{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T17:38:07Z","timestamp":1770917887186,"version":"3.50.1"},"reference-count":20,"publisher":"Springer Science and Business Media LLC","issue":"1","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61370019 and 61572247"],"award-info":[{"award-number":["61370019 and 61572247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2017,12]]},"DOI":"10.1186\/s12859-017-1832-4","type":"journal-article","created":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T08:37:32Z","timestamp":1505723852000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Cleaning by clustering: methodology for addressing data quality issues in biomedical metadata"],"prefix":"10.1186","volume":"18","author":[{"given":"Wei","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amrapali","family":"Zaveri","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Honglei","family":"Qiu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michel","family":"Dumontier","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,9,18]]},"reference":[{"key":"1832_CR1","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1002\/asi.22634","volume":"63","author":"CL Borgman","year":"2012","unstructured":"Borgman CL. The conundrum of sharing research data. J Am Soc Inf Sci Technol. 2012; 63:1059\u201378.","journal-title":"J Am Soc Inf Sci Technol"},{"key":"1832_CR2","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1093\/nar\/gks1193","volume":"41","author":"T Barrett","year":"2013","unstructured":"Barrett T, Wilhite SE, Ledoux P, et al. Ncbi geo: archive for functional genomics data sets \u2013 update. Nucleic Acids Res. 2013; 41:991\u20135.","journal-title":"Nucleic Acids Res"},{"key":"1832_CR3","doi-asserted-by":"crossref","first-page":"365","DOI":"10.1038\/ng1201-365","volume":"29","author":"A Brazma","year":"2011","unstructured":"Brazma A, Hingamp P, Quackenbush J, et al. Minimum information about a microarray experiment (miame) \u2013 toward standards for microarray data. Nat Genet. 2011; 29:365\u201371.","journal-title":"Nat Genet"},{"key":"1832_CR4","doi-asserted-by":"crossref","first-page":"991","DOI":"10.1093\/nar\/gkq848","volume":"39","author":"T Barrett","year":"2011","unstructured":"Barrett T, Troup DB, Wilhite SE, et al. NCBI GEO: archive for functional genomics data sets \u2013 10 years on. Nucleic Acids Res. 2011; 39:991\u20135.","journal-title":"Nucleic Acids Res"},{"issue":"287","key":"1832_CR5","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1126\/scitranslmed.aaa5993","volume":"7","author":"TE Sweeney","year":"2015","unstructured":"Sweeney TE, Shidham A, Wong HR, Khatri P. A comprehensive time-course-based multicohort analysis of sepsis and sterile inflammation reveals a robust diagnostic gene set. Sci Transl Med. 2015; 7(287):287\u201371.","journal-title":"Sci Transl Med"},{"key":"1832_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-10-234","volume":"10","author":"JM Freudenberg","year":"2009","unstructured":"Freudenberg JM, Joshi VK, Hu Z, et al. CLEAN: CLustering Enrichment ANalysis. BMC Bioinforma. 2009; 10:1\u201315.","journal-title":"BMC Bioinforma"},{"key":"1832_CR7","volume-title":"Proceedings of KDNet Symposium on Knowledge-based Systems for the Public Sector","author":"A Loureiro","year":"2004","unstructured":"Loureiro A, Torgo L, Soares C. Outlier detection using clustering methods: a data cleaning application. In: Proceedings of KDNet Symposium on Knowledge-based Systems for the Public Sector. Bonn: Springer: 2004."},{"key":"1832_CR8","doi-asserted-by":"crossref","first-page":"2463","DOI":"10.1093\/bioinformatics\/btr406","volume":"27","author":"B Ulrich","year":"2011","unstructured":"Ulrich B, Andreas K, Sepp H. APCluster: an R package for affinity propagation clustering. Bioinformatics. 2011; 27:2463\u20134.","journal-title":"Bioinformatics"},{"key":"1832_CR9","first-page":"1","volume":"IX","author":"F Giunchiglia","year":"2007","unstructured":"Giunchiglia F, Yatskevich M, Shvaiko P. Semantic matching: algorithms and implementation. J Data Semant. 2007; IX:1\u201338.","journal-title":"J Data Semant"},{"key":"1832_CR10","volume-title":"Proceedings of International Ontology Matching Workshop","author":"M Cheatham","year":"2014","unstructured":"Cheatham M, Hitzler P. The property of property alignment. In: Proceedings of International Ontology Matching Workshop. Trentino: CEUR-WS: 2014."},{"key":"1832_CR11","volume-title":"Proceedings of Empirical Methods in Natural Language Processing","author":"D Chen","year":"2014","unstructured":"Chen D, Manning CD, et al. A fast and accurate dependency parser using neural networks In: Moschitti A, editor. Proceedings of Empirical Methods in Natural Language Processing. Doha: ACL: 2014. p. 740\u201350."},{"key":"1832_CR12","volume-title":"Proceedings of International Semantic Web Conference","author":"M Cheatham","year":"2013","unstructured":"Cheatham M, Hitzler P, et al. String similarity metrics for ontology alignment In: Alani H, editor. Proceedings of International Semantic Web Conference. Sydney: Springer: 2013. p. 294\u2013309."},{"key":"1832_CR13","volume-title":"Proceedings of KDD Workshop on Data Cleaning and Object Consolidation","author":"WW Cohen","year":"2003","unstructured":"Cohen WW, Ravikumar P, Fienberg SE. A comparison of string metrics for matching names and records. In: Proceedings of KDD Workshop on Data Cleaning and Object Consolidation. Washington: AAAI: 2003."},{"key":"1832_CR14","volume-title":"Proceedings of International Conference on Data Engineering","author":"S Guha","year":"1999","unstructured":"Guha S, Rastogi R, Shim K. ROCK: a robust clustering algorithm for categorical attributes. In: Proceedings of International Conference on Data Engineering. Sydney: IEEE: 1999. p. 512\u201321."},{"key":"1832_CR15","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1016\/j.datak.2008.06.003","volume":"67","author":"W Hu","year":"2008","unstructured":"Hu W, Qu Y, Cheng G. Matching large ontologies: a divide-and-conquer approach. Data Knowl Eng. 2008; 67:140\u201360.","journal-title":"Data Knowl Eng"},{"key":"1832_CR16","volume-title":"Data Mining: Concepts and Techniques, Second Edition","author":"J Han","year":"2006","unstructured":"Han J, Kamber M. Data Mining: Concepts and Techniques, Second Edition. Burlington: Morgan Kaufman Publishers; 2006."},{"key":"1832_CR17","volume-title":"Statistical Data Analysis Based on the L 1\u2013norm and Related Methods","author":"L Kaufman","year":"1987","unstructured":"Kaufman L, Rousseeuw P. Clustering by means of medoids In: Dodge Y, editor. Statistical Data Analysis Based on the L\n                    1\u2013norm and Related Methods. North-Holland: Elsevier: 1987. p. 405\u201316."},{"key":"1832_CR18","volume-title":"Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining","author":"M Ester","year":"1996","unstructured":"Ester M, Kriegel HP, Sander J, et al. A density-based algorithm for discovering clusters in large spatial databases with noise. In: Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Portland: AAAI Press: 1996. p. 226\u201331."},{"key":"1832_CR19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2105-12-436","volume":"12","author":"JH Morris","year":"2011","unstructured":"Morris JH, Apeltsin L, Newman AM, et al. clustermaker: a multi-algorithm clustering plugin for cytoscape. BMC Bioinforma. 2011; 12:1.","journal-title":"BMC Bioinforma"},{"issue":"25","key":"1832_CR20","doi-asserted-by":"crossref","first-page":"14863","DOI":"10.1073\/pnas.95.25.14863","volume":"95","author":"MB Eisen","year":"1998","unstructured":"Eisen MB, Spellman PT, Brown PO, Botstein D. Cluster analysis and display of genome-wide expression patterns. Proc Natl Acad Sci. 1998; 95(25):14863\u20138.","journal-title":"Proc Natl Acad Sci"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-017-1832-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2017,9,18]],"date-time":"2017-09-18T08:37:40Z","timestamp":1505723860000},"score":1,"resource":{"primary":{"URL":"http:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-017-1832-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,9,18]]},"references-count":20,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2017,12]]}},"alternative-id":["1832"],"URL":"https:\/\/doi.org\/10.1186\/s12859-017-1832-4","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,9,18]]},"article-number":"415"}}