{"id":"https://openalex.org/W2772617315","doi":"https://doi.org/10.1109/bibm.2017.8217620","title":"Pattern-directed aligned pattern clustering","display_name":"Pattern-directed aligned pattern clustering","publication_year":2017,"publication_date":"2017-11-01","ids":{"openalex":"https://openalex.org/W2772617315","doi":"https://doi.org/10.1109/bibm.2017.8217620","mag":"2772617315"},"language":"en","primary_location":{"id":"doi:10.1109/bibm.2017.8217620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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/A5049126089","display_name":"Antonio Sze-To","orcid":"https://orcid.org/0000-0002-0362-3516"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Antonio Sze-To","raw_affiliation_strings":["Systems Design Engineering, University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems Design Engineering, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5051841038","display_name":"Andrew K. C. Wong","orcid":"https://orcid.org/0000-0002-0019-7152"},"institutions":[{"id":"https://openalex.org/I151746483","display_name":"University of Waterloo","ror":"https://ror.org/01aff2v68","country_code":"CA","type":"education","lineage":["https://openalex.org/I151746483"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Andrew K. C. Wong","raw_affiliation_strings":["Systems Design Engineering, University of Waterloo, Waterloo, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Systems Design Engineering, University of Waterloo, Waterloo, Canada","institution_ids":["https://openalex.org/I151746483"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2243,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.57752421,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"28","last_page":"35"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994000196456909,"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":0.9994000196456909,"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":0.9988999962806702,"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":0.9954000115394592,"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":0.6314094066619873},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.6210432052612305},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6019155979156494},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4422457218170166},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42378100752830505},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.40290018916130066},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.39012953639030457},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24960404634475708}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6314094066619873},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6210432052612305},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6019155979156494},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4422457218170166},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42378100752830505},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.40290018916130066},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.39012953639030457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24960404634475708}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm.2017.8217620","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm.2017.8217620","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","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":16,"referenced_works":["https://openalex.org/W1709815505","https://openalex.org/W1975372386","https://openalex.org/W2051664277","https://openalex.org/W2066376795","https://openalex.org/W2092672051","https://openalex.org/W2115979107","https://openalex.org/W2130468514","https://openalex.org/W2135621733","https://openalex.org/W2137991504","https://openalex.org/W2141224484","https://openalex.org/W2147526198","https://openalex.org/W2150415479","https://openalex.org/W2323530184","https://openalex.org/W2337408142","https://openalex.org/W2557496587","https://openalex.org/W4233624322"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2158836806","https://openalex.org/W2393816671","https://openalex.org/W2083665254","https://openalex.org/W2787993192"],"abstract_inverted_index":{"Functional":[0],"region":[1,70],"identification":[2],"is":[3,31,63,91,159,166],"of":[4,146,163,188],"fundamental":[5],"importance":[6],"for":[7,11,94],"protein":[8,13,68,117],"sequences":[9],"analysis":[10],"a":[12,20,57,64,76,78,100,155,219],"family.":[14],"Such":[15],"knowledge":[16],"not":[17],"only":[18],"provides":[19],"better":[21],"scientific":[22],"understanding":[23],"but":[24,34],"also":[25],"assists":[26],"drug":[27],"discovery.":[28],"Domain":[29],"annotation":[30],"one":[32],"approach":[33],"it":[35,90],"needs":[36,82],"to":[37,74,83,110,141,168,227,234],"leverage":[38],"existing":[39],"databases.":[40],"For":[41],"de":[42],"novo":[43],"discovery,":[44],"motif":[45,206],"discovery":[46,207],"locates":[47],"and":[48,53,112,151,175,199,222],"aligns":[49],"locally":[50],"similar":[51],"sub-sequences":[52],"represents":[54],"them":[55],"as":[56,104,126],"position-weight":[58],"matrix":[59],"(PWM).":[60],"However,":[61],"PWM":[62],"fixed-length":[65],"model":[66,129],"whereas":[67],"functional":[69,118],"size":[71,198],"varies.":[72],"Furthermore,":[73],"obtain":[75],"PWM,":[77],"width":[79],"range":[80],"parameter":[81],"be":[84],"identified":[85],"through":[86],"exhaustive":[87],"search.":[88],"Hence,":[89],"computational":[92,230],"intensive":[93],"large":[95],"dataset.":[96],"This":[97],"paper":[98],"presents":[99],"new":[101],"method":[102],"known":[103],"Pattern-Directed":[105],"Aligned":[106,122],"Pattern":[107,123],"Clustering":[108],"(PD-APCn)":[109],"discover":[111],"align":[113],"residues":[114],"in":[115],"conserved":[116,171],"regions.":[119],"It":[120,135],"adopts":[121],"Cluster":[124],"(APC)":[125],"the":[127,143,147,186,204,216],"representation":[128],"which":[130],"allows":[131],"variable":[132],"pattern":[133],"length.":[134],"uses":[136],"patterns":[137,172],"with":[138,173,196,203,225],"strong":[139],"support":[140],"direct":[142],"incremental":[144],"expansion":[145],"APCs,":[148],"allowing":[149],"substitution":[150,174],"frame-shift":[152,176],"mutations,":[153,177],"until":[154],"robust":[156],"termination":[157],"condition":[158],"reached.":[160],"The":[161],"concept":[162],"breakpoint":[164],"gap":[165],"introduced":[167],"identify":[169],"uncovered":[170],"where":[178],"these":[179],"are":[180],"often":[181],"rare":[182],"mutants.":[183],"To":[184],"evaluate":[185],"performance":[187,214],"PD-APCn,":[189],"we":[190],"conducted":[191],"experiments":[192],"on":[193],"synthetic":[194],"datasets":[195],"different":[197],"noise":[200],"level.":[201],"Comparing":[202],"popular":[205],"algorithm":[208],"MEME,":[209],"PD-APCn":[210],"has":[211],"demonstrated":[212],"competitive":[213],"throughout":[215],"experiments,":[217],"obtaining":[218],"higher":[220],"recall":[221],"F":[223],"measure":[224],"up":[226,232],"400\u00d7":[228],"significant":[229],"speed":[231],"comparing":[233],"MEME.":[235]},"counts_by_year":[{"year":2018,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}