{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,4,1]],"date-time":"2022-04-01T18:39:00Z","timestamp":1648838340664},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"2-3","license":[{"start":{"date-parts":[[2006,8,22]],"date-time":"2006-08-22T00:00:00Z","timestamp":1156204800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Pattern Anal Applic"],"published-print":{"date-parts":[[2006,9,26]]},"DOI":"10.1007\/s10044-006-0040-z","type":"journal-article","created":{"date-parts":[[2006,8,21]],"date-time":"2006-08-21T11:01:48Z","timestamp":1156158108000},"page":"243-255","source":"Crossref","is-referenced-by-count":7,"title":["Efficient median based clustering and classification techniques for protein sequences"],"prefix":"10.1007","volume":"9","author":[{"given":"P. A.","family":"Vijaya","sequence":"first","affiliation":[]},{"given":"M. Narasimha","family":"Murty","sequence":"additional","affiliation":[]},{"given":"D. K.","family":"Subramanian","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2006,8,22]]},"reference":[{"issue":"1","key":"40_CR1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1016\/j.fss.2004.10.011","volume":"152","author":"S Bandyopadhyay","year":"2005","unstructured":"Bandyopadhyay S (2005) An efficient technique for superfamily classification of amino acid sequences: feature extraction, fuzzy clustering and prototype selection. Fuzzy Sets Syst 152(1):5\u201316","journal-title":"Fuzzy Sets Syst"},{"issue":"10","key":"40_CR2","doi-asserted-by":"crossref","first-page":"935","DOI":"10.1093\/bioinformatics\/17.10.935","volume":"17","author":"E Bolten","year":"2001","unstructured":"Bolten E, Schliep A, Schneckener S, Schomburg D, Schrader R (2001) Clustering protein sequences-structure prediction by transitive homology. Bioinformatics 17(10):935\u2013941","journal-title":"Bioinformatics"},{"issue":"1","key":"40_CR3","doi-asserted-by":"crossref","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, Chotia C (2000) SCOP: a structural classification of protein database. Nucleic Acids Res 28(1):257\u2013259","journal-title":"Nucleic Acids Res"},{"issue":"1","key":"40_CR4","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1109\/TIT.1967.1053964","volume":"13","author":"T Cover","year":"1967","unstructured":"Cover T, Hart P (1967) Nearest neighbour pattern classification. IEEE Trans Inform Theory 13(1):21\u201327","journal-title":"IEEE Trans Inform Theory"},{"key":"40_CR5","unstructured":"Duda RO, Hart PE, Stork DG (2000) Pattern classification, 2nd edn. Wiley, New York"},{"key":"40_CR6","doi-asserted-by":"crossref","unstructured":"Durbin R, Eddy S, Krogh A, Mitchison G (1998) Biological sequence analysis. Cambridge University Press, Cambridge","DOI":"10.1017\/CBO9780511790492"},{"key":"40_CR7","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1109\/TKDE.2003.1198387","volume":"153","author":"S Guha","year":"2003","unstructured":"Guha S, Meyerson A, Mishra N, Motwani R, O\u2019Callaghan L (2003) Clustering data streams: theory and practice. IEEE Trans Knowl Data Eng 153:515\u2013528","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"40_CR8","doi-asserted-by":"crossref","unstructured":"Guralnik V, Karypis G (2001) A scalable algorithm for clustering sequential data. In: Proceedings of I IEEE conference on data mining, pp 179\u2013186","DOI":"10.1109\/ICDM.2001.989516"},{"issue":"5","key":"40_CR9","doi-asserted-by":"crossref","first-page":"571","DOI":"10.1109\/34.494648","volume":"18","author":"Y Hamamoto","year":"1996","unstructured":"Hamamoto Y, Uchimura S, Tomita S (1996) On the behavior of artificial neural network classifiers in high-dimensional spaces. IEEE Trans Pattern Anal Mach Intell 18(5):571\u2013574","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"40_CR10","unstructured":"Han E, Karypis G, Kumar V, Mobasher B (1997) Clustering in a high dimensional space using hypergraph models. In: Proceedings of data mining and knowledge discovery"},{"key":"40_CR11","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1006\/geno.1994.1018","volume":"19","author":"S Henikoff","year":"1994","unstructured":"Henikoff S, Henikoff JG (1994) Protein family classification based on searching a database of blocks. Genomics 19:97\u2013107","journal-title":"Genomics"},{"key":"40_CR12","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/0196-8858(91)90017-D","volume":"12","author":"X Huang","year":"1991","unstructured":"Huang X, Webb M (1991) A time-efficient, linear-space local similarity algorithm. Adv Appl Math 12:337\u2013357","journal-title":"Adv Appl Math"},{"key":"40_CR13","volume-title":"Algorithms for clustering data","author":"AK Jain","year":"1988","unstructured":"Jain AK, Dubes RC (1988) Algorithms for clustering data. Prentice-Hall, Upper Saddle River"},{"issue":"3","key":"40_CR14","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","volume":"31","author":"AK Jain","year":"1999","unstructured":"Jain AK, Murty MN, Flynn PJ (1999) Data clustering: a review. ACM Comput Surv 31(3):264\u2013323","journal-title":"ACM Comput Surv"},{"key":"40_CR15","doi-asserted-by":"crossref","DOI":"10.1002\/9780470316801","volume-title":"Finding groups in data: an introduction to cluster analysis","author":"L Kaufman","year":"1990","unstructured":"Kaufman L, Rousseeuw P (1990) Finding groups in data: an introduction to cluster analysis. Wiley, New York"},{"key":"40_CR16","unstructured":"Knuth DE (1998) Art of computer programming, 2nd edn, vol 3. Addison- Wesley, Reading"},{"key":"40_CR17","doi-asserted-by":"crossref","unstructured":"Kohonen T (1985) Median strings. Pattern Recogn Lett (3):309\u2013313","DOI":"10.1016\/0167-8655(85)90061-3"},{"key":"40_CR18","unstructured":"Krause A (2002) Large scale clustering of protein sequences. Ph.D. Thesis, Berlin"},{"issue":"1","key":"40_CR19","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1093\/nar\/29.1.33","volume":"29","author":"EV Kriventseva","year":"2001","unstructured":"Kriventseva EV, Fleischmann W, Zdobnov EM, Apweiler G (2001) CluSTr: a database of clusters of SWISS-PROT+TrEMBL proteins. Nucleic Acids Res 29(1):33\u201336","journal-title":"Nucleic Acids Res"},{"key":"40_CR20","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1016\/S0167-8655(02)00209-X","volume":"24","author":"CD Martinez","year":"2003","unstructured":"Martinez CD, Juan A, Casacuberta F (2003) Median strings for k-nearest neighbour classification. Pattern Recogn Lett 24:173\u2013181","journal-title":"Pattern Recogn Lett"},{"key":"40_CR21","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/0167-8655(94)90095-7","volume":"15","author":"L MicA","year":"1994","unstructured":"MicA L, Oncina J, Vidal E (1994) A new version of the nearest-neighbor approximating and eliminating search algorithm (AESA) with linear preprocessing time and memory requirements. Pattern Recogn Lett 15:9\u201317","journal-title":"Pattern Recogn Lett"},{"key":"40_CR22","doi-asserted-by":"crossref","first-page":"731","DOI":"10.1016\/0167-8655(96)00032-3","volume":"17","author":"L MicA","year":"1996","unstructured":"MicA L, Oncina J, Carrasco R (1996) A fast branch and bound nearest neighbor classifier in metric spaces. Pattern Recogn Lett 17:731\u2013739","journal-title":"Pattern Recogn Lett"},{"key":"40_CR23","volume-title":"Data mining: multimedia, soft computing and bioinformatics","author":"S Mitra","year":"2003","unstructured":"Mitra S, Acharya T (2003) Data mining: multimedia, soft computing and bioinformatics. Wiley, New York"},{"key":"40_CR24","first-page":"1145","volume":"22","author":"F Moreno","year":"2003","unstructured":"Moreno F, MicA L, Oncina J (2003) A modification of the LAESA algorithm for approximated k-NN classification. Pattern Recogn Lett 22:1145\u20131151","journal-title":"Pattern Recogn Lett"},{"key":"40_CR25","volume-title":"Bioinformatics\u2014sequence and genome analysis","author":"DW Mount","year":"2002","unstructured":"Mount DW (2002) Bioinformatics\u2014sequence and genome analysis. Cold Spring Harbor Lab Press, New York"},{"key":"40_CR26","doi-asserted-by":"crossref","first-page":"443","DOI":"10.1016\/0022-2836(70)90057-4","volume":"48","author":"SB Needleman","year":"1970","unstructured":"Needleman SB, Wunsch CD (1970) A general method applicable to the search for similarities in the amino acid sequence of the proteins. J Mol Biol 48:443\u2013453","journal-title":"J Mol Biol"},{"issue":"5","key":"40_CR27","doi-asserted-by":"crossref","first-page":"1003","DOI":"10.1109\/TKDE.2002.1033770","volume":"14","author":"RT Ng","year":"2002","unstructured":"Ng RT, Han J (2002) CLARANS: a method for clustering objects for spatial data mining. IEEE Trans Knowl Data Eng 14(5):1003\u20131016","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"40_CR28","doi-asserted-by":"crossref","unstructured":"Pal SK, Mitra P (2004) Pattern recognition algorithms for data mining: scalability, knowledge discovery and soft granular computing. CHAPMAN & HALL\/CRC","DOI":"10.1201\/9780203998076"},{"key":"40_CR29","unstructured":"Pearson W (1999) The FASTA program package http:\/\/ftp.virginia.edu\/pub\/fasta"},{"key":"40_CR30","unstructured":"Peter C, Rolf B (2000) Computational molecular biology\u2014an introduction. Wiley, New York"},{"key":"40_CR31","unstructured":"Pujari AK (2000) Data mining techniques. Universities Press (India) Private Limited"},{"key":"40_CR32","doi-asserted-by":"crossref","first-page":"1497","DOI":"10.1016\/S0031-3203(99)00134-X","volume":"33","author":"V Ramasubramanian","year":"2000","unstructured":"Ramasubramanian V, Paliwal KK (2000) Fast nearest neighbor search algorithms based on approximation-elimination search. Pattern Recogn 33:1497\u20131510","journal-title":"Pattern Recogn"},{"key":"40_CR33","unstructured":"Sahni S (1998) Data Structures, Algorithms and applications in C++. WCB McGraw Hill"},{"key":"40_CR34","doi-asserted-by":"crossref","first-page":"371","DOI":"10.1016\/0022-2836(92)90892-N","volume":"227","author":"S Salzberg","year":"1992","unstructured":"Salzberg S, Cost S (1992) Predicting protein secondary structure with a nearest neighbour algorithm. J Mol Biol 227:371\u2013374","journal-title":"J Mol Biol"},{"key":"40_CR35","unstructured":"Schutze H (2004) Single-link, complete-link and average-link clustering. \u201c http:\/\/www.csli.stanford.edu\/~schuetze\/completelink.html"},{"key":"40_CR36","unstructured":"Sharan R, Shamir R (2000) CLICK: a clustering algorithm with applications to gene expression analysis. In: Proceedings of 8th ISMB, pp 307\u2013316"},{"key":"40_CR37","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"TF Smith","year":"1981","unstructured":"Smith TF, Waterman MS (1981) Identification of common molecular subsequences. J Mol Biol 147:195\u2013197","journal-title":"J Mol Biol"},{"key":"40_CR38","volume-title":"Cluster analysis algorithms for data reduction and classification","author":"H Spath","year":"1980","unstructured":"Spath H (1980) Cluster analysis algorithms for data reduction and classification. Ellis Horwood, Chichester"},{"key":"40_CR39","doi-asserted-by":"crossref","unstructured":"Somervuo P, Kohonen T (2000) Clustering and visualization of large protein sequence databases by means of an extension of the self-organizing map. In: Proceedings of 3rd international conference on discovery science, pp 76\u201385","DOI":"10.1007\/3-540-44418-1_7"},{"key":"40_CR40","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/0167-8655(86)90013-9","volume":"4","author":"E Vidal","year":"1986","unstructured":"Vidal E (1986) An algorithm for finding nearest neighbors in (approximately) constant average time. Pattern Recogn Lett 4:145\u2013157","journal-title":"Pattern Recogn Lett"},{"key":"40_CR41","doi-asserted-by":"crossref","unstructured":"Vijaya PA, Murty MN, Subramanian DK (2003) An efficient incremental protein sequence clustering algorithm. In: Proceedings of IEEE TENCON, Asia Pacific, pp 409\u2013413","DOI":"10.1109\/TENCON.2003.1273355"},{"issue":"2","key":"40_CR42","first-page":"61","volume":"1","author":"PA Vijaya","year":"2004","unstructured":"Vijaya PA, Murty MN, Subramanian DK (2004) An efficient hierarchical clustering algorithm for protein sequences. Int J Comput Sci Appl 1(2):61\u201375","journal-title":"Int J Comput Sci Appl"},{"key":"40_CR43","unstructured":"Vijaya PA, Murty MN, Subramanian DK (2003) Supervised K-medians algorithm for protein sequence classification. In; Proceedings of 5th international conference on advanced pattern recognition, pp 129\u2013132"},{"key":"40_CR44","doi-asserted-by":"crossref","unstructured":"Vijaya PA, Murty MN, Subramanian DK (2004) An efficient technique for protein sequence clustering and classification. In: Proceedings of 17th international conference on pattern recognition, Cambridge, UK, Vol II, pp 447\u2013450","DOI":"10.1109\/ICPR.2004.1334254"},{"issue":"4","key":"40_CR45","first-page":"559","volume":"6","author":"JTL Wang","year":"1994","unstructured":"Wang JTL, Thomas GM, Dennis S, Bruce S (1994) Chern, discovering active motifs in sets of related protein sequences and using them for classification. Nucleic Acids Res 6(4):559\u2013571","journal-title":"Nucleic Acids Res"},{"key":"40_CR46","doi-asserted-by":"crossref","first-page":"1117","DOI":"10.1006\/jmbi.1993.1464","volume":"232","author":"TM Yi","year":"1993","unstructured":"Yi TM, Eric S (1993) Protein secondary structure prediction using nearest neighbour methods. J Mol Biol 232:1117\u20131129","journal-title":"J Mol Biol"},{"issue":"1","key":"40_CR47","doi-asserted-by":"crossref","first-page":"49","DOI":"10.1093\/nar\/28.1.49","volume":"28","author":"G Yona","year":"2000","unstructured":"Yona G, Linial N, Linial M (2000) ProtoMap: automatic classification of protein sequences and hierarchy of protein families. Nucleic Acids Res 28(1):49\u201355","journal-title":"Nucleic Acids Res"},{"key":"40_CR48","unstructured":"http:\/\/www.pfam.cgb.ki.se\/"},{"key":"40_CR49","unstructured":"http:\/\/www.systers.molgen.mpg.de\/"},{"key":"40_CR50","unstructured":"http:\/\/www.protonet.cs.huji.ac.il\/"},{"key":"40_CR51","unstructured":"http:\/\/www.pir.georgetown.edu\/pirsf\/"}],"container-title":["Pattern Analysis and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-006-0040-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10044-006-0040-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10044-006-0040-z","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,5,29]],"date-time":"2019-05-29T08:02:25Z","timestamp":1559116945000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10044-006-0040-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,8,22]]},"references-count":51,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2006,9,26]]}},"alternative-id":["40"],"URL":"https:\/\/doi.org\/10.1007\/s10044-006-0040-z","relation":{},"ISSN":["1433-7541","1433-755X"],"issn-type":[{"value":"1433-7541","type":"print"},{"value":"1433-755X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006,8,22]]}}}