{"id":"https://openalex.org/W3134677442","doi":"https://doi.org/10.1145/3445967","title":"Data Structures to Represent a Set of <i>k</i> -long DNA Sequences","display_name":"Data Structures to Represent a Set of <i>k</i> -long DNA Sequences","publication_year":2021,"publication_date":"2021-03-08","ids":{"openalex":"https://openalex.org/W3134677442","doi":"https://doi.org/10.1145/3445967","mag":"3134677442","pmid":"https://pubmed.ncbi.nlm.nih.gov/41798316"},"language":"en","primary_location":{"id":"doi:10.1145/3445967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445967","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445967","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3445967","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058310668","display_name":"Rayan Chikhi","orcid":"https://orcid.org/0000-0003-1099-8735"},"institutions":[{"id":"https://openalex.org/I4210133830","display_name":"Laboratoire d\u2019immunologie int\u00e9grative du cancer","ror":"https://ror.org/03cqwn895","country_code":"FR","type":"facility","lineage":["https://openalex.org/I154526488","https://openalex.org/I154526488","https://openalex.org/I204730241","https://openalex.org/I204730241","https://openalex.org/I39804081","https://openalex.org/I39804081","https://openalex.org/I4210092322","https://openalex.org/I4210133830"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Rayan Chikhi","raw_affiliation_strings":["Center of Bioinformatics and Biostatistics and Integrative Biology, Paris, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center of Bioinformatics and Biostatistics and Integrative Biology, Paris, France","institution_ids":["https://openalex.org/I4210133830"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030676152","display_name":"Jan Holub","orcid":"https://orcid.org/0000-0003-3022-2694"},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Jan Holub","raw_affiliation_strings":["Department of Theoretical Computer Science, Czech Technical University in Prague, Th\u00e1kurova, Prague"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Theoretical Computer Science, Czech Technical University in Prague, Th\u00e1kurova, Prague","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066909672","display_name":"Paul Medvedev","orcid":"https://orcid.org/0000-0003-3143-594X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paul Medvedev","raw_affiliation_strings":["Center for Computational Biology and Bioinformatics, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Computational Biology and Bioinformatics, PA, USA","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":3.8861,"has_fulltext":true,"cited_by_count":42,"citation_normalized_percentile":{"value":0.94174594,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"54","issue":"1","first_page":"1","last_page":"22"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9970999956130981,"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":0.9952999949455261,"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":0.8430067300796509},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.6280679702758789},{"id":"https://openalex.org/keywords/field","display_name":"Field (mathematics)","score":0.5533820390701294},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4904443919658661},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.48362603783607483},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4668358564376831},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.45713767409324646},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.45539090037345886},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.4489636719226837},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4333254098892212},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4125511944293976},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.370233416557312},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.19057732820510864},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.14356040954589844},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.08300444483757019}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8430067300796509},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.6280679702758789},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.5533820390701294},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4904443919658661},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.48362603783607483},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4668358564376831},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.45713767409324646},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.45539090037345886},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.4489636719226837},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4333254098892212},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4125511944293976},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.370233416557312},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.19057732820510864},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.14356040954589844},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.08300444483757019},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3445967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445967","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445967","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmid:41798316","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41798316","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":"ACM computing surveys","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:12965495","is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC12965495/","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":"ACM Comput Surv","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1145/3445967","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3445967","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3445967","source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1106789989","display_name":"Y Chromosome Evolution","funder_award_id":"5r01gm130691-04","funder_id":"https://openalex.org/F4320332161","funder_display_name":"National Institutes of Health"},{"id":"https://openalex.org/G1433495602","display_name":null,"funder_award_id":"R01 GM130691","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"},{"id":"https://openalex.org/G1660658834","display_name":"Cryptic Speciation in Acanthocyclops Vernalis Complex (Crustacea: Copepoda): the Hypothesized Role of Chromatin Diminution","funder_award_id":"0000765","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2039187732","display_name":"ABI Innovation: A Novel Framework for Detecting Genomic Structural Variation","funder_award_id":"1356529","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G3426846984","display_name":"III: Small: Reconstructing viral population without using a reference genome","funder_award_id":"1421908","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G4106800444","display_name":"CAREER: De Novo Assembly of Large Genomic Data","funder_award_id":"1453527","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G5196283127","display_name":"Institut Convergences pour l\u2019\u00e9tude de l\u2019Emergence des Pathologies au Travers des Individus et des populatiONs","funder_award_id":"ANR-16-CONV-0005","funder_id":"https://openalex.org/F4320320883","funder_display_name":"Agence Nationale de la Recherche"},{"id":"https://openalex.org/G5641063287","display_name":null,"funder_award_id":"CZ.02.1.01","funder_id":"https://openalex.org/F4320321005","funder_display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320310419","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231"},{"id":"https://openalex.org/F4320320883","display_name":"Agence Nationale de la Recherche","ror":"https://ror.org/00rbzpz17"},{"id":"https://openalex.org/F4320321005","display_name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a T\u011blov\u00fdchovy","ror":"https://ror.org/037n8p820"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320334253","display_name":"Research Center for Informatics, Czech Technical University in Prague","ror":null},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3134677442.pdf","grobid_xml":"https://content.openalex.org/works/W3134677442.grobid-xml"},"referenced_works_count":81,"referenced_works":["https://openalex.org/W6247929","https://openalex.org/W62638829","https://openalex.org/W80321102","https://openalex.org/W1813440684","https://openalex.org/W1822485921","https://openalex.org/W1850079471","https://openalex.org/W1949346071","https://openalex.org/W1964377951","https://openalex.org/W1967373117","https://openalex.org/W1974033543","https://openalex.org/W1993284846","https://openalex.org/W2005228765","https://openalex.org/W2010361633","https://openalex.org/W2018866650","https://openalex.org/W2023797161","https://openalex.org/W2035198268","https://openalex.org/W2046594687","https://openalex.org/W2051511420","https://openalex.org/W2057223122","https://openalex.org/W2074633331","https://openalex.org/W2076747312","https://openalex.org/W2102532874","https://openalex.org/W2102660041","https://openalex.org/W2107082304","https://openalex.org/W2108640362","https://openalex.org/W2111295912","https://openalex.org/W2116435146","https://openalex.org/W2120902911","https://openalex.org/W2123845384","https://openalex.org/W2126540423","https://openalex.org/W2133531097","https://openalex.org/W2136986825","https://openalex.org/W2144560237","https://openalex.org/W2147935317","https://openalex.org/W2156658871","https://openalex.org/W2158322625","https://openalex.org/W2159954944","https://openalex.org/W2179064901","https://openalex.org/W2179933869","https://openalex.org/W2266239166","https://openalex.org/W2278452282","https://openalex.org/W2303656007","https://openalex.org/W2312729946","https://openalex.org/W2406547600","https://openalex.org/W2438121987","https://openalex.org/W2500932352","https://openalex.org/W2517241835","https://openalex.org/W2563930566","https://openalex.org/W2589379462","https://openalex.org/W2592760774","https://openalex.org/W2612838847","https://openalex.org/W2613660619","https://openalex.org/W2729314544","https://openalex.org/W2735897904","https://openalex.org/W2759261668","https://openalex.org/W2773939681","https://openalex.org/W2788348538","https://openalex.org/W2795650864","https://openalex.org/W2809649683","https://openalex.org/W2884435343","https://openalex.org/W2887897252","https://openalex.org/W2895034650","https://openalex.org/W2913847081","https://openalex.org/W2949074212","https://openalex.org/W2951157731","https://openalex.org/W2951550973","https://openalex.org/W2952379095","https://openalex.org/W2954511508","https://openalex.org/W2969627863","https://openalex.org/W2979522844","https://openalex.org/W2994050678","https://openalex.org/W2994991294","https://openalex.org/W2999275798","https://openalex.org/W3000185529","https://openalex.org/W3103672149","https://openalex.org/W3123160398","https://openalex.org/W3124656689","https://openalex.org/W3183881215","https://openalex.org/W4240899876","https://openalex.org/W4247794781","https://openalex.org/W6947873881"],"related_works":["https://openalex.org/W2062195135","https://openalex.org/W2795079307","https://openalex.org/W2793058541","https://openalex.org/W2170356069","https://openalex.org/W3118638206","https://openalex.org/W1983629434","https://openalex.org/W4324271173","https://openalex.org/W1967645776","https://openalex.org/W2352227742","https://openalex.org/W1528771269"],"abstract_inverted_index":{"The":[0,16],"analysis":[1,27],"of":[2,9,13,28,62,95],"biological":[3],"sequencing":[4],"data":[5,97],"has":[6,53,65],"been":[7,101],"one":[8],"the":[10,26,72,96,123,129,136],"biggest":[11],"applications":[12,22,69],"string":[14],"algorithms.":[15],"approaches":[17,42,81],"used":[18],"in":[19,37,78,122],"many":[20,79],"such":[21],"are":[23,32,43],"based":[24],"on":[25],"k":[29,50,63,108],"-mers,":[30],"which":[31],"short":[33],"fixed-length":[34],"strings":[35],"present":[36],"a":[38,49,56,90,107,118],"dataset.":[39],"While":[40],"these":[41],"rather":[44],"diverse,":[45],"storing":[46],"and":[47,68,93,105],"querying":[48],"-mer":[51,109],"set":[52,61],"emerged":[54],"as":[55,117,125,127],"shared":[57],"underlying":[58],"component.":[59],"A":[60],"-mers":[64],"unique":[66],"features":[67],"that,":[70],"over":[71],"past":[73],"10":[74],"years,":[75],"have":[76,100],"resulted":[77],"specialized":[80],"for":[82,120],"its":[83],"representation.":[84],"In":[85],"this":[86,113],"survey,":[87],"we":[88],"give":[89],"unified":[91],"presentation":[92],"comparison":[94],"structures":[98],"that":[99],"proposed":[102],"to":[103,133],"store":[104],"query":[106],"set.":[110],"We":[111],"hope":[112],"survey":[114],"will":[115],"serve":[116],"resource":[119],"researchers":[121,134],"field":[124],"well":[126],"make":[128],"area":[130],"more":[131],"accessible":[132],"outside":[135],"field.":[137]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":8},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
