{"id":"https://openalex.org/W2147461480","doi":null,"title":"Clustering sequence sets for motif discovery","display_name":"Clustering sequence sets for motif discovery","publication_year":2009,"publication_date":"2009-12-07","ids":{"openalex":"https://openalex.org/W2147461480","mag":"2147461480"},"language":"en","primary_location":{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.7746","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.7746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips22/NIPS2009_0774.pdf","raw_type":"text"},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"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/A5100635271","display_name":"Jong Kyoung Kim","orcid":"https://orcid.org/0000-0002-0257-0547","observed_orcids":["https://orcid.org/0000-0002-0257-0547"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jong Kim","raw_affiliation_strings":["[Department of Computer Science, Pohang University of Science and Technology, Pohang, Korea]"],"raw_orcid":"https://orcid.org/0000-0002-0257-0547","affiliations":[{"raw_affiliation_string":"[Department of Computer Science, Pohang University of Science and Technology, Pohang, Korea]","institution_ids":["https://openalex.org/I123900574"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5066405061","display_name":"Seungjin Choi","orcid":"https://orcid.org/0000-0002-7873-4616","observed_orcids":["https://orcid.org/0000-0002-7873-4616"]},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Seungjin Choi","raw_affiliation_strings":["[Department of Computer Science, Pohang University of Science and Technology, Pohang, Korea]"],"raw_orcid":"https://orcid.org/0000-0002-7873-4616","affiliations":[{"raw_affiliation_string":"[Department of Computer Science, Pohang University of Science and Technology, Pohang, Korea]","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I123900574"],"apc_list":null,"apc_paid":null,"fwci":0.1091,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.42050487,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":87,"max":93},"biblio":{"volume":"22","issue":null,"first_page":"970","last_page":"978"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9125999808311462,"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/T10222","display_name":"Genomics and Chromatin Dynamics","score":0.9125999808311462,"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":0.043299999088048935,"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/T10885","display_name":"Gene expression and cancer classification","score":0.004699999932199717,"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/dna-motif-discovery","display_name":"DNA motif discovery","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sequence-clustering","display_name":"sequence clustering","score":0.7089999914169312},{"id":"https://openalex.org/keywords/probabilistic-models","display_name":"probabilistic models","score":0.8259999752044678},{"id":"https://openalex.org/keywords/latent-variables","display_name":"latent variables","score":0.8659999966621399},{"id":"https://openalex.org/keywords/signal-to-noise-ratio","display_name":"signal-to-noise ratio","score":0.8009999990463257}],"concepts":[{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.8362991809844971},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.6338058710098267},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6334476470947266},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.554336667060852},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5282905101776123},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4415603578090668},{"id":"https://openalex.org/C132677234","wikidata":"https://www.wikidata.org/wiki/Q3273544","display_name":"Structural motif","level":2,"score":0.41915425658226013},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3868265748023987},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3572164475917816},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3544943928718567},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.23227527737617493},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.22412031888961792},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22316274046897888},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:CiteSeerX.psu:10.1.1.214.7746","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.214.7746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://books.nips.cc/papers/files/nips22/NIPS2009_0774.pdf","raw_type":"text"},{"id":"mag:2147461480","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/3743-clustering-sequence-sets-for-motif-discovery.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1214546200","https://openalex.org/W1592870802","https://openalex.org/W1981093360","https://openalex.org/W1984053739","https://openalex.org/W1987079970","https://openalex.org/W1987122345","https://openalex.org/W1998300401","https://openalex.org/W2022248788","https://openalex.org/W2042392223","https://openalex.org/W2059203643","https://openalex.org/W2077013196","https://openalex.org/W2080498142","https://openalex.org/W2084908610","https://openalex.org/W2115555186","https://openalex.org/W2121356022","https://openalex.org/W2129795133","https://openalex.org/W2130063415","https://openalex.org/W2134591904","https://openalex.org/W2135221645","https://openalex.org/W2149769193","https://openalex.org/W7099666281"],"related_works":["https://openalex.org/W2887354949","https://openalex.org/W2328452666","https://openalex.org/W7095096268","https://openalex.org/W2249443033","https://openalex.org/W1972111831","https://openalex.org/W2123623874","https://openalex.org/W2055030646","https://openalex.org/W7096270434","https://openalex.org/W2029444854","https://openalex.org/W2520473406"],"abstract_inverted_index":{"Most":[0],"of":[1,13,26,50,54,91,129,157],"existing":[2,150],"methods":[3,151],"for":[4,72,83,136],"DNA":[5,73,138],"motif":[6,36,74,119],"discovery":[7,75,120],"consider":[8,23],"only":[9,153],"a":[10,38,45,69,154],"single":[11,46,155],"set":[12,43,156],"sequences":[14,27,51,158],"to":[15,63,125],"find":[16],"an":[17],"over-represented":[18],"motif.":[19,47],"In":[20],"contrast,":[21],"we":[22,29,77],"multiple":[24,65,79,89,127],"sets":[25,31,49,90,128],"where":[28,76,103,152],"group":[30],"associated":[32],"with":[33,108],"the":[34,141,146],"same":[35],"into":[37],"cluster,":[39],"assuming":[40],"that":[41,113],"each":[42,109],"involves":[44],"Clustering":[48],"yields":[52],"clusters":[53],"coherent":[55],"motifs,":[56],"improving":[57],"signal-to-noise":[58],"ratio":[59],"or":[60],"enabling":[61],"us":[62],"identify":[64,78],"motifs.":[66],"We":[67,111],"present":[68],"probabilistic":[70],"model":[71,94,115],"motifs":[80,101,139],"through":[81],"searching":[82],"patterns":[84],"which":[85],"are":[86],"shared":[87],"across":[88],"sequences.":[92,130],"Our":[93],"infers":[95],"cluster-indicating":[96],"latent":[97],"variables":[98],"and":[99,144],"learns":[100],"simultaneously,":[102],"these":[104],"two":[105],"tasks":[106],"interact":[107],"other.":[110],"show":[112],"our":[114],"can":[116],"handle":[117],"various":[118],"problems,":[121],"depending":[122],"on":[123,132],"how":[124],"construct":[126],"Experiments":[131],"three":[133],"different":[134],"problems":[135],"discovering":[137],"emphasize":[140],"useful":[142],"behavior":[143],"confirm":[145],"substantial":[147],"gains":[148],"over":[149],"is":[159],"considered.":[160],"1":[161]},"counts_by_year":[{"year":2021,"cited_by_count":1},{"year":2012,"cited_by_count":1}],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}