{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T00:21:57Z","timestamp":1775175717534,"version":"3.50.1"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100020963","name":"Moonshot Research and Development Program","doi-asserted-by":"publisher","award":["JPMJMS2024"],"award-info":[{"award-number":["JPMJMS2024"]}],"id":[{"id":"10.13039\/501100020963","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP21H05207"],"award-info":[{"award-number":["JP21H05207"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003382","name":"Core Research for Evolutional Science and Technology","doi-asserted-by":"publisher","award":["JPMJCR22D3"],"award-info":[{"award-number":["JPMJCR22D3"]}],"id":[{"id":"10.13039\/501100003382","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006264","name":"RIKEN","doi-asserted-by":"publisher","award":["AGIS"],"award-info":[{"award-number":["AGIS"]}],"id":[{"id":"10.13039\/501100006264","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>Accurate chemical reaction prediction is critical for reducing both cost and time in drug development. This study introduces ReactionT5, a transformer-based chemical reaction foundation model pre-trained on the Open Reaction Database\u2014a large publicly available reaction dataset. In benchmarks for product prediction, retrosynthesis, and yield prediction, ReactionT5 outperformed existing models. Specifically, ReactionT5 achieved 97.5% accuracy in product prediction, 71.0% in retrosynthesis, and a coefficient of determination of 0.947 in yield prediction. Remarkably, ReactionT5, when fine-tuned with only a limited dataset of reactions, achieved performance on par with models fine-tuned on the complete dataset. Additionally, the visualization of ReactionT5 embeddings illustrates that the model successfully captures and represents the chemical reaction space, indicating effective learning of reaction properties.<\/jats:p>\n          <jats:p>\n            <jats:bold>Graphical Abstract<\/jats:bold>\n          <\/jats:p>","DOI":"10.1186\/s13321-025-01075-4","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T13:54:14Z","timestamp":1755611654000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["ReactionT5: a pre-trained transformer model for accurate chemical reaction prediction with limited data"],"prefix":"10.1186","volume":"17","author":[{"given":"Tatsuya","family":"Sagawa","sequence":"first","affiliation":[]},{"given":"Ryosuke","family":"Kojima","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"1075_CR1","first-page":"199","volume":"9","author":"RC Glem","year":"2006","unstructured":"Glem RC et al (2006) Circular fingerprints: flexible molecular descriptors with applications from physical chemistry to ADME. IDrugs 9:199\u2013204","journal-title":"IDrugs"},{"key":"1075_CR2","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1021\/acscentsci.7b00064","volume":"3","author":"CW Coley","year":"2017","unstructured":"Coley CW, Barzilay R, Jaakkola TS, Green WH, Jensen KF (2017) Prediction of organic reaction outcomes using machine learning. ACS Cent Sci 3:434\u2013443. https:\/\/doi.org\/10.1021\/acscentsci.7b00064","journal-title":"ACS Cent Sci"},{"key":"1075_CR3","doi-asserted-by":"publisher","unstructured":"Xia J, Zhu Y, Du Y, Li SZ (2023) A systematic survey of chemical pre-trained models. In: Proceedings of the thirty-second international joint conference on artificial intelligence. International Joint Conferences on Artificial Intelligence Organization, CA 6787\u20136795. https:\/\/doi.org\/10.24963\/ijcai.2023\/760.","DOI":"10.24963\/ijcai.2023\/760"},{"key":"1075_CR4","doi-asserted-by":"publisher","unstructured":"Wang S, Guo Y, Wang Y, Sun H, Huang J (2019) Smiles-Bert: Large scale unsupervised pre-training for molecular property prediction. In: Proceedings of the 10th ACM international conference on bioinformatics, computational biology and health informatics. ACM, New York, p 429\u2013436. https:\/\/doi.org\/10.1145\/3307339.3342186","DOI":"10.1145\/3307339.3342186"},{"key":"1075_CR5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"1988","unstructured":"Weininger D (1988) SMILES, a chemical language and information system. 1. introduction to methodology and encoding rules. J Chem Inf Comput Sci 28:31\u201336. https:\/\/doi.org\/10.1021\/ci00057a005","journal-title":"J Chem Inf Comput Sci"},{"key":"1075_CR6","doi-asserted-by":"publisher","unstructured":"Chithrananda S, Grand G, Ramsundar B (2020) ChemBERTa: large-scale self-supervised pretraining for molecular property prediction. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2010.09885","DOI":"10.48550\/arXiv.2010.09885"},{"key":"1075_CR7","doi-asserted-by":"publisher","unstructured":"M\u00e9ndez-Lucio O, Nicolaou C, Earnshaw B (2022) MolE: a molecular foundation model for drug discovery. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2211.02657","DOI":"10.48550\/arXiv.2211.02657"},{"key":"1075_CR8","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","volume":"4","author":"Y Wang","year":"2022","unstructured":"Wang Y, Wang J, Cao Z, Barati FA (2022) Molecular contrastive learning of representations via graph neural networks. Nat Mach Intell 4:279\u2013287. https:\/\/doi.org\/10.1038\/s42256-022-00447-x","journal-title":"Nat Mach Intell"},{"key":"1075_CR9","doi-asserted-by":"publisher","first-page":"5312","DOI":"10.1609\/aaai.v37i4.25662","volume":"37","author":"F Wu","year":"2023","unstructured":"Wu F, Radev D, Li Z (2023) Molformer: motif-based transformer on 3D heterogeneous molecular graphs. Proc AAAI Conf Artif Intell 37:5312\u20135320. https:\/\/doi.org\/10.1609\/aaai.v37i4.25662","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"1075_CR10","doi-asserted-by":"publisher","first-page":"1376","DOI":"10.1021\/acs.jcim.1c01467","volume":"62","author":"J Lu","year":"2022","unstructured":"Lu J, Zhang Y (2022) Unified deep learning model for multitask reaction predictions with explanation. J Chem Inf Model 62:1376\u20131387. https:\/\/doi.org\/10.1021\/acs.jcim.1c01467","journal-title":"J Chem Inf Model"},{"key":"1075_CR11","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1021\/acs.jcim.5c00359","volume":"65","author":"A Krzyzanowski","year":"2025","unstructured":"Krzyzanowski A et al (2025) Exploring BERT for reaction yield prediction: evaluating the impact of tokenization, molecular representation, and pretraining data augmentation. J Chem Inf Model 65:4381\u20134402. https:\/\/doi.org\/10.1021\/acs.jcim.5c00359","journal-title":"J Chem Inf Model"},{"key":"1075_CR12","doi-asserted-by":"publisher","unstructured":"Liu Z et al (2024) ReactXT: Understanding Molecular \u2018Reaction-ship\u2019 via Reaction-Contextualized Molecule-Text Pretraining. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2405.14225","DOI":"10.48550\/arXiv.2405.14225"},{"key":"1075_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.48550\/arXiv.1910.10683","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel C et al (2020) Exploring the limits of transfer learning with a unified text-to-text transformer. J Mach Learn Res 21:1\u201367. https:\/\/doi.org\/10.48550\/arXiv.1910.10683","journal-title":"J Mach Learn Res"},{"key":"1075_CR14","doi-asserted-by":"publisher","first-page":"18820","DOI":"10.1021\/jacs.1c09820","volume":"143","author":"SM Kearnes","year":"2021","unstructured":"Kearnes SM et al (2021) The open reaction database. J Am Chem Soc 143:18820\u201318826. https:\/\/doi.org\/10.1021\/jacs.1c09820","journal-title":"J Am Chem Soc"},{"key":"1075_CR15","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s42256-020-00284-w","volume":"3","author":"P Schwaller","year":"2021","unstructured":"Schwaller P et al (2021) Mapping the space of chemical reactions using attention-based neural networks. Nat Mach Intell 3:144\u2013152. https:\/\/doi.org\/10.1038\/s42256-020-00284-w","journal-title":"Nat Mach Intell"},{"key":"1075_CR16","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s13321-022-00638-z","volume":"14","author":"X Wang","year":"2022","unstructured":"Wang X et al (2022) From theory to experiment: transformer-based generation enables rapid discovery of novel reactions. J Cheminform 14:60. https:\/\/doi.org\/10.1186\/s13321-022-00638-z","journal-title":"J Cheminform"},{"key":"1075_CR17","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1162\/tacl_a_00300","volume":"8","author":"M Joshi","year":"2019","unstructured":"Joshi M et al (2019) SpanBERT: improving pre-training by representing and predicting spans. Trans Assoc Comput Linguist 8:64\u201377. https:\/\/doi.org\/10.1162\/tacl_a_00300","journal-title":"Trans Assoc Comput Linguist"},{"key":"1075_CR18","doi-asserted-by":"publisher","unstructured":"Kudo T, Richardson J (2018) SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing. Association for Computational Linguistics, Stroudsburg, PA, USA, p 66\u201371. https:\/\/doi.org\/10.18653\/v1\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"1075_CR19","doi-asserted-by":"publisher","unstructured":"Mielke SJ et al (2021) Between words and characters: A Brief History of Open-Vocabulary Modeling and Tokenization in NLP. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2112.10508","DOI":"10.48550\/arXiv.2112.10508"},{"key":"1075_CR20","doi-asserted-by":"publisher","unstructured":"Shazeer N, Stern M (2018) Adafactor: Adaptive learning rates with sublinear memory cost. International Conference on Machine Learning, Stockholm, Sweden, p 4596\u20134604. https:\/\/doi.org\/10.48550\/arXiv.1804.04235","DOI":"10.48550\/arXiv.1804.04235"},{"key":"1075_CR21","doi-asserted-by":"publisher","first-page":"3790","DOI":"10.1021\/acs.jcim.4c00292","volume":"64","author":"DS Wigh","year":"2022","unstructured":"Wigh DS et al (2022) ORDerly: data sets and benchmarks for chemical reaction data. J Chem Inf Model 64:3790\u20133798. https:\/\/doi.org\/10.1021\/acs.jcim.4c00292","journal-title":"J Chem Inf Model"},{"key":"1075_CR22","doi-asserted-by":"publisher","first-page":"6065","DOI":"10.1021\/acs.jcim.0c00675","volume":"60","author":"JJ Irwin","year":"2020","unstructured":"Irwin JJ et al (2020) ZINC20\u2014a free ultralarge-scale chemical database for ligand discovery. J Chem Inf Model 60:6065\u20136073. https:\/\/doi.org\/10.1021\/acs.jcim.0c00675","journal-title":"J Chem Inf Model"},{"key":"1075_CR23","volume-title":"Extraction of chemical structures and reactions from the literature","author":"DM Lowe","year":"2012","unstructured":"Lowe DM (2012) Extraction of chemical structures and reactions from the literature. University of Cambridge, Cambridge"},{"key":"1075_CR24","first-page":"2607","volume":"2","author":"W Jin","year":"2017","unstructured":"Jin W, Coley CW, Barzilay R, Jaakkola T (2017) Predicting organic reaction outcomes with Weisfeiler-Lehman network. Adv Neural Inf Process Syst 2:2607\u20132616","journal-title":"Adv Neural Inf Process Syst"},{"key":"1075_CR25","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.1021\/acscentsci.7b00303","volume":"3","author":"B Liu","year":"2017","unstructured":"Liu B et al (2017) Retrosynthetic reaction prediction using neural sequence-to-sequence models. ACS Cent Sci 3:1103\u20131113. https:\/\/doi.org\/10.1021\/acscentsci.7b00303","journal-title":"ACS Cent Sci"},{"key":"1075_CR26","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1126\/science.aar5169","volume":"360","author":"DT Ahneman","year":"2018","unstructured":"Ahneman DT, Estrada JG, Lin S, Dreher SD, Doyle AG (2018) Predicting reaction performance in C-N cross-coupling using machine learning. Science 360:186\u2013190. https:\/\/doi.org\/10.1126\/science.aar5169","journal-title":"Science"},{"key":"1075_CR27","doi-asserted-by":"publisher","first-page":"6091","DOI":"10.1039\/c8sc02339e","volume":"9","author":"P Schwaller","year":"2018","unstructured":"Schwaller P, Gaudin T, L\u00e1nyi D, Bekas C, Laino T (2018) \u2018Found in Translation\u2019: predicting outcomes of complex organic chemistry reactions using neural sequence-to-sequence models. Chem Sci 9:6091\u20136098. https:\/\/doi.org\/10.1039\/c8sc02339e","journal-title":"Chem Sci"},{"key":"1075_CR28","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1039\/c8sc04228d","volume":"10","author":"CW Coley","year":"2019","unstructured":"Coley CW et al (2019) A graph-convolutional neural network model for the prediction of chemical reactivity. Chem Sci 10:370\u2013377. https:\/\/doi.org\/10.1039\/c8sc04228d","journal-title":"Chem Sci"},{"key":"1075_CR29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1705.09037","author":"T Lei","year":"2017","unstructured":"Lei T et al (2017) Deriving neural architectures from sequence and graph kernels. Proc Int Conf Mach Learn. https:\/\/doi.org\/10.48550\/arXiv.1705.09037","journal-title":"Proc Int Conf Mach Learn"},{"key":"1075_CR30","doi-asserted-by":"publisher","first-page":"1572","DOI":"10.1021\/acscentsci.9b00576","volume":"5","author":"P Schwaller","year":"2019","unstructured":"Schwaller P et al (2019) Molecular transformer: a model for uncertainty-calibrated chemical reaction prediction. ACS Cent Sci 5:1572\u20131583. https:\/\/doi.org\/10.1021\/acscentsci.9b00576","journal-title":"ACS Cent Sci"},{"key":"1075_CR31","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1021\/acs.jcim.9b00949","volume":"60","author":"S Zheng","year":"2020","unstructured":"Zheng S, Rao J, Zhang Z, Xu J, Yang Y (2020) Predicting retrosynthetic reactions using self-corrected transformer neural networks. J Chem Inf Model 60:47\u201355. https:\/\/doi.org\/10.1021\/acs.jcim.9b00949","journal-title":"J Chem Inf Model"},{"key":"1075_CR32","doi-asserted-by":"publisher","first-page":"1379","DOI":"10.1016\/j.chempr.2020.02.017","volume":"6","author":"F Sandfort","year":"2020","unstructured":"Sandfort F, Strieth-Kalthoff F, K\u00fchnemund M, Beecks C, Glorius F (2020) A structure-based platform for predicting chemical reactivity. Chem 6:1379\u20131390. https:\/\/doi.org\/10.1016\/j.chempr.2020.02.017","journal-title":"Chem"},{"key":"1075_CR33","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/abc81d","volume":"2","author":"P Schwaller","year":"2021","unstructured":"Schwaller P, Vaucher AC, Laino T, Reymond J-L (2021) Prediction of chemical reaction yields using deep learning. Mach Learn Sci Technol 2:015016. https:\/\/doi.org\/10.1088\/2632-2153\/abc81d","journal-title":"Mach Learn Sci Technol"},{"key":"1075_CR34","doi-asserted-by":"publisher","unstructured":"Kaplan J et al (2020) Scaling laws for neural language models. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2001.08361","DOI":"10.48550\/arXiv.2001.08361"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01075-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-025-01075-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-025-01075-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T02:06:52Z","timestamp":1755655612000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-025-01075-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["1075"],"URL":"https:\/\/doi.org\/10.1186\/s13321-025-01075-4","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"6 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","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":"126"}}