{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:14:08Z","timestamp":1757312048174,"version":"3.37.3"},"reference-count":59,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T00:00:00Z","timestamp":1687996800000},"content-version":"vor","delay-in-days":28,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T00:00:00Z","timestamp":1687996800000},"content-version":"tdm","delay-in-days":28,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Science Foundation","award":["OAC 2005572"],"award-info":[{"award-number":["OAC 2005572"]}]},{"name":"Department of Energy, Office of Science, Advanced Scientific Computing Research","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]},{"name":"Laboratory Directed Research and Development (LDRD) funding from Argonne National Laboratory, provided by the Director, Office of Science","award":["DE-AC02-06CH11357"],"award-info":[{"award-number":["DE-AC02-06CH11357"]}]}],"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>We introduce an end-to-end computational framework that allows for hyperparameter optimization using the <jats:monospace>DeepHyper<\/jats:monospace> library, accelerated model training, and interpretable AI inference. The framework is based on state-of-the-art AI models including <jats:monospace>CGCNN<\/jats:monospace>, <jats:monospace>PhysNet<\/jats:monospace>, <jats:monospace>SchNet<\/jats:monospace>, <jats:monospace>MPNN<\/jats:monospace>, <jats:monospace>MPNN-transformer<\/jats:monospace>, and <jats:monospace>TorchMD-NET<\/jats:monospace>. We employ these AI models along with the benchmark <jats:monospace>QM9<\/jats:monospace>, <jats:monospace>hMOF<\/jats:monospace>, and <jats:monospace>MD17<\/jats:monospace> datasets to showcase how the models can predict user-specified material properties within modern computing environments. We demonstrate transferable applications in the modeling of small molecules, inorganic crystals and nanoporous metal organic frameworks with a unified, standalone framework. We have deployed and tested this framework in the ThetaGPU supercomputer at the Argonne Leadership Computing Facility, and in the Delta supercomputer at the National Center for Supercomputing Applications to provide researchers with modern tools to conduct accelerated AI-driven discovery in leadership-class computing environments. We release these digital assets as open source scientific software in GitLab, and ready-to-use Jupyter notebooks in Google Colab.<\/jats:p>","DOI":"10.1088\/2632-2153\/acd434","type":"journal-article","created":{"date-parts":[[2023,5,10]],"date-time":"2023-05-10T22:46:39Z","timestamp":1683758799000},"page":"025036","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["End-to-end AI framework for interpretable prediction of molecular and crystal properties"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-5610","authenticated-orcid":false,"given":"Hyun","family":"Park","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9316-7245","authenticated-orcid":true,"given":"Ruijie","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9682-3604","authenticated-orcid":true,"given":"E A","family":"Huerta","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4328-2947","authenticated-orcid":false,"given":"Santanu","family":"Chaudhuri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8434-1010","authenticated-orcid":false,"given":"Emad","family":"Tajkhorshid","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2432-972X","authenticated-orcid":true,"given":"Donny","family":"Cooper","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2023,6,29]]},"reference":[{"key":"mlstacd434bib1","doi-asserted-by":"publisher","DOI":"10.1063\/1.5019779","volume":"148","author":"Sch\u00fctt","year":"2018","journal-title":"J. Chem. Phys."},{"key":"mlstacd434bib2","doi-asserted-by":"publisher","first-page":"3678","DOI":"10.1021\/acs.jctc.9b00181","volume":"15","author":"Unke","year":"2019","journal-title":"J. Chem. Theory Comput."},{"year":"2022","author":"Th\u00f6lke","key":"mlstacd434bib3"},{"year":"2020","author":"Klicpera","key":"mlstacd434bib4"},{"key":"mlstacd434bib5","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.145301","volume":"120","author":"Xie","year":"2018","journal-title":"Phys. Rev. Lett."},{"key":"mlstacd434bib6","first-page":"1","volume":"22","author":"Liu","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacd434bib7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-021-00554-0","volume":"7","author":"Fung","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstacd434bib8","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1038\/s41597-022-01712-9","volume":"9","author":"Ravi","year":"2022","journal-title":"Sci. Data"},{"key":"mlstacd434bib9","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1186\/s40537-020-00361-2","volume":"7","author":"Huerta","year":"2020","journal-title":"J. Big Data"},{"key":"mlstacd434bib10","doi-asserted-by":"publisher","first-page":"1062","DOI":"10.1038\/s41550-021-01405-0","volume":"5","author":"Huerta","year":"2021","journal-title":"Nat. Astron."},{"key":"mlstacd434bib11","first-page":"pp 42","article-title":"DeepHyper: asynchronous hyperparameter search for deep neural networks","author":"Balaprakash","year":"2018"},{"key":"mlstacd434bib12","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstacd434bib13","doi-asserted-by":"publisher","first-page":"9849","DOI":"10.1039\/c2ee23201d","volume":"5","author":"Wilmer","year":"2012","journal-title":"Energy Environ. Sci."},{"key":"mlstacd434bib14","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.1603015","volume":"3","author":"Chmiela","year":"2017","journal-title":"Sci. Adv."},{"article-title":"Experiment tracking with weights and biases software available from wandb.com","year":"2020","author":"Biewald","key":"mlstacd434bib15"},{"year":"2018","author":"Pope","key":"mlstacd434bib16"},{"key":"mlstacd434bib17","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1007\/s11263-017-1059-x","volume":"126","author":"Zhang","year":"2018","journal-title":"Int. J. Comput. Vis."},{"key":"mlstacd434bib18","first-page":"pp 2921","article-title":"Learning deep features for discriminative localization","author":"Zhou","year":"2016"},{"key":"mlstacd434bib19","first-page":"pp 618","article-title":"Grad-CAM: visual explanations from deep networks via gradient-based localization","author":"Selvaraju","year":"2017"},{"key":"mlstacd434bib20","first-page":"pp 1064","article-title":"Training restricted Boltzmann machines using approximations to the likelihood gradient","author":"Tieleman","year":"2008"},{"key":"mlstacd434bib21","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1038\/s42256-020-0160-y","volume":"2","author":"Moret","year":"2020","journal-title":"Nat. Mach. Intell."},{"year":"2018","author":"McInnes","key":"mlstacd434bib22"},{"article-title":"AI Suite for small molecules and inorganic crystals","year":"2023","author":"Park","key":"mlstacd434bib23"},{"article-title":"Colab AI tutorial for small molecules and inorganic crystals","year":"2023","author":"Park","key":"mlstacd434bib24"},{"year":"2023","author":"Park","key":"mlstacd434bib25"},{"key":"mlstacd434bib26","first-page":"pp 6790","volume":"vol 34","author":"Gasteiger","year":"2021"},{"article-title":"Spherical message passing for 3D molecular graphs","year":"2022","author":"Liu","key":"mlstacd434bib27"},{"article-title":"ComENet: towards complete and efficient message passing for 3D molecular graphs","year":"2022","author":"Wang","key":"mlstacd434bib28"},{"key":"mlstacd434bib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41524-021-00650-1","volume":"7","author":"Choudhary","year":"2021","journal-title":"npj Comput. Mater."},{"key":"mlstacd434bib30","doi-asserted-by":"publisher","first-page":"3564","DOI":"10.1021\/acs.chemmater.9b01294","volume":"31","author":"Chen","year":"2019","journal-title":"Chem. Mater."},{"first-page":"pp 199","year":"2020","author":"Gilmer","key":"mlstacd434bib31"},{"key":"mlstacd434bib32","first-page":"pp 593","article-title":"Modeling relational data with graph convolutional networks","volume":"vol 15","author":"Schlichtkrull","year":"2018"},{"key":"mlstacd434bib33","doi-asserted-by":"publisher","DOI":"10.1088\/1361-648X\/aa680e","volume":"29","author":"Larsen","year":"2017","journal-title":"J. Phys.: Condens. Matter"},{"year":"2019","author":"Wang","key":"mlstacd434bib34"},{"article-title":"Fast graph representation learning with PyTorch geometric","year":"2019","author":"Fey","key":"mlstacd434bib35"},{"article-title":"GraphTSNE: a visualization technique for graph-structured data","year":"2019","author":"Leow","key":"mlstacd434bib36"},{"key":"mlstacd434bib37","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2104878118","volume":"118","author":"Gelman","year":"2021","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstacd434bib38","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"Mnih","year":"2015","journal-title":"Nature"},{"year":"2013","author":"Simonyan","key":"mlstacd434bib39"},{"key":"mlstacd434bib40","first-page":"pp 10772","article-title":"Explainability methods for graph convolutional neural networks","author":"Pope","year":"2019"},{"article-title":"Papers with code\u2014gradient clipping explained","year":"2021","author":"","key":"mlstacd434bib41"},{"key":"mlstacd434bib42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13321-019-0391-2","volume":"11","author":"Glavatskikh","year":"2019","journal-title":"J. Cheminform."},{"key":"mlstacd434bib43","doi-asserted-by":"publisher","first-page":"6682","DOI":"10.1021\/acs.cgd.9b01050","volume":"19","author":"Bucior","year":"2019","journal-title":"Cryst. Growth Des."},{"key":"mlstacd434bib44","doi-asserted-by":"publisher","DOI":"10.1016\/j.commatsci.2022.111388","volume":"210","author":"Choudhary","year":"2022","journal-title":"Comput. Mater. Sci."},{"key":"mlstacd434bib45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-88027-8","volume":"11","author":"Krishnapriyan","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstacd434bib46","doi-asserted-by":"publisher","first-page":"27996","DOI":"10.1021\/acs.jpcc.0c06334","volume":"124","author":"Burner","year":"2020","journal-title":"J. Phys. Chem. C"},{"key":"mlstacd434bib47","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1038\/s41563-022-01374-3","volume":"21","author":"Moosavi","year":"2022","journal-title":"Nat. Mater."},{"key":"mlstacd434bib48","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2015.0202","volume":"374","author":"Jolliffe","year":"2016","journal-title":"Phil. Trans. R. Soc. A"},{"key":"mlstacd434bib49","first-page":"2579","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacd434bib50","first-page":"1","volume":"22","author":"Wang","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacd434bib51","doi-asserted-by":"publisher","first-page":"5571","DOI":"10.1021\/jm0705713","article-title":"J. Med. Chem.","volume":"50","author":"Peltason","year":"2007"},{"key":"mlstacd434bib52","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1021\/ci7004093","volume":"48","author":"Guha","year":"2008","journal-title":"J. Chem. Inf. Model."},{"key":"mlstacd434bib53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/ci400572x","volume":"54","author":"Golbraikh","year":"2014","journal-title":"J. Chem. Inf. Model."},{"key":"mlstacd434bib54","doi-asserted-by":"publisher","first-page":"4660","DOI":"10.1021\/acs.jcim.2c00903","volume":"62","author":"Aldeghi","year":"2022","journal-title":"J. Chem. Inf. Model."},{"key":"mlstacd434bib55","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2018.118","volume":"5","author":"Wilkinson","year":"2018","journal-title":"Sci. Data"},{"key":"mlstacd434bib56","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"Wilkinson","year":"2016","journal-title":"Sci. Data"},{"key":"mlstacd434bib57","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1038\/s41597-021-01109-0","volume":"9","author":"Chen","year":"2022","journal-title":"Sci. Data"},{"key":"mlstacd434bib58","doi-asserted-by":"publisher","first-page":"622","DOI":"10.1038\/s41597-022-01710-x","volume":"9","author":"Barker","year":"2022","journal-title":"Sci. Data"},{"year":"2022","author":"Duarte","key":"mlstacd434bib59"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,29]],"date-time":"2023-06-29T11:23:08Z","timestamp":1688037788000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acd434"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,6,29]]},"published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acd434","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2023,6,1]]},"assertion":[{"value":"End-to-end AI framework for interpretable prediction of molecular and crystal properties","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":"2022-12-21","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-05-10","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-06-29","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}