{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T23:45:21Z","timestamp":1780357521442,"version":"3.54.1"},"reference-count":43,"publisher":"IOP Publishing","issue":"4","license":[{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,7,19]],"date-time":"2021-07-19T00:00:00Z","timestamp":1626652800000},"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":[[2021,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Graph generation is an extremely important task, as graphs are found throughout different areas of science and engineering. In this work, we focus on the modern equivalent of the Erdos\u2013R\u00e9nyi random graph model: the graph variational autoencoder (GVAE) (Simonovsky and Komodakis 2018 <jats:italic>Int. Conf. on Artificial Neural Networks<\/jats:italic> pp 412\u201322). This model assumes edges and nodes are independent in order to generate entire graphs at a time using a multi-layer perceptron decoder. As a result of these assumptions, GVAE has difficulty matching the training distribution and relies on an expensive graph matching procedure. We improve this class of models by building a message passing neural network into GVAE\u2019s encoder and decoder. We demonstrate our model on the specific task of generating small organic molecules.<\/jats:p>","DOI":"10.1088\/2632-2153\/abf5b7","type":"journal-article","created":{"date-parts":[[2021,4,7]],"date-time":"2021-04-07T23:59:54Z","timestamp":1617839994000},"page":"045010","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["MPGVAE: improved generation of small organic molecules using message passing neural nets"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9568-3451","authenticated-orcid":false,"given":"Daniel","family":"Flam-Shepherd","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tony C","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8277-4434","authenticated-orcid":false,"given":"Alan","family":"Aspuru-Guzik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2021,7,19]]},"reference":[{"key":"mlstabf5b7bib1","first-page":"pp 4502","article-title":"Interaction networks for learning about objects, relations and physics","author":"Battaglia","year":"2016"},{"key":"mlstabf5b7bib2","doi-asserted-by":"crossref","DOI":"10.18653\/v1\/K16-1002","article-title":"Generating sentences from a continuous space","author":"Bowman","year":"2016"},{"key":"mlstabf5b7bib3","article-title":"InfoGAN: interpretable representation learning by information maximizing generative adversarial nets","author":"Chen","year":"2016"},{"key":"mlstabf5b7bib4","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014"},{"key":"mlstabf5b7bib5","article-title":"Syntax-directed variational autoencoder for structured data","author":"Dai","year":"2018"},{"key":"mlstabf5b7bib6","article-title":"MolGAN: an implicit generative model for small molecular graphs","author":"De Cao","year":"2018"},{"key":"mlstabf5b7bib7","first-page":"pp 4171","article-title":"Bert: pre-training of deep bidirectional transformers for language understanding","volume":"vol 1","author":"Devlin","year":"2019"},{"key":"mlstabf5b7bib8","article-title":"NICE: non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"mlstabf5b7bib9","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"Duvenaud","year":"2015"},{"key":"mlstabf5b7bib10","first-page":"17","article-title":"On the evolution of random graphs","volume":"5","author":"Erdos","year":"1960","journal-title":"Publ. Math. Inst. Hung. Acad. Sci"},{"key":"mlstabf5b7bib11","first-page":"pp 1263","article-title":"Neural message passing for quantum chemistry","volume":"vol 70","author":"Gilmer","year":"2017"},{"key":"mlstabf5b7bib12","doi-asserted-by":"publisher","first-page":"1120","DOI":"10.1038\/nmat4717","article-title":"Design of efficient molecular organic light-emitting diodes by a high-throughput virtual screening and experimental approach","volume":"15","author":"G\u00f3mez-Bombarelli","year":"2016","journal-title":"Nat. Mater."},{"key":"mlstabf5b7bib13","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":"mlstabf5b7bib14","first-page":"pp 2672","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014"},{"key":"mlstabf5b7bib15","article-title":"Graphite: iterative generative modeling of graphs","author":"Grover","year":"2018"},{"key":"mlstabf5b7bib16","article-title":"Learning graphical state transitions","author":"Johnson","year":"2016"},{"key":"mlstabf5b7bib17","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstabf5b7bib18","article-title":"Glow: generative flow with invertible 1\u2009\u00d7\u20091 convolutions","author":"Kingma","year":"2018"},{"key":"mlstabf5b7bib19","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2014"},{"key":"mlstabf5b7bib20","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"mlstabf5b7bib21","article-title":"SELFIES: a robust representation of semantically constrained graphs with an example application in chemistry","author":"Krenn","year":"2019"},{"key":"mlstabf5b7bib22","first-page":"pp 1945","article-title":"Grammar variational autoencoder","volume":"vol 70","author":"Kusner","year":"2017"},{"key":"mlstabf5b7bib23","author":"Landrum","year":"2013"},{"key":"mlstabf5b7bib24","article-title":"Gated graph sequence neural networks","author":"Li","year":"2015"},{"key":"mlstabf5b7bib25","article-title":"Learning deep generative models of graphs","author":"Li","year":"2018"},{"key":"mlstabf5b7bib26","first-page":"pp 4257","article-title":"Efficient graph generation with graph recurrent attention networks","author":"Liao","year":"2019"},{"key":"mlstabf5b7bib27","first-page":"pp 7795","article-title":"Constrained graph variational autoencoders for molecule design","author":"Liu","year":"2018"},{"key":"mlstabf5b7bib28","first-page":"pp 7113","article-title":"Constrained generation of semantically valid graphs via regularizing variational autoencoders","author":"Ma","year":"2018"},{"key":"mlstabf5b7bib29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-4-1","article-title":"Towards a universal SMILES representation\u2014a standard method to generate canonical SMILES based on the InChI","volume":"4","author":"O\u2019Boyle","year":"2012","journal-title":"J. Cheminformatics"},{"key":"mlstabf5b7bib30","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"Radford","year":"2015"},{"key":"mlstabf5b7bib31","doi-asserted-by":"publisher","DOI":"10.1063\/1.4928757","article-title":"Electronic spectra from TDDFT and machine learning in chemical space","volume":"143","author":"Ramakrishnan","year":"2015","journal-title":"J. Chem. Phys."},{"key":"mlstabf5b7bib32","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","article-title":"Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17","volume":"52","author":"Ruddigkeit","year":"2012","journal-title":"J. Chem. Inf. Model."},{"key":"mlstabf5b7bib33","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","article-title":"The graph neural network model","volume":"20","author":"Scarselli","year":"2008","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstabf5b7bib34","first-page":"pp 10353","article-title":"Discrete object generation with reversible inductive construction","author":"Seff","year":"2019"},{"key":"mlstabf5b7bib35","first-page":"pp 412","article-title":"GraphVAE: towards generation of small graphs using variational autoencoders","author":"Simonovsky","year":"2018"},{"key":"mlstabf5b7bib36","first-page":"pp 3483","article-title":"Learning structured output representation using deep conditional generative models","author":"Sohn","year":"2015"},{"key":"mlstabf5b7bib37","first-page":"pp 1017","article-title":"Generating text with recurrent neural networks","author":"Sutskever","year":"2011"},{"key":"mlstabf5b7bib38","first-page":"p 2017","article-title":"Attention is all you need","author":"Vaswani"},{"key":"mlstabf5b7bib39","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"mlstabf5b7bib40","article-title":"Order matters: sequence to sequence for sets","author":"Vinyals","year":"2015"},{"key":"mlstabf5b7bib41","first-page":"pp 6410","article-title":"Graph convolutional policy network for goal-directed molecular graph generation","author":"You","year":"2018a"},{"key":"mlstabf5b7bib42","article-title":"GraphRNN: generating realistic graphs with deep auto-regressive models","author":"You","year":"2018b"},{"key":"mlstabf5b7bib43","doi-asserted-by":"publisher","first-page":"1038","DOI":"10.1038\/s41587-019-0224-x","article-title":"Deep learning enables rapid identification of potent DDR1 kinase inhibitors","volume":"37","author":"Zhavoronkov","year":"2019","journal-title":"Nat. Biotechnol."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,13]],"date-time":"2021-12-13T16:58:56Z","timestamp":1639414736000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf5b7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,19]]},"references-count":43,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2021,7,19]]},"published-print":{"date-parts":[[2021,12,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abf5b7","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,19]]},"assertion":[{"value":"MPGVAE: improved generation of small organic molecules using message passing neural nets","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 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-11-06","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-04-07","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-07-19","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}