{"id":"https://openalex.org/W2105378773","doi":"https://doi.org/10.1186/1748-7188-3-13","title":"Fast algorithms for computing sequence distances by exhaustive substring composition","display_name":"Fast algorithms for computing sequence distances by exhaustive substring composition","publication_year":2008,"publication_date":"2008-10-28","ids":{"openalex":"https://openalex.org/W2105378773","doi":"https://doi.org/10.1186/1748-7188-3-13","mag":"2105378773","pmid":"https://pubmed.ncbi.nlm.nih.gov/18957094"},"language":"en","primary_location":{"id":"doi:10.1186/1748-7188-3-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-3-13","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-3-13","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-3-13","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5029039590","display_name":"Alberto Apostolico","orcid":null},"institutions":[{"id":"https://openalex.org/I2801187332","display_name":"Accademia Nazionale dei Lincei","ror":"https://ror.org/05wfehw39","country_code":"IT","type":"other","lineage":["https://openalex.org/I2801187332"]},{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]},{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT","US"],"is_corresponding":true,"raw_author_name":"Alberto Apostolico","raw_affiliation_strings":["Academia Nazionale dei Lincei, Rome, Italy. axa@cc.gatech.edu","College of Computing, Georgia Institute of Technology, Atlanta, USA","Department of Information Engineering, Universit\u00e1 di Padova, Padova, Italy","Academia Nazionale dei Lincei, Rome, Italy"],"affiliations":[{"raw_affiliation_string":"Academia Nazionale dei Lincei, Rome, Italy. axa@cc.gatech.edu","institution_ids":["https://openalex.org/I2801187332"]},{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"Department of Information Engineering, Universit\u00e1 di Padova, Padova, Italy","institution_ids":["https://openalex.org/I138689650"]},{"raw_affiliation_string":"Academia Nazionale dei Lincei, Rome, Italy","institution_ids":["https://openalex.org/I2801187332"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085879157","display_name":"Olgert Denas","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Olgert Denas","raw_affiliation_strings":["College of Computing, Georgia Institute of Technology, Atlanta, Georgia, USA","College of Computing, Georgia Inst. of Technology, Atlanta, USA"],"affiliations":[{"raw_affiliation_string":"College of Computing, Georgia Institute of Technology, Atlanta, Georgia, USA","institution_ids":["https://openalex.org/I130701444"]},{"raw_affiliation_string":"College of Computing, Georgia Inst. of Technology, Atlanta, USA","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029039590"],"corresponding_institution_ids":["https://openalex.org/I130701444","https://openalex.org/I138689650","https://openalex.org/I2801187332"],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":5.3142,"has_fulltext":true,"cited_by_count":24,"citation_normalized_percentile":{"value":0.95316247,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"3","issue":"1","first_page":"13","last_page":"13"},"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9987999796867371,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9984999895095825,"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/substring","display_name":"Substring","score":0.953107476234436},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6798341274261475},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.6705707907676697},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5978149771690369},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.5649220943450928},{"id":"https://openalex.org/keywords/phylogenetic-tree","display_name":"Phylogenetic tree","score":0.5416257381439209},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5073122382164001},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5063601732254028},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5063303709030151},{"id":"https://openalex.org/keywords/k-mer","display_name":"k-mer","score":0.4704384207725525},{"id":"https://openalex.org/keywords/extension","display_name":"Extension (predicate logic)","score":0.4553232491016388},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.44229161739349365},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.44078847765922546},{"id":"https://openalex.org/keywords/composition","display_name":"Composition (language)","score":0.42197349667549133},{"id":"https://openalex.org/keywords/alignment-free-sequence-analysis","display_name":"Alignment-free sequence analysis","score":0.41363096237182617},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36408549547195435},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.28929346799850464},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.285767525434494},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.26739731431007385},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.18261095881462097},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.16435164213180542},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13335224986076355},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0917762815952301},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08922028541564941}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.953107476234436},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6798341274261475},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.6705707907676697},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5978149771690369},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.5649220943450928},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.5416257381439209},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5073122382164001},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5063601732254028},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5063303709030151},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.4704384207725525},{"id":"https://openalex.org/C2778029271","wikidata":"https://www.wikidata.org/wiki/Q5421931","display_name":"Extension (predicate logic)","level":2,"score":0.4553232491016388},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.44229161739349365},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.44078847765922546},{"id":"https://openalex.org/C40231798","wikidata":"https://www.wikidata.org/wiki/Q1333743","display_name":"Composition (language)","level":2,"score":0.42197349667549133},{"id":"https://openalex.org/C180384323","wikidata":"https://www.wikidata.org/wiki/Q16335137","display_name":"Alignment-free sequence analysis","level":5,"score":0.41363096237182617},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36408549547195435},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.28929346799850464},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.285767525434494},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.26739731431007385},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.18261095881462097},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.16435164213180542},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13335224986076355},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0917762815952301},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08922028541564941},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/1748-7188-3-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-3-13","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-3-13","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:18957094","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/18957094","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":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:doaj.org/article:4ae260ea5e4a4b2a9514304ca1644b1e","is_oa":true,"landing_page_url":"https://doaj.org/article/4ae260ea5e4a4b2a9514304ca1644b1e","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 3, Iss 1, p 13 (2008)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:2615014","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/2615014","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms Mol Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1748-7188-3-13","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-3-13","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-3-13","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2105378773.pdf","grobid_xml":"https://content.openalex.org/works/W2105378773.grobid-xml"},"referenced_works_count":27,"referenced_works":["https://openalex.org/W616447529","https://openalex.org/W1485516007","https://openalex.org/W1513153538","https://openalex.org/W1971239653","https://openalex.org/W1973243276","https://openalex.org/W1975136411","https://openalex.org/W1992649154","https://openalex.org/W2005097301","https://openalex.org/W2006290495","https://openalex.org/W2008386840","https://openalex.org/W2015696044","https://openalex.org/W2045895701","https://openalex.org/W2077770566","https://openalex.org/W2099111195","https://openalex.org/W2103502708","https://openalex.org/W2116988150","https://openalex.org/W2117825194","https://openalex.org/W2144221002","https://openalex.org/W2144575079","https://openalex.org/W2166162901","https://openalex.org/W2171963266","https://openalex.org/W2591373418","https://openalex.org/W2596773272","https://openalex.org/W2746710705","https://openalex.org/W2797574228","https://openalex.org/W4239545644","https://openalex.org/W4298849694"],"related_works":["https://openalex.org/W2411730464","https://openalex.org/W2051304374","https://openalex.org/W3043769852","https://openalex.org/W4286787697","https://openalex.org/W1505605100","https://openalex.org/W4291327800","https://openalex.org/W4308670360","https://openalex.org/W2950721324","https://openalex.org/W4200187525","https://openalex.org/W4230921427"],"abstract_inverted_index":{"The":[0,84,106,126],"increasing":[1],"throughput":[2],"of":[3,10,36,51,63,81,87,96,118,120,133,136],"sequencing":[4],"raises":[5],"growing":[6],"needs":[7,27],"for":[8],"methods":[9,122],"sequence":[11,37],"analysis":[12],"and":[13,39,44,53,70,76,115],"comparison":[14,132],"on":[15,59,103,130],"a":[16,49,79,111],"genomic":[17],"scale,":[18],"notably,":[19],"in":[20,67,78,123,139],"connection":[21],"with":[22],"phylogenetic":[23],"tree":[24],"reconstruction.":[25],"Such":[26],"are":[28,146],"hardly":[29],"fulfilled":[30],"by":[31],"the":[32,60,113,121,131,134,140,153],"more":[33],"traditional":[34],"measures":[35,89],"similarity":[38],"distance,":[40],"like":[41],"string":[42],"edit":[43],"gene":[45],"rearrangement,":[46],"due":[47],"to":[48,72,149],"mixture":[50],"epistemological":[52],"computational":[54,104],"problems.":[55],"Alternative":[56],"measures,":[57],"based":[58,129],"subword":[61],"composition":[62],"sequences,":[64,143],"have":[65],"emerged":[66],"recent":[68],"years":[69],"proved":[71],"be":[73],"both":[74],"fast":[75],"effective":[77],"variety":[80],"tested":[82],"cases.":[83],"common":[85],"denominator":[86],"such":[88],"is":[90,128],"an":[91],"underlying":[92],"information":[93],"theoretic":[94],"notion":[95],"relative":[97],"compressibility.":[98],"Their":[99],"viability":[100],"depends":[101],"critically":[102],"cost.":[105],"present":[107],"paper":[108],"describes":[109],"as":[110],"paradigm":[112],"extension":[114],"efficient":[116],"implementation":[117],"one":[119],"this":[124],"class.":[125],"method":[127],"frequencies":[135,145],"all":[137],"subwords":[138],"two":[141],"input":[142],"where":[144],"suitably":[147],"adjusted":[148],"take":[150],"into":[151],"account":[152],"statistical":[154],"background.":[155]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":3},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}