{"id":"https://openalex.org/W1972111831","doi":"https://doi.org/10.1145/1134030.1134032","title":"Motif discovery for proteins using subsequence clustering","display_name":"Motif discovery for proteins using subsequence clustering","publication_year":2005,"publication_date":"2005-08-21","ids":{"openalex":"https://openalex.org/W1972111831","doi":"https://doi.org/10.1145/1134030.1134032","mag":"1972111831"},"language":"en","primary_location":{"id":"doi:10.1145/1134030.1134032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1134030.1134032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th international workshop on Bioinformatics","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/A5012775638","display_name":"Hardik A. Sheth","orcid":null},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Hardik A. Sheth","raw_affiliation_strings":["Indiana University, Bloomington, IN"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100460452","display_name":"Sun Kim","orcid":"https://orcid.org/0000-0003-3072-6649"},"institutions":[{"id":"https://openalex.org/I4210119109","display_name":"Indiana University Bloomington","ror":"https://ror.org/02k40bc56","country_code":"US","type":"education","lineage":["https://openalex.org/I4210119109","https://openalex.org/I592451"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sun Kim","raw_affiliation_strings":["Indiana University, Bloomington, IN"],"affiliations":[{"raw_affiliation_string":"Indiana University, Bloomington, IN","institution_ids":["https://openalex.org/I4210119109"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5012775638"],"corresponding_institution_ids":["https://openalex.org/I4210119109"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.0662835,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9980999827384949,"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":0.9945999979972839,"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/subsequence","display_name":"Subsequence","score":0.8640320897102356},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7948041558265686},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.7582299709320068},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6075219511985779},{"id":"https://openalex.org/keywords/homogeneous","display_name":"Homogeneous","score":0.5672863721847534},{"id":"https://openalex.org/keywords/longest-common-subsequence-problem","display_name":"Longest common subsequence problem","score":0.4736979007720947},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.4168719947338104},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4135352075099945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3826885521411896},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.34199637174606323},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.24836358428001404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20885902643203735},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.13286730647087097},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.10770469903945923},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.08145129680633545},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07252317667007446}],"concepts":[{"id":"https://openalex.org/C137877099","wikidata":"https://www.wikidata.org/wiki/Q1332977","display_name":"Subsequence","level":3,"score":0.8640320897102356},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7948041558265686},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.7582299709320068},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6075219511985779},{"id":"https://openalex.org/C66882249","wikidata":"https://www.wikidata.org/wiki/Q169336","display_name":"Homogeneous","level":2,"score":0.5672863721847534},{"id":"https://openalex.org/C120098539","wikidata":"https://www.wikidata.org/wiki/Q141001","display_name":"Longest common subsequence problem","level":2,"score":0.4736979007720947},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.4168719947338104},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4135352075099945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3826885521411896},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.34199637174606323},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.24836358428001404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20885902643203735},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.13286730647087097},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.10770469903945923},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08145129680633545},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07252317667007446},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1134030.1134032","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1134030.1134032","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 5th international workshop on Bioinformatics","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.176.7072","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.176.7072","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bio.informatics.indiana.edu/projects/MOTIF/sheth-biokdd05.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W68361654","https://openalex.org/W1253971689","https://openalex.org/W1998300401","https://openalex.org/W2015292449","https://openalex.org/W2028903194","https://openalex.org/W2032661432","https://openalex.org/W2047630272","https://openalex.org/W2143173841","https://openalex.org/W2158962723"],"related_works":["https://openalex.org/W25732909","https://openalex.org/W4323338832","https://openalex.org/W4289596129","https://openalex.org/W170643605","https://openalex.org/W1999879627","https://openalex.org/W4295189757","https://openalex.org/W2088055539","https://openalex.org/W1574834681","https://openalex.org/W2389167168","https://openalex.org/W2170721049"],"abstract_inverted_index":{"We":[0],"propose":[1],"an":[2,29],"algorithm":[3,94,114,126],"for":[4],"discovering":[5],"motifs":[6,46,132],"using":[7,48],"clustering":[8,41,93],"of":[9,66,78],"subsequences.":[10],"In":[11,35],"our":[12,92],"previous":[13],"approach,":[14],"we":[15,38,90],"were":[16],"successful":[17],"in":[18,130],"guiding":[19],"motif":[20,31,50,54],"discovery":[21,32,51,55],"by":[22],"sampling":[23],"subsequences":[24,42],"and":[25,100,120],"inputting":[26],"them":[27,103],"to":[28,75,95,105,109],"existing":[30],"tool":[33],"MEME.":[34],"this":[36,88],"paper,":[37],"show":[39],"that":[40,124],"can":[43],"also":[44],"detect":[45],"without":[47],"other":[49],"tools.":[52],"Generally,":[53],"algorithms":[56],"do":[57],"not":[58],"perform":[59],"well":[60],"when":[61,81,134],"the":[62,72,82,121,125],"input":[63,83,135],"set":[64],"consists":[65],"non-homogeneous":[67],"sequences.":[68],"Clustering":[69],"tools":[70],"have":[71],"inherent":[73],"ability":[74],"generate":[76,96],"clusters":[77,99],"homogeneous":[79],"sequences":[80,84,136],"are":[85,137],"non-homogeneous.":[86],"For":[87],"reason,":[89],"use":[91],"aligned":[97],"subsequence":[98],"then":[101],"rank":[102],"according":[104],"their":[106],"information":[107],"contents":[108],"produce":[110],"final":[111],"motifs.":[112],"The":[113],"was":[115],"tested":[116],"with":[117],"PROSITE":[118],"database":[119],"results":[122],"suggest":[123],"is":[127],"very":[128],"effective":[129],"finding":[131],"even":[133],"from":[138],"different":[139],"protein":[140],"families.":[141]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}