{"id":"https://openalex.org/W1990572746","doi":"https://doi.org/10.1109/bibm.2013.6732605","title":"Towards simultaneous clustering and motif-modeling for a large number of protein family","display_name":"Towards simultaneous clustering and motif-modeling for a large number of protein family","publication_year":2013,"publication_date":"2013-12-01","ids":{"openalex":"https://openalex.org/W1990572746","doi":"https://doi.org/10.1109/bibm.2013.6732605","mag":"1990572746"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2013.6732605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2013.6732605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"},"type":"article","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/A5027249988","display_name":"Young Joon Yoo","orcid":"https://orcid.org/0000-0001-8186-8263"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Young Joon Yoo","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014386788","display_name":"Tushar Sandhan","orcid":null},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tushar Sandhan","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101702804","display_name":"Jin\u2010Young Choi","orcid":"https://orcid.org/0000-0003-2676-3842"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jinyoung Choi","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Seoul National University","Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Electr. & Comput. Eng., Seoul Nat. Univ., Seoul, South Korea","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460439","display_name":"\ufeffSun Kim","orcid":"https://orcid.org/0000-0001-5385-9546"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sun Kim","raw_affiliation_strings":["Department of Computer Science and Engineering, Seoul National University, Rep of Korea","Dept. of Comput. Sci. & Eng., Seoul Nat. Univ., Seoul, , South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Seoul National University, Rep of Korea","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Dept. of Comput. Sci. & Eng., Seoul Nat. Univ., Seoul, , South Korea","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5027249988"],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":0.28357791,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.6256981,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"11","issue":null,"first_page":"22","last_page":"28"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9997000098228455,"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":0.9990000128746033,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9987000226974487,"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/cluster-analysis","display_name":"Cluster analysis","score":0.6531949639320374},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.6132797598838806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6018356084823608},{"id":"https://openalex.org/keywords/bipartite-graph","display_name":"Bipartite graph","score":0.6004457473754883},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4402579665184021},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3785737454891205},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3690703213214874},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3275420665740967},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.32232266664505005},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32079803943634033},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.2905694246292114},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.11014261841773987},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.09601297974586487},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.08468547463417053}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6531949639320374},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.6132797598838806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6018356084823608},{"id":"https://openalex.org/C197657726","wikidata":"https://www.wikidata.org/wiki/Q174733","display_name":"Bipartite graph","level":3,"score":0.6004457473754883},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4402579665184021},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3785737454891205},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3690703213214874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3275420665740967},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.32232266664505005},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32079803943634033},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.2905694246292114},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.11014261841773987},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.09601297974586487},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.08468547463417053},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2013.6732605","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2013.6732605","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2013 IEEE International Conference on Bioinformatics and Biomedicine","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1969451865","https://openalex.org/W1969851044","https://openalex.org/W1990453950","https://openalex.org/W2049633694","https://openalex.org/W2055043387","https://openalex.org/W2056619794","https://openalex.org/W2067583709","https://openalex.org/W2074231493","https://openalex.org/W2095071222","https://openalex.org/W2117486996","https://openalex.org/W2117694558","https://openalex.org/W2123464221","https://openalex.org/W2127716074","https://openalex.org/W2130231225","https://openalex.org/W2136651963","https://openalex.org/W2140211206","https://openalex.org/W2145268834","https://openalex.org/W2151831732","https://openalex.org/W2166162901","https://openalex.org/W4236236547","https://openalex.org/W6678863094"],"related_works":["https://openalex.org/W2371352078","https://openalex.org/W3170299350","https://openalex.org/W2368410102","https://openalex.org/W2605676258","https://openalex.org/W2368037387","https://openalex.org/W2953461625","https://openalex.org/W190186656","https://openalex.org/W2902352756","https://openalex.org/W3088754131","https://openalex.org/W3038848193"],"abstract_inverted_index":{"In":[0,128],"this":[1],"paper,":[2],"we":[3],"propose":[4],"a":[5,119,166],"novel":[6],"clustering":[7],"and":[8,30,59,86,103,162],"motif":[9,55,144],"modeling":[10],"framework":[11],"for":[12,37,83,137,165],"analyzing":[13],"large":[14,120,167],"number":[15,121,168],"of":[16,23,33,56,68,122,134,145,169],"protein":[17,57,70,123,138,160],"family":[18,58,111,147],"using":[19,24,90,100,107],"k-mer.":[20],"Our":[21],"approach":[22],"k-mers":[25,34],"utilizes":[26],"both":[27,159],"occurring":[28],"frequency":[29],"position":[31],"information":[32],"that":[35,48,114],"essential":[36],"classification":[38,131],"yet":[39],"not":[40],"fully":[41],"used":[42],"in":[43,77],"previous":[44,84],"methods.":[45],"We":[46],"found":[47],"the":[49,94,108,130,135,151,155],"structure":[50],"has":[51,154],"close":[52],"relationship":[53],"between":[54],"hence":[60],"well":[61],"describe":[62],"important":[63],"biological":[64],"features":[65],"or":[66,143],"motifs":[67],"each":[69,146],"family.":[71],"The":[72],"classification/clustering":[73],"procedure":[74],"are":[75],"executed":[76],"incremental":[78],"manner":[79],"which":[80],"was":[81],"difficult":[82],"algorithms":[85],"is":[87],"modeled":[88],"by":[89],"bipartite":[91],"model.":[92],"Furthermore,":[93],"method":[95,153],"can":[96,117],"be":[97],"efficiently":[98],"implemented":[99],"parallel":[101],"computing":[102],"hash.":[104],"Experimental":[105],"results":[106],"entire":[109],"COG":[110],"database":[112],"shows":[113],"our":[115],"model":[116,118,158],"families":[124,161],"without":[125],"sacrificing":[126],"accuracy.":[127],"addition,":[129],"structure,":[132],"path":[133],"graph":[136],"sequences,":[139],"explains":[140],"characteristic":[141],"subsequences":[142],"quite":[148],"well.":[149],"Thus":[150],"proposed":[152],"potential":[156],"to":[157],"motifs,":[163],"even":[164],"families.":[170]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2014,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}