{"id":"https://openalex.org/W2807209975","doi":"https://doi.org/10.1109/tcbb.2018.2843364","title":"Efficient Algorithms for Finding the Closest l-Mers in Biological Data","display_name":"Efficient Algorithms for Finding the Closest l-Mers in Biological Data","publication_year":2018,"publication_date":"2018-06-04","ids":{"openalex":"https://openalex.org/W2807209975","doi":"https://doi.org/10.1109/tcbb.2018.2843364","mag":"2807209975","pmid":"https://pubmed.ncbi.nlm.nih.gov/29993557"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2018.2843364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2843364","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"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/A5013075695","display_name":"Xingyu Cai","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Xingyu Cai","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, CT"],"raw_orcid":"https://orcid.org/0000-0003-1537-7161","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, CT","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001504077","display_name":"Abdullah-Al Mamun","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Abdullah-Al Mamun","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, CT"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, CT","institution_ids":["https://openalex.org/I140172145"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5034177039","display_name":"Sanguthevar Rajasekaran","orcid":null},"institutions":[{"id":"https://openalex.org/I140172145","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97","country_code":"US","type":"education","lineage":["https://openalex.org/I140172145"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanguthevar Rajasekaran","raw_affiliation_strings":["Department of Computer Science and Engineering, University of Connecticut, Storrs, CT"],"raw_orcid":"https://orcid.org/0000-0002-0137-4843","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, University of Connecticut, Storrs, CT","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5013075695"],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.05939524,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"16","issue":"6","first_page":"1912","last_page":"1921"},"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":0.9934999942779541,"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/T13664","display_name":"Genome Rearrangement Algorithms","score":0.9919999837875366,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/hamming-distance","display_name":"Hamming distance","score":0.6499903202056885},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.5732641220092773},{"id":"https://openalex.org/keywords/biological-data","display_name":"Biological data","score":0.5728271007537842},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5615594983100891},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5604069828987122},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.36237579584121704},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.18494239449501038},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.1612142026424408}],"concepts":[{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.6499903202056885},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.5732641220092773},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.5728271007537842},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5615594983100891},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5604069828987122},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.36237579584121704},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.18494239449501038},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.1612142026424408},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","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":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030541","descriptor_name":"Databases, Genetic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2018.2843364","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2018.2843364","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"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:29993557","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/29993557","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","score":0.46000000834465027,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310017","display_name":"University of Connecticut","ror":"https://ror.org/02der9h97"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W167817876","https://openalex.org/W1513731586","https://openalex.org/W1580213736","https://openalex.org/W1602142193","https://openalex.org/W2006761268","https://openalex.org/W2023863508","https://openalex.org/W2049120089","https://openalex.org/W2057907879","https://openalex.org/W2059378307","https://openalex.org/W2107427524","https://openalex.org/W2120771433","https://openalex.org/W2136101247","https://openalex.org/W2206326344","https://openalex.org/W2525058782","https://openalex.org/W2583336059","https://openalex.org/W2584499795","https://openalex.org/W2775514595","https://openalex.org/W3120740533","https://openalex.org/W4250757898","https://openalex.org/W6634719314","https://openalex.org/W6727810314","https://openalex.org/W6788247690"],"related_works":["https://openalex.org/W2595172197","https://openalex.org/W2084856301","https://openalex.org/W2127970246","https://openalex.org/W2885125400","https://openalex.org/W1001352512","https://openalex.org/W1989889224","https://openalex.org/W4382618745","https://openalex.org/W1973775000","https://openalex.org/W2748922771","https://openalex.org/W1987128138"],"abstract_inverted_index":{"With":[0],"the":[1,4,46,53,66,82,97,102,127,135,159,167,191,226],"advances":[2],"in":[3,18,22,28,42,120,165],"next":[5],"generation":[6],"sequencing":[7],"technology,":[8],"huge":[9],"amounts":[10],"of":[11,72,84,88,150,193,211],"data":[12,44],"have":[13,162],"been":[14,163],"and":[15,78,126,182,213],"get":[16],"generated":[17],"biology.":[19],"A":[20],"bottleneck":[21],"dealing":[23],"with":[24,206],"such":[25,95,114,140],"datasets":[26],"lies":[27],"developing":[29],"effective":[30],"algorithms":[31,184],"for":[32,39,48,157,187,190,203],"extracting":[33,49],"useful":[34],"information":[35,51],"from":[36,52,92],"them.":[37],"Algorithms":[38,156],"finding":[40,89,158],"patterns":[41],"biological":[43,74],"pave":[45],"way":[47],"crucial":[50],"voluminous":[54],"datasets.":[55],"In":[56,177,195],"this":[57,178,188],"paper,":[58],"we":[59,106],"focus":[60],"on":[61],"a":[62,70,197,207],"fundamental":[63],"pattern,":[64],"namely,":[65],"closest":[67,160],"$l$l-mers.":[68],"Given":[69],"set":[71],"$m$m":[73,110,132],"strings":[75],"$S_1,S_2,\\ldots,":[76],"S_m$S1,S2,...,Sm":[77],"an":[79,90,118],"integer":[80],"$l$l,":[81],"problem":[83,144,170,189],"interest":[85],"is":[86,101,117,134,153,201],"that":[87,96,115],"$l$l-mer":[91,119],"each":[93],"string":[94],"distance":[98,129,222],"among":[99,130,138],"them":[100],"least.":[103],"For":[104],"example":[105],"want":[107],"to":[108,220],"find":[109],"$l$l-mers":[111,133,161],"$X_1,X_2,\\ldots,":[112],"X_m$X1,X2,...,Xm":[113],"$X_i$Xi":[116],"$S_i$Si":[121],"(for":[122],"$1\\leq":[123],"i\\leq":[124],"m$1\u2264i\u2264m)":[125],"Hamming":[128],"these":[131],"least":[136],"(from":[137],"all":[139],"possible":[141],"$l$l-mers).":[142],"This":[143],"has":[145],"many":[146],"applications.":[147],"An":[148],"application":[149],"great":[151],"importance":[152],"motif":[154],"search.":[155],"used":[164],"solving":[166],"$(l,d)$(l,d)-motif":[168],"search":[169],"(see":[171],"e.g.,":[172],"[1]":[173],",":[174],"[2]":[175],").":[176],"paper":[179],"novel":[180],"exact":[181],"approximate":[183],"are":[185],"proposed":[186],"case":[192],"$m>2$m>2.":[194],"particular,":[196],"comprehensive":[198],"experimental":[199],"evaluation":[200],"performed":[202],"$m=3$m=3,":[204],"along":[205],"further":[208],"empirical":[209],"study":[210],"$m=4$m=4":[212],"5.":[214],"We":[215],"also":[216],"extend":[217],"our":[218],"solution":[219],"euclidean":[221],"measurement":[223],"metric":[224],"if":[225],"sequences":[227],"contain":[228],"real":[229],"numbers.":[230]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-06-13T00:00:00"}