{"id":"https://openalex.org/W2197243329","doi":"https://doi.org/10.1109/bibm.2015.7359740","title":"Improved algorithms for finding edit distance based motifs","display_name":"Improved algorithms for finding edit distance based motifs","publication_year":2015,"publication_date":"2015-11-01","ids":{"openalex":"https://openalex.org/W2197243329","doi":"https://doi.org/10.1109/bibm.2015.7359740","mag":"2197243329"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2015.7359740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5086885083","display_name":"Soumitra Pal","orcid":"https://orcid.org/0000-0003-4840-3944"},"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":"Soumitra Pal","raw_affiliation_strings":["Computer Science and Engineering, University of Connecticut, Storrs, CT, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Computer Science and Engineering, University of Connecticut, Storrs, CT, USA","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":["University of Connecticut, Storrs, CT, US"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Connecticut, Storrs, CT, US","institution_ids":["https://openalex.org/I140172145"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I140172145"],"apc_list":null,"apc_paid":null,"fwci":0.4115,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58804264,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"537","last_page":"542"},"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":0.9957000017166138,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9872000217437744,"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":0.921911358833313},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7840805053710938},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.6716907620429993},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5742884278297424},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5638859868049622},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.4767906665802002},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.42251721024513245},{"id":"https://openalex.org/keywords/efficient-algorithm","display_name":"Efficient algorithm","score":0.4112854301929474},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.38931116461753845},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3219294846057892}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.921911358833313},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7840805053710938},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.6716907620429993},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5742884278297424},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5638859868049622},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.4767906665802002},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.42251721024513245},{"id":"https://openalex.org/C3018263672","wikidata":"https://www.wikidata.org/wiki/Q1296251","display_name":"Efficient algorithm","level":2,"score":0.4112854301929474},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.38931116461753845},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3219294846057892},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bibm.2015.7359740","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2015.7359740","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.943.8278","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.943.8278","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://biorxiv.org/content/biorxiv/early/2015/05/31/020131.full.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","score":0.5899999737739563,"display_name":"Sustainable cities and communities"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1486659038","https://openalex.org/W1531307672","https://openalex.org/W1580213736","https://openalex.org/W1964541472","https://openalex.org/W1977133097","https://openalex.org/W1985716977","https://openalex.org/W2004488542","https://openalex.org/W2045734780","https://openalex.org/W2075277509","https://openalex.org/W2148103646","https://openalex.org/W2163923149","https://openalex.org/W2320801221","https://openalex.org/W2752061190","https://openalex.org/W2752853835","https://openalex.org/W6634719314"],"related_works":["https://openalex.org/W2136519138","https://openalex.org/W1989944203","https://openalex.org/W1998479724","https://openalex.org/W2546839375","https://openalex.org/W2196636117","https://openalex.org/W2067956663","https://openalex.org/W3153057271","https://openalex.org/W2014450733","https://openalex.org/W3082647531","https://openalex.org/W2999485669"],"abstract_inverted_index":{"Motif":[0,50],"search":[1,18,264],"is":[2,19,22,124,157,177],"an":[3],"important":[4],"step":[5],"in":[6,71,118,140,149,169,205,244,255],"extracting":[7],"meaningful":[8],"patterns":[9],"from":[10,190],"biological":[11,61],"data.":[12],"The":[13,82,106],"general":[14],"problem":[15],"of":[16,66,143,152,194],"motif":[17,263],"intractable.":[20],"There":[21],"a":[23,141,150,160,186,227,245],"pressing":[24],"need":[25],"to":[26,33,114,159,179,232,239,261],"develop":[27],"efficient":[28,164],"exact":[29],"and":[30,59,80,103,145,162,238],"approximation":[31],"algorithms":[32,43,83],"solve":[34],"this":[35,38,170,256],"problem.":[36],"In":[37],"paper":[39,257],"we":[40,173,199,212,225,253],"present":[41],"novel":[42,161],"for":[44,84],"solving":[45],"the":[46,181,195,202,206,235,241,251,268],"(l,":[47],"d)":[48],"Edit-distance-based":[49],"Search":[51],"(EMS)":[52],"problem:":[53],"given":[54],"two":[55],"integers":[56],"l,":[57],"d":[58,77,189],"n":[60],"strings,":[62],"find":[63],"all":[64,191],"strings":[65],"length":[67],"l":[68],"that":[69,175,250],"appear":[70],"each":[72],"input":[73,196],"string":[74],"with":[75,220],"atmost":[76],"substitutions,":[78],"insertions":[79],"deletions.":[81],"EMS":[85],"are":[86,184,258],"customarily":[87],"evaluated":[88],"on":[89],"several":[90],"challenging":[91],"instances":[92],"such":[93,266],"as":[94,267],"(9,":[95],"2),":[96],"(11,":[97,116,138],"3),":[98],"(13,":[99],"4),":[100],"(15,":[101],"5),":[102],"so":[104],"on.":[105],"best":[107],"previously":[108],"known":[109],"algorithm,":[110],"EMS1,":[111],"solves":[112,136],"up":[113],"instance":[115,137,146],"3)":[117,139,148],"estimated":[119],"3":[120],"days.":[121],"Our":[122],"algorithm":[123,135],"more":[125],"than":[126,130],"20":[127],"times":[128],"faster":[129],"EMS1.":[131],"For":[132],"example,":[133],"our":[134],"couple":[142,151],"minutes":[144],"(14,":[147],"hours.":[153],"This":[154],"significant":[155],"improvement":[156],"due":[158],"provably":[163],"neighborhood":[165,207],"generation":[166],"technique":[167],"introduced":[168],"paper.":[171],"Firstly,":[172],"show":[174],"it":[176],"enough":[178],"consider":[180],"neighbors":[182],"which":[183],"at":[185],"distance":[187],"exactly":[188],"possible":[192],"substrings":[193],"strings.":[197],"Secondly,":[198],"compactly":[200],"represent":[201],"candidate":[203,216,236],"motifs":[204,217,237,243],"using":[208],"wildcard":[209],"characters.":[210],"Thirdly,":[211],"generate":[213],"these":[214],"compact":[215],"nearly":[218],"uniquely":[219],"very":[221],"few":[222],"repetitions.":[223],"Finally,":[224],"use":[226],"trie":[228],"based":[229],"data":[230],"structure":[231],"efficiently":[233],"store":[234],"output":[240],"final":[242],"sorted":[246],"order.":[247],"We":[248],"believe":[249],"techniques":[252],"introduce":[254],"also":[259],"applicable":[260],"other":[262],"problems":[265],"PMS.":[269]},"counts_by_year":[{"year":2022,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}