{"id":"https://openalex.org/W2090847868","doi":"https://doi.org/10.1109/bibmw.2012.6470220","title":"On the repetitive collection indexing problem","display_name":"On the repetitive collection indexing problem","publication_year":2012,"publication_date":"2012-10-01","ids":{"openalex":"https://openalex.org/W2090847868","doi":"https://doi.org/10.1109/bibmw.2012.6470220","mag":"2090847868"},"language":"en","primary_location":{"id":"doi:10.1109/bibmw.2012.6470220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2012.6470220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","raw_type":"proceedings-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/A5024456936","display_name":"Ali Alatabbi","orcid":"https://orcid.org/0000-0003-4761-3544"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ali Alatabbi","raw_affiliation_strings":["Department of Informatics, Kings College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Kings College London, London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039166412","display_name":"Carl Barton","orcid":"https://orcid.org/0000-0001-6938-9446"},"institutions":[{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Carl Barton","raw_affiliation_strings":["Department of Informatics, Kings College London, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Kings College London, London, UK","institution_ids":["https://openalex.org/I183935753"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058155947","display_name":"Costas S. Iliopoulos","orcid":"https://orcid.org/0000-0003-3909-0077"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]},{"id":"https://openalex.org/I183935753","display_name":"King's College London","ror":"https://ror.org/0220mzb33","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I183935753"]},{"id":"https://openalex.org/I205640436","display_name":"Curtin University","ror":"https://ror.org/02n415q13","country_code":"AU","type":"education","lineage":["https://openalex.org/I205640436"]}],"countries":["AU","GB"],"is_corresponding":false,"raw_author_name":"Costas S. Iliopoulos","raw_affiliation_strings":["Department of Informatics, Kings College London, London, UK","Department of Mathematics and Statistics, University of Western Australia, Perth, Australia","Digital Ecosystems and Business Intelligence Institute, Curtin University, Perth, WA, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Informatics, Kings College London, London, UK","institution_ids":["https://openalex.org/I183935753"]},{"raw_affiliation_string":"Department of Mathematics and Statistics, University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"Digital Ecosystems and Business Intelligence Institute, Curtin University, Perth, WA, Australia","institution_ids":["https://openalex.org/I205640436"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.8846,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.80272653,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"682","last_page":"687"},"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9955000281333923,"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":0.9925000071525574,"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":0.7388685941696167},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6859909296035767},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.6725568771362305},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.564373254776001},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5475647449493408},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5350692272186279},{"id":"https://openalex.org/keywords/section","display_name":"Section (typography)","score":0.5133451819419861},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5093365907669067},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.41569846868515015},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.399684876203537},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.37231019139289856},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12024569511413574},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.0791727602481842}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7388685941696167},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6859909296035767},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.6725568771362305},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.564373254776001},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5475647449493408},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5350692272186279},{"id":"https://openalex.org/C2780129039","wikidata":"https://www.wikidata.org/wiki/Q1931107","display_name":"Section (typography)","level":2,"score":0.5133451819419861},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5093365907669067},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.41569846868515015},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.399684876203537},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.37231019139289856},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12024569511413574},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0791727602481842},{"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/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibmw.2012.6470220","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibmw.2012.6470220","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2012 IEEE International Conference on Bioinformatics and Biomedicine Workshops","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1490635997","https://openalex.org/W1498437305","https://openalex.org/W1938985178","https://openalex.org/W1972418517","https://openalex.org/W1995303482","https://openalex.org/W2001496424","https://openalex.org/W2043481183","https://openalex.org/W2043748616","https://openalex.org/W2045716015","https://openalex.org/W2096375120","https://openalex.org/W2144948334","https://openalex.org/W2978725006","https://openalex.org/W6681194010"],"related_works":["https://openalex.org/W2560853036","https://openalex.org/W2566696415","https://openalex.org/W1563787543","https://openalex.org/W4239980664","https://openalex.org/W3024364549","https://openalex.org/W4249026152","https://openalex.org/W4231213805","https://openalex.org/W4244585678","https://openalex.org/W2909241626","https://openalex.org/W2890304493"],"abstract_inverted_index":{"In":[0,105,126,166],"large":[1,11,41],"data":[2,18,44,101,119,178],"sets":[3,12,99],"such":[4,73,98],"as":[5,150],"genomes":[6,86],"from":[7,28],"a":[8,31,40,46,61,90,122],"single":[9],"species,":[10],"of":[13,35,43,49,67,100,117,175,198],"reads,":[14],"and":[15,51,81,96,154,160,172,186,193],"version":[16],"control":[17],"it":[19],"is":[20,148],"often":[21],"noted":[22],"that":[23,83,133],"each":[24],"entry":[25],"only":[26],"differs":[27],"another":[29],"by":[30],"very":[32],"small":[33],"number":[34],"variations.":[36],"This":[37],"leads":[38],"to":[39,142],"set":[42],"with":[45,72,140],"great":[47],"deal":[48],"redundancy":[50],"repetitiveness.":[52],"Rapid":[53],"development":[54],"in":[55,64,136,183],"DNA":[56,75],"sequencing":[57,76,84],"technologies":[58],"has":[59,77],"caused":[60],"drastic":[62],"growth":[63],"the":[65,128,137,143,157,163,176],"size":[66],"publicly":[68],"available":[69],"sequence":[70,118,139],"databases":[71],"data.":[74],"become":[78,89],"so":[79],"fast":[80],"cost-effective":[82],"individual":[85],"will":[87,180],"soon":[88],"common":[91],"task":[92],"[9]":[93],"making":[94],"querying":[95],"storing":[97],"an":[102,110],"important":[103],"task.":[104],"this":[106],"paper,":[107],"we":[108,169],"propose":[109],"indexing":[111],"structure":[112],"for":[113],"highly":[114],"repetitive":[115],"collections":[116],"based":[120],"on":[121],"multilevel":[123],"g-gram":[124],"model.":[125],"particular,":[127],"proposed":[129,177],"algorithm":[130],"accommodates":[131],"variations":[132],"may":[134],"occur":[135],"target":[138],"respect":[141],"reference":[144],"sequence.":[145],"The":[146],"paper":[147],"organized":[149],"follows.":[151],"Section":[152,167,184,188,194],"[1]":[153],"[2]":[155],"introduce":[156],"basic":[158],"concepts":[159],"go":[161],"through":[162],"related":[164],"literature.":[165],"[3]":[168],"present":[170],"notions":[171],"facts.":[173],"Details":[174],"structure/algorithm":[179],"be":[181],"given":[182],"[5]":[185],"[4],":[187],"[6]":[189],"discusses":[190],"complexity":[191],"analysis":[192],"[7]":[195],"gives":[196],"conclusions":[197],"future":[199],"work.":[200]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}
