{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T11:40:30Z","timestamp":1784115630177,"version":"3.55.0"},"reference-count":44,"publisher":"Oxford University Press (OUP)","issue":"9","license":[{"start":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T00:00:00Z","timestamp":1727568000000},"content-version":"vor","delay-in-days":28,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["NSFC 62322215"],"award-info":[{"award-number":["NSFC 62322215"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172296"],"award-info":[{"award-number":["62172296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Retrosynthesis identifies available precursor molecules for various and novel compounds. With the advancements and practicality of language models, Transformer-based models have increasingly been used to automate this process. However, many existing methods struggle to efficiently capture reaction transformation information, limiting the accuracy and applicability of their predictions.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We introduce RetroCaptioner, an advanced end-to-end, Transformer-based framework featuring a Contrastive Reaction Center Captioner. This captioner guides the training of dual-view attention models using a contrastive learning approach. It leverages learned molecular graph representations to capture chemically plausible constraints within a single-step learning process. We integrate the single-encoder, dual-encoder, and encoder\u2013decoder paradigms to effectively fuse information from the sequence and graph representations of molecules. This involves modifying the Transformer encoder into a uni-view sequence encoder and a dual-view module. Furthermore, we enhance the captioning of atomic correspondence between SMILES and graphs. Our proposed method, RetroCaptioner, achieved outstanding performance with 67.2% in top-1 and 93.4% in top-10 exact matched accuracy on the USPTO-50k dataset, alongside an exceptional SMILES validity score of 99.4%. In addition, RetroCaptioner has demonstrated its reliability in generating synthetic routes for the drug protokylol.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The code and data are available at https:\/\/github.com\/guofei-tju\/RetroCaptioner.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae561","type":"journal-article","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T02:10:17Z","timestamp":1727575817000},"source":"Crossref","is-referenced-by-count":18,"title":["RetroCaptioner: beyond attention in end-to-end retrosynthesis transformer via contrastively captioned learnable graph representation"],"prefix":"10.1093","volume":"40","author":[{"given":"Xiaoyi","family":"Liu","sequence":"first","affiliation":[{"name":"School of Chinese Materia Medica, Beijing University of Chinese Medicine , Beijing, 102488,","place":["China"]},{"name":"Ministry of Education, Engineering Research Center for Pharmaceutics of Chinese Materia Medica and New Drug Development, Beijing, 100102,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengwei","family":"Ai","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Central South University , Changsha, 410083,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongpeng","family":"Yang","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, University of South Carolina , Columbia, South Carolina, 29208,","place":["United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruihan","family":"Dong","sequence":"additional","affiliation":[{"name":"Academy for Advanced Interdisciplinary Studies, Peking University , Beijing, 100871,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jijun","family":"Tang","sequence":"additional","affiliation":[{"name":"Faculty of Computer Science and Control Engineering, Shenzhen University of Advanced Technology , Shenzhen, 518055,","place":["China"]},{"name":"Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences , Nanshan, 518055,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuangjia","family":"Zheng","sequence":"additional","affiliation":[{"name":"Global Institute of Future Technology, Shanghai Jiao Tong University , Shanghai, 200240,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8346-0798","authenticated-orcid":false,"given":"Fei","family":"Guo","sequence":"additional","affiliation":[{"name":"Computer Science and Engineering, Central South University , Changsha, 410083,","place":["China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,9,28]]},"reference":[{"key":"2024102914122267800_btae561-B1","first-page":"1608","author":"Chen","year":"2020"},{"key":"2024102914122267800_btae561-B2","first-page":"4432","author":"Chen","year":"2023"},{"key":"2024102914122267800_btae561-B3","doi-asserted-by":"crossref","first-page":"102","DOI":"10.1038\/s42004-023-00897-3","article-title":"G2retro as a two-step graph generative models for retrosynthesis prediction","volume":"6","author":"Chen","year":"2023","journal-title":"Commun Chem"},{"key":"2024102914122267800_btae561-B4","doi-asserted-by":"crossref","first-page":"1237","DOI":"10.1021\/acscentsci.7b00355","article-title":"Computer-assisted retrosynthesis based on molecular similarity","volume":"3","author":"Coley","year":"2017","journal-title":"ACS Cent Sci"},{"key":"2024102914122267800_btae561-B5","doi-asserted-by":"crossref","first-page":"1748","DOI":"10.1021\/jo9518314","article-title":"Nickel-catalyzed direct electrochemical cross-coupling between aryl halides and activated alkyl halides","volume":"61","author":"Durandetti","year":"1996","journal-title":"J Org Chem"},{"key":"2024102914122267800_btae561-B6","author":"Dwivedi","year":"2023"},{"key":"2024102914122267800_btae561-B7","first-page":"98","volume-title":"Nat Catal","author":"Finnigan"},{"key":"2024102914122267800_btae561-B8","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1002\/(SICI)1096-987X(199604)17:5\/6<490::AID-JCC1>3.0.CO;2-P","article-title":"Merck molecular force field. I. Basis, form, scope, parameterization, and performance of mmff94","volume":"17","author":"Halgren","year":"1996","journal-title":"J Comput Chem"},{"key":"2024102914122267800_btae561-B9","author":"Ishiguro","year":"2020"},{"key":"2024102914122267800_btae561-B10","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1021\/acs.jcim.0c01074","article-title":"Valid, plausible, and diverse retrosynthesis using tied two-way transformers with latent variables","volume":"61","author":"Kim","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2024102914122267800_btae561-B11","author":"Kingma","year":"2014"},{"key":"2024102914122267800_btae561-B12","author":"Landrum","year":"2016"},{"key":"2024102914122267800_btae561-B13","first-page":"2512","author":"Lee"},{"key":"2024102914122267800_btae561-B14","doi-asserted-by":"crossref","first-page":"7747","DOI":"10.1038\/s41467-022-35422-y","article-title":"Merging enzymatic and synthetic chemistry with computational synthesis planning","volume":"13","author":"Levin","year":"2022","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B15","first-page":"1894","volume-title":"J Chem Inf Model","author":"Lin"},{"key":"2024102914122267800_btae561-B16","doi-asserted-by":"crossref","first-page":"btae115","DOI":"10.1093\/bioinformatics\/btae115","article-title":"Mars: a motif-based autoregressive model for retrosynthesis prediction","volume":"40","author":"Liu","year":"2024","journal-title":"Bioinformatics"},{"key":"2024102914122267800_btae561-B17","first-page":"22028","author":"Liu","year":"2023"},{"key":"2024102914122267800_btae561-B18","author":"Liu","year":"2017"},{"key":"2024102914122267800_btae561-B19","first-page":"104","author":"Mallick","year":"2023"},{"key":"2024102914122267800_btae561-B20","doi-asserted-by":"crossref","first-page":"193","DOI":"10.1016\/j.neucom.2021.06.037","article-title":"Molecular graph enhanced transformer for retrosynthesis prediction","volume":"457","author":"Mao","year":"2021","journal-title":"Neurocomputing"},{"key":"2024102914122267800_btae561-B21","author":"Meng","year":"2023"},{"key":"2024102914122267800_btae561-B22","doi-asserted-by":"crossref","first-page":"968","DOI":"10.1021\/tx2001459","article-title":"Synthesis and neurotoxicity profile of 2,4,5-trihydroxymethamphetamine and its 6-(n-acetylcystein-s-yl) conjugate","volume":"24","author":"Neud\u00f6rffer","year":"2011","journal-title":"Chem Res Toxicol"},{"key":"2024102914122267800_btae561-B23","doi-asserted-by":"crossref","first-page":"3273","DOI":"10.1021\/acs.jcim.1c00537","article-title":"Molecule edit graph attention network: modeling chemical reactions as sequences of graph edits","volume":"61","author":"Sacha","year":"2021","journal-title":"J Chem Inf Model"},{"key":"2024102914122267800_btae561-B24","first-page":"531","author":"","year":"2021"},{"key":"2024102914122267800_btae561-B25","first-page":"8818","author":"Shi","year":"2020"},{"key":"2024102914122267800_btae561-B26","first-page":"9405","article-title":"Learning graph models for retrosynthesis prediction","volume":"34","author":"Somnath","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024102914122267800_btae561-B27","doi-asserted-by":"crossref","first-page":"5575","DOI":"10.1038\/s41467-020-19266-y","article-title":"State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis","volume":"11","author":"Tetko","year":"2020","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B28","doi-asserted-by":"crossref","first-page":"3503","DOI":"10.1021\/acs.jcim.2c00321","article-title":"Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction","volume":"62","author":"Tu","year":"2022","journal-title":"J Chem Inf Model"},{"key":"2024102914122267800_btae561-B29","doi-asserted-by":"crossref","first-page":"1186","DOI":"10.1038\/s41467-022-28857-w","article-title":"Retrosynthetic reaction pathway prediction through neural machine translation of atomic environments","volume":"13","author":"Ucak","year":"2022","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B30","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024102914122267800_btae561-B31","first-page":"22475","author":"Wan","year":"2022"},{"key":"2024102914122267800_btae561-B32","doi-asserted-by":"crossref","first-page":"129845","DOI":"10.1016\/j.cej.2021.129845","article-title":"Retroprime: a diverse, plausible and transformer-based method for single-step retrosynthesis predictions","volume":"420","author":"Wang","year":"2021","journal-title":"Chem Eng J"},{"key":"2024102914122267800_btae561-B33","doi-asserted-by":"crossref","first-page":"6155","DOI":"10.1038\/s41467-023-41698-5","article-title":"Retrosynthesis prediction with an interpretable deep-learning framework based on molecular assembly tasks","volume":"14","author":"Wang","year":"2023","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B34","doi-asserted-by":"crossref","first-page":"31","DOI":"10.1021\/ci00057a005","article-title":"Smiles, a chemical language and information system. 1. Introduction to methodology and encoding rules","volume":"28","author":"Weininger","year":"1988","journal-title":"J Chem Inf Comput Sci"},{"key":"2024102914122267800_btae561-B35","first-page":"2120","author":"Xie","year":"2022"},{"key":"2024102914122267800_btae561-B36","doi-asserted-by":"crossref","first-page":"8749","DOI":"10.1021\/acs.jmedchem.9b00959","article-title":"Pushing the boundaries of molecular representation for drug discovery with the graph attention mechanism","volume":"63","author":"Xiong","year":"2019","journal-title":"J Med Chem"},{"key":"2024102914122267800_btae561-B37","first-page":"11248","article-title":"Retroxpert: decompose retrosynthesis prediction like a chemist","volume":"33","author":"Yan","year":"2020","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024102914122267800_btae561-B38","first-page":"28877","article-title":"Do transformers really perform badly for graph representation?","volume":"34","author":"Ying","year":"2021","journal-title":"Adv Neural Inf Process Syst"},{"key":"2024102914122267800_btae561-B39","author":"Yu","year":"2022"},{"key":"2024102914122267800_btae561-B40","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1021\/acs.jcim.9b00949","article-title":"Predicting retrosynthetic reactions using self-corrected transformer neural networks","volume":"60","author":"Zheng","year":"2019","journal-title":"J Chem Inf Model"},{"key":"2024102914122267800_btae561-B41","doi-asserted-by":"crossref","first-page":"3342","DOI":"10.1038\/s41467-022-30970-9","article-title":"Deep learning driven biosynthetic pathways navigation for natural products with BIONAVI-NP","volume":"13","author":"Zheng","year":"2022","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B42","doi-asserted-by":"crossref","first-page":"3009","DOI":"10.1038\/s41467-023-38851-5","article-title":"Retrosynthesis prediction using an end-to-end graph generative architecture for molecular graph editing","volume":"14","author":"Zhong","year":"2023","journal-title":"Nat Commun"},{"key":"2024102914122267800_btae561-B43","doi-asserted-by":"crossref","first-page":"9023","DOI":"10.1039\/D2SC02763A","article-title":"Root-aligned smiles: a tight representation for chemical reaction prediction","volume":"13","author":"Zhong","year":"2022","journal-title":"Chem Sci"},{"key":"2024102914122267800_btae561-B44","first-page":"3615","author":"Zhu","year":"2023"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae561\/60195134\/btae561.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/9\/btae561\/60195134\/btae561.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T14:12:45Z","timestamp":1730211165000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae561\/7789833"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,9]]},"references-count":44,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2024,9,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae561","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,9]]},"published":{"date-parts":[[2024,9]]},"article-number":"btae561"}}