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstad7a4dbib9","article-title":"Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules","author":"Gebauer","year":"2019"},{"key":"mlstad7a4dbib10","doi-asserted-by":"publisher","first-page":"4518","DOI":"10.1021\/acs.jcim.0c00464","volume":"60","author":"Court","year":"2020","journal-title":"J. Chem. Inf. Mod."},{"key":"mlstad7a4dbib11","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1021\/acscentsci.0c00426","volume":"6","author":"Kim","year":"2020","journal-title":"ACS Cent. Sci."},{"key":"mlstad7a4dbib12","doi-asserted-by":"publisher","DOI":"10.1002\/advs.202100566","volume":"8","author":"Zhao","year":"2021","journal-title":"Adv. Sci."},{"key":"mlstad7a4dbib13","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1038\/s41524-021-00526-4","volume":"7","author":"Long","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstad7a4dbib14","article-title":"Crystal diffusion variational autoencoder for periodic material generation","author":"Xie","year":"2021"},{"key":"mlstad7a4dbib15","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3eb4","volume":"3","author":"Meldgaard","year":"2021","journal-title":"Mach. Learn.: Sci. Technol."},{"key":"mlstad7a4dbib16","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1038\/s41467-022-28526-y","volume":"13","author":"Gebauer","year":"2022","journal-title":"Nat. Commun."},{"key":"mlstad7a4dbib17","article-title":"Symphony: symmetry-equivariant point-centered spherical harmonics for molecule generation","author":"Daigavane","year":"2023"},{"key":"mlstad7a4dbib18","article-title":"Mattergen: a generative model for inorganic materials design","author":"Zeni","year":"2024"},{"key":"mlstad7a4dbib19","article-title":"Generative adversarial networks","author":"Goodfellow","year":"2014"},{"key":"mlstad7a4dbib20","article-title":"Wasserstein GAN","author":"Arjovsky","year":"2017"},{"key":"mlstad7a4dbib21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/sdata.2014.22","volume":"1","author":"Ramakrishnan","year":"2014","journal-title":"Sci. Data"},{"key":"mlstad7a4dbib22","doi-asserted-by":"publisher","DOI":"10.1063\/1.4812323","volume":"1","author":"Jain","year":"2013","journal-title":"APL Mater."},{"key":"mlstad7a4dbib23","first-page":"p 3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume":"vol 28","author":"Maas","year":"2013"},{"key":"mlstad7a4dbib24","doi-asserted-by":"publisher","DOI":"10.1063\/1.5111045","volume":"10","author":"Kocer","year":"2020","journal-title":"AIP Adv."},{"key":"mlstad7a4dbib25","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1021\/acs.jcim.1c01380","volume":"62","author":"Montes-Campos","year":"2022","journal-title":"J. Chem. Inf. Mod."},{"key":"mlstad7a4dbib26","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.87.184115","volume":"87","author":"Bart\u00f3k","year":"2013","journal-title":"Phys. Rev. B"},{"key":"mlstad7a4dbib27","article-title":"JAX: composable transformations of Python+NumPy programs","author":"Bradbury","year":"2018"},{"key":"mlstad7a4dbib28","first-page":"26","volume":"4","author":"Tieleman","year":"2012","journal-title":"COURSERA: Neural Netw. Machine Learn."},{"key":"mlstad7a4dbib29","article-title":"Improved training of wasserstein gans","author":"Gulrajani","year":"2017"},{"key":"mlstad7a4dbib30","article-title":"Evaluation of mode collapse in generative adversarial networks","author":"Lala","year":"2018"},{"key":"mlstad7a4dbib31","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/22\/25\/253202","volume":"22","author":"Enkovaara","year":"2010","journal-title":"J. Phys.: Condens. Matter"},{"key":"mlstad7a4dbib32","article-title":"Rdkit: Open-source cheminformatics","author":"Landrum","year":"2006"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T06:44:16Z","timestamp":1727073856000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad7a4d"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,1]]},"references-count":32,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2024,9,23]]},"published-print":{"date-parts":[[2024,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad7a4d","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2024-vf9l1-v2","asserted-by":"object"},{"id-type":"doi","id":"10.26434\/chemrxiv-2024-vf9l1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,1]]},"assertion":[{"value":"LoGAN: local generative adversarial network for novel structure prediction","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 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-04-08","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-09-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-09-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}