{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T22:35:29Z","timestamp":1775687729808,"version":"3.50.1"},"reference-count":46,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T00:00:00Z","timestamp":1516665600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T00:00:00Z","timestamp":1516665600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Science Foundation","award":["CAREER 1150645"],"award-info":[{"award-number":["CAREER 1150645"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"crossref","award":["R01 GM106027"],"award-info":[{"award-number":["R01 GM106027"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2018,12]]},"DOI":"10.1186\/s12859-018-2022-8","type":"journal-article","created":{"date-parts":[[2018,1,23]],"date-time":"2018-01-23T13:28:13Z","timestamp":1516714093000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Shrinkage Clustering: a fast and size-constrained clustering algorithm for biomedical applications"],"prefix":"10.1186","volume":"19","author":[{"given":"Chenyue W.","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanyang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amina A.","family":"Qutub","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,1,23]]},"reference":[{"issue":"14","key":"2022_CR1","doi-asserted-by":"publisher","first-page":"8418","DOI":"10.1073\/pnas.0932692100","volume":"100","author":"T S\u00f8rlie","year":"2003","unstructured":"S\u00f8rlie T, Tibshirani R, Parker J, Hastie T, Marron J, Nobel A, et al.Repeated observation of breast tumor subtypes in independent gene expression data sets. Proc Natl Acad Sci. 2003; 100(14):8418\u201323.","journal-title":"Proc Natl Acad Sci"},{"issue":"4","key":"2022_CR2","doi-asserted-by":"publisher","first-page":"R65","DOI":"10.1186\/bcr2124","volume":"10","author":"P Wirapati","year":"2008","unstructured":"Wirapati P, Sotiriou C, Kunkel S, Farmer P, Pradervand S, Haibe-Kains B, et al.Meta-analysis of gene expression profiles in breast cancer: toward a unified understanding of breast cancer subtyping and prognosis signatures. Breast Cancer Res. 2008; 10(4):R65.","journal-title":"Breast Cancer Res"},{"issue":"16","key":"2022_CR3","doi-asserted-by":"publisher","first-page":"5678","DOI":"10.1158\/1078-0432.CCR-04-2421","volume":"11","author":"R Rouzier","year":"2005","unstructured":"Rouzier R, Perou CM, Symmans WF, Ibrahim N, Cristofanilli M, Anderson K, et al.Breast cancer molecular subtypes respond differently to preoperative chemotherapy. Clin Cancer Res. 2005; 11(16):5678\u201385.","journal-title":"Clin Cancer Res"},{"issue":"7","key":"2022_CR4","doi-asserted-by":"publisher","first-page":"908","DOI":"10.1093\/bioinformatics\/18.7.908","volume":"18","author":"F Abascal","year":"2002","unstructured":"Abascal F, Valencia A. Clustering of proximal sequence space for the identification of protein families. Bioinformatics. 2002; 18(7):908\u201321.","journal-title":"Bioinformatics"},{"issue":"12","key":"2022_CR5","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1093\/protein\/gzl044","volume":"19","author":"MR Stam","year":"2006","unstructured":"Stam MR, Danchin EG, Rancurel C, Coutinho PM, Henrissat B. Dividing the large glycoside hydrolase family 13 into subfamilies: towards improved functional annotations of \u03b1-amylase-related proteins. Protein Eng Des Sel. 2006; 19(12):555\u201362.","journal-title":"Protein Eng Des Sel"},{"issue":"6","key":"2022_CR6","doi-asserted-by":"publisher","first-page":"e1005001","DOI":"10.1371\/journal.pcbi.1005001","volume":"12","author":"EB de Lima","year":"2016","unstructured":"de Lima EB, J\u00fanior WM, de Melo-Minardi RC. Isofunctional Protein Subfamily Detection Using Data Integration and Spectral Clustering. PLoS Comput Biol. 2016; 12(6):e1005001.","journal-title":"PLoS Comput Biol"},{"key":"2022_CR7","doi-asserted-by":"crossref","unstructured":"Chen X, Velliste M, Weinstein S, Jarvik JW, Murphy RF. Location proteomics\u2014Building subcellular location tree from high resolution 3D fluorescence microcope images of randomly-tagged proteins. Manipulation and Analysis of Biomolecules, Cells, and Tissues, Proceedings of SPIE 4962; 2003, pp. 298\u2013306.","DOI":"10.1117\/12.477899"},{"issue":"6","key":"2022_CR8","doi-asserted-by":"publisher","first-page":"6128","DOI":"10.1021\/acsnano.5b01366","volume":"9","author":"JH Slater","year":"2015","unstructured":"Slater JH, Culver JC, Long BL, Hu CW, Hu J, Birk TF, et al.Recapitulation and modulation of the cellular architecture of a user-chosen cell of interest using cell-derived, biomimetic patterning. ACS nano. 2015; 9(6):6128\u201338.","journal-title":"ACS nano"},{"issue":"3","key":"2022_CR9","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1164\/rccm.200711-1754OC","volume":"178","author":"P Haldar","year":"2008","unstructured":"Haldar P, Pavord ID, Shaw DE, Berry MA, Thomas M, Brightling CE, et al.Cluster analysis and clinical asthma phenotypes. Am J Respir Crit Care Med. 2008; 178(3):218\u201324.","journal-title":"Am J Respir Crit Care Med"},{"issue":"4","key":"2022_CR10","doi-asserted-by":"publisher","first-page":"315","DOI":"10.1164\/rccm.200906-0896OC","volume":"181","author":"WC Moore","year":"2010","unstructured":"Moore WC, Meyers DA, Wenzel SE, Teague WG, Li H, Li X, et al.Identification of asthma phenotypes using cluster analysis in the Severe Asthma Research Program. Am J Respir Crit Care Med. 2010; 181(4):315\u201323.","journal-title":"Am J Respir Crit Care Med"},{"issue":"3","key":"2022_CR11","doi-asserted-by":"publisher","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Murty MN, Flynn PJ. Data clustering: a review. ACM Comput Surv (CSUR). 1999; 31(3):264\u2013323.","journal-title":"ACM Comput Surv (CSUR)"},{"issue":"11","key":"2022_CR12","first-page":"1033","volume":"12","author":"C Wiwie","year":"2015","unstructured":"Wiwie C, Baumbach J, R\u00f6ttger R. Comparing the performance of biomedical clustering methods. Nat Med. 2015; 12(11):1033\u20138.","journal-title":"Nat Med"},{"issue":"3","key":"2022_CR13","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/BF02289588","volume":"32","author":"SC Johnson","year":"1967","unstructured":"Johnson SC. Hierarchical clustering schemes. Psychometrika. 1967; 32(3):241\u201354.","journal-title":"Psychometrika"},{"key":"2022_CR14","volume-title":"Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol. 1, No. 14","author":"J MacQueen","year":"1967","unstructured":"MacQueen J, et al.Some methods for classification and analysis of multivariate observations. In: Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, vol. 1, No. 14. California: University of California Press: 1967. p. 281\u201397."},{"issue":"2","key":"2022_CR15","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1109\/TIT.1982.1056489","volume":"28","author":"S Lloyd","year":"1982","unstructured":"Lloyd S. Least squares quantization in PCM. Inf Theory IEEE Trans. 1982; 28(2):129\u201337.","journal-title":"Inf Theory IEEE Trans"},{"key":"2022_CR16","unstructured":"Ester M, Kriegel HP, Sander J, Xu X. A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD. vol. 96, No. 34. Portland: 1996. p. 226\u201331."},{"key":"2022_CR17","volume-title":"Mixture models: inference and applications to clustering","author":"GJ McLachlan","year":"1988","unstructured":"McLachlan GJ, Basford KE. Mixture models: inference and applications to clustering. New York: Marcel Dekker; 1988."},{"issue":"8","key":"2022_CR18","doi-asserted-by":"publisher","first-page":"888","DOI":"10.1109\/34.868688","volume":"22","author":"J Shi","year":"2000","unstructured":"Shi J, Malik J. Normalized cuts and image segmentation. Pattern Anal Mach Intell IEEE Trans. 2000; 22(8):888\u2013905.","journal-title":"Pattern Anal Mach Intell IEEE Trans"},{"key":"2022_CR19","volume-title":"Data Clustering: Algorithms and Applications","author":"T Li","year":"2013","unstructured":"Li T, Ding CH. Data Clustering: Algorithms and Applications. Boca Raton: CRC Press; 2013, pp. 149\u201376."},{"key":"2022_CR20","volume-title":"Proceedings of the 2005 SIAM International Conference on Data Mining","author":"C Ding","year":"2005","unstructured":"Ding C, He X, Simon HD. On the equivalence of nonnegative matrix factorization and spectral clustering. In: Proceedings of the 2005 SIAM International Conference on Data Mining. Philadelphia: SIAM: 2005. p. 606\u201310."},{"issue":"12","key":"2022_CR21","doi-asserted-by":"publisher","first-page":"4164","DOI":"10.1073\/pnas.0308531101","volume":"101","author":"JP Brunet","year":"2004","unstructured":"Brunet JP, Tamayo P, Golub TR, Mesirov JP. Metagenes and molecular pattern discovery using matrix factorization. Proc Natl Acad Sci. 2004; 101(12):4164\u20139.","journal-title":"Proc Natl Acad Sci"},{"key":"2022_CR22","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw PJ. Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J Comput Appl Math. 1987; 20:53\u201365.","journal-title":"J Comput Appl Math"},{"key":"2022_CR23","volume-title":"ICML \u201900 Proceedings of the Seventeenth International Conference on Machine Learning","author":"D Pelleg","year":"2000","unstructured":"Pelleg D, Moore AW, et al.X-means: Extending K-means with Efficient Estimation of the Number of Clusters. In: ICML \u201900 Proceedings of the Seventeenth International Conference on Machine Learning. San Francisco: Morgan Kaufmann Publishers Inc.: 2000. p. 727\u2013734."},{"issue":"2","key":"2022_CR24","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1111\/1467-9868.00293","volume":"63","author":"R Tibshirani","year":"2001","unstructured":"Tibshirani R, Walther G, Hastie T. Estimating the number of clusters in a data set via the gap statistic. J R Stat Soc Ser B Stat Methodol. 2001; 63(2):411\u201323.","journal-title":"J R Stat Soc Ser B Stat Methodol"},{"issue":"1-2","key":"2022_CR25","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/A:1023949509487","volume":"52","author":"S Monti","year":"2003","unstructured":"Monti S, Tamayo P, Mesirov J, Golub T. Consensus clustering: a resampling-based method for class discovery and visualization of gene expression microarray data. Mach Learn. 2003; 52(1-2):91\u2013118.","journal-title":"Mach Learn"},{"issue":"6","key":"2022_CR26","doi-asserted-by":"publisher","first-page":"1299","DOI":"10.1162\/089976604773717621","volume":"16","author":"T Lange","year":"2004","unstructured":"Lange T, Roth V, Braun ML, Buhmann JM. Stability-based validation of clustering solutions. Neural Comput. 2004; 16(6):1299\u2013323.","journal-title":"Neural Comput"},{"key":"2022_CR27","doi-asserted-by":"publisher","unstructured":"Hu CW, Kornblau SM, Slater JH, Qutub AA. Progeny Clustering: A Method to Identify Biological Phenotypes. Sci Rep. 2015; 5(12894):5. \n                    https:\/\/doi.org\/10.1038\/srep12894\n                    \n                  .","DOI":"10.1038\/srep12894"},{"key":"2022_CR28","volume-title":"Proceedings of the 2012 SIAM international conference on data mining","author":"D Kuang","year":"2012","unstructured":"Kuang D, Ding C, Park H. Symmetric nonnegative matrix factorization for graph clustering. In: Proceedings of the 2012 SIAM international conference on data mining. Philadelphia: SIAM: 2012. p. 106\u201317."},{"key":"2022_CR29","volume-title":"Constrained k-means clustering","author":"P Bradley","year":"2000","unstructured":"Bradley P, Bennett K, Demiriz A. Constrained k-means clustering. Redmond: Microsoft Research; 2000, pp. 1\u20138."},{"key":"2022_CR30","volume-title":"Towards the identification of cancer subtypes by integrative clustering of molecular data","author":"N Speicher","year":"2012","unstructured":"Speicher N, Lengauer T. Towards the identification of cancer subtypes by integrative clustering of molecular data. Saarbr\u00fccken: Universit\u00e4t des Saarlandes; 2012."},{"issue":"9","key":"2022_CR31","first-page":"1","volume":"11","author":"A Zeileis","year":"2004","unstructured":"Zeileis A, Hornik K, Smola A, Karatzoglou A. kernlab-an S4 package for kernel methods in R. J Stat Softw. 2004; 11(9):1\u201320.","journal-title":"J Stat Softw"},{"issue":"301","key":"2022_CR32","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1080\/01621459.1963.10500845","volume":"58","author":"JH Ward Jr","year":"1963","unstructured":"Ward Jr JH. Hierarchical grouping to optimize an objective function. J Am Stat Assoc. 1963; 58(301):236\u201344.","journal-title":"J Am Stat Assoc"},{"issue":"2","key":"2022_CR33","first-page":"56","volume":"1","author":"M Maechler","year":"2012","unstructured":"Maechler M, Rousseeuw P, Struyf A, Hubert M, Hornik K. Cluster: cluster analysis basics and extensions. R Package Version. 2012; 1(2):56.","journal-title":"R Package Version"},{"key":"2022_CR34","volume-title":"Finding groups in data: an introduction to cluster analysis, vol. 344.","author":"L Kaufman","year":"2009","unstructured":"Kaufman L, Rousseeuw PJ. Finding groups in data: an introduction to cluster analysis, vol. 344.Hoboken: John Wiley & Sons; 2009."},{"issue":"2","key":"2022_CR35","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1111\/j.1469-1809.1936.tb02137.x","volume":"7","author":"RA Fisher","year":"1936","unstructured":"Fisher RA. The use of multiple measurements in taxonomic problems. Ann Eugenics. 1936; 7(2):179\u201388.","journal-title":"Ann Eugenics"},{"key":"2022_CR36","unstructured":"Aeberhard S, Coomans D, De Vel O. Comparison of classifiers in high dimensional settings. Dept Math Statist, James Cook Univ, North Queensland, Australia. Tech Rep. 1992;92-02."},{"key":"2022_CR37","unstructured":"Bache K, Lichman M. UCI Machine Learning Repository: University of California, Irvine, School of Information and Computer Sciences; 2013. \n                    http:\/\/archive.ics.uci.edu\/ml\n                    \n                  ."},{"key":"2022_CR38","volume-title":"IS&T\/SPIE\u2019s Symposium on Electronic Imaging: Science and Technology","author":"WN Street","year":"1993","unstructured":"Street WN, Wolberg WH, Mangasarian OL. Nuclear feature extraction for breast tumor diagnosis. In: IS&T\/SPIE\u2019s Symposium on Electronic Imaging: Science and Technology. San Jose: International Society for Optics and Photonics: 1993. p. 861\u201370."},{"issue":"4","key":"2022_CR39","doi-asserted-by":"publisher","first-page":"570","DOI":"10.1287\/opre.43.4.570","volume":"43","author":"OL Mangasarian","year":"1995","unstructured":"Mangasarian OL, Street WN, Wolberg WH. Breast cancer diagnosis and prognosis via linear programming. Oper Res. 1995; 43(4):570\u20137.","journal-title":"Oper Res"},{"issue":"5814","key":"2022_CR40","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1126\/science.1136800","volume":"315","author":"BJ Frey","year":"2007","unstructured":"Frey BJ, Dueck D. Clustering by passing messages between data points. Science. 2007; 315(5814):972\u20136.","journal-title":"Science"},{"issue":"6191","key":"2022_CR41","doi-asserted-by":"publisher","first-page":"1492","DOI":"10.1126\/science.1242072","volume":"344","author":"A Rodriguez","year":"2014","unstructured":"Rodriguez A, Laio A. Clustering by fast search and find of density peaks. Science. 2014; 344(6191):1492\u20136.","journal-title":"Science"},{"key":"2022_CR42","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511809071","volume-title":"Introduction to information retrieval, vol. 1.","author":"CD Manning","year":"2008","unstructured":"Manning CD, Raghavan P, Sch\u00fctze H, et al.Introduction to information retrieval, vol. 1.Cambridge: Cambridge university press; 2008."},{"issue":"1","key":"2022_CR43","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1186\/1471-2105-9-497","volume":"9","author":"MC de Souto","year":"2008","unstructured":"de Souto MC, Costa IG, de Araujo DS, Ludermir TB, Schliep A. Clustering cancer gene expression data: a comparative study. BMC Bioinformatics. 2008; 9(1):497.","journal-title":"BMC Bioinformatics"},{"issue":"1","key":"2022_CR44","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1038\/ng1061","volume":"33","author":"L Dyrskj\u00f8t","year":"2003","unstructured":"Dyrskj\u00f8t L, Thykjaer T, Kruh\u00f8ffer M, Jensen JL, Marcussen N, Hamilton-Dutoit S, et al.Identifying distinct classes of bladder carcinoma using microarrays. Nat Genet. 2003; 33(1):90.","journal-title":"Nat Genet"},{"issue":"7","key":"2022_CR45","first-page":"1602","volume":"63","author":"CL Nutt","year":"2003","unstructured":"Nutt CL, Mani D, Betensky RA, Tamayo P, Cairncross JG, Ladd C, et al.Gene expression-based classification of malignant gliomas correlates better with survival than histological classification. Cancer Res. 2003; 63(7):1602\u20137.","journal-title":"Cancer Res"},{"issue":"6","key":"2022_CR46","doi-asserted-by":"publisher","first-page":"718","DOI":"10.2174\/156720512801322555","volume":"9","author":"JT Montine","year":"2012","unstructured":"Montine JT, Sonnen AJ, Montine SK, Crane KP, Larson BE. Adult Changes in Thought study: dementia is an individually varying convergent syndrome with prevalent clinically silent diseases that may be modified by some commonly used therapeutics. Curr Alzheim Res. 2012; 9(6):718\u201323.","journal-title":"Curr Alzheim Res"}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-018-2022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-018-2022-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-018-2022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,5,14]],"date-time":"2020-05-14T11:00:50Z","timestamp":1589454050000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-018-2022-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,1,23]]},"references-count":46,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["2022"],"URL":"https:\/\/doi.org\/10.1186\/s12859-018-2022-8","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,1,23]]},"assertion":[{"value":"20 June 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2018","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 January 2018","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Not applicable.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no competing interests.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Publisher\u2019s Note"}}],"article-number":"19"}}