{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T12:31:35Z","timestamp":1777984295878,"version":"3.51.4"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T00:00:00Z","timestamp":1770595200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:00:00Z","timestamp":1773273600000},"content-version":"vor","delay-in-days":31,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100008867","name":"Zhejiang Provincial Department of Education","doi-asserted-by":"crossref","award":["Y202456962"],"award-info":[{"award-number":["Y202456962"]}],"id":[{"id":"10.13039\/501100008867","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Macao Polytechnic University","award":["RP\/FCA 06\/2024"],"award-info":[{"award-number":["RP\/FCA 06\/2024"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-026-01164-y","type":"journal-article","created":{"date-parts":[[2026,2,9]],"date-time":"2026-02-09T12:06:24Z","timestamp":1770638784000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enzyformer: a two-stage pretrained model for enzymatic retrosynthesis"],"prefix":"10.1186","volume":"18","author":[{"given":"Tiantao","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiangcheng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinke","family":"Zhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaolong","family":"Lin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shirley W. I.","family":"Siu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,2,9]]},"reference":[{"issue":"5","key":"1164_CR1","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(5):1281\u20131289","journal-title":"Acc Chem Res"},{"issue":"6881","key":"1164_CR2","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1038\/416587a","volume":"416","author":"SJ Lippard","year":"2002","unstructured":"Lippard SJ (2002) Chemical synthesis: the art of chemistry. Nature 416(6881):587","journal-title":"Nature"},{"key":"1164_CR3","doi-asserted-by":"publisher","first-page":"876","DOI":"10.1039\/CT9171100876","volume":"111","author":"R Robinson","year":"1917","unstructured":"Robinson R (1917) LXXV.\u2014A theory of the mechanism of the phytochemical synthesis of certain alkaloids. J Chem Soc Trans 111:876\u2013899","journal-title":"J Chem Soc Trans"},{"key":"1164_CR4","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1039\/CS9881700111","volume":"17","author":"EJ Corey","year":"1988","unstructured":"Corey EJ (1988) Robert Robinson lecture. Retrosynthetic thinking\u2014essentials and examples. Chem Soc Rev 17:111\u2013133","journal-title":"Chem Soc Rev"},{"issue":"11","key":"1164_CR5","doi-asserted-by":"publisher","first-page":"2864","DOI":"10.1021\/ci300415d","volume":"52","author":"L Ruddigkeit","year":"2012","unstructured":"Ruddigkeit L, Van Deursen R, Blum LC, Reymond J-L (2012) Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17. J Chem Inf Model 52(11):2864\u20132875","journal-title":"J Chem Inf Model"},{"issue":"9","key":"1164_CR6","doi-asserted-by":"publisher","first-page":"2034","DOI":"10.1021\/ci900157k","volume":"49","author":"JH Chen","year":"2009","unstructured":"Chen JH, Baldi P (2009) No electron left behind: a rule-based expert system to predict chemical reactions and reaction mechanisms. J Chem Inf Model 49(9):2034\u20132043","journal-title":"J Chem Inf Model"},{"issue":"20","key":"1164_CR7","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(20):5904\u20135937","journal-title":"Angew Chem Int Ed"},{"issue":"1","key":"1164_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/wcms.1694","volume":"14","author":"Z Zhong","year":"2024","unstructured":"Zhong Z, Song J, Feng Z, Liu T, Jia L, Yao S, Hou T, Song M (2024) Recent advances in deep learning for retrosynthesis. Wiley Interdiscip Rev Comput Mol Sci 14(1):e1694","journal-title":"Wiley Interdiscip Rev Comput Mol Sci"},{"issue":"12","key":"1164_CR9","doi-asserted-by":"publisher","first-page":"3446","DOI":"10.1021\/jacsau.3c00607","volume":"3","author":"T Liu","year":"2023","unstructured":"Liu T, Cao Z, Huang Y, Wan Y, Wu J, Hsieh C-Y, Hou T, Kang Y (2023) SynCluster: reaction type clustering and recommendation framework for synthesis planning. JACS Au 3(12):3446\u20133461","journal-title":"JACS Au"},{"key":"1164_CR10","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.eng.2022.04.021","volume":"25","author":"Y Jiang","year":"2022","unstructured":"Jiang Y, Yu Y, Kong M, Mei Y, Yuan L, Huang Z, Kuang K, Wang Z, Yao H, Zou J (2022) Artificial intelligence for retrosynthesis prediction. Engineering 25:32\u201350","journal-title":"Engineering"},{"key":"1164_CR11","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1016\/j.cbpa.2014.03.002","volume":"19","author":"H Gr\u00f6ger","year":"2014","unstructured":"Gr\u00f6ger H, Hummel W (2014) Combining the \u2018two worlds\u2019 of chemocatalysis and biocatalysis towards multi-step one-pot processes in aqueous media. Curr Opin Chem Biol 19:171\u2013179","journal-title":"Curr Opin Chem Biol"},{"issue":"1","key":"1164_CR12","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-32414-w","volume":"13","author":"NJ Hern\u00e1ndez Lozada","year":"2022","unstructured":"Hern\u00e1ndez Lozada NJ, Hong B, Wood JC, Caputi L, Basquin J, Chuang L, Kunert M, Rodr\u00edguez L\u00f3pez CE, Langley C, Zhao D (2022) Biocatalytic routes to stereo-divergent iridoids. Nat Commun 13(1):4718","journal-title":"Nat Commun"},{"issue":"1","key":"1164_CR13","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1021\/acscentsci.0c01496","volume":"7","author":"CK Winkler","year":"2021","unstructured":"Winkler CK, Schrittwieser JH, Kroutil W (2021) Power of biocatalysis for organic synthesis. ACS Cent Sci 7(1):55\u201371","journal-title":"ACS Cent Sci"},{"issue":"7553","key":"1164_CR14","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":"1164_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.biotechadv.2025.108698","volume":"84","author":"N Tripathi","year":"2025","unstructured":"Tripathi N, H\u00e9risson J, Faulon J-L (2025) Machine learning in predictive biocatalysis: a comparative review of methods and applications. Biotechnol Adv 84:108698","journal-title":"Biotechnol Adv"},{"issue":"3","key":"1164_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.xcrp.2025.102466","volume":"6","author":"T Liu","year":"2025","unstructured":"Liu T, Zhai S, Zhan X, Siu SW (2025) Data-driven revolution of enzyme catalysis from the perspective of reactions, pathways, and enzymes. Cell Rep Phys Sci 6(3):102466","journal-title":"Cell Rep Phys Sci"},{"issue":"8","key":"1164_CR17","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1021\/acssynbio.4c00091","volume":"13","author":"G Gricourt","year":"2024","unstructured":"Gricourt G, Meyer P, Duigou T, Faulon J-L (2024) Artificial intelligence methods and models for retro-biosynthesis: a scoping review. ACS Synth Biol 13(8):2276\u20132294","journal-title":"ACS Synth Biol"},{"key":"1164_CR18","doi-asserted-by":"publisher","first-page":"101","DOI":"10.1016\/j.copbio.2021.07.024","volume":"73","author":"WD Jang","year":"2022","unstructured":"Jang WD, Kim GB, Kim Y, Lee SY (2022) Applications of artificial intelligence to enzyme and pathway design for metabolic engineering. Curr Opin Biotechnol 73:101\u2013107","journal-title":"Curr Opin Biotechnol"},{"issue":"2","key":"1164_CR19","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1038\/s41929-020-00556-z","volume":"4","author":"W Finnigan","year":"2021","unstructured":"Finnigan W, Hepworth LJ, Flitsch SL, Turner NJ (2021) RetroBioCat as a computer-aided synthesis planning tool for biocatalytic reactions and cascades. Nat Catal 4(2):98\u2013104","journal-title":"Nat Catal"},{"issue":"1","key":"1164_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-28536-w","volume":"13","author":"D Probst","year":"2022","unstructured":"Probst D, Manica M, Nana Teukam YG, Castrogiovanni A, Paratore F, Laino T (2022) Biocatalysed synthesis planning using data-driven learning. Nat Commun 13(1):964","journal-title":"Nat Commun"},{"issue":"1","key":"1164_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-30970-9","volume":"13","author":"S Zheng","year":"2022","unstructured":"Zheng S, Zeng T, Li C, Chen B, Coley CW, Yang Y, Wu R (2022) Deep learning driven biosynthetic pathways navigation for natural products with BioNavi-NP. Nat Commun 13(1):3342","journal-title":"Nat Commun"},{"issue":"47","key":"1164_CR22","doi-asserted-by":"publisher","first-page":"12777","DOI":"10.1039\/D0SC02639E","volume":"11","author":"EE Litsa","year":"2020","unstructured":"Litsa EE, Das P, Kavraki LE (2020) Prediction of drug metabolites using neural machine translation. Chem Sci 11(47):12777\u201312788","journal-title":"Chem Sci"},{"key":"1164_CR23","doi-asserted-by":"crossref","unstructured":"Lee S, Kim T, Choi M-S, Kwak Y, Park J, Hwang SJ, Kim S-G: READRetro. 2023. Natural Product Biosynthesis Planning with Retrieval-Augmented Dual-View Retrosynthesis. bioRxiv.","DOI":"10.1101\/2023.03.21.533616"},{"issue":"1","key":"1164_CR24","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1039\/C9SC04944D","volume":"11","author":"A Thakkar","year":"2020","unstructured":"Thakkar A, Kogej T, Reymond J-L, Engkvist O, Bjerrum EJ (2020) Datasets and their influence on the development of computer assisted synthesis planning tools in the pharmaceutical domain. Chem Sci 11(1):154\u2013168","journal-title":"Chem Sci"},{"issue":"1","key":"1164_CR25","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-024-00827-y","volume":"16","author":"W Qian","year":"2024","unstructured":"Qian W, Wang X, Kang Y, Pan P, Hou T, Hsieh C-Y (2024) A general model for predicting enzyme functions based on enzymatic reactions. J Cheminform 16(1):38","journal-title":"J Cheminform"},{"key":"1164_CR26","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"},{"issue":"11","key":"1164_CR27","doi-asserted-by":"publisher","first-page":"2324","DOI":"10.1021\/acs.jcim.5b00559","volume":"55","author":"T Sterling","year":"2015","unstructured":"Sterling T, Irwin JJ (2015) ZINC 15\u2013ligand discovery for everyone. J Chem Inf Model 55(11):2324\u20132337","journal-title":"J Chem Inf Model"},{"key":"1164_CR28","unstructured":"Ramsundar B, Eastman P, Walters P, Pande V, Leswing K, Wu Z. 2019. Deep Learning for the Life Sciences: O\u2019Reilly Media."},{"issue":"17","key":"1164_CR29","doi-asserted-by":"publisher","first-page":"11771","DOI":"10.1021\/acscatal.3c01418","volume":"13","author":"W Finnigan","year":"2023","unstructured":"Finnigan W, Lubberink M, Hepworth LJ, Citoler J, Mattey AP, Ford GJ, Sangster J, Cosgrove SC, da Costa BZ, Heath RS (2023) RetroBioCat database: a platform for collaborative curation and automated meta-analysis of biocatalysis data. ACS Catal 13(17):11771\u201311780","journal-title":"ACS Catal"},{"issue":"1","key":"1164_CR30","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-020-0416-x","volume":"12","author":"D Probst","year":"2020","unstructured":"Probst D, Reymond J-L (2020) Visualization of very large high-dimensional data sets as minimum spanning trees. J Cheminform 12(1):12","journal-title":"J Cheminform"},{"issue":"2","key":"1164_CR31","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1038\/s42256-020-00284-w","volume":"3","author":"P Schwaller","year":"2021","unstructured":"Schwaller P, Probst D, Vaucher AC, Nair VH, Kreutter D, Laino T, Reymond J-L (2021) Mapping the space of chemical reactions using attention-based neural networks. Nat Mach Intell 3(2):144\u2013152","journal-title":"Nat Mach Intell"},{"issue":"9","key":"1164_CR32","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 Cent Sci 5(9):1572\u20131583","journal-title":"ACS Cent Sci"},{"issue":"10","key":"1164_CR33","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1021\/jacsau.1c00246","volume":"1","author":"S Chen","year":"2021","unstructured":"Chen S, Jung Y (2021) Deep retrosynthetic reaction prediction using local reactivity and global attention. JACS Au 1(10):1612\u20131620","journal-title":"JACS Au"},{"issue":"15","key":"1164_CR34","doi-asserted-by":"publisher","first-page":"3503","DOI":"10.1021\/acs.jcim.2c00321","volume":"62","author":"Z Tu","year":"2022","unstructured":"Tu Z, Coley CW (2022) Permutation invariant graph-to-sequence model for template-free retrosynthesis and reaction prediction. J Chem Inf Model 62(15):3503\u20133513","journal-title":"J Chem Inf Model"},{"issue":"31","key":"1164_CR35","doi-asserted-by":"publisher","first-page":"9023","DOI":"10.1039\/D2SC02763A","volume":"13","author":"Z Zhong","year":"2022","unstructured":"Zhong Z, Song J, Feng Z, Liu T, Jia L, Yao S, Wu M, Hou T, Song M (2022) Root-aligned SMILES: a tight representation for chemical reaction prediction. Chem Sci 13(31):9023\u20139034","journal-title":"Chem Sci"},{"issue":"5","key":"1164_CR36","doi-asserted-by":"publisher","first-page":"782","DOI":"10.1038\/s42256-025-01032-8","volume":"7","author":"J Xiong","year":"2025","unstructured":"Xiong J, Zhang W, Wang Y, Huang J, Shi Y, Xu M, Li M, Fu Z, Kong X, Wang Y et al (2025) Bridging chemistry and artificial intelligence by a reaction description language. Nat Mach Intell 7(5):782\u2013793","journal-title":"Nat Mach Intell"},{"issue":"1","key":"1164_CR37","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ac3ffb","volume":"3","author":"R Irwin","year":"2022","unstructured":"Irwin R, Dimitriadis S, He J, Bjerrum EJ (2022) Chemformer: a pre-trained transformer for computational chemistry. Mach Learn Sci Technol 3(1):015022","journal-title":"Mach Learn Sci Technol"},{"key":"1164_CR38","doi-asserted-by":"crossref","unstructured":"Lewis M, Liu Y, Goyal N, Ghazvininejad M, Mohamed A, Levy O, Stoyanov V, Zettlemoyer L: BART. Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:191013461 2019.","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"1164_CR39","unstructured":"Bjerrum EJ. SMILES enumeration as data augmentation for neural network modeling of molecules. arXiv preprint arXiv:170307076 2017."},{"issue":"6639","key":"1164_CR40","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1126\/science.adf2465","volume":"379","author":"T Yu","year":"2023","unstructured":"Yu T, Cui H, Li JC, Luo Y, Jiang G, Zhao H (2023) Enzyme function prediction using contrastive learning. Science 379(6639):1358\u20131363","journal-title":"Science"},{"issue":"2","key":"1164_CR41","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1039\/D1DD00006C","volume":"1","author":"D Probst","year":"2022","unstructured":"Probst D, Schwaller P, Reymond J-L (2022) Reaction classification and yield prediction using the differential reaction fingerprint DRFP. Digit Discov 1(2):91\u201397","journal-title":"Digit Discov"},{"key":"1164_CR42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.01108","author":"V Sanh","year":"2019","unstructured":"Sanh V, Debut L, Chaumond J, Wolf T (2019) DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter. arXiv preprint arXiv. https:\/\/doi.org\/10.48550\/arXiv.1910.01108","journal-title":"arXiv preprint arXiv"},{"issue":"9","key":"1164_CR43","doi-asserted-by":"publisher","first-page":"4381","DOI":"10.1021\/acs.jcim.5c00359","volume":"65","author":"A Krzyzanowski","year":"2025","unstructured":"Krzyzanowski A, Pickett SD, Pog\u00e1ny P (2025) Exploring BERT for reaction yield prediction: evaluating the impact of tokenization, molecular representation, and pretraining data augmentation. J Chem Inf Model 65(9):4381\u20134402","journal-title":"J Chem Inf Model"},{"issue":"1","key":"1164_CR44","doi-asserted-by":"publisher","DOI":"10.1186\/s13321-023-00784-y","volume":"15","author":"D Probst","year":"2023","unstructured":"Probst D (2023) An explainability framework for deep learning on chemical reactions exemplified by enzyme-catalysed reaction classification. J Cheminform 15(1):113","journal-title":"J Cheminform"},{"issue":"10","key":"1164_CR45","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 Cent Sci 3(10):1103\u20131113","journal-title":"ACS Cent Sci"},{"issue":"25","key":"1164_CR46","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\u2010symbolic machine learning for retrosynthesis and reaction prediction. Chem Eur J 23(25):5966\u20135971","journal-title":"Chem Eur J"},{"issue":"1","key":"1164_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-020-19266-y","volume":"11","author":"IV Tetko","year":"2020","unstructured":"Tetko IV, Karpov P, Van Deursen R, Godin G (2020) State-of-the-art augmented NLP transformer models for direct and single-step retrosynthesis. Nat Commun 11(1):1\u201311","journal-title":"Nat Commun"},{"key":"1164_CR48","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825\u20132830","journal-title":"J Mach Learn Res"},{"issue":"5","key":"1164_CR49","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1016\/j.eswa.2009.11.040","volume":"37","author":"J-M Wei","year":"2010","unstructured":"Wei J-M, Yuan X-J, Hu Q-H, Wang S-Q (2010) A novel measure for evaluating classifiers. Expert Syst Appl 37(5):3799\u20133809","journal-title":"Expert Syst Appl"},{"issue":"8","key":"1164_CR50","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0041882","volume":"7","author":"G Jurman","year":"2012","unstructured":"Jurman G, Riccadonna S, Furlanello C (2012) A comparison of MCC and CEN error measures in multi-class prediction. PLoS ONE 7(8):e41882","journal-title":"PLoS ONE"},{"issue":"1","key":"1164_CR51","doi-asserted-by":"publisher","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":"18","key":"1164_CR52","doi-asserted-by":"publisher","first-page":"9398","DOI":"10.1021\/acs.jcim.5c01609","volume":"65","author":"JR Ash","year":"2025","unstructured":"Ash JR, Wognum C, Rodr\u00edguez-P\u00e9rez R, Aldeghi M, Cheng AC, Clevert D-A, Engkvist O, Fang C, Price DJ, Hughes-Oliver JM (2025) Practically significant method comparison protocols for machine learning in small molecule drug discovery. J Chem Inf Model 65(18):9398\u20139411","journal-title":"J Chem Inf Model"},{"issue":"Nov","key":"1164_CR53","first-page":"2579","volume":"9","author":"L Maaten","year":"2008","unstructured":"Maaten L, Hinton G (2008) Visualizing data using t-SNE. J Mach Learn Res 9(Nov):2579\u20132605","journal-title":"J Mach Learn Res"},{"key":"1164_CR54","first-page":"291","volume":"140","author":"HT Bucherer","year":"1934","unstructured":"Bucherer HT, Steiner W (1934) Syntheses of hydantoins. I. On reactions of \u03b1-hydroxy and \u03b1-amino nitriles. J prakt Chem 140:291\u2013316","journal-title":"J prakt Chem"},{"issue":"7","key":"1164_CR55","doi-asserted-by":"publisher","first-page":"1764","DOI":"10.1039\/c3gc40588e","volume":"15","author":"K Durchschein","year":"2013","unstructured":"Durchschein K, Hall M, Faber K (2013) Unusual reactions mediated by FMN-dependent ene-and nitro-reductases. Green Chem 15(7):1764\u20131772","journal-title":"Green Chem"},{"issue":"10","key":"1164_CR56","doi-asserted-by":"publisher","first-page":"2765","DOI":"10.1021\/jo00036a001","volume":"57","author":"C Giordano","year":"1992","unstructured":"Giordano C, Coppi L (1992) Br 3-vs Br2: opposite diastereoselectivity in the bromination of enantiomerically pure ketals. J Org Chem 57(10):2765\u20132766","journal-title":"J Org Chem"},{"issue":"5","key":"1164_CR57","doi-asserted-by":"publisher","first-page":"387","DOI":"10.2165\/00003495-198529050-00001","volume":"29","author":"M Chaffman","year":"1985","unstructured":"Chaffman M, Brogden RN (1985) Diltiazem: a review of its pharmacological properties and therapeutic efficacy. Drugs 29(5):387\u2013454","journal-title":"Drugs"},{"key":"1164_CR58","doi-asserted-by":"publisher","DOI":"10.1016\/j.ecoenv.2022.114016","volume":"243","author":"Y-D Deng","year":"2022","unstructured":"Deng Y-D, Wang L-J, Zhang W-H, Xu J, Gao J-J, Wang B, Fu X-Y, Han H-J, Li Z-J, Wang Y (2022) Construction of complete degradation pathway for nitrobenzene in Escherichia coli. Ecotoxicol Environ Saf 243:114016","journal-title":"Ecotoxicol Environ Saf"},{"issue":"D1","key":"1164_CR59","doi-asserted-by":"publisher","first-page":"D609","DOI":"10.1093\/nar\/gkae1010","volume":"53","author":"UniProt","year":"2025","unstructured":"UniProt (2025) The universal protein knowledgebase in 2025. Nucleic Acids Res 53(D1):D609\u2013D617","journal-title":"Nucleic Acids Res"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01164-y","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01164-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01164-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T15:07:10Z","timestamp":1773328030000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13321-026-01164-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2,9]]},"references-count":59,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1164"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01164-y","relation":{"has-preprint":[{"id-type":"doi","id":"10.26434\/chemrxiv-2025-8ggs5","asserted-by":"object"}]},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2,9]]},"assertion":[{"value":"2 November 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2026","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":"35"}}