{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T01:47:36Z","timestamp":1772502456912,"version":"3.50.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T00:00:00Z","timestamp":1681689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T00:00:00Z","timestamp":1681689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Cheminform"],"DOI":"10.1186\/s13321-023-00718-8","type":"journal-article","created":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T08:02:45Z","timestamp":1681718565000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Biomedical data analyses facilitated by open cheminformatics workflows"],"prefix":"10.1186","volume":"15","author":[{"given":"Eva","family":"Nittinger","sequence":"first","affiliation":[]},{"given":"Alex","family":"Clark","sequence":"additional","affiliation":[]},{"given":"Anna","family":"Gaulton","sequence":"additional","affiliation":[]},{"given":"Barbara","family":"Zdrazil","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,4,17]]},"reference":[{"issue":"20","key":"718_CR1","doi-asserted-by":"publisher","first-page":"10762","DOI":"10.1073\/pnas.1909046117","volume":"117","author":"Y Yang","year":"2020","unstructured":"Yang Y, Youyou W, Uzzi B (2020) Estimating the deep replicability of scientific findings using human and artificial intelligence. Proc Natl Acad Sci 117(20):10762\u201310768. https:\/\/doi.org\/10.1073\/pnas.1909046117","journal-title":"Proc Natl Acad Sci"},{"key":"718_CR2","doi-asserted-by":"publisher","DOI":"10.7554\/eLife.67995","volume":"10","author":"TM Errington","year":"2021","unstructured":"Errington TM, Denis A, Perfito N, Iorns E, Nosek BA (2021) Challenges for assessing replicability in preclinical cancer biology. eLife 10:e67995","journal-title":"eLife"},{"key":"718_CR3","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1186\/s13104-022-05942-3","volume":"15","author":"M Munaf\u00f2","year":"2022","unstructured":"Munaf\u00f2 M, Chambers C, Collins A, Fortunato L, Macleod M (2022) The reproducibility debate is an opportunity, not a crisis. BMC Res Notes 15:43. https:\/\/doi.org\/10.1186\/s13104-022-05942-3","journal-title":"BMC Res Notes"},{"key":"718_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2016.18","volume":"3","author":"MD Wilkinson","year":"2016","unstructured":"Wilkinson MD, Dumontier M, Aalbersberg IJ, Appleton G, Axton M, Baak A, Blomberg N, Boiten J-W, da Silva Santos LB, Bourne PE, Bouwman J, Brookes AJ, Clark T, Crosas M, Dillo I, Dumon O, Edmunds S, Evelo CT, Finkers R, Gonzalez-Beltran A, Gray AJG, Groth P, Goble C, Grethe JS, Heringa J, \u2019t Hoen PAC, Hooft R, Kuhn T, Kok R, Kok J, Lusher SJ, Martone ME, Mons A, Packer AL, Persson B, Rocca-Serra P, Roos M, van Schaik R, Sansone S-A, Schultes E, Sengstag T, Slater T, Strawn G, Swertz MA, Thompson M, van der Lei J, van Mulligen E, Velterop J, Waagmeester A, Wittenburg P, Wolstencroft K, Zhao J, Mons B, (2016) The FAIR guiding principles for scientific data management and stewardship. Sci Data 3:160018","journal-title":"Sci Data"},{"key":"718_CR5","doi-asserted-by":"publisher","unstructured":"Barker M, Chue Hong NP, Katz DS et al (2022) Introducing the FAIR principles for research software. Sci Data 9: 622. https:\/\/doi.org\/10.1038\/s41597-022-01710-x","DOI":"10.1038\/s41597-022-01710-x"},{"key":"718_CR6","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1002\/3527603743.CH9","volume":"23","author":"M Olah","year":"2005","unstructured":"Olah M, Mracec M, Ostopovici L, Rad R, Bora A, Hadaruga N, Olah I, Banda M, Simon Z, Mracec M, Oprea TI (2005) Wombat: world of molecular bioactivity. Chemoinform Drug Discov 23:221\u2013239. https:\/\/doi.org\/10.1002\/3527603743.CH9","journal-title":"Chemoinform Drug Discov"},{"key":"718_CR7","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 27:1337\u20131345. https:\/\/doi.org\/10.1002\/QSAR.200810084","journal-title":"QSAR Comb Sci"},{"key":"718_CR8","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 Inform Model 50:1189\u20131204. https:\/\/doi.org\/10.1021\/ci100176x","journal-title":"J Chem Inform Model"},{"key":"718_CR9","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1021\/ci00057a005","volume":"28","author":"D Weininger","year":"2002","unstructured":"Weininger D (2002) Smiles, a chemical language and information system. 1. introduction to methodology and encoding rules. J Chem Inform Comput Sci 28:31\u201336. https:\/\/doi.org\/10.1021\/ci00057a005","journal-title":"J Chem Inform Comput Sci"},{"key":"718_CR10","doi-asserted-by":"publisher","first-page":"1","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 - the worldwide chemical structure identifier standard. J Cheminform 5:1\u20139. https:\/\/doi.org\/10.1186\/1758-2946-5-7","journal-title":"J Cheminform"},{"key":"718_CR11","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/S13321-015-0068-4","volume":"7","author":"SR Heller","year":"2015","unstructured":"Heller SR, McNaught A, Pletnev I, Stein S, Tchekhovskoi D (2015) Inchi, the iupac international chemical identifier. J Cheminform 7:1\u201334. https:\/\/doi.org\/10.1186\/S13321-015-0068-4","journal-title":"J Cheminform"},{"key":"718_CR12","doi-asserted-by":"publisher","first-page":"1","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, Bellis LJ, Veij MD, Leach AR (2020) An open source chemical structure curation pipeline using rdkit. J Cheminform 12:1\u201316. https:\/\/doi.org\/10.1186\/S13321-020-00456-1","journal-title":"J Cheminform"},{"key":"718_CR13","doi-asserted-by":"publisher","first-page":"1","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\u201340. https:\/\/doi.org\/10.1186\/S13321-018-0293-8","journal-title":"J Cheminform"},{"key":"718_CR14","doi-asserted-by":"publisher","first-page":"1","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\u201320. https:\/\/doi.org\/10.1186\/S13321-022-00606-7","journal-title":"J Cheminform"},{"key":"718_CR15","doi-asserted-by":"publisher","first-page":"4417","DOI":"10.1021\/acs.jcim.0c01000","volume":"60","author":"WP Walters","year":"2020","unstructured":"Walters WP (2020) Code sharing in the open science era. J Chem Inf Model 60:4417\u20134420","journal-title":"J Chem Inf Model"},{"key":"718_CR16","first-page":"100002","volume":"1","author":"J Bajorath","year":"2021","unstructured":"Bajorath J, Coley CW, Landon MR, Walters WP, Zheng M (2021) Reproducibility, reusability, and community efforts in artificial intelligence research. Artif Intel Life Sci 1:100002","journal-title":"Artif Intel Life Sci"},{"key":"718_CR17","doi-asserted-by":"publisher","first-page":"381","DOI":"10.1007\/s10822-021-00417-2","volume":"36","author":"WP Walters","year":"2022","unstructured":"Walters WP (2022) Comparing classification models-a practical tutorial. J Comput Aided Mol Des 36:381\u2013389","journal-title":"J Comput Aided Mol Des"},{"key":"718_CR18","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1038\/nrd2649","volume":"7","author":"D Bradley","year":"2008","unstructured":"Bradley D (2008) Dealing with a data dilemma. Nature Rev Drug Discov 7:632\u2013633","journal-title":"Nature Rev Drug Discov"},{"key":"718_CR19","doi-asserted-by":"publisher","first-page":"4713","DOI":"10.1021\/acsomega.8b00462","volume":"3","author":"R Rodr\u00edguez-P\u00e9rez","year":"2018","unstructured":"Rodr\u00edguez-P\u00e9rez R, Miyao T, Jasial S, Vogt M, Bajorath J (2018) Prediction of compound profiling matrices using machine learning. ACS Omega 3:4713\u20134723","journal-title":"ACS Omega"},{"key":"718_CR20","doi-asserted-by":"publisher","first-page":"5957","DOI":"10.1021\/acs.jcim.0c00565","volume":"60","author":"EL C\u00e1ceres","year":"2020","unstructured":"C\u00e1ceres EL, Mew NC, Keiser MJ (2020) Adding stochastic negative examples into machine learning improves molecular bioactivity prediction. J Chem Inf Model 60:5957\u20135970","journal-title":"J Chem Inf Model"},{"key":"718_CR21","doi-asserted-by":"publisher","first-page":"115244","DOI":"10.1016\/j.taap.2020.115244","volume":"407","author":"C Valsecchi","year":"2020","unstructured":"Valsecchi C, Grisoni F, Motta S, Bonati L, Ballabio D (2020) NURA: a curated dataset of nuclear receptor modulators. Tox Appl Pharmaco 407:115244","journal-title":"Tox Appl Pharmaco"},{"key":"718_CR22","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1186\/s13321-020-00422-x","volume":"12","author":"A Morger","year":"2020","unstructured":"Morger A, Mathea M, Achenbach JH, Wolf A, Buesen R, Schleifer K-J, Landsiedel R, Volkamer A (2020) KnowTox: pipeline and case study for confident prediction of potential toxic effects of compounds in early phases of development. J Cheminf 12:24","journal-title":"J Cheminf"},{"key":"718_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/S13321-022-00657-W","volume":"14","author":"D Boldini","year":"2022","unstructured":"Boldini D, Friedrich L, Kuhn D, Sieber SA (2022) Tuning gradient boosting for imbalanced bioassay modelling with custom loss functions. J Cheminform 14:1\u201313. https:\/\/doi.org\/10.1186\/S13321-022-00657-W","journal-title":"J Cheminform"},{"issue":"1","key":"718_CR24","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/1656274.1656280","volume":"11","author":"MR Berthold","year":"2009","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, K\u00f6tter T, Meinl T, Ohl P, Thiel K, Wiswedel B (2009) Knime - the konstanz information miner: Version 20 and beyond. SIGKDD Explor Newsl 11(1):26\u201331. https:\/\/doi.org\/10.1145\/1656274.1656280","journal-title":"SIGKDD Explor Newsl"},{"issue":"W1","key":"718_CR25","doi-asserted-by":"publisher","first-page":"537","DOI":"10.1093\/nar\/gky379","volume":"46","author":"E Afgan","year":"2018","unstructured":"Afgan E, Baker D, Batut B, van den Beek M, Bouvier D, \u010cech M, Chilton J, Clements D, Coraor N, Gr\u00fcning BA, Guerler A, Hillman-Jackson J, Hiltemann S, Jalili V, Rasche H, Soranzo N, Goecks J, Taylor J, Nekrutenko A, Blankenberg D (2018) The Galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2018 update. Nucleic Acids Res 46(W1):537\u2013544. https:\/\/doi.org\/10.1093\/nar\/gky379","journal-title":"Nucleic Acids Res"},{"key":"718_CR26","first-page":"87","volume-title":"Positioning and power in academic publishing: players, agents and agendas","author":"T Kluyver","year":"2016","unstructured":"Kluyver T, Ragan-Kelley B, P\u00e9rez F, Granger BE, Bussonnier M, Frederic J, Kelley K, Hamrick JB, Grout J, Corlay S, Ivanov P, Avila D, Abdalla S, Willing C, Jupyter Development Team (2016) Jupyter Notebooks - a publishing format for reproducible computational workflows. In: Loizides F, Scmidt B (eds) International Conference on Electronic Publishing. IOS Press, Amsterdam, pp 87\u201390"},{"key":"718_CR27","unstructured":"github (2023).  GitHub. Retrieved from https:\/\/github.com\/"},{"key":"718_CR28","doi-asserted-by":"publisher","DOI":"10.25495\/7GXK-RD71","author":"European Organization For Nuclear Research, OpenAIRE","year":"2013","unstructured":"European Organization For Nuclear Research, OpenAIRE (2013) Zenodo. CERN. https:\/\/doi.org\/10.25495\/7GXK-RD71","journal-title":"CERN"},{"issue":"239","key":"718_CR29","first-page":"2","volume":"2014","author":"D Merkel","year":"2014","unstructured":"Merkel D (2014) Docker: lightweight linux containers for consistent development and deployment. Linux J 2014(239):2","journal-title":"Linux J"},{"key":"718_CR30","first-page":"135","volume-title":"Teaching computer-aided drug design using TeachOpenCADD","author":"D Sydow","year":"2021","unstructured":"Sydow D, Rodr\u00edguez-Guerra J, Volkamer A (2021) Teaching computer-aided drug design using TeachOpenCADD. In: Teaching Programming across the Chemistry Curriculum, Washington, pp 135\u2013158. https:\/\/pubs.acs.org\/doi\/abs\/10.1021\/bk-2021-1387.ch010"},{"key":"718_CR31","doi-asserted-by":"publisher","DOI":"10.1093\/nar\/gkac267","author":"D Sydow","year":"2022","unstructured":"Sydow D, Rodr\u00edguez-Guerra J, Kimber TB, Schaller D, Taylor CJ, Chen Y, Leja M, Misra S, Wichmann M, Ariamajd A, Volkamer A (2022) TeachOpenCADD 2022: open source and FAIR Python pipelines to assist in structural bioinformatics and cheminformatics research. Nucleic Acids Res. https:\/\/doi.org\/10.1093\/nar\/gkac267","journal-title":"Nucleic Acids Res"},{"key":"718_CR32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.08871","author":"M Oldenhof","year":"2022","unstructured":"Oldenhof M, \u00c1cs G, Pejo B, Schuffenhauer A, Holway N, Sturm N, Dieckmann A, Fortmeier O, Boniface E, Mayer C, Gohier A, Schmidtke P, Niwayama R, Kopecky D, Mervin L, Rathi PC, Friedrich L, Formanek A, Antal P, Rahaman J, Zalewski A, Heyndrickx W, Oluoch E, St\u00f6ssel M, Vanco M, Endico D, Gelus F, de Boisfoss\u00e9 T, Darbier A, Nicollet A, Blotti\u00e8re M, Telenczuk M, Nguyen VT, Martinez T, Boillet C, Moutet K, Picosson A, Gasser A, Djafar I, Simon A, Arany A, Simm J, Moreau Y, Engkvist O, Ceulemans H, Marini C, Galtier M (2022) Industry-scale orchestrated federated learning for drug discovery. arXiv. https:\/\/doi.org\/10.48550\/arXiv.2210.08871","journal-title":"arXiv"}],"container-title":["Journal of Cheminformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00718-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13321-023-00718-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13321-023-00718-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,17]],"date-time":"2023-04-17T08:06:58Z","timestamp":1681718818000},"score":1,"resource":{"primary":{"URL":"https:\/\/jcheminf.biomedcentral.com\/articles\/10.1186\/s13321-023-00718-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,17]]},"references-count":32,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["718"],"URL":"https:\/\/doi.org\/10.1186\/s13321-023-00718-8","relation":{},"ISSN":["1758-2946"],"issn-type":[{"value":"1758-2946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,4,17]]},"assertion":[{"value":"17 April 2023","order":1,"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 that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"46"}}