{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:54:20Z","timestamp":1780930460258,"version":"3.54.1"},"reference-count":98,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T00:00:00Z","timestamp":1772409600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T00:00:00Z","timestamp":1775520000000},"content-version":"vor","delay-in-days":36,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"DOI":"10.13039\/501100001691","name":"Japan Society for the Promotion of Science","doi-asserted-by":"publisher","award":["JP23K14382"],"award-info":[{"award-number":["JP23K14382"]}],"id":[{"id":"10.13039\/501100001691","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100009619","name":"Japan Agency for Medical Research and Development","doi-asserted-by":"publisher","award":["JP25ama121028"],"award-info":[{"award-number":["JP25ama121028"]}],"id":[{"id":"10.13039\/100009619","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Japan Science and Technology Agency National Bioscience Database Center","award":["JPMJND2401"],"award-info":[{"award-number":["JPMJND2401"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-026-01174-w","type":"journal-article","created":{"date-parts":[[2026,3,2]],"date-time":"2026-03-02T14:43:22Z","timestamp":1772462602000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Data curation in cheminformatics: importance and implementation"],"prefix":"10.1186","volume":"18","author":[{"given":"Tsuyoshi","family":"Esaki","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kazuyoshi","family":"Ikeda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,2]]},"reference":[{"issue":"7","key":"1174_CR1","doi-asserted-by":"publisher","first-page":"1243","DOI":"10.1021\/acs.jcim.6b00129","volume":"56","author":"D Fourches","year":"2016","unstructured":"Fourches D, Muratov E, Tropsha A (2016) Trust, but verify II: a practical guide to chemogenomics data curation. J Chem Inf Model 56(7):1243\u20131252. https:\/\/doi.org\/10.1021\/acs.jcim.6b00129","journal-title":"J Chem Inf Model"},{"key":"1174_CR2","doi-asserted-by":"publisher","first-page":"D1180","DOI":"10.1093\/nar\/gkad1004","volume":"52","author":"B Zdrazil","year":"2024","unstructured":"Zdrazil B, Felix E, Hunter F, Manners EJ, Blackshaw J, Corbett S et al (2024) The ChEMBL database in 2023: a drug discovery platform spanning multiple bioactivity data types and time periods. Nucleic Acids Res 52:D1180\u2013D1192. https:\/\/doi.org\/10.1093\/nar\/gkad1004","journal-title":"Nucleic Acids Res"},{"key":"1174_CR3","doi-asserted-by":"publisher","first-page":"D1516","DOI":"10.1093\/nar\/gkae1059","volume":"53","author":"S Kim","year":"2025","unstructured":"Kim S, Chen J, Cheng T, Gindulyte A, He J, He S et al (2025) PubChem 2025 update. Nucleic Acids Res 53:D1516\u2013D1525. https:\/\/doi.org\/10.1093\/nar\/gkae1059","journal-title":"Nucleic Acids Res"},{"key":"1174_CR4","doi-asserted-by":"publisher","first-page":"D1100","DOI":"10.1093\/nar\/gkr777","volume":"40","author":"A Gaulton","year":"2012","unstructured":"Gaulton A, Bellis LJ, Bento AP, Chambers J, Davies M, Hersey A et al (2012) ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res 40:D1100\u2013D1107. https:\/\/doi.org\/10.1093\/nar\/gkr777","journal-title":"Nucleic Acids Res"},{"issue":"6","key":"1174_CR5","doi-asserted-by":"publisher","first-page":"957","DOI":"10.1136\/amiajnl-2014-002974","volume":"21","author":"R Margolis","year":"2014","unstructured":"Margolis R, Derr L, Dunn M, Huerta M, Larkin J, Sheehan J et al (2014) The National Institutes of Health\u2019s big data to knowledge (BD2K) initiative: capitalizing on biomedical big data. J Am Med Inform Assoc 21(6):957\u2013958. https:\/\/doi.org\/10.1136\/amiajnl-2014-002974","journal-title":"J Am Med Inform Assoc"},{"key":"1174_CR6","unstructured":"National Institutes of Health (2025) NIH strategic plan for data science. National Institutes of Health, Bethesda, MD, p 2025\u20132030. https:\/\/datascience.nih.gov\/nih-strategic-plan-data-science. Accessed 16 Dec 2025"},{"key":"1174_CR7","unstructured":"National Institutes of Health (2025) NIH to prioritize human-based research technologies: New initiative aims to reduce use of animals in NIH-funded research. Accessed 29 Apr 2025. . https:\/\/www.nih.gov\/news-events\/news-releases\/nih-prioritize-human-based-research-technologies"},{"key":"1174_CR8","doi-asserted-by":"publisher","DOI":"10.1038\/d41586-022-03569-9","author":"R Nuwer","year":"2022","unstructured":"Nuwer R (2022) US agency seeks to phase out animal testing. Nature. https:\/\/doi.org\/10.1038\/d41586-022-03569-9","journal-title":"Nature"},{"key":"1174_CR9","unstructured":"U.S. Food and Drug Administration (2025) FDA Announces Plan to Phase Out Animal Testing Requirement for Monoclonal Antibodies and Other Drugs. Accessed 10 Apr 2025. https:\/\/www.fda.gov\/news-events\/press-announcements\/fda-announces-plan-phase-out-animal-testing-requirement-monoclonal-antibodies-and-other-drugs"},{"issue":"1","key":"1174_CR10","doi-asserted-by":"publisher","first-page":"3","DOI":"10.14573\/altex.2412291","volume":"42","author":"T Hartung","year":"2025","unstructured":"Hartung T, Kleinstreuer N (2025) Challenges and opportunities for validation of AI-based new approach methods. ALTEX Altern Anim Exp 42(1):3\u201321. https:\/\/doi.org\/10.14573\/altex.2412291","journal-title":"ALTEX Altern Anim Exp"},{"key":"1174_CR11","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2212.11854","author":"MV Johannes Jakubik","year":"2022","unstructured":"Johannes Jakubik MV, K\u00fchl N, Walk J, Satzger G (2022) Data-centric artificial intelligence. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2212.11854","journal-title":"arXiv"},{"key":"1174_CR12","unstructured":"Andrew NG (2021) DeepLearningAI. A Chat with Andrew on MLOps: From Model-Centric to Data-Centric AI. Accessed 24 Mar 2021. https:\/\/www.youtube.com\/watch?v=06-AZXmwHjo"},{"key":"1174_CR13","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1038\/s43586-021-00084-5","volume":"2","author":"AL Satz","year":"2022","unstructured":"Satz AL, Brunschweiger A, Flanagan ME, Gloger A, Hansen NJV, Kuai L et al (2022) DNA-encoded chemical libraries. Nat Rev Methods Primers 2:3. https:\/\/doi.org\/10.1038\/s43586-021-00084-5","journal-title":"Nat Rev Methods Primers"},{"key":"1174_CR14","doi-asserted-by":"publisher","first-page":"1828","DOI":"10.1016\/j.drudis.2016.07.013","volume":"21","author":"G Zimmermann","year":"2016","unstructured":"Zimmermann G, Neri D (2016) DNA-encoded chemical libraries: foundations and applications in lead discovery. Drug Discov Today 21:1828\u20131834. https:\/\/doi.org\/10.1016\/j.drudis.2016.07.013","journal-title":"Drug Discov Today"},{"key":"1174_CR15","doi-asserted-by":"publisher","first-page":"2168","DOI":"10.1002\/1873-3468.13068","volume":"592","author":"N Favalli","year":"2018","unstructured":"Favalli N, Bassi G, Scheuermann J, Neri D (2018) DNA-encoded chemical libraries: achievements and remaining challenges. FEBS Lett 592:2168\u20132180. https:\/\/doi.org\/10.1002\/1873-3468.13068","journal-title":"FEBS Lett"},{"key":"1174_CR16","doi-asserted-by":"publisher","first-page":"10952","DOI":"10.1039\/d5cc02904j","volume":"61","author":"Y Gao","year":"2025","unstructured":"Gao Y, Liu J, Huang S, Du N, Zhang G, Li Y (2025) Recent advances in DNA-encoded libraries. Chem Commun 61:10952\u201310968. https:\/\/doi.org\/10.1039\/d5cc02904j","journal-title":"Chem Commun"},{"key":"1174_CR17","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.cell.2019.11.031","volume":"181","author":"GM Burslem","year":"2020","unstructured":"Burslem GM, Crews CM (2020) Proteolysis-targeting chimeras as therapeutics and tools for biological discovery. Cell 181:102\u2013114. https:\/\/doi.org\/10.1016\/j.cell.2019.11.031","journal-title":"Cell"},{"key":"1174_CR18","doi-asserted-by":"publisher","first-page":"D1510","DOI":"10.1093\/nar\/gkae768","volume":"53","author":"J Ge","year":"2025","unstructured":"Ge J, Li S, Weng G, Wang H, Fang M, Sun H et al (2025) PROTAC-DB 3.0: an updated database of PROTACs with extended pharmacokinetic parameters. Nucleic Acids Res 53:D1510\u2013D1515. https:\/\/doi.org\/10.1093\/nar\/gkae768","journal-title":"Nucleic Acids Res"},{"key":"1174_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1002\/3527603743.ch9","volume-title":"Chemoinformatics in drug discovery","author":"M Olah","year":"2005","unstructured":"Olah M, Mracec M, Ostopovici L, Rad R, Bora A, Hadaruga N et al (2005) WOMBAT: World of molecular bioactivity. In: Oprea TI (ed) Chemoinformatics in drug discovery. John Wiley & Sons, Chichester, pp 221\u2013239"},{"issue":"11\u201312","key":"1174_CR20","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1002\/qsar.200810084","volume":"27","author":"D Young","year":"2008","unstructured":"Young D, Martin T, Venkatapathy R, Harten P (2008) Are the chemical structures in your QSAR correct? QSAR Comb Sci 27(11\u201312):1337\u20131345. https:\/\/doi.org\/10.1002\/qsar.200810084","journal-title":"QSAR Comb Sci"},{"issue":"10","key":"1174_CR21","doi-asserted-by":"publisher","first-page":"2499","DOI":"10.1021\/ci400099q","volume":"53","author":"P Tiikkainen","year":"2013","unstructured":"Tiikkainen P, Bellis L, Light Y, Franke L (2013) Estimating error rates in bioactivity databases. J Chem Inf Model 53(10):2499\u20132505. https:\/\/doi.org\/10.1021\/ci400099q","journal-title":"J Chem Inf Model"},{"key":"1174_CR22","doi-asserted-by":"publisher","first-page":"941","DOI":"10.1039\/d2va00225f","volume":"2","author":"J Gl\u00fcge","year":"2023","unstructured":"Gl\u00fcge J, McNeill K, Scheringer M (2023) Getting the SMILES right: identifying inconsistent chemical identifiers in regulatory and non-regulatory databases. Environ Sci Adv 2:941\u2013955. https:\/\/doi.org\/10.1039\/d2va00225f","journal-title":"Environ Sci Adv"},{"issue":"3","key":"1174_CR23","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1021\/acs.chemrestox.2c00379","volume":"36","author":"CN Lowe","year":"2023","unstructured":"Lowe CN, Charest N, Ramsland C, Chang DT, Martin TM, Williams AJ (2023) Transparency in modeling through careful application of OECD\u2019s QSAR\/QSPR principles via a curated water solubility data set. Chem Res Toxicol 36(3):465\u2013478. https:\/\/doi.org\/10.1021\/acs.chemrestox.2c00379","journal-title":"Chem Res Toxicol"},{"key":"1174_CR24","doi-asserted-by":"publisher","first-page":"100087","DOI":"10.1016\/j.ailsci.2023.100087","volume":"4","author":"CA Hern\u00e1ndez-Garrido","year":"2023","unstructured":"Hern\u00e1ndez-Garrido CA, S\u00e1nchez-Cruz N (2023) Experimental uncertainty in training data for protein-ligand binding affinity prediction models. Artif Intell Life Sci 4:100087. https:\/\/doi.org\/10.1016\/j.ailsci.2023.100087","journal-title":"Artif Intell Life Sci"},{"issue":"1","key":"1174_CR25","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1186\/s13321-025-01103-3","volume":"17","author":"R Parrondo-Pizarro","year":"2025","unstructured":"Parrondo-Pizarro R, Menestrina L, Garcia-Serna R, Fern\u00e1ndez-Torras A, Mestres J (2025) Enhancing molecular property prediction through data integration and consistency assessment. J Cheminform 17(1):163. https:\/\/doi.org\/10.1186\/s13321-025-01103-3","journal-title":"J Cheminform"},{"key":"1174_CR26","doi-asserted-by":"publisher","first-page":"104069","DOI":"10.1016\/j.etap.2023.104069","volume":"98","author":"NG Nikolov","year":"2023","unstructured":"Nikolov NG, Nissen ACVE, Wedebye EB (2023) A method for in vitro data and structure curation to optimize for QSAR modelling of minimum absolute potency levels and a comparative use case. Environ Toxicol Pharmacol 98:104069. https:\/\/doi.org\/10.1016\/j.etap.2023.104069","journal-title":"Environ Toxicol Pharmacol"},{"issue":"1","key":"1174_CR27","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1038\/s41597-022-01154-3","volume":"9","author":"J Meng","year":"2022","unstructured":"Meng J, Chen P, Wahib M, Yang M, Zheng L, Wei Y et al (2022) Boosting the predictive performance with aqueous solubility dataset curation. Sci Data 9(1):71. https:\/\/doi.org\/10.1038\/s41597-022-01154-3","journal-title":"Sci Data"},{"issue":"1","key":"1174_CR28","doi-asserted-by":"publisher","first-page":"289","DOI":"10.1038\/s41597-021-01069-5","volume":"8","author":"F Meng","year":"2021","unstructured":"Meng F, Xi Y, Huang J, Ayers PW (2021) A curated diverse molecular database of blood\u2013brain barrier permeability with chemical descriptors. Sci Data 8(1):289. https:\/\/doi.org\/10.1038\/s41597-021-01069-5","journal-title":"Sci Data"},{"issue":"1\u20132","key":"1174_CR29","doi-asserted-by":"publisher","first-page":"e1800086","DOI":"10.1002\/minf.201800086","volume":"38","author":"T Esaki","year":"2019","unstructured":"Esaki T, Watanabe R, Kawashima H, Ohashi R, Natsume-Kitatani Y, Nagao C et al (2019) Data curation can improve the prediction accuracy of metabolic intrinsic clearance. Mol Inform 38(1\u20132):e1800086. https:\/\/doi.org\/10.1002\/minf.201800086","journal-title":"Mol Inform"},{"issue":"2","key":"1174_CR30","doi-asserted-by":"publisher","first-page":"bbae081","DOI":"10.1093\/bib\/bbae081","volume":"25","author":"H Wang","year":"2024","unstructured":"Wang H (2024) Prediction of protein\u2013ligand binding affinity via deep learning models. Brief Bioinform 25(2):bbae081. https:\/\/doi.org\/10.1093\/bib\/bbae081","journal-title":"Brief Bioinform"},{"issue":"8","key":"1174_CR31","doi-asserted-by":"publisher","first-page":"535","DOI":"10.1038\/nchembio.1881","volume":"11","author":"D Fourches","year":"2015","unstructured":"Fourches D, Muratov E, Tropsha A (2015) Curation of chemogenomics data. Nat Chem Biol 11(8):535\u2013535. https:\/\/doi.org\/10.1038\/nchembio.1881","journal-title":"Nat Chem Biol"},{"issue":"1","key":"1174_CR32","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/s13321-020-0408-x","volume":"12","author":"N Schaduangrat","year":"2020","unstructured":"Schaduangrat N, Lampa S, Simeon S, Gleeson MP, Spjuth O, Nantasenamat C (2020) Towards reproducible computational drug discovery. J Cheminform 12(1):9. https:\/\/doi.org\/10.1186\/s13321-020-0408-x","journal-title":"J Cheminform"},{"key":"1174_CR33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1712.00409","author":"J Hestness","year":"2017","unstructured":"Hestness J, Newsha Ardalani SN, Diamos G, Jun H, Kianinejad H, Patwary MMA et al (2017) Deep learning scaling is predictable, empirically. arXiv. https:\/\/doi.org\/10.48550\/arXiv.1712.00409","journal-title":"arXiv"},{"issue":"6","key":"1174_CR34","doi-asserted-by":"publisher","first-page":"2574","DOI":"10.1109\/TKDE.2020.3015777","volume":"34","author":"M Wang","year":"2020","unstructured":"Wang M, Fu W, He X, Hao S, Wu X (2020) A survey on large-scale machine learning. IEEE Trans Knowl Data Eng 34(6):2574\u20132594. https:\/\/doi.org\/10.1109\/TKDE.2020.3015777","journal-title":"IEEE Trans Knowl Data Eng"},{"issue":"3","key":"1174_CR35","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1016\/j.bdr.2015.04.001","volume":"2","author":"OY Al-Jarrah","year":"2015","unstructured":"Al-Jarrah OY, Yoo PD, Muhaidat S, Karagiannidis GK, Taha K (2015) Efficient machine learning for big data: a review. Big Data Res 2(3):87\u201393. https:\/\/doi.org\/10.1016\/j.bdr.2015.04.001","journal-title":"Big Data Res"},{"issue":"Suppl 1","key":"1174_CR36","doi-asserted-by":"publisher","first-page":"S1","DOI":"10.1186\/1752-153X-4-S1-S1","volume":"4","author":"A Lombardo","year":"2010","unstructured":"Lombardo A, Roncaglioni A, Boriani E, Milan C, Benfenati E (2010) Assessment and validation of the Caesar predictive model for bioconcentration factor (BCF) in fish. Chem Cent J 4(Suppl 1):S1. https:\/\/doi.org\/10.1186\/1752-153X-4-S1-S1","journal-title":"Chem Cent J"},{"issue":"7","key":"1174_CR37","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1021\/ci100176x","volume":"50","author":"D Fourches","year":"2010","unstructured":"Fourches D, Muratov E, Tropsha A (2010) Trust, but verify: on the importance of chemical structure curation in cheminformatics and QSAR modeling research. J Chem Inf Model 50(7):1189\u20131204. https:\/\/doi.org\/10.1021\/ci100176x","journal-title":"J Chem Inf Model"},{"issue":"1","key":"1174_CR38","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1186\/s13321-025-00963-z","volume":"17","author":"B Zdrazil","year":"2025","unstructured":"Zdrazil B (2025) Fifteen years of ChEMBL and its role in cheminformatics and drug discovery. J Cheminform 17(1):32. https:\/\/doi.org\/10.1186\/s13321-025-00963-z","journal-title":"J Cheminform"},{"issue":"2","key":"1174_CR39","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1021\/acs.chemrestox.0c00296","volume":"34","author":"FMI Hunter","year":"2021","unstructured":"Hunter FMI, Bento AP, Bosc N, Gaulton A, Hersey A, Leach AR (2021) Drug safety data curation and modeling in ChEMBL: boxed warnings and withdrawn drugs. Chem Res Toxicol 34(2):385\u2013395. https:\/\/doi.org\/10.1021\/acs.chemrestox.0c00296","journal-title":"Chem Res Toxicol"},{"issue":"11","key":"1174_CR40","doi-asserted-by":"publisher","first-page":"939","DOI":"10.1080\/1062936X.2016.1253611","volume":"27","author":"K Mansouri","year":"2016","unstructured":"Mansouri K, Grulke CM, Richard AM, Judson RS, Williams AJ (2016) An automated curation procedure for addressing chemical errors and inconsistencies in public datasets used in QSAR modelling. SAR QSAR Environ Res 27(11):939\u2013965. https:\/\/doi.org\/10.1080\/1062936X.2016.1253611","journal-title":"SAR QSAR Environ Res"},{"key":"1174_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1273\/cbij.23.1","volume":"23","author":"T Esaki","year":"2023","unstructured":"Esaki T, Ikeda K (2023) Difficulties and prospects of data curation for ADME in silico modeling. Chem-Bio Inf J 23:1\u20136. https:\/\/doi.org\/10.1273\/cbij.23.1","journal-title":"Chem-Bio Inf J"},{"issue":"6\u20137","key":"1174_CR42","doi-asserted-by":"publisher","first-page":"476","DOI":"10.1002\/minf.201000061","volume":"29","author":"A Tropsha","year":"2010","unstructured":"Tropsha A (2010) Best practices for QSAR model development, validation, and exploitation. Mol Inform 29(6\u20137):476\u2013488. https:\/\/doi.org\/10.1002\/minf.201000061","journal-title":"Mol Inform"},{"issue":"1","key":"1174_CR43","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1186\/s13321-022-00606-7","volume":"14","author":"D Dolciami","year":"2022","unstructured":"Dolciami D, Villasclaras-Fernandez E, Kannas C, Meniconi M, Al-Lazikani B, Antolin AA (2022) CanSAR chemistry registration and standardization pipeline. J Cheminform 14(1):28. https:\/\/doi.org\/10.1186\/s13321-022-00606-7","journal-title":"J Cheminform"},{"key":"1174_CR44","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1186\/s13321-022-00672-x","volume":"15","author":"OJM B\u00e9quignon","year":"2023","unstructured":"B\u00e9quignon OJM, Bongers BJ, Jespers W, IJzerman AP, van der Water B, van Westen GJP (2023) Papyrus: a large-scale curated dataset aimed at bioactivity predictions. J Cheminform 15:3. https:\/\/doi.org\/10.1186\/s13321-022-00672-x","journal-title":"J Cheminform"},{"key":"1174_CR45","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1186\/s13321-023-00718-8","volume":"15","author":"E Nittinger","year":"2023","unstructured":"Nittinger E, Clark A, Gaulton A, Zdrazil B (2023) Biomedical data analyses facilitated by open cheminformatics workflows. J Cheminform 15:46. https:\/\/doi.org\/10.1186\/s13321-023-00718-8","journal-title":"J Cheminform"},{"key":"1174_CR46","unstructured":"Richardsons (2023) ChemSpider data cleanup. ChemSpider Blog (Royal Society of Chemistry). Accessed 15 Dec 2023. https:\/\/blogs.rsc.org\/chemspider\/category\/behind-the-scenes\/data-quality\/"},{"issue":"1","key":"1174_CR47","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1186\/s13321-025-01064-7","volume":"17","author":"S M\u00fcller","year":"2025","unstructured":"M\u00fcller S (2025) How to crack a SMILES: automatic crosschecked chemical structure resolution across multiple services using MoleculeResolver. J Cheminform 17(1):117. https:\/\/doi.org\/10.1186\/s13321-025-01064-7","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR48","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1186\/s13321-018-0315-6","volume":"10","author":"D Gadaleta","year":"2018","unstructured":"Gadaleta D, Lombardo A, Toma C, Benfenati E (2018) A new semi-automated workflow for chemical data retrieval and quality checking for modeling applications. J Cheminform 10(1):60. https:\/\/doi.org\/10.1186\/s13321-018-0315-6","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR49","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1186\/s13321-020-00456-1","volume":"12","author":"AP Bento","year":"2020","unstructured":"Bento AP, Hersey A, F\u00e9lix E, Landrum G, Gaulton A, Atkinson F et al (2020) An open source chemical structure curation pipeline using RDKit. J Cheminform 12(1):51. https:\/\/doi.org\/10.1186\/s13321-020-00456-1","journal-title":"J Cheminform"},{"issue":"10","key":"1174_CR50","doi-asserted-by":"publisher","first-page":"693","DOI":"10.1007\/s10822-009-9303-2","volume":"23","author":"YC Martin","year":"2009","unstructured":"Martin YC (2009) Let\u2019s not forget tautomers. J Comput Aided Mol Des 23(10):693\u2013704. https:\/\/doi.org\/10.1007\/s10822-009-9303-2","journal-title":"J Comput Aided Mol Des"},{"issue":"6\u20137","key":"1174_CR51","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/s10822-010-9346-4","volume":"24","author":"M Sitzmann","year":"2010","unstructured":"Sitzmann M, Ihlenfeldt WD, Nicklaus MC (2010) Tautomerism in large databases. J Comput Aided Mol Des 24(6\u20137):521\u2013551. https:\/\/doi.org\/10.1007\/s10822-010-9346-4","journal-title":"J Comput Aided Mol Des"},{"key":"1174_CR52","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ace878","author":"MT Cretu","year":"2023","unstructured":"Cretu MT, Toniato A, Thakkar A, Debabeche A, Laino T, Vaucher AC (2023) Standardizing chemical compounds with language models. Mach Learn Sci Technol. https:\/\/doi.org\/10.1088\/2632-2153\/ace878","journal-title":"Mach Learn Sci Technol"},{"issue":"D1","key":"1174_CR53","doi-asserted-by":"publisher","first-page":"D1373","DOI":"10.1093\/nar\/gkac956","volume":"51","author":"S Kim","year":"2023","unstructured":"Kim S, Chen J, Cheng T, Gindulyte A, He J, He S et al (2023) PubChem 2023 update. Nucleic Acids Res 51(D1):D1373\u2013D1380. https:\/\/doi.org\/10.1093\/nar\/gkac956","journal-title":"Nucleic Acids Res"},{"key":"1174_CR54","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-mn4wm","author":"R Chitsazi","year":"2024","unstructured":"Chitsazi R, Gingrich P, Long J, Wu C, Al-Lazikani B (2024) OpencanSARchem: chemistry registration and standardization pipeline for FAIR integration of bioassay data. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2024-mn4wm","journal-title":"ChemRxiv"},{"key":"1174_CR55","unstructured":"Garrett (2022) Better models through molecular standardization, Oxford protein informatics group blog. Accessed 9 May 2022. https:\/\/www.blopig.com\/blog\/2022\/05\/molecular-standardization\/"},{"key":"1174_CR56","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1186\/s13321-025-00978-6","volume":"17","author":"AB Chetry","year":"2025","unstructured":"Chetry AB, Ohto K (2025) From molecules to data: the emerging impact of chemoinformatics in chemistry. J Cheminform 17:121. https:\/\/doi.org\/10.1186\/s13321-025-00978-6","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR57","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1186\/s13321-024-00814-3","volume":"16","author":"K Mansouri","year":"2024","unstructured":"Mansouri K, Moreira-Filho JT, Lowe CN, Charest N, Martin T, Tkachenko V et al (2024) Free and open-source QSAR-ready workflow for automated standardization of chemical structures in support of QSAR modeling. J Cheminform 16(1):19. https:\/\/doi.org\/10.1186\/s13321-024-00814-3","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR58","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(1):31\u201336. https:\/\/doi.org\/10.1021\/ci00057a005","journal-title":"J Chem Inf Comput Sci."},{"issue":"1","key":"1174_CR59","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1186\/1758-2946-5-7","volume":"5","author":"S Heller","year":"2013","unstructured":"Heller S, McNaught A, Stein S, Tchekhovskoi D, Pletnev I (2013) InChI\u2014the worldwide chemical structure identifier standard. J Cheminform 5(1):7. https:\/\/doi.org\/10.1186\/1758-2946-5-7","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR60","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1186\/1758-2946-4-22","volume":"4","author":"NM O\u2019Boyle","year":"2012","unstructured":"O\u2019Boyle NM (2012) Towards a universal SMILES representation\u2014a standard method to generate canonical SMILES based on the InChI. J Cheminform 4(1):22. https:\/\/doi.org\/10.1186\/1758-2946-4-22","journal-title":"J Cheminform"},{"issue":"3\u20134","key":"1174_CR61","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1080\/10629360902949567","volume":"20","author":"JC Dearden","year":"2009","unstructured":"Dearden JC, Cronin MTD, Kaiser KLE (2009) How not to develop a quantitative structure\u2013activity or structure\u2013property relationship (QSAR\/QSPR). SAR QSAR Environ Res 20(3\u20134):241\u2013266. https:\/\/doi.org\/10.1080\/10629360902949567","journal-title":"SAR QSAR Environ Res"},{"key":"1174_CR62","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.ddtec.2015.01.005","volume":"14","author":"A Hersey","year":"2015","unstructured":"Hersey A, Chambers J, Bellis L, Patr\u00edcia Bento A, Gaulton A, Overington JP (2015) Chemical databases: curation or integration by user-defined equivalence? Drug Discov Today Technol 14:17\u201324. https:\/\/doi.org\/10.1016\/j.ddtec.2015.01.005","journal-title":"Drug Discov Today Technol"},{"key":"1174_CR63","unstructured":"Nizami B (2021) Chemical Descriptors & Standardizers for Machine Learning Models\u2014Cheminfo stories APAC 2020. ChemAxon. Accessed 13 Sep 2021. https:\/\/chemaxon.com\/blog\/presentation\/chemical-descriptors-standardizers-for-machine-learning-models-cheminfo-stories-apac-2020"},{"key":"1174_CR64","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1186\/s13321-023-00762-4","volume":"15","author":"V Chandrasekhar","year":"2023","unstructured":"Chandrasekhar V, Sharma N, Schaub J, Steinbeck C, Rajan K (2023) Cheminformatics microservice: unifying access to open cheminformatics toolkits. J Cheminform 15:98. https:\/\/doi.org\/10.1186\/s13321-023-00762-4","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR65","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1186\/s13321-018-0293-8","volume":"10","author":"VD H\u00e4hnke","year":"2018","unstructured":"H\u00e4hnke VD, Kim S, Bolton EE (2018) PubChem chemical structure standardization. J Cheminform 10(1):36. https:\/\/doi.org\/10.1186\/s13321-018-0293-8","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR66","doi-asserted-by":"publisher","first-page":"bbab350","DOI":"10.1093\/bib\/bbab350","volume":"23","author":"Z Tanoli","year":"2022","unstructured":"Tanoli Z, Aldahdooh J, Alam F, Wang Y, Seemab U, Fratelli M et al (2022) Minimal information for chemosensitivity assays (MICHA): a next-generation pipeline to enable the FAIRification of drug screening experiments. Brief Bioinform 23(1):bbab350. https:\/\/doi.org\/10.1093\/bib\/bbab350","journal-title":"Brief Bioinform"},{"issue":"4","key":"1174_CR67","doi-asserted-by":"publisher","first-page":"1969","DOI":"10.1021\/acs.jcim.9b01067","volume":"60","author":"RP Sheridan","year":"2020","unstructured":"Sheridan RP, Karnachi P, Tudor M, Xu Y, Liaw A, Shah F et al (2020) Experimental error, kurtosis, activity cliffs, and methodology: what limits the predictivity of quantitative structure\u2013activity relationship models? J Chem Inf Model 60(4):1969\u20131982. https:\/\/doi.org\/10.1021\/acs.jcim.9b01067","journal-title":"J Chem Inf Model"},{"issue":"1","key":"1174_CR68","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1186\/s13321-021-00571-7","volume":"13","author":"SS Kolmar","year":"2021","unstructured":"Kolmar SS, Grulke CM (2021) The effect of noise on the predictive limit of QSAR models. J Cheminform 13(1):92. https:\/\/doi.org\/10.1186\/s13321-021-00571-7","journal-title":"J Cheminform"},{"issue":"4","key":"1174_CR69","doi-asserted-by":"publisher","first-page":"302","DOI":"10.2174\/157341107782109617","volume":"3","author":"H Komura","year":"2007","unstructured":"Komura H, Iwaki M (2007) Pitfalls in high throughput screening for drug absorption optimization in drug discovery. Curr Anal Chem 3(4):302\u2013309. https:\/\/doi.org\/10.2174\/157341107782109617","journal-title":"Curr Anal Chem"},{"issue":"5","key":"1174_CR70","doi-asserted-by":"publisher","first-page":"e62325","DOI":"10.1371\/journal.pone.0062325","volume":"8","author":"S Ekins","year":"2013","unstructured":"Ekins S, Olechno J, Williams AJ (2013) Dispensing processes impact apparent biological activity as determined by computational and statistical analyses. PLoS ONE 8(5):e62325. https:\/\/doi.org\/10.1371\/journal.pone.0062325","journal-title":"PLoS ONE"},{"issue":"3","key":"1174_CR71","doi-asserted-by":"publisher","first-page":"1293","DOI":"10.1021\/acs.molpharmaceut.4c00975","volume":"22","author":"K Storchmannov\u00e1","year":"2025","unstructured":"Storchmannov\u00e1 K, Balouch M, Jura\u010dka JJ, \u0160t\u011bp\u00e1nek F, Berka K (2025) Meta-analysis of permeability literature data shows possibilities and limitations of popular methods. Mol Pharm 22(3):1293\u20131304. https:\/\/doi.org\/10.1021\/acs.molpharmaceut.4c00975","journal-title":"Mol Pharm"},{"issue":"1","key":"1174_CR72","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1038\/s41597-024-03793-0","volume":"11","author":"Z Niu","year":"2024","unstructured":"Niu Z, Xiao X, Wu W, Cai Q, Jiang Y, Jin W et al (2024) PharmaBench: enhancing ADMET benchmarks with large language models. Sci Data 11(1):985. https:\/\/doi.org\/10.1038\/s41597-024-03793-0","journal-title":"Sci Data"},{"key":"1174_CR73","doi-asserted-by":"publisher","DOI":"10.26434\/chemrxiv-2024-3ld27","author":"M Ali","year":"2024","unstructured":"Ali M, Vanderheiden S, Grathwol CW, Friederich P, Jung N, Br\u00e4se S (2024) Advancing aqueous solubility prediction: a machine learning approach for organic compounds using a curated dataset. ChemRxiv. https:\/\/doi.org\/10.26434\/chemrxiv-2024-3ld27","journal-title":"ChemRxiv"},{"issue":"1","key":"1174_CR74","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1186\/s13321-023-00752-6","volume":"15","author":"A Tayyebi","year":"2023","unstructured":"Tayyebi A, Alshami AS, Rabiei Z, Yu X, Ismail N, Talukder MJ et al (2023) Prediction of organic compound aqueous solubility using machine learning: a comparison study of descriptor-based and fingerprints-based models. J Cheminform 15(1):99. https:\/\/doi.org\/10.1186\/s13321-023-00752-6","journal-title":"J Cheminform"},{"key":"1174_CR75","doi-asserted-by":"publisher","first-page":"1780","DOI":"10.1039\/d4em00431k","volume":"26","author":"P K\u00f6rner","year":"2024","unstructured":"K\u00f6rner P, Gl\u00fcge J, Gl\u00fcge S, Scheringer M (2024) Critical insights into data curation and label noise for accurate ML toxicity prediction. Enrivon Sci Processes Impacts 26:1780\u20131795. https:\/\/doi.org\/10.1039\/d4em00431k","journal-title":"Enrivon Sci Processes Impacts"},{"key":"1174_CR76","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-540-78246-9_38","volume-title":"Data analysis, machine learning and applications","author":"MR Berthold","year":"2008","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, K\u00f6tter T, Meinl T et al (2008) KNIME: the Konstanz information miner. In: Preisach C, Burkhardt H, Schmidt-Thieme L, Decker R (eds) Data analysis, machine learning and applications. Springer, Berlin, pp 319\u2013326"},{"issue":"17","key":"1174_CR77","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1186\/1471-2105-13-S17-S9","volume":"13","author":"A Tharatipyakul","year":"2012","unstructured":"Tharatipyakul A, Numnark S, Wichadakul D, Ingsriswang S (2012) ChemEx: information extraction system for chemical data curation. BMC Bioinformatics 13(17):9. https:\/\/doi.org\/10.1186\/1471-2105-13-S17-S9","journal-title":"BMC Bioinformatics"},{"issue":"5","key":"1174_CR78","doi-asserted-by":"publisher","first-page":"587","DOI":"10.1016\/j.gpb.2022.01.004","volume":"20","author":"S Zheng","year":"2022","unstructured":"Zheng S, Wang W, Aldahdooh J, Malyutina A, Shadbahr T, Tanoli Z et al (2022) SynergyFinder Plus: toward better interpretation and annotation of drug combination screening datasets. Genomics Proteomics Bioinf 20(5):587\u2013600. https:\/\/doi.org\/10.1016\/j.gpb.2022.01.004","journal-title":"Genomics Proteomics Bioinf"},{"issue":"2","key":"1174_CR79","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.1093\/bib\/bbaa003","volume":"22","author":"ZR Tanoli","year":"2021","unstructured":"Tanoli ZR, Seemab U, Scherer A, Wennerberg K, Tang J, V\u00e4h\u00e4-Koskela M (2021) Exploration of databases and methods supporting drug repurposing: a comprehensive survey. Brief Bioinform 22(2):1656\u20131678. https:\/\/doi.org\/10.1093\/bib\/bbaa003","journal-title":"Brief Bioinform"},{"key":"1174_CR80","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1007\/978-1-0716-3397-7_3","volume":"2706","author":"L Isigkeit","year":"2023","unstructured":"Isigkeit L, Merk D (2023) Compilation of custom compound\/bioactivity datasets from public repositories. Methods Mol Biol 2706:25\u201350. https:\/\/doi.org\/10.1007\/978-1-0716-3397-7_3","journal-title":"Methods Mol Biol"},{"issue":"113","key":"1174_CR81","doi-asserted-by":"publisher","first-page":"8844","DOI":"10.21105\/joss.08844","volume":"10","author":"CT Hoyt","year":"2025","unstructured":"Hoyt CT (2025) Improving reproducibility of cheminformatics workflows with chembl-downloader. J Open Source Softw 10(113):8844. https:\/\/doi.org\/10.21105\/joss.08844","journal-title":"J Open Source Softw"},{"issue":"1","key":"1174_CR82","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3458754","volume":"3","author":"Y Gu","year":"2021","unstructured":"Gu Y, Tinn R, Cheng H, Lucas M, Usuyama N, Liu X et al (2021) Domain-specific language model pretraining for biomedical natural language processing. ACM Trans Comput Healthc 3(1):1\u201323. https:\/\/doi.org\/10.1145\/3458754","journal-title":"ACM Trans Comput Healthc"},{"issue":"4","key":"1174_CR83","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, Kang J (2020) BioBERT: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics 36(4):1234\u20131240. https:\/\/doi.org\/10.1093\/bioinformatics\/btz682","journal-title":"Bioinformatics"},{"issue":"1","key":"1174_CR84","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/s13321-018-0263-1","volume":"10","author":"K Mansouri","year":"2018","unstructured":"Mansouri K, Grulke CM, Judson RS, Williams AJ (2018) OPERA models for predicting physicochemical properties and environmental fate endpoints. J Cheminform 10(1):10. https:\/\/doi.org\/10.1186\/s13321-018-0263-1","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR85","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1186\/s13321-024-00826-z","volume":"16","author":"T Esaki","year":"2024","unstructured":"Esaki T, Yonezawa T, Ikeda K (2024) A new workflow for the effective curation of membrane permeability data from open ADME information. J Cheminform 16(1):30. https:\/\/doi.org\/10.1186\/s13321-024-00826-z","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR86","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1038\/s41591-024-03434-4","volume":"31","author":"K Zhang","year":"2025","unstructured":"Zhang K, Yang X, Wang Y, Yu Y, Huang N, Li G et al (2025) Artificial intelligence in drug development. Nat Med 31(1):45\u201359. https:\/\/doi.org\/10.1038\/s41591-024-03434-4","journal-title":"Nat Med"},{"key":"1174_CR87","doi-asserted-by":"publisher","first-page":"baae104","DOI":"10.1093\/database\/baae104","volume":"2024","author":"CP Phan","year":"2024","unstructured":"Phan CP, Phan B, Chiang JH (2024) Optimized biomedical entity relation extraction method with data augmentation and classification using GPT-4 and Gemini. Database 2024:baae104. https:\/\/doi.org\/10.1093\/database\/baae104","journal-title":"Database"},{"key":"1174_CR88","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.08774","author":"OpenAI","year":"2023","unstructured":"OpenAI (2023) GPT-4 technical report. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2303.08774","journal-title":"arXiv"},{"key":"1174_CR89","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2312.11805","author":"Gemini Team","year":"2023","unstructured":"Gemini Team (2023) Gemini: a family of highly capable multimodal models. arXir. https:\/\/doi.org\/10.48550\/arXiv.2312.11805","journal-title":"arXir"},{"key":"1174_CR90","doi-asserted-by":"publisher","first-page":"baaf011","DOI":"10.1093\/database\/baaf011","volume":"2025","author":"E Poretsky","year":"2025","unstructured":"Poretsky E, Blake VC, Andorf CM, Sen TZ (2025) Assessing the performance of generative artificial intelligence in retrieving information against manually curated genetic and genomic data. Database 2025:baaf011. https:\/\/doi.org\/10.1093\/database\/baaf011","journal-title":"Database"},{"issue":"D1","key":"1174_CR91","doi-asserted-by":"publisher","first-page":"D1467","DOI":"10.1093\/nar\/gkae1128","volume":"53","author":"A Buniello","year":"2025","unstructured":"Buniello A, Suveges D, Cruz-Castillo C, Llinares MB, Cornu H, Lopez I et al (2025) Open targets platform: facilitating therapeutic hypotheses building in drug discovery. Nucleic Acids Res 53(D1):D1467\u2013D1475. https:\/\/doi.org\/10.1093\/nar\/gkae1128","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"1174_CR92","doi-asserted-by":"publisher","first-page":"108","DOI":"10.1186\/s13321-025-01041-0","volume":"17","author":"G Kamuntavi\u010dius","year":"2025","unstructured":"Kamuntavi\u010dius G, Paquet T, Bastas O, \u0160alkauskas D, Prat A, Aty HA et al (2025) Benchmarking ML in ADMET predictions: the practical impact of feature representations in ligand-based models. J Cheminform 17(1):108. https:\/\/doi.org\/10.1186\/s13321-025-01041-0","journal-title":"J Cheminform"},{"issue":"1","key":"1174_CR93","doi-asserted-by":"publisher","first-page":"145","DOI":"10.1186\/s13321-024-00931-z","volume":"16","author":"D Gadaleta","year":"2024","unstructured":"Gadaleta D, Serrano-Candelas E, Ortega-Vallbona R, Colombo E, de Garcia Lomana M, Biava G et al (2024) Comprehensive benchmarking of computational tools for predicting toxicokinetic and physicochemical properties of chemicals. J Cheminform 16(1):145. https:\/\/doi.org\/10.1186\/s13321-024-00931-z","journal-title":"J Cheminform"},{"issue":"7","key":"1174_CR94","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1021\/acs.jcim.3c00799","volume":"64","author":"W Heyndrickx","year":"2024","unstructured":"Heyndrickx W, Mervin L, Morawietz T, Sturm N, Friedrich L, Zalewski A et al (2024) MELLODDY: cross-pharma federated learning at unprecedented scale unlocks benefits in QSAR without compromising proprietary information. J Chem Inf Model 64(7):2331\u20132344. https:\/\/doi.org\/10.1021\/acs.jcim.3c00799","journal-title":"J Chem Inf Model"},{"issue":"1","key":"1174_CR95","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1186\/s13321-025-00983-9","volume":"17","author":"AJ Williams","year":"2025","unstructured":"Williams AJ, Richard AM (2025) Three pillars for ensuring public access and integrity of chemical databases powering cheminformatics. J Cheminform 17(1):40. https:\/\/doi.org\/10.1186\/s13321-025-00983-9","journal-title":"J Cheminform"},{"key":"1174_CR96","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1186\/1471-2105-12-257","volume":"12","author":"U Visser","year":"2011","unstructured":"Visser U, Abeyruwan S, Vempati U, Smith RP, Lemmon V, Sch\u00fcrer SC (2011) BioAssay ontology (BAO): a semantic description of bioassays and high-throughput screening results. BMC Bioinformatics 12:257. https:\/\/doi.org\/10.1186\/1471-2105-12-257","journal-title":"BMC Bioinformatics"},{"key":"1174_CR97","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1038\/nrd3503","volume":"10","author":"S Orchard","year":"2011","unstructured":"Orchard S, Al-Lazikani B, Bryant S, Clark D, Calder E, Dix I et al (2011) Minimum information about a bioactive entity (MIABE). Nat Rev Drug Discov 10:661\u2013669. https:\/\/doi.org\/10.1038\/nrd3503","journal-title":"Nat Rev Drug Discov"},{"issue":"8","key":"1174_CR98","doi-asserted-by":"publisher","first-page":"100188","DOI":"10.1016\/j.slasd.2024.100188","volume":"29","author":"R Balakrishnan","year":"2024","unstructured":"Balakrishnan R, Berg EL, Butler CC, Clark AM, Denker SP, Feierberg I et al (2024) Bioassay protocol metadata annotation: proposed standards adoption. SLAS Discov 29(8):100188. https:\/\/doi.org\/10.1016\/j.slasd.2024.100188","journal-title":"SLAS Discov"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-026-01174-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-026-01174-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:33:16Z","timestamp":1775568796000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s13321-026-01174-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,2]]},"references-count":98,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["1174"],"URL":"https:\/\/doi.org\/10.1186\/s13321-026-01174-w","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,2]]},"assertion":[{"value":"29 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 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":"43"}}