{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,6]],"date-time":"2026-11-06T04:43:49Z","timestamp":1793940229955,"version":"4.8.0"},"reference-count":109,"publisher":"Informa UK Limited","issue":"8","license":[{"start":{"date-parts":[[2022,8,3]],"date-time":"2022-08-03T00:00:00Z","timestamp":1659484800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000057","name":"National Institute of General Medical Sciences","doi-asserted-by":"publisher","award":["R01GM122845"],"award-info":[{"award-number":["R01GM122845"]}],"id":[{"id":"10.13039\/100000057","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institute of Aging","award":["R01AG057555"],"award-info":[{"award-number":["R01AG057555"]}]}],"content-domain":{"domain":["www.tandfonline.com"],"crossmark-restriction":true},"short-container-title":["Expert Opinion on Drug Discovery"],"published-print":{"date-parts":[[2022,8,3]]},"DOI":"10.1080\/17460441.2022.2072288","type":"journal-article","created":{"date-parts":[[2022,5,5]],"date-time":"2022-05-05T12:51:55Z","timestamp":1651755115000},"page":"849-863","update-policy":"https:\/\/doi.org\/10.1080\/tandf_crossmark_01","source":"Crossref","is-referenced-by-count":51,"title":["Reinforcement learning for systems pharmacology-oriented and personalized drug design"],"prefix":"10.1080","volume":"17","author":[{"given":"Ryan K.","family":"Tan","sequence":"first","affiliation":[{"name":"Department of Computer Science, Hunter College, The City University of New York, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1163-6771","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hunter College, The City University of New York, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Xie","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Hunter College, The City University of New York, New York, New York, USA"},{"name":"Program in Computer Science, Biology & Biochemistry, The Graduate Center, The City University of New York, New York, New York, USA"},{"name":"Helen and Robert Appel Alzheimer\u2019s Disease Research Institute, Feil Family Brain & Mind Research Institute, Weill Cornell Medicine, Cornell University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"301","published-online":{"date-parts":[[2022,8,5]]},"reference":[{"key":"cit0001","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-013-9672-4"},{"key":"cit0002","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"cit0003","volume-title":"2nd Int Conf Learn Represent ICLR 2014 - Conf Track Proc","author":"Kingma DP"},{"key":"cit0004","first-page":"1530","volume-title":"32nd Int Conf Mach Learn ICML 2015","volume":"2","author":"Rezende DJ","year":"2015"},{"key":"cit0005","unstructured":"Madhawa K, Ishiguro K, Nakago K, et al. GraphNVP: an invertible flow model for generating molecular graphs. 2019."},{"key":"cit0006","doi-asserted-by":"publisher","DOI":"10.1613\/jair.301"},{"key":"cit0007","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-017-0235-x"},{"key":"cit0008","first-page":"6410","author":"You J","year":"2018","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0009","unstructured":"Guimaraes G, Sanchez-Lengeling B, Outeiral C, et al. Objective-reinforced generative adversarial networks (organ) for sequence generation models."},{"key":"cit0010","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-pharmtox-010611-134630"},{"key":"cit0011","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.25813.1"},{"key":"cit0012","doi-asserted-by":"publisher","DOI":"10.1038\/nrd.2017.111"},{"key":"cit0013","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-020-00285-9"},{"key":"cit0014","doi-asserted-by":"crossref","unstructured":"M\u00e9ndez-Lucio O, Zapata PAM, Wichard J, et al. Cell morphology-guided de novo hit design by conditioning generative adversarial networks on phenotypic image features. 2020.","DOI":"10.26434\/chemrxiv.11594067"},{"key":"cit0015","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03819-2"},{"key":"cit0016","doi-asserted-by":"publisher","DOI":"10.1126\/science.abj8754"},{"key":"cit0017","doi-asserted-by":"crossref","unstructured":"Cai T, Xie L, Chen M, et al. Exploration of dark chemical genomics space via portal learning: applied to targeting the undruggable genome and COVID-19 anti-infective polypharmacology. arXiv Prepr arXiv211114283. 2021.","DOI":"10.21203\/rs.3.rs-1109318\/v1"},{"issue":"5","key":"cit0018","first-page":"679","volume":"6","author":"BELLMAN R","year":"1957","journal-title":"J Math Mech"},{"key":"cit0019","first-page":"1006","volume-title":"Proceedings of the 20th National Conference on Artificial Intelligence -","volume":"2","author":"Munos R","year":"2005"},{"key":"cit0020","doi-asserted-by":"publisher","DOI":"10.1287\/moor.2015.0733"},{"key":"cit0021","first-page":"2005881","volume-title":"ICML 2005 - Proc 22nd Int Conf Mach Learn","author":"Szepesv\u00e1ri C"},{"key":"cit0022","volume-title":"Advances in neural information processing systems","author":"Ghavamzadeh M","year":"2011"},{"key":"cit0023","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"cit0024","unstructured":"Rummery GA, Niranjan M On-line q-learning using connectionist systems; 1994."},{"key":"cit0025","volume-title":"Approximate solutions to Markov decision processes","author":"Gordon GJ","year":"1999"},{"key":"cit0026","volume-title":"Reinforcement learning: an introduction","author":"Sutton RS","year":"2018"},{"key":"cit0027","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.2002.803530"},{"key":"cit0028","doi-asserted-by":"publisher","DOI":"10.1023\/A:1017928328829"},{"key":"cit0029","first-page":"9558","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"35","author":"Shen J","year":"2021"},{"key":"cit0030","first-page":"503","volume":"6","author":"Ernst D","year":"2005","journal-title":"J Mach Learn Res"},{"key":"cit0031","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"cit0032","first-page":"2613","volume":"23","author":"Hasselt H","year":"2010","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0033","first-page":"1995","volume-title":"International conference on machine learning","author":"Wang Z","year":"2016"},{"key":"cit0034","unstructured":"Schaul T, Quan J, Antonoglou I, et al. Prioritized experience replay. arXiv Prepr arXiv151105952. 2015."},{"key":"cit0035","first-page":"449","volume-title":"34th Int Conf Mach Learn ICML","author":"Bellemare MG","year":"2017"},{"key":"cit0036","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11791"},{"key":"cit0037","first-page":"32","author":"Yang D","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0038","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992696"},{"key":"cit0039","first-page":"173","author":"Ghavamzadeh M","year":"2003","journal-title":"Comput Sci Dep Fac Publ Ser"},{"issue":"9","key":"cit0040","volume":"5","author":"Greensmith E","year":"2004","journal-title":"J Mach Learn Res"},{"key":"cit0041","first-page":"1008","author":"Konda VR","year":"2000","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0042","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2012.6315022"},{"key":"cit0043","first-page":"1928","volume-title":"International conference on machine learning","author":"Mnih V","year":"2016"},{"key":"cit0044","author":"Schulman J","year":"2016","journal-title":"Proceedings of the International Conference on Learning Representations (ICLR)"},{"key":"cit0045","first-page":"449","volume":"70","author":"Kimura H","year":"1998","journal-title":"ICML"},{"key":"cit0046","first-page":"1889","author":"Schulman J","year":"2015","journal-title":"International conference on machine learning"},{"key":"cit0047","unstructured":"Schulman J, Wolski F, Dhariwal P, et al. Proximal policy optimization algorithms. ArXiv preprint arXiv:1707.06347. 2017 Jul 20."},{"key":"cit0048","unstructured":"Lillicrap TP, Hunt JJ, Pritzel A, et al. Continuous control with deep reinforcement learning. Continuous control with deep reinforcement learning. arXiv preprint. arXiv:1509.02971. 2015 Sep 9."},{"key":"cit0049","unstructured":"Fujimoto S, van Hoof H, Meger D. Addressing function approximation error in actor-critic methods. In International conference on machine learning. 2018 Jul 3; pp 1587-1596."},{"key":"cit0050","unstructured":"Haarnoja T, Zhou A, Abbeel P, et al. Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: In International conference on machine learning. 2018 Jul 3; pp. 1861-1870."},{"key":"cit0051","unstructured":"Kaiser \u0141, Babaeizadeh M, Mi\u0142os P, et al. Model-Based Reinforcement Learning for Atari. arXiv preprint. arXiv:1903.00374. 2019 Mar 1."},{"key":"cit0052","doi-asserted-by":"publisher","DOI":"10.1109\/ROBOT.1997.606886"},{"key":"cit0053","unstructured":"Berkenkamp F, Turchetta M, Schoellig A, et al.Safe model-based reinforcement learning with stability guarantees.Advances in neural information processing systems. 2017;30."},{"key":"cit0054","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511546877"},{"issue":"1","key":"cit0055","first-page":"497","volume":"135","author":"Rao AV","year":"2009","journal-title":"Adv Astronaut Sci"},{"key":"cit0056","doi-asserted-by":"publisher","DOI":"10.1016\/S0967-0661(02)00186-7"},{"key":"cit0057","unstructured":"Chua K, Calandra R, McAllister R, et al. Deep reinforcement learning in a handful of trials using probabilistic dynamics models. Advances in neural information processing systems. 2018;31."},{"key":"cit0058","doi-asserted-by":"crossref","unstructured":"Nagabandi A, Kahn G, Fearing RS, et al. Neural Network dynamics for model-based deep reinforcement learning with model-free fine-tuning. In 2018 IEEE International Conference on Robotics and Automation (ICRA) 2018 May 21 (pp. 7559-7566).","DOI":"10.1109\/ICRA.2018.8463189"},{"key":"cit0059","unstructured":"Deisenroth M, Rasmussen C. PILCO: a model-based and data-efficient approach to policy search. 2011."},{"key":"cit0060","first-page":"1","volume-title":"International conference on machine learning; PMLR","author":"Levine S","year":"2013"},{"key":"cit0061","unstructured":"Heess N, Wayne G, Silver D, et al. Learning continuous control policies by stochastic value gradients. Advances in neural information processing systems. 2015;28."},{"key":"cit0062","doi-asserted-by":"publisher","DOI":"10.1016\/B978-1-55860-141-3.50030-4"},{"key":"cit0063","volume-title":"6th Int Conf Learn Represent ICLR 2018 - Conf Track Proc","author":"Kurutach T","year":"2018"},{"key":"cit0064","first-page":"6463","volume-title":"35th Int Conf Mach Learn ICML 2018","volume":"9","author":"Parmas P","year":"2019"},{"key":"cit0065","first-page":"32","author":"Janner M","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0066","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1203"},{"key":"cit0067","first-page":"11","author":"Polykovskiy D","year":"2020","journal-title":"Front Pharmacol"},{"key":"cit0068","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.8b00839"},{"key":"cit0069","volume-title":"ICLR Workshop Track","author":"Neil D","year":"2018"},{"key":"cit0070","unstructured":"Yang X, Aasawat TK, Yoshizoe K Practical massively parallEl monte-carlo tree search applied to molecular design. 2020."},{"key":"cit0071","first-page":"12008","volume":"33","author":"Ahn S","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0072","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2020.07.063"},{"key":"cit0073","volume-title":"5th Int Conf Learn Represent ICLR 2017 - Workshop Track Proc","author":"Bello I","year":"2016"},{"key":"cit0074","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab333"},{"key":"cit0075","doi-asserted-by":"crossref","unstructured":"Atance SR, Diez JV, Engkvist O, et al. De Novo drug design using reinforcement learning with graph-based deep generative models. 2021.","DOI":"10.1021\/acs.jcim.2c00838"},{"key":"cit0076","unstructured":"Popova M, Shvets M, Oliva J, et al. MolecularRNN: generating realistic molecular graphs with optimized properties. arXiv Prepr arXiv190513372. 2019."},{"key":"cit0077","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-019-0355-6"},{"key":"cit0078","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-021-00498-z"},{"issue":"1","key":"cit0079","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"Zhou Z","year":"2019","journal-title":"Sci Rep"},{"key":"cit0080","author":"Tang B","journal-title":"Biomolecules. 2022 May 25;12(6):746."},{"key":"cit0081","unstructured":"Wen J, Kumar S, Gummadi R, et al. Characterizing the gap between actor-critic and policy gradient. arXiv Prepr arXiv210606932. 2021."},{"key":"cit0082","unstructured":"Simm GNC, Pinsler R, Cs\u00e1nyi G, et al. Symmetry-aware actor-critic for 3D molecular design. arXiv preprint arXiv:2011.12747. 2020 Nov 25."},{"key":"cit0083","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.9b00325"},{"key":"cit0084","doi-asserted-by":"publisher","DOI":"10.1021\/acsomega.0c04153"},{"key":"cit0085","volume-title":"AAAI","author":"Gottipati SK","year":"2021"},{"key":"cit0086","volume-title":"ICML","author":"Gottipati SK","year":"2020"},{"key":"cit0087","doi-asserted-by":"publisher","DOI":"10.1080\/17460441.2018.1496079"},{"key":"cit0088","doi-asserted-by":"publisher","DOI":"10.1007\/s12247-012-9145-7"},{"key":"cit0089","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2017.02.004"},{"key":"cit0090","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2014.02.003"},{"key":"cit0091","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3058954"},{"key":"cit0092","volume-title":"In International Conference on Machine Learning. 2020 Nov 21","author":"Chandak Y"},{"key":"cit0093","first-page":"34","author":"Ghosh D","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0094","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/656"},{"key":"cit0095","first-page":"6910","volume-title":"35th Int Conf Mach Learn ICML 2018","volume":"10","author":"Riedmiller M","year":"2018"},{"key":"cit0096","doi-asserted-by":"publisher","DOI":"10.1016\/j.drudis.2017.05.008"},{"key":"cit0097","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.06.014"},{"key":"cit0098","first-page":"130","volume-title":"36th Int Conf Mach Learn ICML 2019","author":"Agarwal R","year":"2019"},{"key":"cit0099","first-page":"32","author":"Yang R","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"cit0100","first-page":"1063","volume":"325","author":"Chen D","year":"2020","journal-title":"Front Artif Intell Appl"},{"key":"cit0101","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.0c01285"},{"key":"cit0102","unstructured":"Cai T, Abbu KA, Liu Y, et al. DeepREAL: a deep learning powered multi-scale modeling framework towards predicting out-of-distribution receptor activity of ligand binding. bioRxiv. 20212021.09.12.460001."},{"key":"cit0103","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkaa913"},{"key":"cit0104","doi-asserted-by":"crossref","unstructured":"Liu Y, Wu Y, Shen X, et al. COVID-19 multi-targeted drug repurposing using few-shot learning. Frontiers in Bioinformatics. 2021;1:18.","DOI":"10.3389\/fbinf.2021.693177"},{"key":"cit0105","unstructured":"Liu Q, Qiu Y, Xie L. Predictive modeling of multiplex chemical phenomics for novel cells and patients: applied to personalized alzheimer\u2019s disease drug repurposing. bioRxiv. 20212021.08.09.455708."},{"key":"cit0106","author":"He D","year":"2021","journal-title":"bioRxiv"},{"key":"cit0107","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-021-01199-z"},{"key":"cit0108","doi-asserted-by":"publisher","DOI":"10.3390\/molecules190710150"},{"key":"cit0109","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1007680"}],"container-title":["Expert Opinion on Drug Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.tandfonline.com\/doi\/pdf\/10.1080\/17460441.2022.2072288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,4]],"date-time":"2023-02-04T13:06:47Z","timestamp":1675516007000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.tandfonline.com\/doi\/full\/10.1080\/17460441.2022.2072288"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,8,3]]},"references-count":109,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2022,8,3]]}},"alternative-id":["10.1080\/17460441.2022.2072288"],"URL":"https:\/\/doi.org\/10.1080\/17460441.2022.2072288","relation":{},"ISSN":["1746-0441","1746-045X"],"issn-type":[{"value":"1746-0441","type":"print"},{"value":"1746-045X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,8,3]]},"assertion":[{"value":"The publishing and review policy for this title is described in its Aims & Scope.","order":1,"name":"peerreview_statement","label":"Peer Review Statement"},{"value":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=iedc20","URL":"http:\/\/www.tandfonline.com\/action\/journalInformation?show=aimsScope&journalCode=iedc20","order":2,"name":"aims_and_scope_url","label":"Aim & Scope"},{"value":"2021-12-15","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-04-27","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-08-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}