{"id":"https://openalex.org/W1496422306","doi":null,"title":"Biological sequence compression algorithms.","display_name":"Biological sequence compression algorithms.","publication_year":2000,"publication_date":"2000-01-01","ids":{"openalex":"https://openalex.org/W1496422306","mag":"1496422306","pmid":"https://pubmed.ncbi.nlm.nih.gov/11700586"},"language":"en","primary_location":{"id":"pmid:11700586","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11700586","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome informatics. Workshop on Genome Informatics","raw_type":"Journal Article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5027256693","display_name":"Takashi Matsumoto","orcid":"https://orcid.org/0000-0002-5274-2669","observed_orcids":["https://orcid.org/0000-0002-5274-2669"]},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"T Matsumoto","raw_affiliation_strings":["Department of Information Science, University of Tokyo,7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, Japan. toshikom@is.s.u-tokyo.ac.jp"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Information Science, University of Tokyo,7-3-1 Hongo, Bunkyo-ku, Tokyo 113-0033, Japan. toshikom@is.s.u-tokyo.ac.jp","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077610103","display_name":"Kunihiko Sadakane","orcid":"https://orcid.org/0000-0002-8212-3682","observed_orcids":["https://orcid.org/0000-0002-8212-3682"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"K Sadakane","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":null,"display_name":"H Imai","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H Imai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.1953,"has_fulltext":false,"cited_by_count":132,"citation_normalized_percentile":{"value":0.71641791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"11","issue":null,"first_page":"43","last_page":"52"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":1.0,"subfield":{"id":"https://openalex.org/subfields/2614","display_name":"Theoretical Computer Science"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10901","display_name":"Advanced Data Compression Techniques","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/dna-sequence-compression","display_name":"DNA sequence compression","score":0.8970000147819519},{"id":"https://openalex.org/keywords/context-tree-weighting","display_name":"context tree weighting","score":0.9399999976158142},{"id":"https://openalex.org/keywords/palindromes","display_name":"palindromes","score":0.9639999866485596},{"id":"https://openalex.org/keywords/reverse-complement","display_name":"reverse complement","score":0.8489999771118164},{"id":"https://openalex.org/keywords/hash-tables","display_name":"hash tables","score":0.46700000762939453},{"id":"https://openalex.org/keywords/dynamic-programming","display_name":"dynamic programming","score":0.949999988079071},{"id":"https://openalex.org/keywords/compression-ratio","display_name":"compression ratio","score":0.6470000147819519},{"id":"https://openalex.org/keywords/biological-sequence-databases","display_name":"biological sequence databases","score":0.7009999752044678}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987455487251282},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6976708173751831},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6197648048400879},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5072516798973083},{"id":"https://openalex.org/C44667518","wikidata":"https://www.wikidata.org/wiki/Q12321","display_name":"Palindrome","level":4,"score":0.5025746822357178},{"id":"https://openalex.org/C134400042","wikidata":"https://www.wikidata.org/wiki/Q2372244","display_name":"Symbol (formal)","level":2,"score":0.4899875223636627},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4643557071685791},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4433457553386688},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4245196282863617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3802603483200073},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.3693295121192932},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1641097068786621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11826881766319275},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.11254271864891052},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C98108389","wikidata":"https://www.wikidata.org/wiki/Q412563","display_name":"CRISPR","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030561","descriptor_name":"Databases, Nucleic Acid","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":4,"locations":[{"id":"pmid:11700586","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11700586","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Genome informatics. Workshop on Genome Informatics","raw_type":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.21.3908","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.21.3908","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.jsbi.org/journal/GIW00/GIW00F05.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.26.5013","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.26.5013","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://masamune.dais.is.tohoku.ac.jp/~sada/papers/MatSadIma00.ps.gz","raw_type":"text"},{"id":"mag:1496422306","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/11700586","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"PubMed","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1510807444","https://openalex.org/W1970231722","https://openalex.org/W1980569719","https://openalex.org/W2038180954","https://openalex.org/W2161628678","https://openalex.org/W2163294786","https://openalex.org/W2166127198"],"related_works":["https://openalex.org/W345075761","https://openalex.org/W2108278098","https://openalex.org/W2012680439","https://openalex.org/W2144514096","https://openalex.org/W7098206803","https://openalex.org/W2506946498","https://openalex.org/W1979405897","https://openalex.org/W2147144569","https://openalex.org/W7096996102","https://openalex.org/W2552510699"],"abstract_inverted_index":{"Today,":[0],"more":[1,3],"and":[2,22,30,119,172,176,198],"DNA":[4,12,67,86,108,130,157],"sequences":[5,13,87,109,131,158],"are":[6,14,110,159],"becoming":[7],"available.":[8,160],"The":[9,20,56],"information":[10,37],"about":[11],"stored":[15,40],"in":[16,32,73],"molecular":[17],"biology":[18],"databases.":[19],"size":[21],"importance":[23],"of":[24,101,107,156,215],"these":[25,134],"databases":[26],"will":[27],"be":[28,39,48],"bigger":[29,31],"the":[33,76,120,150,163,166],"future,":[34],"therefore":[35],"this":[36,146,202],"must":[38],"or":[41,63,116,184],"communicated":[42],"efficiently.":[43],"Furthermore,":[44],"sequence":[45],"compression":[46,58,211,218,224],"can":[47,84,136],"used":[49],"to":[50],"define":[51],"similarities":[52],"between":[53],"biological":[54,102],"sequences.":[55,103,228],"standard":[57],"algorithms":[59,95,128],"such":[60],"as":[61],"gzip":[62],"compress":[64,66,85,137],"cannot":[65],"sequences,":[68],"but":[69],"only":[70],"expand":[71],"them":[72,138],"size.":[74],"On":[75],"other":[77,121],"hand,":[78],"CTW":[79,151],"(Context":[80],"Tree":[81],"Weighting":[82],"Method)":[83],"less":[88,139],"than":[89,140,213],"two":[90,141],"bits":[91,142],"per":[92,143],"symbol.":[93,144],"These":[94],"do":[96],"not":[97],"use":[98,133],"special":[99],"structures":[100,106,135,155],"Two":[104],"characteristic":[105,154],"known.":[111],"One":[112],"is":[113,123,181],"called":[114],"palindromes":[115],"reverse":[117],"complements":[118],"structure":[122],"approximate":[124,170,186],"repeats.":[125],"Several":[126],"specific":[127],"for":[129,226],"that":[132,153,214],"In":[145],"paper,":[147],"we":[148],"improve":[149],"so":[152],"Before":[161],"encoding":[162],"next":[164],"symbol,":[165],"algorithm":[167,193,225],"searches":[168],"an":[169,185],"repeat":[171,187],"palindrome":[173,183],"using":[174,201],"hash":[175],"dynamic":[177],"programming.":[178],"If":[179],"there":[180],"a":[182,204,208],"with":[188,196],"enough":[189],"length":[190,197],"then":[191],"our":[192],"represents":[194],"it":[195],"distance.":[199],"By":[200],"preprocessing,":[203],"new":[205,223],"program":[206],"achieves":[207],"little":[209],"higher":[210],"ratio":[212],"existing":[216],"DNA-oriented":[217],"algorithms.":[219],"We":[220],"also":[221],"describe":[222],"protein":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":6},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":7},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":11},{"year":2014,"cited_by_count":8},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":8}],"updated_date":"2026-11-03T10:50:19.383937","created_date":"2016-06-24T00:00:00"}