{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,16]],"date-time":"2025-06-16T08:24:27Z","timestamp":1750062267169,"version":"3.37.3"},"reference-count":47,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"vor","delay-in-days":15,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T00:00:00Z","timestamp":1686873600000},"content-version":"tdm","delay-in-days":15,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100012913","name":"Tata Consultancy Services","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100012913","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001843","name":"Science and Engineering Research Board","doi-asserted-by":"crossref","award":["CRG\/2021\/008036"],"award-info":[{"award-number":["CRG\/2021\/008036"]}],"id":[{"id":"10.13039\/501100001843","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>The generation of low-energy 3D structures of metal clusters depends on the efficiency of the search algorithm and the accuracy of inter-atomic interaction description. In this work, we formulate the search algorithm as a reinforcement learning (RL) problem. Concisely, we propose a novel actor-critic architecture that generates low-lying isomers of metal clusters at a fraction of computational cost than conventional methods. Our RL-based search algorithm uses a previously developed DART model as a reward function to describe the inter-atomic interactions to validate predicted structures. Using the DART model as a reward function incentivizes the RL model to generate low-energy structures and helps generate valid structures. We demonstrate the advantages of our approach over conventional methods for scanning local minima on potential energy surface. Our approach not only generates isomer of gallium clusters at a minimal computational cost but also predicts isomer families that were not discovered through previous density-functional theory (DFT)-based approaches.<\/jats:p>","DOI":"10.1088\/2632-2153\/acdc03","type":"journal-article","created":{"date-parts":[[2023,6,6]],"date-time":"2023-06-06T22:40:42Z","timestamp":1686091242000},"page":"025032","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["MeGen - generation of gallium metal clusters using reinforcement learning"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2012-8031","authenticated-orcid":false,"given":"Rohit","family":"Modee","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ashwini","family":"Verma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kavita","family":"Joshi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7114-3955","authenticated-orcid":true,"given":"U","family":"Deva Priyakumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,6,16]]},"reference":[{"key":"mlstacdc03bib1","doi-asserted-by":"publisher","first-page":"10560","DOI":"10.1073\/pnas.0601782103","article-title":"Clusters: a bridge across the disciplines of physics and chemistry","volume":"103","author":"Jena","year":"2006","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstacdc03bib2","doi-asserted-by":"publisher","first-page":"611","DOI":"10.1103\/RevModPhys.65.611","article-title":"The physics of simple metal clusters: experimental aspects and simple models","volume":"65","author":"De Heer","year":"1993","journal-title":"Rev. Mod. Phys."},{"key":"mlstacdc03bib3","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.92.135506","article-title":"Why do gallium clusters have a higher melting point than the bulk?","volume":"92","author":"Chacko","year":"2004","journal-title":"Phys. Rev. Lett."},{"key":"mlstacdc03bib4","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1103\/RevModPhys.77.371","article-title":"Structural properties of nanoclusters: energetic, thermodynamic and kinetic effects","volume":"77","author":"Baletto","year":"2005","journal-title":"Rev. Mod. Phys."},{"key":"mlstacdc03bib5","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1016\/j.surfrep.2004.10.001","article-title":"Magnetic and structural properties of isolated and assembled clusters","volume":"56","author":"Bansmann","year":"2005","journal-title":"Surf. Sci. Rep."},{"key":"mlstacdc03bib6","doi-asserted-by":"publisher","first-page":"L419","DOI":"10.1088\/0305-4470\/18\/8\/003","article-title":"Computational complexity of the ground-state determination of atomic clusters","volume":"18","author":"Wille","year":"1985","journal-title":"J. Phys. A: Math. Gen."},{"key":"mlstacdc03bib7","doi-asserted-by":"publisher","DOI":"10.1088\/0953-8984\/23\/5\/053201","article-title":"Ab initio random structure searching","volume":"23","author":"Pickard","year":"2011","journal-title":"J. Phys.: Condens. Matter"},{"year":"1992","author":"Holland","key":"mlstacdc03bib8"},{"key":"mlstacdc03bib9","doi-asserted-by":"publisher","first-page":"9973","DOI":"10.1021\/j100141a013","article-title":"Global geometry optimization of clusters using genetic algorithms","volume":"97","author":"Hartke","year":"1993","journal-title":"J. Phys. Chem."},{"key":"mlstacdc03bib10","doi-asserted-by":"publisher","first-page":"9911","DOI":"10.1063\/1.1724816","article-title":"Minima hopping: an efficient search method for the global minimum of the potential energy surface of complex molecular systems","volume":"120","author":"Goedecker","year":"2004","journal-title":"J. Chem. Phys."},{"key":"mlstacdc03bib11","doi-asserted-by":"publisher","first-page":"6611","DOI":"10.1073\/pnas.84.19.6611","article-title":"Monte Carlo-minimization approach to the multiple-minima problem in protein folding","volume":"84","author":"Li","year":"1987","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstacdc03bib12","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.82.094116","article-title":"Crystal structure prediction via particle-swarm optimization","volume":"82","author":"Wang","year":"2010","journal-title":"Phys. Rev. B"},{"key":"mlstacdc03bib13","doi-asserted-by":"publisher","DOI":"10.1088\/1674-1056\/ab4274","article-title":"Cluster structure prediction via calypso method","volume":"28","author":"Tian","year":"2019","journal-title":"Chin. Phys. B"},{"key":"mlstacdc03bib14","doi-asserted-by":"publisher","DOI":"10.1002\/qua.26553","article-title":"Global optimization of chemical cluster structures: methods, applications and challenges","volume":"121","author":"Zhang","year":"2021","journal-title":"Int. J. Quantum Chem."},{"key":"mlstacdc03bib15","doi-asserted-by":"publisher","first-page":"5755","DOI":"10.1021\/acs.chemrev.7b00524","article-title":"Super atomic clusters: design rules and potential for building blocks of materials","volume":"118","author":"Jena","year":"2018","journal-title":"Chem. Rev."},{"key":"mlstacdc03bib16","doi-asserted-by":"publisher","first-page":"4234","DOI":"10.1063\/1.470729","article-title":"The effect of the range of the potential on the structures of clusters","volume":"103","author":"Doye","year":"1995","journal-title":"J. Chem. Phys."},{"key":"mlstacdc03bib17","first-page":"pp 3072","article-title":"Grammar variational autoencoder","volume":"vol 4","author":"Kusner","year":"2017"},{"key":"mlstacdc03bib18","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":"mlstacdc03bib19","first-page":"pp 412","article-title":"Graphvae: towards generation of small graphs using variational autoencoders","volume":"vol 11139 LNCS","author":"Simonovsky","year":"2018"},{"key":"mlstacdc03bib20","first-page":"pp 2323","article-title":"Junction tree variational autoencoder for molecular graph generation","author":"Jin","year":"2018"},{"key":"mlstacdc03bib21","first-page":"pp 1","article-title":"Syntax-directed variational autoencoder for structured data","author":"Dai","year":"2018"},{"article-title":"Objective-Reinforced Generative Adversarial Networks (ORGAN) for sequence generation models","year":"2017","author":"Lima Guimaraes","key":"mlstacdc03bib22"},{"article-title":"MolGAN: an implicit generative model for small molecular graphs","year":"2018","author":"De Cao","key":"mlstacdc03bib23"},{"key":"mlstacdc03bib24","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","article-title":"Generating focused molecule libraries for drug discovery with recurrent neural networks","volume":"4","author":"Segler","year":"2018","journal-title":"ACS Cent. Sci."},{"key":"mlstacdc03bib25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1126\/sciadv.aap7885","article-title":"Deep reinforcement learning for de novo drug design","volume":"4","author":"Popova","year":"2018","journal-title":"Sci. Adv."},{"key":"mlstacdc03bib26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-019-0404-1","article-title":"Mol-CycleGAN: a generative model for molecular optimization","volume":"12","author":"Maziarka","year":"2020","journal-title":"J. Cheminform."},{"key":"mlstacdc03bib27","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-56773-5","article-title":"Molecular geometry prediction using a deep generative graph neural network","volume":"9","author":"Mansimov","year":"2019","journal-title":"Sci. Rep."},{"article-title":"Generating equilibrium molecules with deep neural networks","year":"2018","author":"Gebauer","key":"mlstacdc03bib28"},{"key":"mlstacdc03bib29","doi-asserted-by":"publisher","first-page":"6","DOI":"10.1038\/ncomms13890","article-title":"Quantum-chemical insights from deep tensor neural networks","volume":"8","author":"Sch\u00fctt","year":"2017","journal-title":"Nat. Commun."},{"article-title":"Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules","year":"2019","author":"Gebauer","key":"mlstacdc03bib30"},{"key":"mlstacdc03bib31","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":"mlstacdc03bib32","doi-asserted-by":"publisher","first-page":"1412","DOI":"10.1021\/acscentsci.0c00426","article-title":"Generative adversarial networks for crystal structure prediction","volume":"6","author":"Kim","year":"2020","journal-title":"ACS Cent. Sci."},{"key":"mlstacdc03bib33","first-page":"pp 77","article-title":"PointNet: deep learning on point sets for 3D classification and segmentation","volume":"vol 2017","author":"Qi","year":"2017"},{"key":"mlstacdc03bib34","first-page":"p 2350","article-title":"CrystalGAN: learning to discover crystallographic structures with generative adversarial networks","author":"Nouira","year":"2019"},{"key":"mlstacdc03bib35","doi-asserted-by":"publisher","first-page":"4518","DOI":"10.1021\/acs.jcim.0c00464","article-title":"3-D inorganic crystal structure generation and property prediction via representation learning","volume":"60","author":"Court","year":"2020","journal-title":"J. Chem. Inf. Model."},{"key":"mlstacdc03bib36","doi-asserted-by":"publisher","first-page":"21995","DOI":"10.1039\/D1CP02956H","article-title":"DART: deep learning enabled topological interaction model for energy prediction of metal clusters and its application in identifying unique low energy isomers","volume":"23","author":"Modee","year":"2021","journal-title":"Phys. Chem. Chem. Phys."},{"key":"mlstacdc03bib37","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"},{"key":"mlstacdc03bib38","doi-asserted-by":"publisher","first-page":"1758","DOI":"10.1103\/PhysRevB.59.1758","article-title":"From ultrasoft pseudopotentials to the projector augmented-wave method","volume":"59","author":"Kresse","year":"1999","journal-title":"Phys. Rev. B"},{"key":"mlstacdc03bib39","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":"mlstacdc03bib40","doi-asserted-by":"publisher","first-page":"1396","DOI":"10.1103\/PhysRevLett.78.1396","article-title":"Generalized gradient approximation made simple","volume":"78","author":"Perdew","year":"1997","journal-title":"Phys. Rev. Lett."},{"key":"mlstacdc03bib41","doi-asserted-by":"publisher","first-page":"14251","DOI":"10.1103\/PhysRevB.49.14251","article-title":"Ab initio molecular-dynamics simulation of the liquid-metal\u2013amorphous-semiconductor transition in germanium","volume":"49","author":"Kresse","year":"1994","journal-title":"Phys. Rev. B"},{"key":"mlstacdc03bib42","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":"mlstacdc03bib43","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":"mlstacdc03bib44","first-page":"1","article-title":"Symmetry-aware actor-critic for 3d molecular design","author":"Simm","year":"2020"},{"key":"mlstacdc03bib45","article-title":"Cormorant: covariant molecular neural networks","volume":"vol 32","author":"Anderson","year":"2019"},{"article-title":"Automatic differentiation in PyTorch","year":"2017","author":"Paszke","key":"mlstacdc03bib46"},{"key":"mlstacdc03bib47","doi-asserted-by":"publisher","DOI":"10.1063\/1.4891867","article-title":"Scaling up the shape: a novel growth pattern of gallium clusters","volume":"141","author":"Kaware","year":"2014","journal-title":"J. Chem. Phys."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T10:57:04Z","timestamp":1686913024000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acdc03"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":47,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,6,16]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acdc03","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"assertion":[{"value":"MeGen - generation of gallium metal clusters using reinforcement learning","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-02-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-06","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-16","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}