{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T22:53:32Z","timestamp":1768344812061,"version":"3.49.0"},"reference-count":38,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T00:00:00Z","timestamp":1647302400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100001475","name":"Nanyang Technological University","doi-asserted-by":"publisher","award":["CN Yang Scholars Programme"],"award-info":[{"award-number":["CN Yang Scholars Programme"]}],"id":[{"id":"10.13039\/501100001475","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Machine Learning and Pharmaceutical Discovery and Synthesis consortium"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:sec><jats:title>Abstract<\/jats:title><jats:p>Retrosynthesis is at the core of organic chemistry. Recently, the rapid growth of artificial intelligence (AI) has spurred a variety of novel machine learning approaches for data-driven synthesis planning. These methods learn complex patterns from reaction databases in order to predict, for a given product, sets of reactants that can be used to synthesise that product. However, their performance as measured by the top-<jats:italic>N<\/jats:italic>accuracy in matching published reaction precedents still leaves room for improvement. This work aims to enhance these models by learning to re-rank their reactant predictions. Specifically, we design and train an energy-based model to re-rank, for each product, the published reaction as the top suggestion and the remaining reactant predictions as lower-ranked. We show that re-ranking can improve one-step models significantly using the standard USPTO-50k benchmark dataset, such as RetroSim, a similarity-based method, from 35.7 to 51.8% top-1 accuracy and NeuralSym, a deep learning method, from 45.7 to 51.3%, and also that re-ranking the union of two models\u2019 suggestions can lead to better performance than either alone. However, the state-of-the-art top-1 accuracy is not improved by this method.<\/jats:p><\/jats:sec><jats:sec><jats:title>Graphical Abstract<\/jats:title><\/jats:sec>","DOI":"10.1186\/s13321-022-00594-8","type":"journal-article","created":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T12:03:55Z","timestamp":1647345835000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Improving the performance of models for one-step retrosynthesis through re-ranking"],"prefix":"10.1186","volume":"14","author":[{"given":"Min Htoo","family":"Lin","sequence":"first","affiliation":[]},{"given":"Zhengkai","family":"Tu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8271-8723","authenticated-orcid":false,"given":"Connor W.","family":"Coley","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"594_CR1","doi-asserted-by":"publisher","first-page":"762","DOI":"10.1039\/CT9171100762","volume":"111","author":"R Robinson","year":"1917","unstructured":"Robinson R (1917) A synthesis of tropinone. J Chem Soc Trans 111:762\u2013768","journal-title":"J Chem Soc Trans"},{"key":"594_CR2","doi-asserted-by":"publisher","first-page":"178","DOI":"10.1126\/science.166.3902.178","volume":"166","author":"EJ Corey","year":"1969","unstructured":"Corey EJ, Wipke WT (1969) Computer-assisted design of complex organic syntheses. Science 166:178\u2013192","journal-title":"Science"},{"key":"594_CR3","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1002\/anie.199104553","volume":"30","author":"EJ Corey","year":"1991","unstructured":"Corey EJ (1991) The logic of chemical synthesis: multistep synthesis of complex carbogenic molecules (Nobel Lecture). Angew Chem Int Ed Eng 30:455\u2013465","journal-title":"Angew Chem Int Ed Eng"},{"key":"594_CR4","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1126\/science.3838594","volume":"228","author":"EJ Corey","year":"1985","unstructured":"Corey EJ, Long AK, Rubenstein SD (1985) Computer-assisted analysis in organic synthesis. Science 228:408\u2013418","journal-title":"Science"},{"key":"594_CR5","doi-asserted-by":"publisher","first-page":"522","DOI":"10.1016\/j.chempr.2018.02.002","volume":"4","author":"T Klucznik","year":"2018","unstructured":"Klucznik T, Mikulak-Klucznik B, McCormack MP, Lima H, Szymku\u0107 S, Bhowmick M, Molga K, Zhou Y, Rickershauser L, Gajewska EP, Toutchkine A (2018) Efficient syntheses of diverse, medicinally relevant targets planned by computer and executed in the laboratory. Chem 4:522\u2013532","journal-title":"Chem"},{"key":"594_CR6","doi-asserted-by":"publisher","first-page":"5966","DOI":"10.1002\/chem.201605499","volume":"23","author":"MH Segler","year":"2017","unstructured":"Segler MH, Waller MP (2017) Neural-symbolic machine learning for retrosynthesis and reaction prediction. Chem Eur J 23:5966\u20135971","journal-title":"Chem Eur J"},{"key":"594_CR7","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1021\/acscentsci.7b00303","volume":"3","author":"B Liu","year":"2017","unstructured":"Liu B, Ramsundar B, Kawthekar P, Shi J, Gomes J, Luu Nguyen Q, Ho S, Sloane J, Wender P, Pande V (2017) Retrosynthetic reaction prediction using neural sequence-to-sequence models. ACS Central Sci 3:1103\u20131113","journal-title":"ACS Central Sci"},{"key":"594_CR8","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1021\/acscentsci.7b00355","volume":"3","author":"CW Coley","year":"2017","unstructured":"Coley CW, Rogers L, Green WH, Jensen KF (2017) Computer-assisted retrosynthesis based on molecular similarity. ACS Central Sci 3:1237\u20131245","journal-title":"ACS Central Sci"},{"key":"594_CR9","unstructured":"Dai H, Li C, Coley C, Dai B, Song L (2019) Retrosynthesis prediction with conditional graph logic network. Adv Neural Inf Process Syst"},{"key":"594_CR10","doi-asserted-by":"crossref","unstructured":"Sacha M, B\u0142a\u017c M, Byrski P, W\u0142odarczyk-Pruszy\u0144ski P, Jastrz\u0119bski S (2020) Molecule edit graph attention network: modeling chemical reactions as sequences of graph edits. arXiv preprint arXiv:2006.15426","DOI":"10.1021\/scimeetings.0c07021"},{"key":"594_CR11","doi-asserted-by":"publisher","first-page":"1281","DOI":"10.1021\/acs.accounts.8b00087","volume":"51","author":"CW Coley","year":"2018","unstructured":"Coley CW, Green WH, Jensen KF (2018) Machine learning in computer-aided synthesis planning. Acc Chem Res 51:1281\u20131289","journal-title":"Acc Chem Res"},{"key":"594_CR12","doi-asserted-by":"publisher","first-page":"5904","DOI":"10.1002\/anie.201506101","volume":"55","author":"S Szymku\u0107","year":"2016","unstructured":"Szymku\u0107 S, Gajewska EP, Klucznik T, Molga K, Dittwald P, Startek M, Bajczyk M, Grzybowski BA (2016) Computer-assisted synthetic planning: the end of the beginning. Angew Chem Int Ed 55:5904\u20135937","journal-title":"Angew Chem Int Ed"},{"key":"594_CR13","doi-asserted-by":"publisher","first-page":"6118","DOI":"10.1002\/chem.201604556","volume":"23","author":"MH Segler","year":"2017","unstructured":"Segler MH, Waller MP (2017) Modelling chemical reasoning to predict and invent reactions. Chem Eur J 23:6118\u20136128","journal-title":"Chem Eur J"},{"key":"594_CR14","doi-asserted-by":"publisher","first-page":"3355","DOI":"10.1039\/C9SC03666K","volume":"11","author":"K Lin","year":"2020","unstructured":"Lin K, Xu Y, Pei J, Lai L (2020) Automatic retrosynthetic route planning using template-free models. Chem Sci 11:3355\u20133364","journal-title":"Chem Sci"},{"key":"594_CR15","unstructured":"Shi C, Xu M, Guo H, Zhang M, Tang J (2020) A Graph to Graphs Framework for Retrosynthesis Prediction. In: Proceedings of the 37th International Conference on Machine Learning, pp 8818\u20138827"},{"key":"594_CR16","unstructured":"Grathwohl W, Wang K-C, Jacobsen J-H, Duvenaud D, Norouzi M, Swersky K (2019) Your classifier is secretly an energy based model and you should treat it like one. arXiv preprint arXiv:1912.03263"},{"key":"594_CR17","unstructured":"Du Y, Mordatch I (2019) Implicit generation and generalization in energy-based models. arXiv preprint arXiv:1903.08689"},{"key":"594_CR18","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1021\/ci00023a005","volume":"35","author":"H Satoh","year":"1995","unstructured":"Satoh H, Funatsu K (1995) SOPHIA, a knowledge base-guided reaction prediction system-utilization of a knowledge base derived from a reaction database. J Chem Inf Comput Sci 35:34\u201344","journal-title":"J Chem Inf Comput Sci"},{"key":"594_CR19","doi-asserted-by":"publisher","first-page":"604","DOI":"10.1038\/nature25978","volume":"555","author":"MH Segler","year":"2018","unstructured":"Segler MH, Preuss M, Waller MP (2018) Planning chemical syntheses with deep neural networks and symbolic AI. Nature 555:604\u2013610","journal-title":"Nature"},{"key":"594_CR20","doi-asserted-by":"publisher","first-page":"3316","DOI":"10.1039\/C9SC05704H","volume":"11","author":"P Schwaller","year":"2020","unstructured":"Schwaller P, Petraglia R, Zullo V, Nair VH, Haeuselmann RA, Pisoni R, Bekas C, Iuliano A, Laino T (2020) Predicting retrosynthetic pathways using transformer-based models and a hyper-graph exploration strategy. Chem Sci 11:3316\u20133325","journal-title":"Chem Sci"},{"key":"594_CR21","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller P, Laino T, Gaudin T, Bolgar P, Hunter CA, Bekas C, Lee AA (2019) Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Central Sci 5:1572\u20131583","journal-title":"ACS Central Sci"},{"key":"594_CR22","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1021\/acs.jcim.7b00622","volume":"58","author":"CW Coley","year":"2018","unstructured":"Coley CW, Rogers L, Green WH, Jensen KF (2018) SCScore: synthetic complexity learned from a reaction corpus. J Chem Inf Model 58:252\u2013261","journal-title":"J Chem Inf Model"},{"key":"594_CR23","unstructured":"IBM RXN for Chemistry: the free AI tool in the cloud for digital chemistry. https:\/\/rxn.res.ibm.com\/. Accessed 15 May 2021"},{"key":"594_CR24","unstructured":"Sun R, Dai H, Li L, Kearnes S, Dai B (2020) Energy-based view of retrosynthesis. arXiv preprint arXiv:2007.13437"},{"key":"594_CR25","doi-asserted-by":"crossref","unstructured":"LeCun Y, Chopra S, Hadsell R, Ranzato M, Huang F (2006) A tutorial on energy-based learning. Predicting structured data 1","DOI":"10.7551\/mitpress\/7443.003.0014"},{"key":"594_CR26","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1021\/ci5006614","volume":"55","author":"N Schneider","year":"2015","unstructured":"Schneider N, Lowe DM, Sayle RA, Landrum GA (2015) Development of a novel fingerprint for chemical reactions and its application to large-scale reaction classification and similarity. J Chem Inf Model 55:39\u201353","journal-title":"J Chem Inf Model"},{"key":"594_CR27","doi-asserted-by":"crossref","unstructured":"Yang Y, Yuan S, Cer D, Kong S-Y, Constant N, Pilar P, Ge H, Sung Y-H, Strope B, Kurzweil R (2018) Learning semantic textual similarity from conversations. arXiv preprint arXiv:1804.07754","DOI":"10.18653\/v1\/W18-3022"},{"key":"594_CR28","unstructured":"Somnath VR, Bunne C, Coley CW, Krause A, Barzilay R (2020) Learning graph models for template-free retrosynthesis. arXiv preprint arXiv:2006.07038"},{"key":"594_CR29","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry. In: International Conference on Machine Learning, pp 1263\u20131272"},{"key":"594_CR30","unstructured":"others et al (2018) Universal sentence encoder. arXiv preprint arXiv:1803.11175"},{"key":"594_CR31","doi-asserted-by":"publisher","first-page":"2336","DOI":"10.1021\/acs.jcim.6b00564","volume":"56","author":"N Schneider","year":"2016","unstructured":"Schneider N, Stiefl N, Landrum GA (2016) What\u2019s what: the (nearly) definitive guide to reaction role assignment. J Chem Inf Model 56:2336\u20132346","journal-title":"J Chem Inf Model"},{"key":"594_CR32","first-page":"11248","volume":"33","author":"C Yan","year":"2020","unstructured":"Yan C, Ding Q, Zhao P, Zheng S, Yang J, Yu Y, Huang J, (2020) RetroXpert: decompose retrosynthesis prediction like a chemist. Adv Neural Inf Process Syst. 33:11248\u201311258","journal-title":"Adv Neural Inf Process Syst."},{"key":"594_CR33","unstructured":"Python Software Foundation. Python Language Reference, version 3.6. http:\/\/www.python.org. Accessed 19 May 2021"},{"key":"594_CR34","unstructured":"Paszke A et al (2019) In: Wallach H, Larochelle H, Beygelzimer A, d\u2019 Alch\u00e9-Buc F, Fox E, Garnett R (eds) Advances in neural information processing systems 32. Curran Associates, Inc., pp 8024\u20138035"},{"key":"594_CR35","unstructured":"RDKit: Open-source cheminformatics. http:\/\/www.rdkit.org. Accessed 15 May 2021"},{"key":"594_CR36","doi-asserted-by":"publisher","first-page":"2529","DOI":"10.1021\/acs.jcim.9b00286","volume":"59","author":"CW Coley","year":"2019","unstructured":"Coley CW, Green WH, Jensen KF (2019) RDChiral: an RDKit wrapper for handling stereochemistry in retrosynthetic template extraction and application. J Chem Inf Model 59:2529\u20132537","journal-title":"J Chem Inf Model"},{"key":"594_CR37","doi-asserted-by":"crossref","unstructured":"Hagberg AA, Schult DA, Swart PJ (2008) Exploring network structure, dynamics, and function using networkX. In: Proceedings of the 7th Python in Science Conference. Pasadena, CA USA, pp 11\u201315","DOI":"10.25080\/TCWV9851"},{"key":"594_CR38","doi-asserted-by":"publisher","first-page":"801","DOI":"10.1002\/anie.197508011","volume":"14","author":"R Appel","year":"1975","unstructured":"Appel R (1975) Tertiary phosphane\/tetrachloromethane, a versatile reagent for chlorination, dehydration, and P-N linkage. Angew Chem Int Ed Engl 14:801\u2013811","journal-title":"Angew Chem Int Ed Engl"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-022-00594-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-022-00594-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-022-00594-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T08:58:58Z","timestamp":1726822738000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-022-00594-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,15]]},"references-count":38,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["594"],"URL":"https:\/\/doi.org\/10.1186\/s13321-022-00594-8","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,15]]},"assertion":[{"value":"12 January 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 March 2022","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"15"}}