{"id":"https://openalex.org/W2091572769","doi":"https://doi.org/10.1186/1748-7188-6-6","title":"WildSpan: mining structured motifs from protein sequences","display_name":"WildSpan: mining structured motifs from protein sequences","publication_year":2011,"publication_date":"2011-03-31","ids":{"openalex":"https://openalex.org/W2091572769","doi":"https://doi.org/10.1186/1748-7188-6-6","mag":"2091572769","pmid":"https://pubmed.ncbi.nlm.nih.gov/21453542"},"language":"en","primary_location":{"id":"doi:10.1186/1748-7188-6-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-6-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-6-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-6-6","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5025757592","display_name":"Chen\u2010Ming Hsu","orcid":"https://orcid.org/0000-0001-5838-8886"},"institutions":[{"id":"https://openalex.org/I154864474","display_name":"National Taiwan University of Science and Technology","ror":"https://ror.org/00q09pe49","country_code":"TW","type":"education","lineage":["https://openalex.org/I154864474"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chen-Ming Hsu","raw_affiliation_strings":["Department of Bio-Industrial Mechatronics Engineering, National Taiwan University, Taipei, 106, Taiwan. cychen@mars.csie.ntu.edu.tw","Department of Computer Science and Information Engineering,, Ching Yun University,, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bio-Industrial Mechatronics Engineering, National Taiwan University, Taipei, 106, Taiwan. cychen@mars.csie.ntu.edu.tw","institution_ids":["https://openalex.org/I154864474"]},{"raw_affiliation_string":"Department of Computer Science and Information Engineering,, Ching Yun University,, Taiwan","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100710720","display_name":"Chien\u2010Yu Chen","orcid":"https://orcid.org/0000-0002-6940-6389"},"institutions":[{"id":"https://openalex.org/I16733864","display_name":"National Taiwan University","ror":"https://ror.org/05bqach95","country_code":"TW","type":"education","lineage":["https://openalex.org/I16733864"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chien-Yu Chen","raw_affiliation_strings":["Department of Bio-Industrial Mechatronics Engineering, National Taiwan University, Taipei, 106, Taiwan","Department of Bio-Industrial Mechatronics Engineering, National Taiwan University Taipei, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Bio-Industrial Mechatronics Engineering, National Taiwan University, Taipei, 106, Taiwan","institution_ids":["https://openalex.org/I16733864"]},{"raw_affiliation_string":"Department of Bio-Industrial Mechatronics Engineering, National Taiwan University Taipei, Taiwan","institution_ids":["https://openalex.org/I16733864"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5047461400","display_name":"Baw\u2010Jhiune Liu","orcid":null},"institutions":[{"id":"https://openalex.org/I99908691","display_name":"Yuan Ze University","ror":"https://ror.org/01fv1ds98","country_code":"TW","type":"education","lineage":["https://openalex.org/I99908691"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Baw-Jhiune Liu","raw_affiliation_strings":["Department of Computer Science and Engineering, Yuan Ze University, Jung-Li, 320, Taiwan","Department of Computer Science and Engineering, Yuan Ze University, Jung-Li, Taiwan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Jung-Li, 320, Taiwan","institution_ids":["https://openalex.org/I99908691"]},{"raw_affiliation_string":"Department of Computer Science and Engineering, Yuan Ze University, Jung-Li, Taiwan","institution_ids":["https://openalex.org/I99908691"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1490,"currency":"GBP","value_usd":1827},"apc_paid":{"value":1490,"currency":"GBP","value_usd":1827},"fwci":5.349,"has_fulltext":true,"cited_by_count":13,"citation_normalized_percentile":{"value":0.95538563,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"6","issue":"1","first_page":"6","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8212000131607056,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.8212000131607056,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.05849999934434891,"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":0.019099999219179153,"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/computer-science","display_name":"Computer science","score":0.6373052597045898},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5011210441589355},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.46766483783721924},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.32272982597351074},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.14761781692504883}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6373052597045898},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5011210441589355},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.46766483783721924},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.32272982597351074},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.14761781692504883}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1186/1748-7188-6-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-6-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-6-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},{"id":"pmid:21453542","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/21453542","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for molecular biology : AMB","raw_type":null},{"id":"pmh:oai:doaj.org/article:9d87cfae50384e3397a938f4104d22f7","is_oa":true,"landing_page_url":"https://doaj.org/article/9d87cfae50384e3397a938f4104d22f7","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms for Molecular Biology, Vol 6, Iss 1, p 6 (2011)","raw_type":"article"},{"id":"pmh:oai:europepmc.org:2091092","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/3082213","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1186/1748-7188-6-6","is_oa":true,"landing_page_url":"https://doi.org/10.1186/1748-7188-6-6","pdf_url":"https://almob.biomedcentral.com/counter/pdf/10.1186/1748-7188-6-6","source":{"id":"https://openalex.org/S205663195","display_name":"Algorithms for Molecular Biology","issn_l":"1748-7188","issn":["1748-7188"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms for Molecular Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321040","display_name":"National Science Council","ror":"https://ror.org/02kv4zf79"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2091572769.pdf","grobid_xml":"https://content.openalex.org/works/W2091572769.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1518105754","https://openalex.org/W1556480481","https://openalex.org/W1596496559","https://openalex.org/W1982481323","https://openalex.org/W1982871387","https://openalex.org/W1995924392","https://openalex.org/W2003341203","https://openalex.org/W2014744153","https://openalex.org/W2019019284","https://openalex.org/W2022148737","https://openalex.org/W2028903194","https://openalex.org/W2036667662","https://openalex.org/W2047630272","https://openalex.org/W2047792838","https://openalex.org/W2050284387","https://openalex.org/W2054984882","https://openalex.org/W2063732674","https://openalex.org/W2076898137","https://openalex.org/W2086770662","https://openalex.org/W2094070589","https://openalex.org/W2098359740","https://openalex.org/W2103818457","https://openalex.org/W2105438341","https://openalex.org/W2115156437","https://openalex.org/W2122182354","https://openalex.org/W2124815120","https://openalex.org/W2132109794","https://openalex.org/W2135498219","https://openalex.org/W2154440943","https://openalex.org/W2158714788","https://openalex.org/W2159003775","https://openalex.org/W2161062388","https://openalex.org/W2162665632","https://openalex.org/W2166086559","https://openalex.org/W4317639370"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2530322880","https://openalex.org/W1596801655","https://openalex.org/W2359140296"],"abstract_inverted_index":{"BACKGROUND:":[0],"Automatic":[1],"extraction":[2],"of":[3,15,31,62,96,119,166,264,268,274,282,291,326,337,378,393,416,431],"motifs":[4,26,98,118,181],"from":[5,162,419],"biological":[6],"sequences":[7,293],"is":[8,21,50,134,234,276,328,387,408,425,434],"an":[9,210],"important":[10],"research":[11],"problem":[12,205],"in":[13,45,81,247,389,402,412,427,436,448],"study":[14,404,438],"molecular":[16],"biology.":[17],"For":[18],"proteins,":[19],"it":[20],"desired":[22],"to":[23,75,83,110,176,206,226,236,260,288,302],"discover":[24,190],"sequence":[25,194,306,319,332],"containing":[27,240],"a":[28,106,135,163,283,289,335,341],"large":[29,112,147,151,218],"number":[30],"wildcard":[32,113,219],"symbols,":[33],"as":[34,359,361],"the":[35,78,92,97,125,154,177,204,229,262,304,308,313,351,362,370,383,391,394,429,440,462],"residues":[36,158,242],"associated":[37],"with":[38,146,252,312,356],"functional":[39,117,157,280,414],"sites":[40],"are":[41,68,129,159,182,244,300,310,354,459],"usually":[42],"largely":[43,227],"separated":[44,246],"sequences.":[46,248,420,451],"Discovering":[47],"such":[48],"patterns":[49,122,358,363],"time-consuming":[51],"because":[52],"abundant":[53],"combinations":[54],"exist":[55],"when":[56],"long":[57],"gaps":[58,152],"(a":[59],"gap":[60],"consists":[61],"one":[63],"or":[64],"more":[65],"successive":[66],"wildcards)":[67],"considered.":[69],"Mining":[70],"algorithms":[71],"often":[72],"employ":[73],"constraints":[74],"narrow":[76],"down":[77],"search":[79],"space":[80],"order":[82],"increase":[84],"efficiency.":[85],"However,":[86],"improper":[87],"constraint":[88,108,127],"models":[89],"might":[90],"degrade":[91],"sensitivity":[93],"and":[94,169,196,208,257,266,307,410,455],"specificity":[95],"discovered":[99,298,352,442],"by":[100,286,317,365,443],"computational":[101],"methods.":[102],"We":[103,249],"previously":[104],"proposed":[105,126,384,395,422],"new":[107],"model":[109,128],"handle":[111],"regions":[114,281],"for":[115,192,278,330,334,344],"discovering":[116,279,413],"proteins.":[120],"The":[121,270,297,322,398,421,452],"that":[123,138,156,179,221,243,382,406,439],"satisfy":[124],"called":[130],"W-patterns.":[131],"A":[132],"W-pattern":[133],"structured":[136],"motif":[137,140,171],"groups":[139],"symbols":[141,172],"into":[142,173],"pattern":[143,215],"blocks":[144],"interleaved":[145],"irregular":[148],"gaps.":[149],"Considering":[150],"reflects":[153],"fact":[155],"not":[160],"always":[161],"single":[164,284],"region":[165],"protein":[167,186,285,305,342,345,450],"sequences,":[168],"restricting":[170],"clusters":[174],"corresponds":[175],"observation":[178],"short":[180],"frequently":[183],"present":[184],"within":[185],"families.":[187],"To":[188],"efficiently":[189,237],"W-patterns":[191,239,265,299,353,441],"large-scale":[193],"annotation":[195],"function":[197,346],"prediction,":[198],"this":[199,349,403,437],"paper":[200],"first":[201],"formally":[202],"introduces":[203],"solve":[207],"proposes":[209],"algorithm":[211],"named":[212],"WildSpan":[213,233,275,327,380,407,444,453],"(sequential":[214],"mining":[216,230,254,272,324,399],"across":[217],"regions)":[220],"incorporates":[222],"several":[223],"pruning":[224,385,423],"strategies":[225],"reduce":[228],"cost.":[231],"RESULTS:":[232],"shown":[235],"find":[238],"conserved":[241,314],"far":[245],"conducted":[250,401],"experiments":[251],"two":[253],"strategies,":[255],"protein-based":[256,271],"family-based":[258,323],"mining,":[259],"evaluate":[261],"usefulness":[263],"performance":[267],"WildSpan.":[269,432],"mode":[273,325],"developed":[277,329],"referring":[287],"set":[290],"related":[292,338],"(e.g.":[294,340],"its":[295],"homologues).":[296],"used":[301],"characterize":[303],"results":[309,400],"compared":[311,355],"positions":[315],"identified":[316],"multiple":[318],"alignment":[320],"(MSA).":[321],"extracting":[331],"signatures":[333,415],"group":[336],"proteins":[339,417],"family)":[343],"classification.":[347],"In":[348],"situation,":[350],"PROSITE":[357],"well":[360],"generated":[364],"three":[366],"existing":[367],"methods":[368],"performing":[369],"similar":[371],"task.":[372],"Finally,":[373],"analysis":[374],"on":[375,461],"execution":[376],"time":[377],"running":[379],"reveals":[381],"strategy":[386,424],"effective":[388,411,426],"improving":[390,428],"scalability":[392,430],"algorithm.":[396],"CONCLUSIONS:":[397],"reveal":[405],"efficient":[409],"directly":[418],"It":[433],"demonstrated":[435],"provides":[445],"useful":[446],"information":[447],"characterizing":[449],"executable":[454],"open":[456],"source":[457],"codes":[458],"available":[460],"web":[463],"(http://biominer.csie.cyu.edu.tw/wildspan).":[464]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}