{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T00:57:01Z","timestamp":1775609821218,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2015,2,5]],"date-time":"2015-02-05T00:00:00Z","timestamp":1423094400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"published-print":{"date-parts":[[2015,12]]},"DOI":"10.1186\/s12859-014-0445-4","type":"journal-article","created":{"date-parts":[[2015,2,4]],"date-time":"2015-02-04T13:39:45Z","timestamp":1423057185000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Evaluation and improvements of clustering algorithms for detecting remote homologous protein families"],"prefix":"10.1186","volume":"16","author":[{"given":"Juliana S","family":"Bernardes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fabio RJ","family":"Vieira","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lygia MM","family":"Costa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerson","family":"Zaverucha","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,2,5]]},"reference":[{"key":"445_CR1","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"SF Altschul","year":"1990","unstructured":"Altschul SF, Gish W, Miller W, Myers EW, Lipman DJ. Basic local alignment search tool. J Mol Biol. 1990; 215:403\u201310.","journal-title":"J Mol Biol"},{"key":"445_CR2","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1186\/gb-2006-7-1-r8","volume":"7","author":"S Brown","year":"2006","unstructured":"Brown S, Gerlt J, Seffernick J, Babbitt P. A gold standard set of mechanistically diverse enzyme superfamilies. Genome Biol. 2006; 7:8\u20131815.","journal-title":"Genome Biol"},{"key":"445_CR3","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1093\/nar\/28.1.257","volume":"28","author":"LL Conte","year":"2000","unstructured":"Conte LL, Ailey B, Hubbard TJP, Brenner SE, Murzin AG, Chothia C. SCOP: a structural classification of proteins database. Nucleic Acids Res. 2000; 28:257\u20139.","journal-title":"Nucleic Acids Res"},{"key":"445_CR4","doi-asserted-by":"publisher","first-page":"1575","DOI":"10.1093\/nar\/30.7.1575","volume":"30","author":"AJ Enright","year":"2002","unstructured":"Enright AJ, van Dongen S, Ouzounis CA. An efficient algorithm for large-scale detection of protein families. Nucleic Acids Res. 2002; 30:1575\u201384.","journal-title":"Nucleic Acids Res"},{"key":"445_CR5","doi-asserted-by":"publisher","first-page":"419","DOI":"10.1038\/nmeth0610-419","volume":"7","author":"T Wittkop","year":"2010","unstructured":"Wittkop T, Emig D, Lange S, Rahmann S, Albrecht M, Morris JH, et al. Partitioning biological data with transitivity clustering. Nat Methods. 2010; 7:419\u2013420.","journal-title":"Nat Methods"},{"key":"445_CR6","doi-asserted-by":"publisher","first-page":"120","DOI":"10.1186\/1471-2105-11-120","volume":"11","author":"T Nepusz","year":"2010","unstructured":"Nepusz T, Sasidharan R, Paccanaro A. SCPS: a fast implementation of a spectral method for detecting protein families on a genome-wide scale. BMC Bioinformatics. 2010; 11:120\u2013132.","journal-title":"BMC Bioinformatics"},{"key":"445_CR7","doi-asserted-by":"publisher","first-page":"1078","DOI":"10.1093\/bioinformatics\/bts098","volume":"28","author":"V Miele","year":"2012","unstructured":"Miele V, Penel S, Daubin V, Picard F, Kahn D, Duret L. High-quality sequence clustering guided by network topology and multiple alignment likelihood. Bioinformatics. 2012; 28:1078\u201385.","journal-title":"Bioinformatics"},{"key":"445_CR8","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1038\/nmeth.1818","volume":"9","author":"M Remmert","year":"2012","unstructured":"Remmert M, Biegert A, Hauser A, Soding J. HHblits: lightning-fast iterative protein sequence searching by HMM-HMM alignment. Nat Methods. 2012; 9:173\u20135.","journal-title":"Nat Methods"},{"key":"445_CR9","volume-title":"Research in computational molecular biology, volume 3909","author":"A Vashist","year":"2006","unstructured":"Vashist A, Kulikowski C, Muchnik I. Protein function annotation based on ortholog clusters extracted from incomplete genomes using combinatorial optimization. In: Research in computational molecular biology, volume 3909. Berlin, Germany: Springer Berlin Heidelberg: 2006. p. 99\u2013113."},{"issue":"3","key":"445_CR10","doi-asserted-by":"publisher","first-page":"683","DOI":"10.1002\/prot.10449","volume":"53","author":"F Abascal","year":"2003","unstructured":"Abascal F, Valencia A. Automatic annotation of protein function based on family identification. Proteins: Struct Function Bioinformatics. 2003; 53(3):683\u201392.","journal-title":"Proteins: Struct Function Bioinformatics"},{"issue":"10","key":"445_CR11","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1038\/nrg3053","volume":"12","author":"D Tautz","year":"2011","unstructured":"Tautz D, Domazet-Loso T. The evolutionary origin of orphan genes. Nat Rev Genet. 2011; 12(10):692\u2013702.","journal-title":"Nat Rev Genet"},{"key":"445_CR12","volume-title":"Proceedings of the 14th international joint conference on artificial intelligence","author":"R Kohavi","year":"1995","unstructured":"Kohavi R. A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of the 14th international joint conference on artificial intelligence. San Francisco, CA, USA: Morgan Kaufmann Publishers Inc.: 1995. p. 1137\u201345."},{"key":"445_CR13","doi-asserted-by":"publisher","first-page":"150","DOI":"10.1186\/1471-2105-10-150","volume":"10","author":"N Zaki","year":"2009","unstructured":"Zaki N, Lazarova-Molnar S, El-Hajj W, Campbell P. Protein-protein interaction based on pairwise similarity. BMC Bioinformatics. 2009; 10:150\u201361.","journal-title":"BMC Bioinformatics"},{"key":"445_CR14","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1093\/nar\/28.1.254","volume":"28","author":"SE Brenner","year":"2000","unstructured":"Brenner SE, Koehl P, Levitt M. The ASTRAL compendium for protein structure and sequence analysis. Nucleic Acids Res. 2000; 28:254\u20136.","journal-title":"Nucleic Acids Res"},{"key":"445_CR15","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1186\/1471-2105-12-116","volume":"12","author":"V Miele","year":"2011","unstructured":"Miele V, Penel S, Duret L. Ultra-fast sequence clustering from similarity networks with SiLiX. BMC Bioinformatics. 2011; 12:116\u201324.","journal-title":"BMC Bioinformatics"},{"key":"445_CR16","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1093\/bioinformatics\/bti125","volume":"21","author":"J Soding","year":"2005","unstructured":"Soding J. Protein homology detection by HMM-HMM comparison. Bioinformatics. 2005; 21:951\u201360.","journal-title":"Bioinformatics"},{"key":"445_CR17","doi-asserted-by":"publisher","first-page":"1571","DOI":"10.1093\/nar\/gkj515","volume":"34","author":"A Paccanaro","year":"2006","unstructured":"Paccanaro A, Casbon JA, Saqi MAS. Spectral clustering of protein sequences. Nucleic Acids Res. 2006; 34:1571\u201380.","journal-title":"Nucleic Acids Res"},{"key":"445_CR18","first-page":"95","volume":"12","author":"R Hughey","year":"1996","unstructured":"Hughey R, Krogh A. Hidden markov models for sequence analysis: extension and analysis of the basic method. Comput Appl Biosci. 1996; 12:95\u2013107.","journal-title":"Comput Appl Biosci"},{"issue":"1","key":"445_CR19","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1186\/1471-2105-11-89","volume":"11","author":"M Margelevicius","year":"2010","unstructured":"Margelevicius M, Venclovas C. Detection of distant evolutionary relationships between protein families using theory of sequence profile-profile comparison. BMC Bioinformatics. 2010; 11(1):89.","journal-title":"BMC Bioinformatics"},{"key":"445_CR20","doi-asserted-by":"crossref","unstructured":"Soding J, Remmert M, Hauser A. HH-suite for sensitive protein sequence searching based on HMM-HMM alignment; 2012. http:\/\/gts.sourceforge.net\/ .","DOI":"10.1038\/nmeth.1818"},{"key":"445_CR21","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1007\/s00453-009-9339-7","volume":"60","author":"S Bocker","year":"2011","unstructured":"Bocker S, Briesemeister S, Klau GW. Exact algorithms for cluster editing: Evaluation and experiments. Algorithmica. 2011; 60:316\u201334.","journal-title":"Algorithmica"},{"key":"445_CR22","volume-title":"The nature of computation. Logic, algorithms, applications, volume 7921","author":"S Bocker","year":"2013","unstructured":"Bocker S, Baumbach J. Cluster editing. In: The nature of computation. Logic, algorithms, applications, volume 7921. Berlin, Germany: Springer Berlin Heidelberg: 2013. p. 33\u201344."},{"key":"445_CR23","doi-asserted-by":"publisher","first-page":"281","DOI":"10.1089\/106652799318274","volume":"6","author":"A Ben-Dor","year":"1999","unstructured":"Ben-Dor A, Shamir R, Yakhini Z. Clustering gene expression patterns. J Comput Biol. 1999; 6:281\u201397.","journal-title":"J Comput Biol"},{"key":"445_CR24","doi-asserted-by":"publisher","first-page":"396","DOI":"10.1186\/1471-2105-8-396","volume":"8","author":"T Wittkop","year":"2007","unstructured":"Wittkop T, Baumbach J, Lobo F, Rahmann S. Large scale clustering of protein sequences with FORCE -A layout based heuristic for weighted cluster editing. BMC Bioinformatics. 2007; 8:396\u2013407.","journal-title":"BMC Bioinformatics"},{"key":"445_CR25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-29807-3","volume-title":"Advances in K-means clustering","author":"J Wu","year":"2012","unstructured":"Wu J. Cluster analysis and K-means clustering: an introduction. In: Advances in K-means clustering. Springer Theses, Berlin, Germany: Springer Berlin Heidelberg: 2012. p. 1\u201316."},{"key":"445_CR26","doi-asserted-by":"publisher","first-page":"10008","DOI":"10.1088\/1742-5468\/2008\/10\/P10008","volume":"2008","author":"VD Blondel","year":"2008","unstructured":"Blondel VD, Guillaume J, Lambiotte R, Lefebvre E. Fast unfolding of communities in large networks. J Stat Mech: Theory Exp. 2008; 2008:10008\u201319.","journal-title":"J Stat Mech: Theory Exp"},{"key":"445_CR27","doi-asserted-by":"publisher","first-page":"719","DOI":"10.1109\/34.865189","volume":"22","author":"C Biernacki","year":"2000","unstructured":"Biernacki C, Celeux G, Govaert G. Assessing a mixture model for clustering with the integrated completed likelihood. IEEE Trans Pattern Anal Mach Intell. 2000; 22:719\u201325.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"445_CR28","volume-title":"Introduction to data mining","author":"P Tan","year":"2005","unstructured":"Tan P, Steinbach M, Kumar V. Introduction to data mining, 1st ed. Boston, MA: Addison-Wesley Longman Publishing; 2005."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1186\/s12859-014-0445-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-014-0445-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-014-0445-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-014-0445-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,8,20]],"date-time":"2019-08-20T16:27:28Z","timestamp":1566318448000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-014-0445-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,5]]},"references-count":28,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2015,12]]}},"alternative-id":["445"],"URL":"https:\/\/doi.org\/10.1186\/s12859-014-0445-4","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2015,2,5]]},"assertion":[{"value":"2 June 2014","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 November 2014","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 February 2015","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"34"}}