{"id":"https://openalex.org/W3001026891","doi":"https://doi.org/10.1109/tcbb.2020.2968531","title":"An Ultra-Fast and Parallelizable Algorithm for Finding k-Mismatch Shortest Unique Substrings","display_name":"An Ultra-Fast and Parallelizable Algorithm for Finding k-Mismatch Shortest Unique Substrings","publication_year":2020,"publication_date":"2020-01-21","ids":{"openalex":"https://openalex.org/W3001026891","doi":"https://doi.org/10.1109/tcbb.2020.2968531","mag":"3001026891","pmid":"https://pubmed.ncbi.nlm.nih.gov/31985439"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2020.2968531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2968531","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5102954773","display_name":"Daniel R. Allen","orcid":"https://orcid.org/0000-0002-2331-928X"},"institutions":[{"id":"https://openalex.org/I4210149135","display_name":"Zillow Group (United States)","ror":"https://ror.org/03n86v874","country_code":"US","type":"company","lineage":["https://openalex.org/I4210149135"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Daniel R. Allen","raw_affiliation_strings":["Zillow Group, Seattle, WA, USA"],"raw_orcid":"https://orcid.org/0000-0002-2331-928X","affiliations":[{"raw_affiliation_string":"Zillow Group, Seattle, WA, USA","institution_ids":["https://openalex.org/I4210149135"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5049669178","display_name":"Sharma V. Thankachan","orcid":"https://orcid.org/0000-0002-6852-1035"},"institutions":[{"id":"https://openalex.org/I106165777","display_name":"University of Central Florida","ror":"https://ror.org/036nfer12","country_code":"US","type":"education","lineage":["https://openalex.org/I106165777"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sharma V. Thankachan","raw_affiliation_strings":["Department of Computer Science, University of Central Florida, Orlando, FL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Central Florida, Orlando, FL, USA","institution_ids":["https://openalex.org/I106165777"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5058084642","display_name":"Bojian Xu","orcid":"https://orcid.org/0000-0001-5642-6826"},"institutions":[{"id":"https://openalex.org/I159107703","display_name":"Eastern Washington University","ror":"https://ror.org/002g57a93","country_code":"US","type":"education","lineage":["https://openalex.org/I159107703"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bojian Xu","raw_affiliation_strings":["Department of Computer Science, Eastern Washington University, Cheney, WA, USA"],"raw_orcid":"https://orcid.org/0000-0001-5642-6826","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Eastern Washington University, Cheney, WA, USA","institution_ids":["https://openalex.org/I159107703"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.403,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69395225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"18","issue":"1","first_page":"138","last_page":"148"},"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9950000047683716,"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":0.9933000206947327,"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":0.9794002771377563},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6429895758628845},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.6193637847900391},{"id":"https://openalex.org/keywords/parallelizable-manifold","display_name":"Parallelizable manifold","score":0.6162125468254089},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5251474380493164},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5170979499816895},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.43422627449035645},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.4331910014152527},{"id":"https://openalex.org/keywords/simple","display_name":"Simple (philosophy)","score":0.4139050841331482},{"id":"https://openalex.org/keywords/implementation","display_name":"Implementation","score":0.41347530484199524},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.4005070924758911},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.25573426485061646},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2556302547454834}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.9794002771377563},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6429895758628845},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.6193637847900391},{"id":"https://openalex.org/C148047603","wikidata":"https://www.wikidata.org/wiki/Q1014612","display_name":"Parallelizable manifold","level":2,"score":0.6162125468254089},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5251474380493164},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5170979499816895},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.43422627449035645},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.4331910014152527},{"id":"https://openalex.org/C2780586882","wikidata":"https://www.wikidata.org/wiki/Q7520643","display_name":"Simple (philosophy)","level":2,"score":0.4139050841331482},{"id":"https://openalex.org/C26713055","wikidata":"https://www.wikidata.org/wiki/Q245962","display_name":"Implementation","level":2,"score":0.41347530484199524},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.4005070924758911},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.25573426485061646},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2556302547454834},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"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":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D004247","descriptor_name":"DNA","qualifier_ui":"Q000235","qualifier_name":"genetics","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":"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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2020.2968531","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2020.2968531","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043","2998-4165"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:31985439","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/31985439","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.6499999761581421}],"awards":[{"id":"https://openalex.org/G1536446692","display_name":"AF: Medium: Collaborative Research: Sequential and Parallel Algorithms for Approximate Sequence Matching with Applications to Computational Biology","funder_award_id":"1703489","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W212038867","https://openalex.org/W263816278","https://openalex.org/W296365942","https://openalex.org/W938539187","https://openalex.org/W1614203862","https://openalex.org/W1962019683","https://openalex.org/W1966552686","https://openalex.org/W1990061958","https://openalex.org/W2002204859","https://openalex.org/W2024147613","https://openalex.org/W2040322457","https://openalex.org/W2073921136","https://openalex.org/W2149098716","https://openalex.org/W2336925273","https://openalex.org/W2345969517","https://openalex.org/W2524597039","https://openalex.org/W2533248932","https://openalex.org/W2533951358","https://openalex.org/W2621569787","https://openalex.org/W2794525315","https://openalex.org/W2803612680","https://openalex.org/W2844403901","https://openalex.org/W2950025489","https://openalex.org/W6608611251","https://openalex.org/W6609742353","https://openalex.org/W6610526105","https://openalex.org/W6650585354","https://openalex.org/W6727341658","https://openalex.org/W6728921054","https://openalex.org/W6752823121"],"related_works":["https://openalex.org/W2051304374","https://openalex.org/W4286787697","https://openalex.org/W1505605100","https://openalex.org/W3043769852","https://openalex.org/W3210979406","https://openalex.org/W4308670360","https://openalex.org/W2950721324","https://openalex.org/W4200187525","https://openalex.org/W4230921427","https://openalex.org/W1970688438"],"abstract_inverted_index":{"This":[0],"paper":[1],"revisits":[2],"the$k$-mismatch":[3,21,333],"shortest":[4,80,305,334],"unique":[5,81,306,335],"substring":[6,24,82,307,336],"finding":[7,308,337],"problem":[8,25,338],"and":[9,29,95,236,290,301],"demonstrates":[10,96],"that":[11,87,141,180,221,297,332],"a":[12,39,51,118,191,252,269,278,329,355],"technique":[13,147],"recently":[14],"presented":[15],"in":[16,38,99,151,160,320],"the":[17,34,57,63,71,75,104,133,145,173,184,222,243,315,349],"context":[18],"of":[19,33,74,144,205,207,224,255,271,282,358],"solving":[20],"average":[22],"common":[23],"can":[26,148,266,339],"be":[27,149,234,340],"adapted":[28,146],"combined":[30],"with":[31,132,203,277],"parts":[32],"existing":[35],"solution,":[36],"resulting":[37,159],"new":[40,67,89,261,299,356],"algorithm":[41,90,303],"which":[42,61,285],"has":[43],"expected":[44,296],"time":[45,101,187],"complexity":[46,54,73],"of$O(n\\;\\log":[47],"\\!^{k}\\;{n})$,":[48],"while":[49,259],"maintaining":[50],"practical":[52,92,163,302],"space":[53],"at$O(kn)$,":[55],"where$n$is":[56],"string":[58],"length.":[59],"When$k&gt;0$,":[60],"is":[62,91,139,219,286,295],"hard":[64],"case,":[65],"our":[66,88,115],"proposal":[68],"significantly":[69,229],"improves":[70],"any-case$O(n^2)$time":[72],"prior":[76,105,134,245],"best":[77,106,135,244],"method":[78,116],"for$k$-mismatch":[79,304],"finding.":[83],"Experimental":[84],"study":[85],"shows":[86],"to":[93,103,129,250,312],"implement":[94],"significant":[97,142,162],"improvements":[98],"processing":[100,178,190,231,268],"compared":[102,128],"solution's":[107],"implementation":[108],"when$k$is":[109],"small":[110],"relative":[111],"to$n$.":[112],"For":[113,241],"example,":[114,168,242],"processes":[117],"200":[119],"KB":[120],"sample":[121,194,254,270],"DNA":[122,195,253],"sequence":[123,196],"with$k=1$in":[124,274],"just":[125],"0.18":[126],"seconds":[127,131,276],"174.37":[130],"solution.":[136],"Further,":[137],"it":[138,218],"observed":[140],"portions":[143],"executed":[150],"parallel,":[152],"using":[153,170,263,314],"two":[154],"different":[155],"simple":[156],"concurrency":[157],"models,":[158],"further":[161],"performance":[164],"improvement.":[165],"As":[166],"an":[167,199],"when":[169,189],"8":[171],"cores,":[172,265],"parallel":[174],"implementations":[175],"both":[176,287],"achieved":[177],"times":[179,232],"are":[181,209],"less":[182],"than$1/4$of":[183],"serial":[185],"implementation's":[186],"cost,":[188],"10":[192],"MB":[193],"with$k=2$.":[197],"In":[198],"age":[200],"where":[201],"instances":[202],"thousands":[204],"gigabytes":[206],"RAM":[208],"readily":[210],"available":[211,289],"for":[212,228,257],"use":[213],"through":[214],"Cloud":[215],"infrastructure":[216],"providers,":[217],"likely":[220],"trade-off":[223],"additional":[225],"memory":[226,280],"usage":[227,281],"improved":[230],"will":[233,309],"desirable":[235],"needed":[237],"by":[238],"many":[239],"users.":[240],"solution":[246],"may":[247],"spend":[248],"years":[249],"finish":[251,267],"200MB":[256],"any$k&gt;0$,":[258],"this":[260,272,298],"proposal,":[262],"24":[264],"size":[273],"206.376":[275],"peak":[279],"46":[283],"GB,":[284],"easily":[288],"affordable":[291],"on":[292,317],"Cloud.":[293],"It":[294],"efficient":[300],"prove":[310],"useful":[311],"those":[313],"measure":[316],"long":[318],"sequences":[319],"fields":[321],"such":[322],"as":[323,354],"computational":[324],"biology.":[325],"We":[326],"also":[327],"give":[328],"theoretical":[330],"bound":[331],"solved":[341],"using$O(n\\;\\log":[342],"\\!^{k}\\;{n})$time":[343],"and$O(n)$space,":[344],"asymptotically":[345],"much":[346],"better":[347],"than":[348],"one":[350],"we":[351],"implemented,":[352],"serving":[353],"discovery":[357],"interest.":[359]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":2}],"updated_date":"2026-08-06T08:24:18.245995","created_date":"2025-10-10T00:00:00"}
