{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T12:40:08Z","timestamp":1748004008428,"version":"3.41.0"},"reference-count":51,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T00:00:00Z","timestamp":1747958400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"crossref","award":["Turing AI World-Leading Researcher Fellowship"],"award-info":[{"award-number":["Turing AI World-Leading Researcher Fellowship"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100014438","name":"Business Finland","doi-asserted-by":"crossref","award":["Virtual- Lab4Pharma project number 3597\/31\/2023"],"award-info":[{"award-number":["Virtual- Lab4Pharma project number 3597\/31\/2023"]}],"id":[{"id":"10.13039\/501100014438","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100009047","name":"Strategic Research Council","doi-asserted-by":"crossref","award":["Flagship programme: Finnish Center for Ar- tificia"],"award-info":[{"award-number":["Flagship programme: Finnish Center for Ar- tificia"]}],"id":[{"id":"10.13039\/501100009047","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":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Multi-target property prediction has the potential to improve generalization by exploiting the positive transfer between targets. Molecular generative models utilize independent single-target property prediction networks to discover novel molecules. We propose using multi-target networks to jointly predict several molecular properties and learn better representations by exploiting auxiliary information. Our multi-target model shows improvement in prediction accuracy on the test set. We additionally present results demonstrating promising performance in property prediction in these generative models does not translate to optimization. More specifically, random exploration is competitive with gradient-based strategies and better methods are needed.<\/jats:p>","DOI":"10.1088\/2632-2153\/add8e0","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T22:55:04Z","timestamp":1747263304000},"page":"025042","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-target property prediction and optimization using latent spaces of generative model"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8193-9778","authenticated-orcid":true,"given":"Anirudh","family":"Jain","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7741-2279","authenticated-orcid":true,"given":"Markus","family":"Heinonen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2475-4880","authenticated-orcid":true,"given":"Heikki","family":"K\u00e4sn\u00e4nen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0526-2873","authenticated-orcid":true,"given":"Julius","family":"Sipil\u00e4","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Samuel","family":"Kaski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,5,23]]},"reference":[{"key":"mlstadd8e0bib1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","article-title":"Quantifying the chemical beauty of drugs","volume":"4","author":"Bickerton","year":"2012","journal-title":"Nat. Chem."},{"key":"mlstadd8e0bib2","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."},{"article-title":"Multi-task neural networks for QSAR predictions","year":"2014","author":"Dahl","key":"mlstadd8e0bib3"},{"article-title":"MolGAN: an implicit generative model for small molecular graphs","year":"2018","author":"De Cao","key":"mlstadd8e0bib4"},{"article-title":"Density estimation using real NVP","year":"2017","author":"Dinh","key":"mlstadd8e0bib5"},{"key":"mlstadd8e0bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-1-8","article-title":"Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions","volume":"1","author":"Ertl","year":"2009","journal-title":"J. Cheminform."},{"year":"2010","author":"Faulon","key":"mlstadd8e0bib7"},{"key":"mlstadd8e0bib8","first-page":"595","article-title":"Evolutionary latent space exploration of generative adversarial networks","author":"Fernandes","year":"2020"},{"key":"mlstadd8e0bib9","doi-asserted-by":"publisher","first-page":"5922","DOI":"10.48550\/arXiv.2007.05674","article-title":"Illuminating Mario Scenes in the latent space of a generative adversarial network","volume":"35","author":"Fontaine","year":"2021"},{"key":"mlstadd8e0bib10","doi-asserted-by":"publisher","first-page":"13345","DOI":"10.1007\/s00521-021-05961-4","article-title":"Prediction of chemical compounds properties using a deep learning model","volume":"33","author":"Galushka","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"mlstadd8e0bib11","first-page":"63","article-title":"Modeling ADMET","author":"Ghosh","year":"2016"},{"key":"mlstadd8e0bib12","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"Gilmer","year":"2017"},{"key":"mlstadd8e0bib13","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":"mlstadd8e0bib14","doi-asserted-by":"publisher","first-page":"770","DOI":"10.1109\/CVPR.2016.90","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"article-title":"Graph residual flow for molecular graph generation","year":"2019","author":"Honda","key":"mlstadd8e0bib15"},{"key":"mlstadd8e0bib16","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v37i4.25549","article-title":"Conditional diffusion based on discrete graph structures for molecular graph generation","author":"Huang","year":"2023"},{"key":"mlstadd8e0bib17","doi-asserted-by":"publisher","first-page":"1757","DOI":"10.1021\/ci3001277","article-title":"ZINC: a free tool to discover chemistry for biology","volume":"52","author":"Irwin","year":"2012","journal-title":"J. Chem. Inf. Model."},{"article-title":"Junction tree variational autoencoder for molecular graph generation","year":"2018","author":"Jin","key":"mlstadd8e0bib18"},{"key":"mlstadd8e0bib19","doi-asserted-by":"publisher","first-page":"7482","DOI":"10.1109\/CVPR.2018.00781","article-title":"Multi-task learning using uncertainty to weigh losses for scene geometry and semantics","author":"Kendall","year":"2018"},{"key":"mlstadd8e0bib20","first-page":"10215","article-title":"Glow: generative flow with invertible 1x1 convolutions","author":"Kingma","year":"2018"},{"article-title":"Grammar variational autoencoder","year":"2017","author":"Kusner","key":"mlstadd8e0bib21"},{"key":"mlstadd8e0bib22","doi-asserted-by":"publisher","first-page":"2017","DOI":"10.1016\/j.drudis.2019.07.006","article-title":"Deep learning in drug discovery: opportunities, challenges and future prospects","volume":"24","author":"Lavecchia","year":"2019","journal-title":"Drug Discov. Today"},{"key":"mlstadd8e0bib23","doi-asserted-by":"publisher","DOI":"10.5555\/3327345.3327535","article-title":"Visualizing the loss landscape of neural nets","author":"Li","year":"2018"},{"article-title":"Gated graph sequence neural networks","year":"2015","author":"Li","key":"mlstadd8e0bib24"},{"key":"mlstadd8e0bib25","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.3390\/molecules25061375","article-title":"A review on applications of computational methods in drug screening and design","volume":"25","author":"Lin","year":"2020","journal-title":"Molecules"},{"article-title":"GraphEBM: molecular graph generation with energy-based models","year":"2021","author":"Liu","key":"mlstadd8e0bib26"},{"key":"mlstadd8e0bib27","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157362","article-title":"Stein variational gradient descent: a general purpose Bayesian inference algorithm","author":"Liu","year":"2016"},{"key":"mlstadd8e0bib28","first-page":"7192","article-title":"GraphDF: a discrete flow model for molecular graph generation","author":"Luo","year":"2021"},{"article-title":"GraphNVP: an invertible flow model for generating molecular graphs","year":"2019","author":"Madhawa","key":"mlstadd8e0bib29"},{"key":"mlstadd8e0bib30","doi-asserted-by":"publisher","first-page":"4450","DOI":"10.1021\/acs.jcim.9b00375","article-title":"All-Assay-Max2 pQSAR: activity predictions as accurate as four-concentration IC 50S for 8558 Novartis assays","volume":"59","author":"Martin","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"mlstadd8e0bib31","doi-asserted-by":"publisher","first-page":"2707","DOI":"10.1016\/j.drudis.2021.05.019","article-title":"De novo molecular design and generative models","volume":"26","author":"Meyers","year":"2021","journal-title":"Drug Discov. Today"},{"key":"mlstadd8e0bib32","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1021\/c160017a018","article-title":"The generation of a unique machine description for chemical structures\u2014a technique developed at chemical abstracts service","volume":"5","author":"Morgan","year":"1965","journal-title":"J. Chem. Doc."},{"key":"mlstadd8e0bib33","doi-asserted-by":"publisher","first-page":"266","DOI":"10.1109\/WACV51458.2022.00131","article-title":"Joint classification and trajectory regression of online handwriting using a multi-task learning approach","author":"Ott","year":"2022"},{"key":"mlstadd8e0bib34","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5555\/3546258.3546315","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"article-title":"Masked autoregressive flow for density estimation","year":"2017","author":"Papamakarios","key":"mlstadd8e0bib35"},{"article-title":"Massively multitask networks for drug discovery","year":"2015","author":"Ramsundar","key":"mlstadd8e0bib36"},{"key":"mlstadd8e0bib37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1609\/aaai.v33i01.33011110","article-title":"NEVAE: a deep generative model for molecular graphs","volume":"21","author":"Samanta","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"mlstadd8e0bib38","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"Schlichtkrull","year":"2018"},{"article-title":"GraphAF: a flow-based autoregressive model for molecular graph generation","year":"2020","author":"Shi","key":"mlstadd8e0bib39"},{"key":"mlstadd8e0bib40","first-page":"412","article-title":"GraphVAE: towards generation of small graphs using variational autoencoders","author":"Simonovsky","year":"2018"},{"key":"mlstadd8e0bib41","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","article-title":"ZINC 15\u2013ligand discovery for everyone","volume":"55","author":"Sterling","year":"2015","journal-title":"J. Chem. Inf. Model."},{"key":"mlstadd8e0bib42","doi-asserted-by":"publisher","first-page":"11259","DOI":"10.5555\/3495724.3496669","article-title":"Sample-efficient optimization in the latent space of deep generative models via weighted retraining","volume":"33","author":"Tripp","year":"2020"},{"article-title":"DiGress: discrete denoising diffusion for graph generation","year":"2022","author":"Vignac","key":"mlstadd8e0bib43"},{"key":"mlstadd8e0bib44","doi-asserted-by":"publisher","first-page":"681","DOI":"10.5555\/3104482.3104568","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","author":"Welling","year":"2011"},{"key":"mlstadd8e0bib45","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1021\/acs.jcim.8b00785","article-title":"Predictive multitask deep neural network models for ADME-ToX properties: learning from large data sets","volume":"59","author":"Wenzel","year":"2019","journal-title":"J. Chem. Inf. Model."},{"key":"mlstadd8e0bib46","doi-asserted-by":"publisher","first-page":"8016","DOI":"10.1039\/C9SC01928F","article-title":"Efficient multi-objective molecular optimization in a continuous latent space","volume":"10","author":"Winter","year":"2019","journal-title":"Chem. Sci."},{"key":"mlstadd8e0bib47","doi-asserted-by":"publisher","first-page":"844","DOI":"10.1001\/jama.2020.1166","article-title":"Estimated research and development investment needed to bring a new medicine to market, 2009-2018","volume":"323","author":"Wouters","year":"2020","journal-title":"JAMA"},{"key":"mlstadd8e0bib48","doi-asserted-by":"publisher","first-page":"4451","DOI":"10.1039\/D1GC00331C","article-title":"A multi-task deep learning neural network for predicting flammability-related properties from molecular structures","volume":"23","author":"Yang","year":"2021","journal-title":"Green Chem."},{"article-title":"Graph convolutional policy network for goal-directed molecular graph generation","year":"2018","author":"You","key":"mlstadd8e0bib49"},{"key":"mlstadd8e0bib50","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"Zagoruyko","year":"2016"},{"key":"mlstadd8e0bib51","doi-asserted-by":"publisher","first-page":"617","DOI":"10.1145\/3394486.3403104","article-title":"MoFlow: an invertible flow model for generating molecular graphs","author":"Zang","year":"2020"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T11:59:37Z","timestamp":1748001577000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/add8e0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,23]]},"references-count":51,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,5,23]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/add8e0","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,5,23]]},"assertion":[{"value":"Multi-target property prediction and optimization using latent spaces of generative model","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 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-12-26","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-14","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}