{"id":"https://openalex.org/W2161048357","doi":"https://doi.org/10.1093/bioinformatics/btq217","title":"Efficient construction of an assembly string graph using the FM-index","display_name":"Efficient construction of an assembly string graph using the FM-index","publication_year":2010,"publication_date":"2010-06-01","ids":{"openalex":"https://openalex.org/W2161048357","doi":"https://doi.org/10.1093/bioinformatics/btq217","mag":"2161048357","pmid":"https://pubmed.ncbi.nlm.nih.gov/20529929"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btq217","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq217","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/12/i367/48859513/bioinformatics_26_12_i367.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/26/12/i367/48859513/bioinformatics_26_12_i367.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003935660","display_name":"Jared T. Simpson","orcid":"https://orcid.org/0000-0002-2116-2602"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Jared T. Simpson","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge, CB10 1SA, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082040351","display_name":"Richard Durbin","orcid":"https://orcid.org/0000-0002-9130-1006"},"institutions":[{"id":"https://openalex.org/I2802476451","display_name":"Wellcome Sanger Institute","ror":"https://ror.org/05cy4wa09","country_code":"GB","type":"nonprofit","lineage":["https://openalex.org/I2802476451","https://openalex.org/I87048295"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Richard Durbin","raw_affiliation_strings":["Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge, CB10 1SA, UK"],"affiliations":[{"raw_affiliation_string":"Wellcome Trust Sanger Institute, Wellcome Trust Genome Campus, Cambridge, CB10 1SA, UK","institution_ids":["https://openalex.org/I2802476451"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5003935660"],"corresponding_institution_ids":["https://openalex.org/I2802476451"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":8.8101,"has_fulltext":true,"cited_by_count":258,"citation_normalized_percentile":{"value":0.98575887,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"26","issue":"12","first_page":"i367","last_page":"i373"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9998000264167786,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9977999925613403,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9912999868392944,"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/de-bruijn-graph","display_name":"De Bruijn graph","score":0.7315579652786255},{"id":"https://openalex.org/keywords/de-bruijn-sequence","display_name":"De Bruijn sequence","score":0.7177581787109375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6229914426803589},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.5626144409179688},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5498266220092773},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5303041934967041},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.5099993944168091},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.4885154962539673},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.4743322730064392},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.47298964858055115},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.45701199769973755},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4267578125},{"id":"https://openalex.org/keywords/compressed-suffix-array","display_name":"Compressed suffix array","score":0.4161486327648163},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3947994112968445},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2432277500629425},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.2234957218170166},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.21563595533370972},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.18026596307754517},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.13834452629089355}],"concepts":[{"id":"https://openalex.org/C20218877","wikidata":"https://www.wikidata.org/wiki/Q3066095","display_name":"De Bruijn graph","level":3,"score":0.7315579652786255},{"id":"https://openalex.org/C170320093","wikidata":"https://www.wikidata.org/wiki/Q1953457","display_name":"De Bruijn sequence","level":2,"score":0.7177581787109375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6229914426803589},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.5626144409179688},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5498266220092773},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5303041934967041},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.5099993944168091},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.4885154962539673},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.4743322730064392},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.47298964858055115},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.45701199769973755},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4267578125},{"id":"https://openalex.org/C100903775","wikidata":"https://www.wikidata.org/wiki/Q5157028","display_name":"Compressed suffix array","level":4,"score":0.4161486327648163},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3947994112968445},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2432277500629425},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.2234957218170166},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.21563595533370972},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.18026596307754517},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.13834452629089355},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D023281","descriptor_name":"Genomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btq217","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq217","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/12/i367/48859513/bioinformatics_26_12_i367.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:20529929","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20529929","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:2881401","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2881401","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btq217","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btq217","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/12/i367/48859513/bioinformatics_26_12_i367.pdf","source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320311904","display_name":"Wellcome Trust","ror":"https://ror.org/029chgv08"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2161048357.pdf","grobid_xml":"https://content.openalex.org/works/W2161048357.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W938539187","https://openalex.org/W1826264422","https://openalex.org/W1850079471","https://openalex.org/W1966822396","https://openalex.org/W1969173824","https://openalex.org/W1976682045","https://openalex.org/W1990061958","https://openalex.org/W2000484009","https://openalex.org/W2023911006","https://openalex.org/W2077333702","https://openalex.org/W2097341408","https://openalex.org/W2103441770","https://openalex.org/W2114133992","https://openalex.org/W2118703123","https://openalex.org/W2119279650","https://openalex.org/W2124985265","https://openalex.org/W2136651963","https://openalex.org/W2139749722","https://openalex.org/W2141850746","https://openalex.org/W2151017710","https://openalex.org/W2156104322","https://openalex.org/W2158322625","https://openalex.org/W2160969485","https://openalex.org/W2161488606","https://openalex.org/W2477408078","https://openalex.org/W4247053599","https://openalex.org/W6621160150","https://openalex.org/W6650339521","https://openalex.org/W6680367870","https://openalex.org/W6683030939","https://openalex.org/W6683504902"],"related_works":["https://openalex.org/W2120956621","https://openalex.org/W2915362964","https://openalex.org/W3215786367","https://openalex.org/W3205360317","https://openalex.org/W2562683361","https://openalex.org/W4214573178","https://openalex.org/W3200242814","https://openalex.org/W4282946044","https://openalex.org/W4200364103","https://openalex.org/W2296788912"],"abstract_inverted_index":{"Standard":[0],"overlap":[1],"assembly":[2,85,116],"methods":[3,86],"have":[4],"time":[5,78],"complexity":[6],"O(N(2)),":[7],"where":[8],"N":[9],"is":[10],"the":[11,14,17,21,27,68,101,112],"sum":[12],"of":[13,16,33,41,82],"lengths":[15],"reads.":[18,42],"We":[19],"use":[20],"Ferragina-Manzini":[22],"index":[23],"(FM-index)":[24],"derived":[25],"from":[26],"Burrows-Wheeler":[28],"transform":[29],"to":[30,56,64,79,118,123],"find":[31],"overlaps":[32,51],"length":[34,90],"at":[35],"least":[36],"tau":[37],"among":[38],"a":[39,58],"set":[40],"As":[43],"well":[44],"as":[45],"an":[46],"approach":[47],"that":[48,121],"finds":[49],"all":[50],"then":[52],"implements":[53],"transitive":[54],"reduction":[55],"produce":[57],"string":[59],"graph,":[60],"we":[61,108],"show":[62],"how":[63],"output":[65],"directly":[66],"only":[67],"irreducible":[69],"overlaps,":[70],"significantly":[71],"shrinking":[72],"memory":[73],"requirements":[74],"and":[75],"reducing":[76],"compute":[77],"O(N),":[80],"independent":[81],"depth.":[83],"Overlap-based":[84],"naturally":[87],"handle":[88],"mixed":[89],"read":[91],"sets,":[92],"including":[93],"capillary":[94],"reads":[95,98],"or":[96],"long":[97],"promised":[99],"by":[100],"third":[102],"generation":[103],"sequencing":[104],"technologies.":[105],"The":[106],"algorithms":[107],"present":[109],"here":[110],"pave":[111],"way":[113],"for":[114],"overlap-based":[115],"approaches":[117],"be":[119],"developed":[120],"scale":[122],"whole":[124],"vertebrate":[125],"genome":[126],"de":[127],"novo":[128],"assembly.":[129]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":8},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":26},{"year":2018,"cited_by_count":14},{"year":2017,"cited_by_count":22},{"year":2016,"cited_by_count":27},{"year":2015,"cited_by_count":21},{"year":2014,"cited_by_count":20},{"year":2013,"cited_by_count":24},{"year":2012,"cited_by_count":27}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
