{"id":"https://openalex.org/W2423803971","doi":"https://doi.org/10.1109/icde.2016.7498321","title":"Fast motif discovery in short sequences","display_name":"Fast motif discovery in short sequences","publication_year":2016,"publication_date":"2016-05-01","ids":{"openalex":"https://openalex.org/W2423803971","doi":"https://doi.org/10.1109/icde.2016.7498321","mag":"2423803971"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2016.7498321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","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":null,"display_name":"Honglei Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Honglei Liu","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013081925","display_name":"Fangqiu Han","orcid":"https://orcid.org/0009-0006-0309-7284"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fangqiu Han","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5021549182","display_name":"Hongjun Zhou","orcid":"https://orcid.org/0000-0002-8873-293X"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Hongjun Zhou","raw_affiliation_strings":["Neuroscience Research Institute, University of California, Santa Barbara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neuroscience Research Institute, University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047709762","display_name":"Xifeng Yan","orcid":"https://orcid.org/0009-0000-6508-4792"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xifeng Yan","raw_affiliation_strings":["Department of Computer Science, University of California, Santa Barbara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016853030","display_name":"Kenneth S. Kosik","orcid":"https://orcid.org/0000-0003-3224-5179"},"institutions":[{"id":"https://openalex.org/I154570441","display_name":"University of California, Santa Barbara","ror":"https://ror.org/02t274463","country_code":"US","type":"education","lineage":["https://openalex.org/I154570441"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kenneth S. Kosik","raw_affiliation_strings":["Neuroscience Research Institute, University of California, Santa Barbara, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Neuroscience Research Institute, University of California, Santa Barbara, USA","institution_ids":["https://openalex.org/I154570441"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I154570441"],"apc_list":null,"apc_paid":null,"fwci":9.3618,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.98617335,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"3","issue":null,"first_page":"1158","last_page":"1169"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9977999925613403,"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":0.9977999925613403,"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/T10602","display_name":"Glycosylation and Glycoproteins Research","score":0.9962000250816345,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9962000250816345,"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/motif","display_name":"Motif (music)","score":0.8491974472999573},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7620158195495605},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.7118680477142334},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.697500467300415},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6496222615242004},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44265320897102356},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.328830361366272},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32710087299346924},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31450825929641724},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.12685957551002502},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09976407885551453},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08165103197097778}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.8491974472999573},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7620158195495605},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.7118680477142334},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.697500467300415},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6496222615242004},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44265320897102356},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.328830361366272},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32710087299346924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31450825929641724},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.12685957551002502},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09976407885551453},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08165103197097778},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2016.7498321","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2016.7498321","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE 32nd International Conference on Data Engineering (ICDE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/17","display_name":"Partnerships for the goals","score":0.4300000071525574}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W1583518118","https://openalex.org/W1602142193","https://openalex.org/W1873119440","https://openalex.org/W1955121107","https://openalex.org/W1983143858","https://openalex.org/W2054131408","https://openalex.org/W2054984882","https://openalex.org/W2062058474","https://openalex.org/W2087342608","https://openalex.org/W2092336114","https://openalex.org/W2097175728","https://openalex.org/W2105423800","https://openalex.org/W2109088164","https://openalex.org/W2110738405","https://openalex.org/W2118393799","https://openalex.org/W2120900302","https://openalex.org/W2127774996","https://openalex.org/W2128591967","https://openalex.org/W2131989567","https://openalex.org/W2140952049","https://openalex.org/W2145091349","https://openalex.org/W2145295592","https://openalex.org/W2147087392","https://openalex.org/W2148014281","https://openalex.org/W2150916025","https://openalex.org/W2157009395","https://openalex.org/W2157952888","https://openalex.org/W2159959024","https://openalex.org/W2166811939","https://openalex.org/W2168157737","https://openalex.org/W2168171990","https://openalex.org/W2171574281","https://openalex.org/W2295100167","https://openalex.org/W6628896446","https://openalex.org/W6681544251","https://openalex.org/W6685232391"],"related_works":["https://openalex.org/W2168642461","https://openalex.org/W3003818906","https://openalex.org/W2057508801","https://openalex.org/W2110403456","https://openalex.org/W2605190264","https://openalex.org/W2044328609","https://openalex.org/W2516633321","https://openalex.org/W2150849570","https://openalex.org/W1996543580","https://openalex.org/W2161965550"],"abstract_inverted_index":{"Motif":[0],"discovery":[1],"in":[2,18,48,181],"sequence":[3,96,106],"data":[4,36],"is":[5,74,100,162],"fundamental":[6],"to":[7,24,58,76,103,135,139,207],"many":[8],"biological":[9],"problems":[10],"such":[11],"as":[12,153],"antibody":[13],"biomarker":[14],"identification.":[15],"Recent":[16],"advances":[17],"instrumental":[19],"techniques":[20],"make":[21],"it":[22,73],"possible":[23,75],"generate":[25,140],"thousands":[26],"of":[27,52,81,166,197],"protein":[28,179],"sequences":[29,55,114,180],"at":[30,91],"once,":[31],"which":[32],"raises":[33],"a":[34,49,105,198,208],"big":[35],"issue":[37],"for":[38,61],"the":[39,79,83,116,123,143,145,182,194],"existing":[40,84,128,186],"motif":[41,85,118,129,171,201],"finding":[42,86,130,172,202],"algorithms:":[43],"They":[44],"either":[45],"work":[46],"only":[47],"small":[50],"scale":[51,183],"several":[53],"hundred":[54],"or":[56],"have":[57],"trade":[59],"accuracy":[60,90],"efficiency.":[62],"In":[63,142,190],"this":[64],"work,":[65],"we":[66],"demonstrate":[67],"that":[68,113,159,184],"by":[69],"intelligently":[70],"clustering":[71,97],"sequences,":[72],"significantly":[77],"improve":[78],"scalability":[80],"all":[82],"algorithms":[87],"without":[88],"losing":[89],"all.":[92],"An":[93],"anchor":[94],"based":[95],"algorithm":[98,131,187],"(ASC)":[99],"thus":[101],"proposed":[102],"divide":[104],"dataset":[107],"into":[108,122],"multiple":[109,148],"smaller":[110],"clusters":[111,149],"so":[112],"sharing":[115],"same":[117,124],"will":[119],"be":[120,133],"located":[121],"cluster.":[125],"Then":[126],"an":[127],"can":[132,175,188],"applied":[134],"each":[136],"individual":[137],"cluster":[138],"motifs.":[141],"end,":[144],"results":[146,157],"from":[147,178,205],"are":[150],"merged":[151],"together":[152],"final":[154],"output.":[155],"Experimental":[156],"show":[158],"our":[160],"approach":[161],"generic":[163],"and":[164],"orders":[165],"magnitude":[167],"faster":[168],"than":[169],"traditional":[170],"algorithms.":[173],"It":[174],"discover":[176],"motifs":[177],"no":[185],"handle.":[189],"particular,":[191],"ASC":[192],"reduces":[193],"running":[195],"time":[196],"very":[199],"popular":[200],"algorithm,":[203],"MEME,":[204],"weeks":[206],"few":[209],"minutes":[210],"with":[211],"even":[212],"better":[213],"accuracy.":[214]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}