{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T04:43:52Z","timestamp":1743137032788,"version":"3.40.3"},"publisher-location":"Cham","reference-count":16,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030791209"},{"type":"electronic","value":"9783030791216"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-79121-6_15","type":"book-chapter","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T17:04:20Z","timestamp":1624381460000},"page":"178-189","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Approximate Hashing for Bioinformatics"],"prefix":"10.1007","author":[{"given":"Guy","family":"Arbitman","sequence":"first","affiliation":[]},{"given":"Shmuel T.","family":"Klein","sequence":"additional","affiliation":[]},{"given":"Pierre","family":"Peterlongo","sequence":"additional","affiliation":[]},{"given":"Dana","family":"Shapira","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,23]]},"reference":[{"issue":"2","key":"15_CR1","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1016\/S0196-6774(03)00097-X","volume":"50","author":"A Amir","year":"2004","unstructured":"Amir, A., Lewenstein, M., Porat, E.: Faster algorithms for string matching with $$k$$ mismatches. J. Algorithms 50(2), 257\u2013275 (2004)","journal-title":"J. Algorithms"},{"key":"15_CR2","doi-asserted-by":"crossref","unstructured":"Aronovich, L., Asher, R., Bachmat, E., Bitner, H., Hirsch, M., Klein, S.T.: The design of a similarity based deduplication system. In: Proceedings of SYSTOR, p. 6 (2009)","DOI":"10.1145\/1534530.1534539"},{"key":"15_CR3","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1016\/j.dam.2015.09.018","volume":"212","author":"L Aronovich","year":"2016","unstructured":"Aronovich, L., Asher, R., Harnik, D., Hirsch, M., Klein, S.T., Toaff, Y.: Similarity based deduplication with small data chunks. Discret. Appl. Math. 212, 10\u201322 (2016)","journal-title":"Discret. Appl. Math."},{"issue":"3","key":"15_CR4","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1007\/s004530010062","volume":"29","author":"MJ Atallah","year":"2001","unstructured":"Atallah, M.J., Chyzak, F., Dumas, P.: A randomized algorithm for approximate string matching. Algorithmica 29(3), 468\u2013486 (2001). https:\/\/doi.org\/10.1007\/s004530010062","journal-title":"Algorithmica"},{"key":"15_CR5","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1186\/s12859-015-0875-7","volume":"17","author":"VB Dubinkina","year":"2016","unstructured":"Dubinkina, V.B., Ischenko, D.S., Ulyantsev, V.I., Tyakht, A.V., Alexeev, D.G.: Assessment of $$k$$-mer spectrum applicability for metagenomic dissimilarity analysis. BMC Bioinform. 17, 38 (2016)","journal-title":"BMC Bioinform."},{"issue":"D1","key":"15_CR6","doi-asserted-by":"publisher","first-page":"D802","DOI":"10.1093\/nar\/gkx1011","volume":"46","author":"PJ Kersey","year":"2017","unstructured":"Kersey, P.J., et al.: Ensembl Genomes 2018: an integrated omics infrastructure for non-vertebrate species. Nucleic Acids Res. 46(D1), D802\u2013D808 (2017)","journal-title":"Nucleic Acids Res."},{"key":"15_CR7","unstructured":"Hirsch, M., Bitner, H., Aronovich, L., Asher, R., Bachmat, E., Klein, S.T.: Systems and methods for efficient data searching, storage and reduction, U.S. Patent 7,523,098, issued 21 April 2009"},{"key":"15_CR8","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1177\/117693430600200016","volume":"2","author":"M H\u00f6hl","year":"2006","unstructured":"H\u00f6hl, M., Rigoutsos, I., Ragan, M.: Pattern-based phylogenetic distance estimation and tree reconstruction. Evol. Bioinform. Online 2, 359\u201375 (2006)","journal-title":"Evol. Bioinform. Online"},{"key":"15_CR9","doi-asserted-by":"crossref","unstructured":"Indyk, P., Motwani, R.: Approximate nearest neighbors: towards removing the curse of dimensionality. In: Proceedings of the 30th STOC, pp. 604\u2013613 (1998)","DOI":"10.1145\/276698.276876"},{"key":"15_CR10","doi-asserted-by":"crossref","unstructured":"James, B.T., Girgis, H.Z.: MeShClust$$^2$$: application of alignment-free identity scores in clustering long DNA sequences. bioRxiv, 451278 (2018)","DOI":"10.1101\/451278"},{"issue":"2","key":"15_CR11","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1147\/rd.312.0249","volume":"31","author":"RM Karp","year":"1987","unstructured":"Karp, R.M., Rabin, M.O.: Efficient randomized pattern-matching algorithms. IBM J. Res. Dev. 31(2), 249\u2013260 (1987)","journal-title":"IBM J. Res. Dev."},{"issue":"13","key":"15_CR12","doi-asserted-by":"publisher","first-page":"1658","DOI":"10.1093\/bioinformatics\/btl158","volume":"22","author":"W Li","year":"2006","unstructured":"Li, W., Godzik, A.: cd-hit: a fast program for clustering and comparing large sets of protein or nucleotide sequences. Bioinformatics 22(13), 1658\u20131659 (2006)","journal-title":"Bioinformatics"},{"key":"15_CR13","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1186\/s13015-015-0032-x","volume":"10","author":"B Morgenstern","year":"2015","unstructured":"Morgenstern, B., Zhu, B., Horwege, S., Leimeister, C.: Estimating evolutionary distances between genomic sequences from spaced-word matches. Algorithms Mol. Biol. 10, 5 (2015). https:\/\/doi.org\/10.1186\/s13015-015-0032-x","journal-title":"Algorithms Mol. Biol."},{"key":"15_CR14","unstructured":"Quinlan, S., Dorward, S.: Venti: a new approach to archival storage. In: Proceedings of FAST 2002 Conference on File and Storage Technologies, pp. 89\u2013101 (2002)"},{"key":"15_CR15","first-page":"1","volume":"1321","author":"RL Rivest","year":"1992","unstructured":"Rivest, R.L.: The MD5 message-digest algorithm. RFC 1321, 1\u201321 (1992)","journal-title":"RFC"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: A new method for rapid genome classification, clustering, visualization, and novel taxa discovery from metagenome. BioRxiv, 812917 (2019)","DOI":"10.1101\/812917"}],"container-title":["Lecture Notes in Computer Science","Implementation and Application of Automata"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-79121-6_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T17:08:09Z","timestamp":1624381689000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-79121-6_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030791209","9783030791216"],"references-count":16,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-79121-6_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"23 June 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CIAA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Implementation and Application of Automata","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19 July 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 July 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"wia2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/wwwdb.informatik.uni-bremen.de\/ciaa2021\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"20","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}