{"id":"https://openalex.org/W2155490398","doi":"https://doi.org/10.1093/database/bap013","title":"Differential direct coding: a compression algorithm for nucleotide sequence data","display_name":"Differential direct coding: a compression algorithm for nucleotide sequence data","publication_year":2009,"publication_date":"2009-01-01","ids":{"openalex":"https://openalex.org/W2155490398","doi":"https://doi.org/10.1093/database/bap013","mag":"2155490398","pmid":"https://pubmed.ncbi.nlm.nih.gov/20157486"},"language":"en","primary_location":{"id":"doi:10.1093/database/bap013","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bap013","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bap013/16728567/bap013.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bap013/16728567/bap013.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5087832269","display_name":"Gregory Vey","orcid":"https://orcid.org/0000-0003-1574-1373"},"institutions":[{"id":"https://openalex.org/I75381157","display_name":"Wilfrid Laurier University","ror":"https://ror.org/00fn7gb05","country_code":"CA","type":"education","lineage":["https://openalex.org/I75381157"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Gregory Vey","raw_affiliation_strings":["Department of Biology, Wilfrid Laurier University, 75 University Avenue West, Waterloo ON, Canada N2L 3C5"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biology, Wilfrid Laurier University, 75 University Avenue West, Waterloo ON, Canada N2L 3C5","institution_ids":["https://openalex.org/I75381157"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5087832269"],"corresponding_institution_ids":["https://openalex.org/I75381157"],"apc_list":{"value":1415,"currency":"GBP","value_usd":1735},"apc_paid":{"value":1415,"currency":"GBP","value_usd":1735},"fwci":2.6105,"has_fulltext":true,"cited_by_count":17,"citation_normalized_percentile":{"value":0.91426458,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"2009","issue":null,"first_page":"bap013","last_page":"bap013"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9976999759674072,"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/T12029","display_name":"DNA and Biological Computing","score":0.987500011920929,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.772598147392273},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.6634637117385864},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6043565273284912},{"id":"https://openalex.org/keywords/coding","display_name":"Coding (social sciences)","score":0.4690554440021515},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.42715656757354736},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4138796329498291},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3978120684623718},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36101555824279785},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11958149075508118}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.772598147392273},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.6634637117385864},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6043565273284912},{"id":"https://openalex.org/C179518139","wikidata":"https://www.wikidata.org/wiki/Q5140297","display_name":"Coding (social sciences)","level":2,"score":0.4690554440021515},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.42715656757354736},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4138796329498291},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3978120684623718},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36101555824279785},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11958149075508118},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/database/bap013","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bap013","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bap013/16728567/bap013.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},{"id":"pmid:20157486","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20157486","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,"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":"Database : the journal of biological databases and curation","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:2797453","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2797453","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Database (Oxford)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/database/bap013","is_oa":true,"landing_page_url":"https://doi.org/10.1093/database/bap013","pdf_url":"https://academic.oup.com/database/article-pdf/doi/10.1093/database/bap013/16728567/bap013.pdf","source":{"id":"https://openalex.org/S4210201630","display_name":"Database","issn_l":"1758-0463","issn":["1758-0463"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311647","host_organization_name":"University of Oxford","host_organization_lineage":["https://openalex.org/P4310311647"],"host_organization_lineage_names":["University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Database","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2155490398.pdf","grobid_xml":"https://content.openalex.org/works/W2155490398.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W224821934","https://openalex.org/W1482763047","https://openalex.org/W1528514765","https://openalex.org/W1532892811","https://openalex.org/W1572929865","https://openalex.org/W1588594383","https://openalex.org/W1970231722","https://openalex.org/W2004941704","https://openalex.org/W2012680439","https://openalex.org/W2022690669","https://openalex.org/W2060108852","https://openalex.org/W2094995159","https://openalex.org/W2107745473","https://openalex.org/W2108781775","https://openalex.org/W2113601822","https://openalex.org/W2115019748","https://openalex.org/W2122962290","https://openalex.org/W2146028503","https://openalex.org/W2147492358","https://openalex.org/W2294475439","https://openalex.org/W2593831237","https://openalex.org/W4240231372","https://openalex.org/W6628932382","https://openalex.org/W6681790542"],"related_works":["https://openalex.org/W2112284452","https://openalex.org/W3085798047","https://openalex.org/W2374269412","https://openalex.org/W371123309","https://openalex.org/W2085500676","https://openalex.org/W2186272223","https://openalex.org/W2365096715","https://openalex.org/W2012817876","https://openalex.org/W4287666945","https://openalex.org/W595097604"],"abstract_inverted_index":{"While":[0],"modern":[1],"hardware":[2],"can":[3,75,124,146,243],"provide":[4,150],"vast":[5],"amounts":[6],"of":[7,15,21,47,51,87,94,97,120,143,158,165,170,180,202,235],"inexpensive":[8],"storage":[9],"for":[10,182,189,251],"biological":[11],"databases,":[12],"the":[13,48,64,85,95,141,155,168,200,232,238],"compression":[14,72,108],"nucleotide":[16,71,99],"sequence":[17,78,114,219],"data":[18,54,79,82,128,192,198],"is":[19,205],"still":[20],"paramount":[22],"importance":[23],"in":[24,36,45,177],"order":[25],"to":[26,115,149,208],"facilitate":[27],"fast":[28],"search":[29],"and":[30,80,106,129,173,254],"retrieval":[31],"operations":[32],"through":[33],"a":[34,69,113,117,162,178,211,245],"reduction":[35],"disk":[37,249],"traffic.":[38],"This":[39,110],"issue":[40],"becomes":[41],"even":[42],"more":[43],"important":[44],"light":[46],"recent":[49],"increase":[50],"very":[52,190],"large":[53,191],"sets,":[55],"such":[56,132],"as":[57,133,210],"metagenomes.":[58],"In":[59,139],"this":[60,186,195],"article,":[61],"I":[62],"propose":[63],"Differential":[65,239],"Direct":[66,240],"Coding":[67,241],"algorithm,":[68],"general-purpose":[70,107],"protocol":[73],"that":[74,90,123,153],"differentiate":[76],"between":[77,104],"auxiliary":[81,121],"by":[83],"supporting":[84,161],"inclusion":[86],"supplementary":[88],"symbols":[89,122,166],"are":[91],"not":[92],"members":[93],"set":[96,164],"expected":[98],"bases,":[100],"thereby":[101,230],"offering":[102],"reconciliation":[103],"sequence-specific":[105],"strategies.":[109],"algorithm":[111,187,196,242],"permits":[112],"contain":[116],"rich":[118],"lexicon":[119],"represent":[125],"wildcards,":[126],"annotation":[127],"special":[130,137,144],"subsequences,":[131],"functional":[134],"domains":[135],"or":[136],"repeats.":[138],"particular,":[140],"representation":[142],"subsequences":[145],"be":[147,221],"incorporated":[148],"structure-based":[151],"coding":[152],"increases":[154],"overall":[156],"degree":[157,234],"compression.":[159,236],"Moreover,":[160],"robust":[163],"removes":[167],"requirement":[169],"wildcard":[171],"elimination":[172],"restoration":[174],"phases,":[175],"resulting":[176],"complexity":[179],"O(n)":[181],"execution":[183],"time,":[184],"making":[185],"suitable":[188],"sets.":[193],"Because":[194],"compresses":[197],"on":[199,248],"basis":[201],"triplets,":[203],"it":[204],"highly":[206],"amenable":[207],"interpretation":[209],"polypeptide":[212],"at":[213],"decompression":[214],"time.":[215],"Also,":[216],"an":[217],"encoded":[218],"may":[220],"further":[222],"compressed":[223],"using":[224],"other":[225,255],"existing":[226],"algorithms,":[227],"like":[228],"gzip,":[229],"maximizing":[231],"final":[233],"Overall,":[237],"offer":[244],"beneficial":[246],"impact":[247],"traffic":[250],"database":[252],"queries":[253],"disk-intensive":[256],"operations.":[257]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}