{"id":"https://openalex.org/W2904205944","doi":"https://doi.org/10.1109/tkde.2018.2885952","title":"VA-Store: A Virtual Approximate Store Approach to Supporting Repetitive Big Data in Genome Sequence Analyses","display_name":"VA-Store: A Virtual Approximate Store Approach to Supporting Repetitive Big Data in Genome Sequence Analyses","publication_year":2018,"publication_date":"2018-12-11","ids":{"openalex":"https://openalex.org/W2904205944","doi":"https://doi.org/10.1109/tkde.2018.2885952","mag":"2904205944"},"language":"en","primary_location":{"id":"doi:10.1109/tkde.2018.2885952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2885952","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"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/A5101804184","display_name":"Xianying Liu","orcid":"https://orcid.org/0000-0002-5658-5875"},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xianying Liu","raw_affiliation_strings":["Department of Computer and Information Science, University of Michigan - Dearborn, Dearborn, MI, USA","University of Michigan - Dearborn, Dearborn, USA"],"raw_orcid":"https://orcid.org/0000-0002-5658-5875","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Michigan - Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]},{"raw_affiliation_string":"University of Michigan - Dearborn, Dearborn, USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103136845","display_name":"Qiang Zhu","orcid":"https://orcid.org/0000-0001-7094-9236"},"institutions":[{"id":"https://openalex.org/I4210130704","display_name":"University of Michigan\u2013Dearborn","ror":"https://ror.org/035wtm547","country_code":"US","type":"education","lineage":["https://openalex.org/I4210130704"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qiang Zhu","raw_affiliation_strings":["Department of Computer and Information Science, University of Michigan - Dearborn, Dearborn, MI, USA","University of Michigan - Dearborn, Dearborn, USA"],"raw_orcid":"https://orcid.org/0000-0001-7094-9236","affiliations":[{"raw_affiliation_string":"Department of Computer and Information Science, University of Michigan - Dearborn, Dearborn, MI, USA","institution_ids":["https://openalex.org/I4210130704"]},{"raw_affiliation_string":"University of Michigan - Dearborn, Dearborn, USA","institution_ids":["https://openalex.org/I4210130704"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059755229","display_name":"Sakti Pramanik","orcid":null},"institutions":[{"id":"https://openalex.org/I87216513","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993","country_code":"US","type":"education","lineage":["https://openalex.org/I87216513"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sakti Pramanik","raw_affiliation_strings":["Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, USA","Michigan State University, East Lansing, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Michigan State University, East Lansing, MI, USA","institution_ids":["https://openalex.org/I87216513"]},{"raw_affiliation_string":"Michigan State University, East Lansing, USA","institution_ids":["https://openalex.org/I87216513"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036229691","display_name":"C. Titus Brown","orcid":"https://orcid.org/0000-0001-6001-2677"},"institutions":[{"id":"https://openalex.org/I84218800","display_name":"University of California, Davis","ror":"https://ror.org/05rrcem69","country_code":"US","type":"education","lineage":["https://openalex.org/I84218800"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Titus Brown","raw_affiliation_strings":["Genome Center, University of California, Davis, CA, USA","Genome Center, University of California, Davis, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Genome Center, University of California, Davis, CA, USA","institution_ids":["https://openalex.org/I84218800"]},{"raw_affiliation_string":"Genome Center, University of California, Davis, USA","institution_ids":["https://openalex.org/I84218800"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101785723","display_name":"Gang Qian","orcid":"https://orcid.org/0000-0002-2201-461X"},"institutions":[{"id":"https://openalex.org/I139325414","display_name":"University of Central Oklahoma","ror":"https://ror.org/02n455404","country_code":"US","type":"education","lineage":["https://openalex.org/I139325414"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gang Qian","raw_affiliation_strings":["Department of Computer Science, University of Central Oklahoma, Edmond, OK, USA","University of Central Oklahoma, Edmond, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Oklahoma, Edmond, OK, USA","institution_ids":["https://openalex.org/I139325414"]},{"raw_affiliation_string":"University of Central Oklahoma, Edmond, USA","institution_ids":["https://openalex.org/I139325414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5101804184"],"corresponding_institution_ids":["https://openalex.org/I4210130704"],"apc_list":null,"apc_paid":null,"fwci":0.5077,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.75141488,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":"32","issue":"3","first_page":"602","last_page":"616"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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":0.9994999766349792,"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.989300012588501,"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/computer-science","display_name":"Computer science","score":0.7760083675384521},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6839228868484497},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6004014015197754},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4962649941444397},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4693741798400879},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.4342536926269531},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39113518595695496},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3706379532814026},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34702998399734497},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11201167106628418}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7760083675384521},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6839228868484497},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6004014015197754},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4962649941444397},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4693741798400879},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4342536926269531},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39113518595695496},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3706379532814026},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34702998399734497},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11201167106628418},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tkde.2018.2885952","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tkde.2018.2885952","pdf_url":null,"source":{"id":"https://openalex.org/S30698027","display_name":"IEEE Transactions on Knowledge and Data Engineering","issn_l":"1041-4347","issn":["1041-4347","1558-2191","2326-3865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Knowledge and Data Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3622241812","display_name":null,"funder_award_id":"#IIS-1320078","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G6658052466","display_name":null,"funder_award_id":"#IIS-1319909","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320309652","display_name":"University of Michigan","ror":"https://ror.org/00jmfr291"},{"id":"https://openalex.org/F4320310016","display_name":"Michigan State University","ror":"https://ror.org/05hs6h993"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W126282444","https://openalex.org/W868336060","https://openalex.org/W1490635997","https://openalex.org/W1498437305","https://openalex.org/W1598134722","https://openalex.org/W1822485921","https://openalex.org/W1963994909","https://openalex.org/W1981420413","https://openalex.org/W2005349538","https://openalex.org/W2005533448","https://openalex.org/W2030063144","https://openalex.org/W2037444377","https://openalex.org/W2041391522","https://openalex.org/W2052039291","https://openalex.org/W2055043387","https://openalex.org/W2057253402","https://openalex.org/W2081930221","https://openalex.org/W2096128575","https://openalex.org/W2103014446","https://openalex.org/W2104677379","https://openalex.org/W2118526609","https://openalex.org/W2120902911","https://openalex.org/W2123837096","https://openalex.org/W2133531097","https://openalex.org/W2133956160","https://openalex.org/W2135631159","https://openalex.org/W2136145671","https://openalex.org/W2139099874","https://openalex.org/W2142678478","https://openalex.org/W2163830511","https://openalex.org/W2163932369","https://openalex.org/W2165093166","https://openalex.org/W2165480965","https://openalex.org/W2169413171","https://openalex.org/W2172031170","https://openalex.org/W2553985332","https://openalex.org/W2613949307","https://openalex.org/W2763390627","https://openalex.org/W4236236547","https://openalex.org/W6629219293","https://openalex.org/W6638588823","https://openalex.org/W6675441415","https://openalex.org/W6684112385","https://openalex.org/W6737983892","https://openalex.org/W6745193047"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4233347783","https://openalex.org/W2910064364","https://openalex.org/W4255224757","https://openalex.org/W4295068701"],"abstract_inverted_index":{"In":[0,43],"recent":[1],"years,":[2],"we":[3,46],"have":[4],"witnessed":[5],"an":[6],"increasing":[7],"demand":[8],"to":[9,54,167],"process":[10],"big":[11,33,201],"data":[12,27,34,62,202],"in":[13,28,63,185],"numerous":[14],"applications.":[15,207],"It":[16],"is":[17,182],"observed":[18],"that":[19,179],"there":[20],"often":[21],"exist":[22],"substantial":[23],"amounts":[24],"of":[25,31,73,89,107],"repetitive":[26,61,124,200],"different":[29],"portions":[30,106],"a":[32,48,83,129,133,195],"repository/dataset":[35],"for":[36,60,86,104,145,157,193,203],"applications":[37],"such":[38],"as":[39],"genome":[40,65,204],"sequence":[41,66,205],"analyses.":[42],"this":[44],"paper,":[45],"present":[47],"novel":[49],"method,":[50],"called":[51],"the":[52,56,90,108,126,142,180],"VA-Store,":[53],"reduce":[55],"large":[57],"space":[58],"requirement":[59],"prevailing":[64],"analysis":[67,206],"tasks":[68],"using":[69,173],"k-mers":[70,111],"(i.e.,":[71,93,110],"subsequences":[72],"length":[74],"k)":[75],"with":[76,112],"multiple":[77,101],"k":[78,94,113,115],"values.":[79],"The":[80],"VA-Store":[81,127,181],"maintains":[82],"physical":[84,143],"store":[85,135,144],"one":[87,137],"portion":[88],"input":[91],"dataset":[92,109],"<sub":[95,116],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[96,117],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">0</sub>":[97,118],"-mers)":[98],"and":[99,149,175,189],"supports":[100],"virtual":[102,134],"stores":[103],"other":[105],"\u2260":[114],").":[119],"Utilizing":[120],"important":[121],"relationships":[122],"among":[123],"data,":[125],"transforms":[128],"given":[130],"query":[131,169,191],"on":[132,141,199],"into":[136],"or":[138],"more":[139],"queries":[140],"execution.":[146],"Both":[147],"precise":[148],"approximate":[150,158],"transformations":[151],"are":[152,160,165],"considered.":[153],"Accuracy":[154],"estimation":[155],"models":[156],"solutions":[159],"derived.":[161],"Query":[162],"optimization":[163],"strategies":[164],"suggested":[166],"improve":[168],"performance.":[170],"Our":[171],"experiments":[172],"real":[174],"synthetic":[176],"datasets":[177],"demonstrate":[178],"quite":[183],"promising":[184],"providing":[186],"effective":[187],"storage":[188],"efficient":[190],"processing":[192],"solving":[194],"kernel":[196],"database":[197],"problem":[198]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-01-28T23:14:49.684275","created_date":"2025-10-10T00:00:00"}
