{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,10]],"date-time":"2026-11-10T19:38:25Z","timestamp":1794339505858,"version":"4.9.0"},"publisher-location":"Berlin, Heidelberg","reference-count":29,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"value":"9783540333470","type":"print"},{"value":"9783540333487","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2006]]},"DOI":"10.1007\/11735106_38","type":"book-chapter","created":{"date-parts":[[2006,3,13]],"date-time":"2006-03-13T01:58:59Z","timestamp":1142215139000},"page":"432-443","source":"Crossref","is-referenced-by-count":2,"title":["Fast Discovery of Similar Sequences in Large Genomic Collections"],"prefix":"10.1007","author":[{"given":"Yaniv","family":"Bernstein","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Cameron","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","reference":[{"issue":"3","key":"38_CR1","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1016\/S0022-2836(05)80360-2","volume":"215","author":"S. Altschul","year":"1990","unstructured":"Altschul, S., Gish, W., Miller, W., Myers, E., Lipman, D.: Basic local alignment search tool. Journal of Molecular Biology\u00a0215(3), 403\u2013410 (1990)","journal-title":"Journal of Molecular Biology"},{"issue":"17","key":"38_CR2","doi-asserted-by":"publisher","first-page":"3389","DOI":"10.1093\/nar\/25.17.3389","volume":"25","author":"S. Altschul","year":"1997","unstructured":"Altschul, S., Madden, T., Schaffer, A., Zhang, J., Zhang, Z., Miller, W., Lipman, D.: Gapped BLAST and PSI\u2013BLAST: A new generation of protein database search programs. Nucleic Acids Research\u00a025(17), 3389\u20133402 (1997)","journal-title":"Nucleic Acids Research"},{"key":"38_CR3","volume-title":"Proc. String Processing and Information Retrieval Symposium (SPIRE)","author":"Y. Bernstein","year":"2004","unstructured":"Bernstein, Y., Zobel, J.: A scalable system for identifying co-derivative documents. In: Apostolico, A., Melucci, M. (eds.) Proc. String Processing and Information Retrieval Symposium (SPIRE), Padova, Italy. Springer, Heidelberg (2004)"},{"key":"38_CR4","first-page":"736","volume-title":"Proc. CIKM conference","author":"Y. Bernstein","year":"2005","unstructured":"Bernstein, Y., Zobel, J.: Redundant documents and search effectiveness. In: Chowdhury, A., Fuhr, N., Ronthaler, M., Schek, H., Teiken, W. (eds.) Proc. CIKM conference, Bremen, Germany, pp. 736\u2013743. ACM Press, New York (2005)"},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Brin, S., Davis, J., Garc\u00b4\u0131a-Molina, H.: Copy detection mechanisms for digital documents. In: Proceedings of the ACM SIGMOD Annual Conference, pp. 398\u2013409 (1995)","DOI":"10.1145\/223784.223855"},{"issue":"8-13","key":"38_CR6","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1016\/S0169-7552(97)00031-7","volume":"29","author":"A.Z. Broder","year":"1997","unstructured":"Broder, A.Z., Glassman, S.C., Manasse, M.S., Zweig, G.: Syntactic clustering of the web. Computer Networks and ISDN Systems\u00a029(8-13), 1157\u20131166 (1997)","journal-title":"Computer Networks and ISDN Systems"},{"key":"38_CR7","first-page":"33","volume-title":"Proc. ACM SIGIR conference","author":"C. Buckley","year":"2000","unstructured":"Buckley, C., Voorhees, E.M.: Evaluating evaluation measure stability. In: Proc. ACM SIGIR conference, pp. 33\u201340. ACM Press, New York (2000)"},{"issue":"11","key":"38_CR8","doi-asserted-by":"publisher","first-page":"1135","DOI":"10.1101\/gr.9.11.1135","volume":"9","author":"J. Burke","year":"1999","unstructured":"Burke, J., Davison, D., Hide, W.: d2 cluster: A validated method for clustering EST and full-length DNA sequences. Genome Research\u00a09(11), 1135\u20131142 (1999)","journal-title":"Genome Research"},{"issue":"3","key":"38_CR9","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1109\/TCBB.2004.32","volume":"1","author":"M. Cameron","year":"2004","unstructured":"Cameron, M., Williams, H.E., Cannane, A.: Improved gapped alignment in BLAST. IEEE Transactions on Computational Biology and Bioinformatics\u00a01(3), 116\u2013129 (2004)","journal-title":"IEEE Transactions on Computational Biology and Bioinformatics"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Cameron, M., Williams, H.E., Cannane, A.: A deterministic finite automaton for faster protein hit detection in BLAST. Journal of Computational Biology (2005) (to appear)","DOI":"10.1089\/cmb.2006.13.965"},{"key":"38_CR11","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1093\/nar\/gkh034","volume":"32","author":"J. Chandonia","year":"2004","unstructured":"Chandonia, J., Hon, G., Walker, N., Conte, L.L., Koehl, P., Levitt, M., Brenner, S.: The ASTRAL compendium in 2004. Nucleic Acids Research\u00a032, D189\u2013D192 (2004)","journal-title":"Nucleic Acids Research"},{"issue":"5","key":"38_CR12","first-page":"481","volume":"8","author":"K. Chao","year":"1992","unstructured":"Chao, K., Pearson, W., Miller, W.: Aligning two sequences within a specified diagonal band. Computer Applications in the Biosciences\u00a08(5), 481\u2013487 (1992)","journal-title":"Computer Applications in the Biosciences"},{"key":"38_CR13","first-page":"37","volume-title":"Proc. 1st Latin American Web Congress","author":"D. Fetterly","year":"2003","unstructured":"Fetterly, D., Manasse, M., Najork, M.: On the evolution of clusters of near-duplicate web pages. In: Baeza-Yates, R. (ed.) Proc. 1st Latin American Web Congress, pp. 37\u201345. IEEE, Santiago (2003)"},{"key":"38_CR14","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1145\/335305.335351","volume-title":"STOC 2000: Proceedings of the thirty-second annual ACM symposium on Theory of computing","author":"R. Grossi","year":"2000","unstructured":"Grossi, R., Vitter, J.S.: Compressed suffix arrays and suffix trees with applications to text indexing and string matching (extended abstract). In: STOC 2000: Proceedings of the thirty-second annual ACM symposium on Theory of computing, pp. 397\u2013406. ACM Press, New York (2000)"},{"key":"38_CR15","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9780511574931","volume-title":"Algorithms on Strings, Trees, and Sequences","author":"D. Gusfield","year":"1997","unstructured":"Gusfield, D.: Algorithms on Strings, Trees, and Sequences. Cambridge University Press, Cambridge (1997)"},{"key":"38_CR16","unstructured":"Heintze, N.: Scalable document fingerprinting. In: 1996 USENIX Workshop on Electronic Commerce (1996)"},{"issue":"5","key":"38_CR17","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1093\/bioinformatics\/14.5.423","volume":"14","author":"L. Holm","year":"1998","unstructured":"Holm, L., Sander, C.: Removing near-neighbour redundancy from large protein sequence collections. Bioinformatics\u00a014(5), 423\u2013429 (1998)","journal-title":"Bioinformatics"},{"key":"38_CR18","doi-asserted-by":"crossref","unstructured":"Kurtz, S., Phillippy, A., Delcher, A., Smoot, M., Shumway, M., Antonescu, C., Salzberg, S.: Versatile and open software for comparing large genomes. Genome Biology\u00a05(2) (2004)","DOI":"10.1186\/gb-2004-5-2-r12"},{"issue":"3","key":"38_CR19","doi-asserted-by":"publisher","first-page":"282","DOI":"10.1093\/bioinformatics\/17.3.282","volume":"17","author":"W. Li","year":"2001","unstructured":"Li, W., Jaroszewski, L., Godzik, A.: Clustering of highly homologous sequences to reduce the size of large protein databases. Bioinformatics\u00a017(3), 282\u2013283 (2001a)","journal-title":"Bioinformatics"},{"key":"38_CR20","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1093\/bioinformatics\/18.1.77","volume":"18","author":"W. Li","year":"2001","unstructured":"Li, W., Jaroszewski, L., Godzik, A.: Tolerating some redundancy significantly speeds up clustering of large protein databases. Bioinformatics\u00a018, 77\u201382 (2001b)","journal-title":"Bioinformatics"},{"issue":"8","key":"38_CR21","doi-asserted-by":"publisher","first-page":"643","DOI":"10.1093\/protein\/15.8.643","volume":"15","author":"W. Li","year":"2002","unstructured":"Li, W., Jaroszewski, L., Godzik, A.: Sequence clustering strategies improve remote homology recognitions while reducing search times. Protein Engineering\u00a015(8), 643\u2013649 (2002)","journal-title":"Protein Engineering"},{"issue":"10","key":"38_CR22","doi-asserted-by":"publisher","first-page":"1221","DOI":"10.1093\/bioinformatics\/btg138","volume":"19","author":"K. Malde","year":"2003","unstructured":"Malde, K., Coward, E., Jonassen, I.: Fast sequence clustering using a suffix array algorithm. Bioinformatics\u00a019(10), 1221\u20131226 (2003)","journal-title":"Bioinformatics"},{"key":"38_CR23","unstructured":"Manber, U.: Finding similar files in a large file system, in Proceedings of the USENIX Winter, Technical Conference, San Fransisco, CA, USA, pp. 1\u201310 (1994)"},{"issue":"5","key":"38_CR24","doi-asserted-by":"publisher","first-page":"935","DOI":"10.1137\/0222058","volume":"22","author":"U. Manber","year":"1993","unstructured":"Manber, U., Myers, G.: Suffix arrays: a new method for on-line string searches. SIAM Journal on Computing\u00a022(5), 935\u2013948 (1993)","journal-title":"SIAM Journal on Computing"},{"issue":"5","key":"38_CR25","doi-asserted-by":"publisher","first-page":"458","DOI":"10.1093\/bioinformatics\/16.5.458","volume":"16","author":"J. Park","year":"2000","unstructured":"Park, J., Holm, L., Heger, A., Chothia, C.: RSDB: representative sequence databases have high information content. Bioinformatics\u00a016(5), 458\u2013464 (2000)","journal-title":"Bioinformatics"},{"issue":"8","key":"38_CR26","doi-asserted-by":"publisher","first-page":"2444","DOI":"10.1073\/pnas.85.8.2444","volume":"85","author":"W. Pearson","year":"1988","unstructured":"Pearson, W., Lipman, D.: Improved tools for biological sequence comparison. Proceedings of the National Academy of Sciences USA\u00a085(8), 2444\u20132448 (1988)","journal-title":"Proceedings of the National Academy of Sciences USA"},{"key":"38_CR27","volume-title":"WEBDB: International Workshop on the World Wide Web and Databases, WebDB","author":"N. Shivakumar","year":"1999","unstructured":"Shivakumar, N., Garc\u00eda-Molina, H.: Finding near-replicas of documents on the web. In: WEBDB: International Workshop on the World Wide Web and Databases, WebDB. Springer, Heidelberg (1999)"},{"issue":"1","key":"38_CR28","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/0022-2836(81)90087-5","volume":"147","author":"T. Smith","year":"1981","unstructured":"Smith, T., Waterman, M.: Identification of common molecular subsequences. Journal of Molecular Biology\u00a0147(1), 195\u2013197 (1981)","journal-title":"Journal of Molecular Biology"},{"key":"38_CR29","volume-title":"Managing Gigabytes: Compressing and Indexing Documents and Images","author":"I.H. Witten","year":"1999","unstructured":"Witten, I.H., Moffat, A., Bell, T.C.: Managing Gigabytes: Compressing and Indexing Documents and Images. Morgan Kauffman, San Francisco (1999)"}],"container-title":["Lecture Notes in Computer Science","Advances in Information Retrieval"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/11735106_38.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,4,27]],"date-time":"2021-04-27T02:53:41Z","timestamp":1619492021000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/11735106_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006]]},"ISBN":["9783540333470","9783540333487"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/11735106_38","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/11735106","asserted-by":"object"}]},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2006]]}}}