{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,5]],"date-time":"2024-09-05T15:59:38Z","timestamp":1725551978921},"publisher-location":"Berlin, Heidelberg","reference-count":34,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642124754"},{"type":"electronic","value":"9783642124761"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2010]]},"DOI":"10.1007\/978-3-642-12476-1_2","type":"book-chapter","created":{"date-parts":[[2010,4,8]],"date-time":"2010-04-08T13:46:37Z","timestamp":1270734397000},"page":"34-44","source":"Crossref","is-referenced-by-count":11,"title":["Maximal Words in Sequence Comparisons Based on Subword Composition"],"prefix":"10.1007","author":[{"given":"Alberto","family":"Apostolico","sequence":"first","affiliation":[]}],"member":"297","reference":[{"key":"2_CR1","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1007\/978-3-642-82456-2_6","volume-title":"Combinatorial Algorithms on Words","author":"A. Apostolico","year":"1985","unstructured":"Apostolico, A.: The myriad virtues of suffix trees. In: Apostolico, A., Galil, Z. (eds.) Combinatorial Algorithms on Words, pp. 85\u201396. Springer, Berlin (1985)"},{"key":"2_CR2","doi-asserted-by":"crossref","unstructured":"Apostolico, A., Denas, O.: Fast algorithms for computing sequence distances by exhaustive substring composition. Algorithms for Molecular Biology\u00a03 (2008)","DOI":"10.1186\/1748-7188-3-13"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Apostolico, A., Denas, O., Dress, A.: Efficient tools for comparative substring analysis (submitted, 2009)","DOI":"10.1016\/j.jbiotec.2010.05.006"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Blaidsell, B.: A measure of the similarity of sets of sequences not requiring sequence alignment. Proceedings of the National Academy of Sciences, 5155\u20135159 (1986)","DOI":"10.1073\/pnas.83.14.5155"},{"key":"2_CR5","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1016\/0304-3975(85)90157-4","volume":"40","author":"A. Blumer","year":"1985","unstructured":"Blumer, A., Blumer, J., Haussler, D., Ehrenfeucht, A., Chen, M.T., Seiferas, J.I.: The smallest automaton recognizing the subwords of a text. Theor. Comput. Sci.\u00a040, 31\u201355 (1985)","journal-title":"Theor. Comput. Sci."},{"key":"2_CR6","volume-title":"Science and Information Theory","author":"L. Brillouin","year":"1971","unstructured":"Brillouin, L.: Science and Information Theory. Academic Press, London (1971)"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1006\/jtbi.2000.1077","volume":"204","author":"A. Colosimo","year":"2000","unstructured":"Colosimo, A., de Luca, A.: Special factors in biological strings. J. Theor. Biol.\u00a0204, 29\u201347 (2000)","journal-title":"J. Theor. Biol."},{"key":"2_CR8","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611","volume-title":"Elements of Information Theory","author":"T.M. Cover","year":"1991","unstructured":"Cover, T.M., Thomas, J.A.: Elements of Information Theory. Wiley-Interscience, Hoboken (1991)"},{"key":"2_CR9","first-page":"380","volume":"32","author":"R. Edgar","year":"2004","unstructured":"Edgar, R.: Local homology recognition and distance measures in linear time using compressed amino-acid alphabets. Bioinformatics\u00a032, 380\u2013385 (2004)","journal-title":"Bioinformatics"},{"key":"2_CR10","doi-asserted-by":"publisher","first-page":"252","DOI":"10.1186\/1471-2105-8-252","volume":"8","author":"P. Ferragina","year":"2007","unstructured":"Ferragina, P., Giancarlo, R., Greco, V., Manzini, G., Valiente, G.: Compression-based classification of biological sequences and structures via the universal similarity metric: experimental assessment. BMC Bioinformatics\u00a08, 252\u2013272 (2007)","journal-title":"BMC Bioinformatics"},{"key":"2_CR11","volume-title":"Data mining: concepts and techniques","author":"J. Han","year":"2000","unstructured":"Han, J., Kamber, M.: Data mining: concepts and techniques. Morgan Kaufmann Publishers Inc., San Francisco (2000)"},{"key":"2_CR12","unstructured":"Hao, B.: Personal communication (2008)"},{"key":"2_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1142\/S0219720004000442","volume":"2","author":"B. Hao","year":"2004","unstructured":"Hao, B., Qi, J.: Procaryote phylogeny without sequence alignment: from avoidance singature to composition distance. Journal of Bioinformatics and Computational Biology\u00a02, 1\u201319 (2004)","journal-title":"Journal of Bioinformatics and Computational Biology"},{"key":"2_CR14","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1093\/bioinformatics\/btg425","volume":"20","author":"J. Helden Van","year":"2004","unstructured":"Van Helden, J.: Metrics for comparing regulatory sequences on the basis of pattern counts. Bioinformatics\u00a020, 399\u2013406 (2004)","journal-title":"Bioinformatics"},{"issue":"2","key":"2_CR15","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1080\/10635150701294741","volume":"56","author":"M. H\u00f6hl","year":"2007","unstructured":"H\u00f6hl, M., Ragan, M.A.: Is multiple-sequence alignment required for accurate inference of phylogeny? Syst. Biol.\u00a056(2), 206\u2013221 (2007)","journal-title":"Syst. Biol."},{"key":"2_CR16","first-page":"357","volume":"2","author":"M. H\u00f6hl","year":"2006","unstructured":"H\u00f6hl, M., Rigutsos, I., Ragan, M.A.: Pattern-based phylogenetic distance estimation and tree recosntruction. Evolutionary Bioinformatics Online\u00a02, 357\u2013373 (2006)","journal-title":"Evolutionary Bioinformatics Online"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Hopcroft, J.E., Wong, J.K.: Linear time algorithm for isomorphism of planar graphs (preliminary report). In: STOC, pp. 172\u2013184 (1974)","DOI":"10.1145\/800119.803896"},{"issue":"1","key":"2_CR18","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1145\/602382.602397","volume":"50","author":"F.P. Brooks Jr.","year":"2003","unstructured":"Brooks Jr., F.P.: Three great challenges for half-century-old computer science. J. ACM\u00a050(1), 25\u201326 (2003)","journal-title":"J. ACM"},{"issue":"7","key":"2_CR19","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/S0168-9525(00)89076-9","volume":"11","author":"S. Karlin","year":"1995","unstructured":"Karlin, S., Burge, C.: Dinucleotide relative abundance extremes: a genomic signature. Trends in genetics: TIG\u00a011(7), 283\u2013290 (1995)","journal-title":"Trends in genetics: TIG"},{"key":"2_CR20","unstructured":"Kolmogorov, A.N.: Three approaches to the quantitative definition of information. Problemi Pederachi Inf.\u00a01 (1965)"},{"key":"2_CR21","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1109\/TIT.1976.1055501","volume":"22","author":"A. Lempel","year":"1976","unstructured":"Lempel, A., Ziv, J.: On the complexity of finite sequences. IEEE Transactions on Information Theory\u00a022, 75\u201381 (1976)","journal-title":"IEEE Transactions on Information Theory"},{"issue":"1","key":"2_CR22","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1093\/bioinformatics\/17.2.149","volume":"17","author":"M. Li","year":"2001","unstructured":"Li, M., Badger, J.H., Chen, X., Kwong, S., Kearney, P.E., Zhang, H.: An information-based sequence distance and its application to whole mitochondrial genome phylogeny. Bioinformatics\u00a017(1), 149\u2013154 (2001)","journal-title":"Bioinformatics"},{"issue":"12","key":"2_CR23","doi-asserted-by":"publisher","first-page":"3250","DOI":"10.1109\/TIT.2004.838101","volume":"50","author":"M. Li","year":"2004","unstructured":"Li, M., Chen, X., Li, X., Ma, B., Vit\u00e1nyi, P.M.B.: The similarity metric. IEEE Transactions on Information Theory\u00a050(12), 3250\u20133264 (2004)","journal-title":"IEEE Transactions on Information Theory"},{"key":"2_CR24","doi-asserted-by":"publisher","first-page":"2122","DOI":"10.1093\/bioinformatics\/btg295","volume":"19","author":"H. Otu","year":"2003","unstructured":"Otu, H., Sayood, K.: A new sequence distance measure for phylogenetic tree reconstruction. Bioinformatics\u00a019, 2122\u20132130 (2003)","journal-title":"Bioinformatics"},{"issue":"1","key":"2_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00239-003-2493-7","volume":"58","author":"J. Qi","year":"2004","unstructured":"Qi, J., Wang, B., Hao, B.: Whole proteome prokaryote phylogeny without sequence alignment: A k-string composition approach. Molecular Evolution\u00a058(1), 1\u201311 (2004)","journal-title":"Molecular Evolution"},{"key":"2_CR26","unstructured":"R\u00e9nyi, A.: On measures of information and entropy. In: Proceedings of the 4th Berkeley Symposium on Mathematics, Statistics and Probability, pp. 547\u2013561 (1960)"},{"issue":"8","key":"2_CR27","doi-asserted-by":"publisher","first-page":"2677","DOI":"10.1073\/pnas.0813249106","volume":"106","author":"G.E. Sims","year":"2009","unstructured":"Sims, G.E., Jun, S.R., Wu, G.A., Kim, S.H.: Alignment-free genome comparison with feature frequency profiles (ffp) and optimal resolutions. Proceedings of the National Academy of Sciences\u00a0106(8), 2677\u20132682 (2009)","journal-title":"Proceedings of the National Academy of Sciences"},{"issue":"1","key":"2_CR28","doi-asserted-by":"publisher","first-page":"191","DOI":"10.1016\/0304-3975(92)90143-4","volume":"92","author":"E. Ukkonen","year":"1992","unstructured":"Ukkonen, E.: Approximate string matching with q-grams and maximal matches. Theor. Comput. Sci.\u00a092(1), 191\u2013211 (1992)","journal-title":"Theor. Comput. Sci."},{"issue":"3","key":"2_CR29","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1007\/BF01206331","volume":"14","author":"E. Ukkonen","year":"1995","unstructured":"Ukkonen, E.: On-line construction of suffix trees. Algorithmica\u00a014(3), 249\u2013260 (1995)","journal-title":"Algorithmica"},{"issue":"2","key":"2_CR30","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1089\/cmb.2006.13.336","volume":"13","author":"I. Ulitsky","year":"2006","unstructured":"Ulitsky, I., Burstein, D., Tuller, T., Chor, B.: The average common substring approach to phylogenetic reconstruction. Journal of Computational Biology\u00a013(2), 336\u2013350 (2006)","journal-title":"Journal of Computational Biology"},{"key":"2_CR31","doi-asserted-by":"publisher","first-page":"206","DOI":"10.1093\/bioinformatics\/btg392","volume":"20","author":"S. Vinga","year":"2004","unstructured":"Vinga, S., Almeida, J.: Alignment-free sequence comparison \u2013 a review. Bioinformatics\u00a020, 206\u2013215 (2004)","journal-title":"Bioinformatics"},{"key":"2_CR32","volume-title":"Probability, Statistics and Truth","author":"R. Mises von","year":"1939","unstructured":"von Mises, R.: Probability, Statistics and Truth. MacMillan, Basingstoke (1939)"},{"key":"2_CR33","doi-asserted-by":"publisher","first-page":"1431","DOI":"10.2307\/2533509","volume":"53","author":"T.J. Wu","year":"1997","unstructured":"Wu, T.J., Bruke, J., Davison, D.: A measure of DNA dissimilarity based on the mahalanobis distance between frequencies of words. Biometrics\u00a053, 1431\u20131439 (1997)","journal-title":"Biometrics"},{"issue":"3","key":"2_CR34","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1109\/TIT.1977.1055714","volume":"23","author":"J. Ziv","year":"1977","unstructured":"Ziv, J., Lempel, A.: A universal algorithm for sequential data compression. IEEE Transactions on Information Theory\u00a023(3), 337\u2013343 (1977)","journal-title":"IEEE Transactions on Information Theory"}],"container-title":["Lecture Notes in Computer Science","Algorithms and Applications"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-12476-1_2.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T02:54:28Z","timestamp":1606186468000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-12476-1_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2010]]},"ISBN":["9783642124754","9783642124761"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-12476-1_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2010]]}}}