{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:38:45Z","timestamp":1783643925825,"version":"3.55.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T00:00:00Z","timestamp":1732579200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-024-00928-8","type":"journal-article","created":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T10:13:16Z","timestamp":1732615996000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Suitability of large language models for extraction of high-quality chemical reaction dataset from patent literature"],"prefix":"10.1186","volume":"16","author":[{"given":"Sarveswara Rao","family":"Vangala","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sowmya Ramaswamy","family":"Krishnan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Navneet","family":"Bung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dhandapani","family":"Nandagopal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gomathi","family":"Ramasamy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Satyam","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sridharan","family":"Sankaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rajgopal","family":"Srinivasan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,11,26]]},"reference":[{"key":"928_CR1","doi-asserted-by":"publisher","DOI":"10.1038\/s41587-024-02143-0","author":"F Ren","year":"2024","unstructured":"Ren F, Aliper A, Chen J, Zhao H, Rao S, Kuppe C et al (2024) A small-molecule TNIK inhibitor targets fibrosis in preclinical and clinical models. Nat Biotechnol. https:\/\/doi.org\/10.1038\/s41587-024-02143-0","journal-title":"Nat Biotechnol"},{"issue":"6","key":"928_CR2","doi-asserted-by":"publisher","first-page":"891","DOI":"10.3390\/ph16060891","volume":"16","author":"A Blanco-Gonzalez","year":"2023","unstructured":"Blanco-Gonzalez A, Cabezon A, Seco-Gonzalez A, Conde-Torres D, Antelo-Riveiro P, Pineiro A et al (2023) The role of AI in drug discovery: challenges, opportunities, and strategies. Pharmaceuticals 16(6):891","journal-title":"Pharmaceuticals"},{"issue":"4","key":"928_CR3","doi-asserted-by":"publisher","first-page":"1040","DOI":"10.1016\/j.drudis.2020.11.037","volume":"26","author":"A Bender","year":"2021","unstructured":"Bender A, Cortes-Ciriano I (2021) Artificial intelligence in drug discovery: what is realistic, what are illusions? Part 2: a discussion of chemical and biological data. Drug Discov Today 26(4):1040\u20131052","journal-title":"Drug Discov Today"},{"issue":"6453","key":"928_CR4","doi-asserted-by":"publisher","first-page":"eaax1566","DOI":"10.1126\/science.aax1566","volume":"365","author":"CW Coley","year":"2019","unstructured":"Coley CW, Thomas DA III, Lummiss JAM, Jaworski JN, Breen CP, Schultz V et al (2019) A robotic platform for flow synthesis of organic compounds informed by AI planning. Science 365(6453):eaax1566","journal-title":"Science"},{"issue":"1","key":"928_CR5","doi-asserted-by":"publisher","first-page":"15016","DOI":"10.1088\/2632-2153\/abc81d","volume":"2","author":"P Schwaller","year":"2021","unstructured":"Schwaller P, Vaucher AC, Laino T, Reymond JL (2021) Prediction of chemical reaction yields using deep learning. Mach Learn Sci Technol 2(1):15016","journal-title":"Mach Learn Sci Technol"},{"key":"928_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmgm.2024.108734","volume":"129","author":"SR Krishnan","year":"2024","unstructured":"Krishnan SR, Bung N, Srinivasan R, Roy A (2024) Target-specific novel molecules with their recipe: incorporating synthesizability in the design process. J Mol Graph Model 129:108734","journal-title":"J Mol Graph Model"},{"issue":"6","key":"928_CR7","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1016\/j.drudis.2018.01.039","volume":"23","author":"H Chen","year":"2018","unstructured":"Chen H, Engkvist O, Wang Y, Olivecrona M, Blaschke T (2018) The rise of deep learning in drug discovery. Drug Discov Today 23(6):1241\u20131250","journal-title":"Drug Discov Today"},{"issue":"3","key":"928_CR8","doi-asserted-by":"publisher","first-page":"442","DOI":"10.1039\/C7ME00107J","volume":"3","author":"D Fooshee","year":"2018","unstructured":"Fooshee D, Mood A, Gutman E, Tavakoli M, Urban G, Liu F et al (2018) Deep learning for chemical reaction prediction. Mol Syst Des Eng 3(3):442\u2013452","journal-title":"Mol Syst Des Eng"},{"key":"928_CR9","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1021\/bk-2014-1164.ch008","volume-title":"the future of the history of chemical information","author":"AJ Lawson","year":"2014","unstructured":"Lawson AJ, Swienty-Busch J, G\u00e9oui T, Evans D (2014) The making of reaxys\u2014towards unobstructed access to relevant chemistry information. the future of the history of chemical information. American Chemical Society, pp 127\u2013148"},{"issue":"4","key":"928_CR10","doi-asserted-by":"publisher","first-page":"588","DOI":"10.5195\/jmla.2018.515","volume":"106","author":"SW Gabrielson","year":"2018","unstructured":"Gabrielson SW (2018) SciFinder. J Med Libr Assoc 106(4):588","journal-title":"J Med Libr Assoc"},{"key":"928_CR11","unstructured":"Lowe, D. M. Extraction of Chemical Structures and Reactions from the Literature. Doctoral dissertation. Cambridge: University of Cambridge; 2012."},{"issue":"9","key":"928_CR12","doi-asserted-by":"publisher","first-page":"2035","DOI":"10.1021\/acs.jcim.1c00284","volume":"62","author":"J Guo","year":"2022","unstructured":"Guo J, Ibanez-Lopez AS, Gao H, Quach V, Coley CW, Jensen KF, Barzilay R (2022) Automated chemical reaction extraction from scientific literature. J Chem Inf Model 62(9):2035\u20132045. https:\/\/doi.org\/10.1021\/acs.jcim.1c00284","journal-title":"J Chem Inf Model"},{"key":"928_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1758-2946-3-17","volume":"3","author":"L Hawizy","year":"2011","unstructured":"Hawizy L, Jessop DM, Adams N, Murray-Rust P (2011) ChemicalTagger: a tool for semantic text-mining in chemistry. J Cheminform 3:1\u201313","journal-title":"J Cheminform"},{"issue":"45","key":"928_CR14","doi-asserted-by":"publisher","first-page":"18820","DOI":"10.1021\/jacs.1c09820","volume":"143","author":"SM Kearnes","year":"2021","unstructured":"Kearnes SM, Maser MR, Wleklinski M, Kast A, Doyle AG, Dreher SD et al (2021) The open reaction database. J Am Chem Soc 143(45):18820\u201318826","journal-title":"J Am Chem Soc"},{"issue":"12","key":"928_CR15","doi-asserted-by":"publisher","first-page":"2100119","DOI":"10.1002\/minf.202100119","volume":"40","author":"TR Gimadiev","year":"2021","unstructured":"Gimadiev TR, Lin A, Afonina VA, Batyrshin D, Nugmanov RI, Akhmetshin T et al (2021) Reaction data curation I: chemical structures and transformations standardization. Mol Inform 40(12):2100119","journal-title":"Mol Inform"},{"key":"928_CR16","unstructured":"Mayfield J, Lowe D, Sayle R. Pistachio: search and faceting of large reaction databases. In: Abstracts of papers of the American Chemical Society, vol. 254; 2017."},{"key":"928_CR17","doi-asserted-by":"publisher","DOI":"10.3389\/frma.2021.654438","volume":"6","author":"J He","year":"2021","unstructured":"He J, Nguyen DQ, Akhondi SA, Druckenbrodt C, Thorne C, Hoessel R et al (2021) Chemu 2020: natural language processing methods are effective for information extraction from chemical patents. Front Res Metr Anal 6:654438","journal-title":"Front Res Metr Anal"},{"key":"928_CR18","unstructured":"Chithrananda, S.; Grand, G.; Ramsundar, B. ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction. arXiv preprint arXiv:2010.098852020."},{"key":"928_CR19","unstructured":"Zhang J, Zhang Y. Melaxtech: a report for CLEF 2020\u2013ChEMU task of chemical reaction extraction from patent. Work Notes CLEF. 2020."},{"key":"928_CR20","doi-asserted-by":"crossref","unstructured":"Yasunaga M, Leskovec J, Liang P. Linkbert: pretraining language models with document links. arXiv preprint arXiv:2203.15827; 2022.","DOI":"10.18653\/v1\/2022.acl-long.551"},{"key":"928_CR21","unstructured":"Malarkodi CS, Rao PR, Devi SL. CLRG ChemNER: a chemical named entity recognizer@ ChEMU CLEF 2020. In: CLEF (Working Notes); 2020."},{"issue":"19","key":"928_CR22","doi-asserted-by":"publisher","first-page":"6053","DOI":"10.1021\/acs.jcim.3c00422","volume":"63","author":"DM Wilary","year":"2023","unstructured":"Wilary DM, Cole JM (2023) ReactionDataExtractor 2.0: a deep learning approach for data extraction from chemical reaction schemes. J Chem Inf Model 63(19):6053\u20136067","journal-title":"J Chem Inf Model"},{"issue":"13","key":"928_CR23","doi-asserted-by":"publisher","first-page":"4030","DOI":"10.1021\/acs.jcim.3c00439","volume":"63","author":"Y Qian","year":"2023","unstructured":"Qian Y, Guo J, Tu Z, Coley CW, Barzilay R (2023) RxnScribe: a sequence generation model for reaction diagram parsing. J Chem Inf Model 63(13):4030\u20134041","journal-title":"J Chem Inf Model"},{"key":"928_CR24","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2023-05v1b-v2","author":"L Patiny","year":"2023","unstructured":"Patiny L, Godin G (2023) Automatic extraction of FAIR data from publications using LLM. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2023-05v1b-v2","journal-title":"ChemRxiv"},{"key":"928_CR25","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-979fz","author":"Q Ai","year":"2024","unstructured":"Ai Q, Meng F, Shi J, Pelkie B, Coley CW (2024) Extracting structured data from organic synthesis procedures using a fine-tuned large language model. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2024-979fz","journal-title":"ChemRxiv"},{"key":"928_CR26","unstructured":"Schilling-Wilhelmi M, R\u00edos-Garc\u00eda M, Shabih S, Gil MV, Miret S, Koch CT, Jablonka KM. From text to insight: large language models for materials science data extraction. arXiv preprint arXiv:2407.16867; 2024"},{"issue":"15","key":"928_CR27","doi-asserted-by":"publisher","first-page":"eabe4166","DOI":"10.1126\/sciadv.abe4166","volume":"7","author":"P Schwaller","year":"2021","unstructured":"Schwaller P, Hoover B, Reymond J-L, Strobelt H, Laino T (2021) Extraction of organic chemistry grammar from unsupervised learning of chemical reactions. Sci Adv 7(15):eabe4166","journal-title":"Sci Adv"},{"issue":"1","key":"928_CR28","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1021\/acs.jcim.3c01524","volume":"64","author":"V Voinarovska","year":"2023","unstructured":"Voinarovska V, Kabeshov M, Dudenko D, Genheden S, Tetko IV (2023) When yield prediction does not yield prediction: an overview of the current challenges. J Chem Inf Model 64(1):42\u201356","journal-title":"J Chem Inf Model"},{"issue":"1","key":"928_CR29","doi-asserted-by":"publisher","first-page":"1418","DOI":"10.1038\/s41467-024-45563-x","volume":"15","author":"J Dagdelen","year":"2024","unstructured":"Dagdelen J, Dunn A, Lee S, Walker N, Rosen AS, Ceder G et al (2024) Structured information extraction from scientific text with large language models. Nat Commun 15(1):1418","journal-title":"Nat Commun"},{"key":"928_CR30","unstructured":"Nori H, Lee YT, Zhang S, Carignan D, Edgar R, Fusi N et al. Can generalist foundation models outcompete special-purpose tuning? Case study in medicine. arXiv preprint arXiv:2311.16452; 2023."},{"key":"928_CR31","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown T, Mann B, Ryder N, Subbiah M, Kaplan JD, Dhariwal P et al (2020) Language models are few-shot learners. Adv Neural Inf Process Syst 33:1877\u20131901","journal-title":"Adv Neural Inf Process Syst"},{"key":"928_CR32","unstructured":"Team G, Anil R, Borgeaud S, Wu Y, Alayrac JB, Yu J et al. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805; 2023."},{"key":"928_CR33","unstructured":"Claude 2. https:\/\/www.anthropic.com\/news\/claude-2. Accessed 15 Oct 2023."},{"key":"928_CR34","unstructured":"Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y et al. Llama 2: open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288; 2023."},{"issue":"4","key":"928_CR35","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1093\/bioinformatics\/btz682","volume":"36","author":"J Lee","year":"2020","unstructured":"Lee J, Yoon W, Kim S, Kim D, Kim S, So CH et al (2020) BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4):1234\u20131240","journal-title":"Bioinformatics"},{"key":"928_CR36","unstructured":"Rish I. An empirical study of the Naive Bayes classifier. In: IJCAI 2001 workshop on empirical methods in artificial intelligence, vol. 3; 2001. P. 41\u201346."},{"issue":"1","key":"928_CR37","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/1758-2946-3-40","volume":"3","author":"DM Jessop","year":"2011","unstructured":"Jessop DM, Sam EA, Peter M (2011) Mining chemical information from open patents. J Cheminform 3(1):40","journal-title":"J Cheminform"},{"key":"928_CR38","unstructured":"Yu B, Baker FN, Chen Z, Ning X, Sun H. Llasmol: advancing large language models for chemistry with a large-scale, comprehensive, high-quality instruction tuning dataset. arXiv preprint arXiv:2402.09391; 2024."},{"issue":"1","key":"928_CR39","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1186\/s13321-021-00512-4","volume":"13","author":"K Rajan","year":"2021","unstructured":"Rajan K, Zielesny A, Steinbeck C (2021) STOUT: SMILES to IUPAC names using neural machine translation. J Cheminform 13(1):34","journal-title":"J Cheminform"},{"issue":"3","key":"928_CR40","doi-asserted-by":"publisher","first-page":"739","DOI":"10.1021\/ci100384d","volume":"51","author":"DM Lowe","year":"2011","unstructured":"Lowe DM, Corbett PT, Murray-Rust P, Glen RC (2011) Chemical name to structure: OPSIN, an open source solution. J Chem Inf Model 51(3):739\u2013753","journal-title":"J Chem Inf Model"},{"issue":"Suppl 1","key":"928_CR41","doi-asserted-by":"publisher","first-page":"P4","DOI":"10.1186\/1758-2946-3-S1-P4","volume":"3","author":"D Pavlov","year":"2011","unstructured":"Pavlov D, Rybalkin M, Karulin B, Kozhevnikov M, Savelyev A, Churinov A (2011) Indigo: universal cheminformatics API. J Cheminform 3(Suppl 1):P4","journal-title":"J Cheminform"},{"issue":"1","key":"928_CR42","doi-asserted-by":"publisher","first-page":"1434","DOI":"10.1038\/s41467-019-09440-2","volume":"10","author":"W Jaworski","year":"2019","unstructured":"Jaworski W, Szymku\u0107 S, Mikulak-Klucznik B, Piecuch K, Klucznik T, Ka\u017amierowski M et al (2019) Automatic mapping of atoms across both simple and complex chemical reactions. Nat Commun 10(1):1434","journal-title":"Nat Commun"},{"key":"928_CR43","unstructured":"Tiny but mighty: The Phi-3 small language models with big potential. https:\/\/news.microsoft.com\/source\/features\/ai\/the-phi-3-small-language-models-with-big-potential\/. Accessed 20 Sept 2024."}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-024-00928-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-024-00928-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-024-00928-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T11:07:35Z","timestamp":1732619255000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-024-00928-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,26]]},"references-count":43,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["928"],"URL":"https:\/\/doi.org\/10.1186\/s13321-024-00928-8","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,26]]},"assertion":[{"value":"12 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 November 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors are employed by Tata Consultancy Services Limited.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"131"}}