{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,13]],"date-time":"2026-03-13T10:21:47Z","timestamp":1773397307909,"version":"3.50.1"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T00:00:00Z","timestamp":1676851200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100004543","name":"Chinese Scholarship Council","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004543","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100003246","name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","doi-asserted-by":"publisher","award":["STW-Veni #14410"],"award-info":[{"award-number":["STW-Veni #14410"]}],"id":[{"id":"10.13039\/501100003246","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Rational drug design often starts from specific scaffolds to which side chains\/substituents are added or modified due to the large drug-like chemical space available to search for novel drug-like molecules. With the rapid growth of  deep learning in drug discovery, a variety of effective approaches have been developed for de novo drug design. In previous work we proposed a method named\n                    <jats:italic>DrugEx<\/jats:italic>\n                    , which can be applied in polypharmacology based on multi-objective deep reinforcement learning. However, the previous version is trained under fixed objectives and does not allow users to input any prior information (\n                    <jats:italic>i.e.<\/jats:italic>\n                    a desired scaffold). In order to improve the general applicability, we updated\n                    <jats:italic>DrugEx<\/jats:italic>\n                    to design drug molecules based on scaffolds which consist of multiple fragments provided by users. Here, a\u00a0 Transformer model was employed to generate molecular structures. The Transformer is a multi-head self-attention deep learning model containing an encoder to receive scaffolds as input and a decoder to generate molecules as output. In order to deal with the graph representation of molecules a novel positional encoding for each atom and bond based on an adjacency matrix was proposed, extending the architecture of the Transformer. The graph Transformer model contains growing and connecting procedures for molecule generation starting from\u00a0  a\u00a0given scaffold based on fragments. Moreover, the generator was trained under a reinforcement learning framework to increase the number of desired ligands. As a proof of concept, the method was applied to design ligands for the adenosine A\n                    <jats:sub>2A<\/jats:sub>\n                    receptor (A\n                    <jats:sub>2A<\/jats:sub>\n                    AR) and compared with SMILES-based methods. The results show that 100% of the generated molecules are valid and most of them had a high predicted affinity value towards A\n                    <jats:sub>2A<\/jats:sub>\n                    AR with given scaffolds.\n                  <\/jats:p>","DOI":"10.1186\/s13321-023-00694-z","type":"journal-article","created":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T03:03:08Z","timestamp":1676862188000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":62,"title":["DrugEx v3: scaffold-constrained drug design with graph transformer-based reinforcement learning"],"prefix":"10.1186","volume":"15","author":[{"given":"Xuhan","family":"Liu","sequence":"first","affiliation":[]},{"given":"Kai","family":"Ye","sequence":"additional","affiliation":[]},{"given":"Herman W. T.","family":"van Vlijmen","sequence":"additional","affiliation":[]},{"given":"Adriaan P.","family":"IJzerman","sequence":"additional","affiliation":[]},{"given":"Gerard J. P.","family":"van Westen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,20]]},"reference":[{"issue":"8","key":"694_CR1","doi-asserted-by":"publisher","first-page":"675","DOI":"10.1007\/s10822-013-9672-4","volume":"27","author":"PG Polishchuk","year":"2013","unstructured":"Polishchuk PG, Madzhidov TI, Varnek A (2013) Estimation of the size of drug-like chemical space based on GDB-17 data. J Comput Aided Mol Des 27(8):675\u2013679","journal-title":"J Comput Aided Mol Des"},{"issue":"3","key":"694_CR2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1038\/nrd2220","volume":"6","author":"PJ Hajduk","year":"2007","unstructured":"Hajduk PJ, Greer J (2007) A decade of fragment-based drug design: strategic advances and lessons learned. Nat Rev Drug Discov 6(3):211\u2013219","journal-title":"Nat Rev Drug Discov"},{"issue":"2","key":"694_CR3","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1038\/nbt1059","volume":"23","author":"GL Card","year":"2005","unstructured":"Card GL, Blasdel L, England BP, Zhang C, Suzuki Y, Gillette S, Fong D, Ibrahim PN, Artis DR, Bollag G et al (2005) A family of phosphodiesterase inhibitors discovered by cocrystallography and scaffold-based drug design. Nat Biotechnol 23(2):201\u2013207","journal-title":"Nat Biotechnol"},{"issue":"3","key":"694_CR4","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1208\/s12248-018-0216-7","volume":"20","author":"Y Bian","year":"2018","unstructured":"Bian Y, Xie XS (2018) Computational fragment-based drug design: current trends, strategies, and applications. AAPS J 20(3):59","journal-title":"AAPS J"},{"issue":"6","key":"694_CR5","doi-asserted-by":"publisher","first-page":"1239","DOI":"10.1111\/j.1476-5381.2010.01127.x","volume":"162","author":"JP Hughes","year":"2011","unstructured":"Hughes JP, Rees S, Kalindjian SB, Philpott KL (2011) Principles of early drug discovery. Br J Pharmacol 162(6):1239\u20131249","journal-title":"Br J Pharmacol"},{"issue":"3","key":"694_CR6","doi-asserted-by":"publisher","first-page":"554","DOI":"10.1002\/med.21255","volume":"33","author":"C Sheng","year":"2013","unstructured":"Sheng C, Zhang W (2013) Fragment informatics and computational fragment-based drug design: an overview and update. Med Res Rev 33(3):554\u2013598","journal-title":"Med Res Rev"},{"issue":"1","key":"694_CR7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1038\/nrd.2016.230","volume":"16","author":"R Santos","year":"2017","unstructured":"Santos R, Ursu O, Gaulton A, Bento AP, Donadi RS, Bologa CG, Karlsson A, Al-Lazikani B, Hersey A, Oprea TI et al (2017) A comprehensive map of molecular drug targets. Nat Rev Drug Discov 16(1):19\u201334","journal-title":"Nat Rev Drug Discov"},{"issue":"8","key":"694_CR8","doi-asserted-by":"publisher","first-page":"1284","DOI":"10.1016\/j.yexcr.2010.02.004","volume":"316","author":"BB Fredholm","year":"2010","unstructured":"Fredholm BB (2010) Adenosine receptors as drug targets. Exp Cell Res 316(8):1284\u20131288","journal-title":"Exp Cell Res"},{"issue":"4","key":"694_CR9","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1038\/nrd3955","volume":"12","author":"JF Chen","year":"2013","unstructured":"Chen JF, Eltzschig HK, Fredholm BB (2013) Adenosine receptors as drug targets\u2013what are the challenges? Nat Rev Drug Discov 12(4):265\u2013286","journal-title":"Nat Rev Drug Discov"},{"issue":"2","key":"694_CR10","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1002\/med.20048","volume":"26","author":"S Moro","year":"2006","unstructured":"Moro S, Gao ZG, Jacobson KA, Spalluto G (2006) Progress in the pursuit of therapeutic adenosine receptor antagonists. Med Res Rev 26(2):131\u2013159","journal-title":"Med Res Rev"},{"key":"694_CR11","doi-asserted-by":"crossref","unstructured":"Jespers W, Oliveira A, Prieto-Diaz R, Majellaro M, Aqvist J, Sotelo E, Gutierrez-de-Teran H (2017) Structure-Based Design of Potent and Selective Ligands at the Four Adenosine Receptors. Molecules 22(11): 1945.","DOI":"10.3390\/molecules22111945"},{"issue":"7553","key":"694_CR12","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"key":"694_CR13","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1007\/978-1-0716-0826-5_6","volume":"2190","author":"X Liu","year":"2021","unstructured":"Liu X, IJzerman AP, van Westen GJP (2021) Computational approaches for de novo drug design: past, present, and future. Methods Mol Biol 2190:139\u2013165","journal-title":"Methods Mol Biol"},{"issue":"2","key":"694_CR14","doi-asserted-by":"publisher","first-page":"268","DOI":"10.1021\/acscentsci.7b00572","volume":"4","author":"R Gomez-Bombarelli","year":"2018","unstructured":"Gomez-Bombarelli R, Wei JN, Duvenaud D, Hernandez-Lobato JM, Sanchez-Lengeling B, Sheberla D, Aguilera-Iparraguirre J, Hirzel TD, Adams RP, Aspuru-Guzik A (2018) Automatic chemical design using a data-driven continuous representation of molecules. ACS Cent Sci 4(2):268\u2013276","journal-title":"ACS Cent Sci"},{"issue":"1","key":"694_CR15","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1021\/acscentsci.7b00512","volume":"4","author":"MHS Segler","year":"2018","unstructured":"Segler MHS, Kogej T, Tyrchan C, Waller MP (2018) Generating focused molecule libraries for drug discovery with recurrent neural networks. ACS Cent Sci 4(1):120\u2013131","journal-title":"ACS Cent Sci"},{"key":"694_CR16","unstructured":"Benjamin S-L, Carlos O, Gabriel L. G, Alan A-G (2017) Optimizing distributions over molecular space. An Objective-Reinforced Generative Adversarial Network for Inverse-design Chemistry (ORGANIC)."},{"issue":"1","key":"694_CR17","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1186\/s13321-017-0235-x","volume":"9","author":"M Olivecrona","year":"2017","unstructured":"Olivecrona M, Blaschke T, Engkvist O, Chen H (2017) Molecular de-novo design through deep reinforcement learning. J Cheminform 9(1):48","journal-title":"J Cheminform"},{"issue":"12","key":"694_CR18","doi-asserted-by":"publisher","first-page":"5918","DOI":"10.1021\/acs.jcim.0c00915","volume":"60","author":"T Blaschke","year":"2020","unstructured":"Blaschke T, Arus-Pous J, Chen H, Margreitter C, Tyrchan C, Engkvist O, Papadopoulos K, Patronov A (2020) REINVENT 2.0: An AI tool for de novo drug design. J Chem Inf Model 60(12):5918\u20135922","journal-title":"J Chem Inf Model"},{"issue":"4","key":"694_CR19","doi-asserted-by":"publisher","first-page":"1153","DOI":"10.1039\/C9SC04503A","volume":"11","author":"J Lim","year":"2019","unstructured":"Lim J, Hwang SY, Moon S, Kim S, Kim WY (2019) Scaffold-based molecular design with a graph generative model. Chem Sci 11(4):1153\u20131164","journal-title":"Chem Sci"},{"issue":"1","key":"694_CR20","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1021\/acs.jcim.9b00727","volume":"60","author":"Y Li","year":"2020","unstructured":"Li Y, Hu J, Wang Y, Zhou J, Zhang L, Liu Z (2020) DeepScaffold: a comprehensive tool for scaffold-based de novo drug discovery using deep learning. J Chem Inf Model 60(1):77\u201391","journal-title":"J Chem Inf Model"},{"issue":"1","key":"694_CR21","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1186\/s13321-020-00441-8","volume":"12","author":"J Arus-Pous","year":"2020","unstructured":"Arus-Pous J, Patronov A, Bjerrum EJ, Tyrchan C, Reymond JL, Chen H, Engkvist O (2020) SMILES-based deep generative scaffold decorator for de-novo drug design. J Cheminform 12(1):38","journal-title":"J Cheminform"},{"key":"694_CR22","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin IJae-p (2017) Attention is all you need. In.: arXiv:1706.03762."},{"issue":"31","key":"694_CR23","doi-asserted-by":"publisher","first-page":"8312","DOI":"10.1039\/D0SC03126G","volume":"11","author":"Y Yang","year":"2020","unstructured":"Yang Y, Zheng S, Su S, Zhao C, Xu J, Chen H (2020) SyntaLinker: automatic fragment linking with deep conditional transformer neural networks. Chem Sci 11(31):8312\u20138322","journal-title":"Chem Sci"},{"issue":"1","key":"694_CR24","doi-asserted-by":"publisher","first-page":"35","DOI":"10.1186\/s13321-019-0355-6","volume":"11","author":"X Liu","year":"2019","unstructured":"Liu X, Ye K, van Vlijmen HWT, IJzerman AP, van Westen GJP, (2019) An exploration strategy improves the diversity of de novo ligands using deep reinforcement learning: a case for the adenosine A2A receptor. J Cheminform 11(1):35","journal-title":"J Cheminform"},{"issue":"1","key":"694_CR25","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1186\/s13321-021-00561-9","volume":"13","author":"X Liu","year":"2021","unstructured":"Liu X, Ye K, van Vlijmen HWT, Emmerich MTM, IJzerman AP, van Westen GJP (2021) DrugEx v2: de novo design of drug molecules by Pareto-based multi-objective reinforcement learning in polypharmacology. J Cheminform 13(1):85","journal-title":"J Cheminform"},{"issue":"Database issue","key":"694_CR26","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A, Bellis LJ, Bento AP, Chambers J, Davies M, Hersey A, Light Y, McGlinchey S, Michalovich D, Al-Lazikani B et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40(Database issue):D1100-1107","journal-title":"Nucleic Acids Res"},{"issue":"9","key":"694_CR27","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1007\/s10822-015-9860-5","volume":"29","author":"G Papadatos","year":"2015","unstructured":"Papadatos G, Gaulton A, Hersey A, Overington JP (2015) Activity, assay and target data curation and quality in the ChEMBL database. J Comput Aided Mol Des 29(9):885\u2013896","journal-title":"J Comput Aided Mol Des"},{"issue":"1","key":"694_CR28","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1186\/s13321-017-0232-0","volume":"9","author":"EB Lenselink","year":"2017","unstructured":"Lenselink EB, Ten Dijke N, Bongers B, Papadatos G, van Vlijmen HWT, Kowalczyk W, IJzerman AP, van Westen GJP, (2017) Beyond the hype: deep neural networks outperform established methods using a ChEMBL bioactivity benchmark set. J Cheminform 9(1):45","journal-title":"J Cheminform"},{"issue":"10","key":"694_CR29","doi-asserted-by":"publisher","first-page":"1503","DOI":"10.1002\/cmdc.200800178","volume":"3","author":"J Degen","year":"2008","unstructured":"Degen J, Wegscheid-Gerlach C, Zaliani A, Rarey M (2008) On the art of compiling and using \u201cdrug-like\u201d chemical fragment spaces. ChemMedChem 3(10):1503\u20131507","journal-title":"ChemMedChem"},{"key":"694_CR30","unstructured":"PyTorch. https:\/\/pytorch.org\/."},{"key":"694_CR31","unstructured":"Dosovitskiy A, Beyer L, Kolesnikov A, Weissenborn D, Zhai X, Unterthiner T, Dehghani M, Minderer M, Heigold G, Gelly S et al (2020) An image is worth 16x16 words: transformers for image recognition at scale. In.: arXiv:2010.11929."},{"issue":"2","key":"694_CR32","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/nchem.1243","volume":"4","author":"GR Bickerton","year":"2012","unstructured":"Bickerton GR, Paolini GV, Besnard J, Muresan S, Hopkins AL (2012) Quantifying the chemical beauty of drugs. Nat Chem 4(2):90\u201398","journal-title":"Nat Chem"},{"key":"694_CR33","unstructured":"Scikit-Learn: machine learning in Python. http:\/\/www.scikit-learn.org\/."},{"issue":"1","key":"694_CR34","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/1758-2946-1-8","volume":"1","author":"P Ertl","year":"2009","unstructured":"Ertl P, Schuffenhauer A (2009) Estimation of synthetic accessibility score of drug-like molecules based on molecular complexity and fragment contributions. J Cheminform 1(1):8","journal-title":"J Cheminform"},{"issue":"2","key":"694_CR35","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1007\/BF02426650","volume":"1","author":"AR Solow","year":"1994","unstructured":"Solow AR, Polasky S (1994) Measuring biological diversity. Environ Ecol Stat 1(2):95\u2013103","journal-title":"Environ Ecol Stat"},{"issue":"11","key":"694_CR36","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0027518","volume":"6","author":"GJ van Westen","year":"2011","unstructured":"van Westen GJ, Wegner JK, Geluykens P, Kwanten L, Vereycken I, Peeters A, Ijzerman AP, van Vlijmen HW, Bender A (2011) Which compound to select in lead optimization? Prospectively validated proteochemometric models guide preclinical development. PLoS ONE 6(11):e27518","journal-title":"PLoS ONE"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00694-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-023-00694-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00694-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,20]],"date-time":"2023-02-20T03:05:05Z","timestamp":1676862305000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-023-00694-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,20]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["694"],"URL":"https:\/\/doi.org\/10.1186\/s13321-023-00694-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2021-px6kz","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,20]]},"assertion":[{"value":"9 April 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"24"}}