{"id":"https://openalex.org/W2150415479","doi":"https://doi.org/10.1109/tcbb.2014.2306840","title":"Aligning and Clustering Patterns to Reveal the Protein Functionality of Sequences","display_name":"Aligning and Clustering Patterns to Reveal the Protein Functionality of Sequences","publication_year":2014,"publication_date":"2014-02-20","ids":{"openalex":"https://openalex.org/W2150415479","doi":"https://doi.org/10.1109/tcbb.2014.2306840","mag":"2150415479","pmid":"https://pubmed.ncbi.nlm.nih.gov/26356022"},"language":"en","primary_location":{"id":"doi:10.1109/tcbb.2014.2306840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2306840","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5051841038","display_name":"Andrew K. C. Wong","orcid":"https://orcid.org/0000-0002-0019-7152"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Andrew K. C. Wong","raw_affiliation_strings":["Department of Systems Design Engineering, Waterloo, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Design Engineering, Waterloo, Ontario, Canada","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054354683","display_name":"En-Shiun Annie Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"En-Shiun Annie Lee","raw_affiliation_strings":["Department of Systems Design Engineering, Waterloo, Ontario, Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Systems Design Engineering, Waterloo, Ontario, Canada","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.5656,"has_fulltext":false,"cited_by_count":29,"citation_normalized_percentile":{"value":0.83037679,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"11","issue":"3","first_page":"548","last_page":"560"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9955999851226807,"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":0.9955999851226807,"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":0.9890999794006348,"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":0.986299991607666,"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":0.6923233270645142},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6038677096366882},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5879495739936829},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5595850348472595},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.510158360004425},{"id":"https://openalex.org/keywords/triosephosphate-isomerase","display_name":"Triosephosphate isomerase","score":0.502952516078949},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.462080717086792},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43814817070961},{"id":"https://openalex.org/keywords/multiple-sequence-alignment","display_name":"Multiple sequence alignment","score":0.41872987151145935},{"id":"https://openalex.org/keywords/protein-family","display_name":"Protein family","score":0.4111171066761017},{"id":"https://openalex.org/keywords/sequence-alignment","display_name":"Sequence alignment","score":0.38896387815475464},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.38050535321235657},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2764394283294678},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2678021788597107},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.23359331488609314},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1445692479610443}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6923233270645142},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6038677096366882},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5879495739936829},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5595850348472595},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.510158360004425},{"id":"https://openalex.org/C2778727959","wikidata":"https://www.wikidata.org/wiki/Q24777683","display_name":"Triosephosphate isomerase","level":3,"score":0.502952516078949},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.462080717086792},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43814817070961},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.41872987151145935},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.4111171066761017},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.38896387815475464},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.38050535321235657},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2764394283294678},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2678021788597107},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.23359331488609314},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1445692479610443},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016000","descriptor_name":"Cluster Analysis","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1109/tcbb.2014.2306840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcbb.2014.2306840","pdf_url":null,"source":{"id":"https://openalex.org/S36029991","display_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","issn_l":"1545-5963","issn":["1545-5963","1557-9964","2374-0043"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE/ACM Transactions on Computational Biology and Bioinformatics","raw_type":"journal-article"},{"id":"pmid:26356022","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26356022","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":"IEEE/ACM transactions on computational biology and bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15","score":0.6200000047683716}],"awards":[],"funders":[{"id":"https://openalex.org/F4320310207","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":40,"referenced_works":["https://openalex.org/W2812445","https://openalex.org/W1483191758","https://openalex.org/W1499798127","https://openalex.org/W1531116739","https://openalex.org/W1560026119","https://openalex.org/W1580213736","https://openalex.org/W1967305892","https://openalex.org/W1985856261","https://openalex.org/W1985912243","https://openalex.org/W1998300401","https://openalex.org/W2003967338","https://openalex.org/W2012019831","https://openalex.org/W2028904582","https://openalex.org/W2030284680","https://openalex.org/W2047082004","https://openalex.org/W2049591520","https://openalex.org/W2051664277","https://openalex.org/W2056002855","https://openalex.org/W2065200208","https://openalex.org/W2073719763","https://openalex.org/W2074231493","https://openalex.org/W2087064593","https://openalex.org/W2092672051","https://openalex.org/W2101220662","https://openalex.org/W2103447044","https://openalex.org/W2106882534","https://openalex.org/W2126625758","https://openalex.org/W2129448726","https://openalex.org/W2130468514","https://openalex.org/W2141224484","https://openalex.org/W2141408320","https://openalex.org/W2143210482","https://openalex.org/W2144362290","https://openalex.org/W2147580225","https://openalex.org/W2147758638","https://openalex.org/W2157009395","https://openalex.org/W2164814636","https://openalex.org/W4245696637","https://openalex.org/W4255447217","https://openalex.org/W6600102646"],"related_works":["https://openalex.org/W2051969447","https://openalex.org/W2111937814","https://openalex.org/W2162923930","https://openalex.org/W1482324242","https://openalex.org/W2133116680","https://openalex.org/W2091678889","https://openalex.org/W2029514038","https://openalex.org/W2075451741","https://openalex.org/W2036521446","https://openalex.org/W2765585254"],"abstract_inverted_index":{"Discovering":[0],"sequence":[1,77],"patterns":[2,17,50,131,186],"with":[3,18,51,178,187],"variations":[4,19,52,106,188],"unveils":[5],"significant":[6,76,130],"functions":[7],"of":[8,15,31,73,88,107,120,185],"a":[9,43,54,70],"protein":[10,89,150],"family.":[11],"Existing":[12],"combinatorial":[13],"methods":[14,25],"discovering":[16],"are":[20],"computationally":[21,45],"expensive,":[22],"and":[23,95,105,134,146,181,195],"probabilistic":[24,29],"require":[26],"more":[27,118],"elaborate":[28],"representation":[30,56,87],"the":[32,65,86,103,108,124,141,144,147,155,161,175],"amino":[33],"acid":[34],"associations.":[35],"To":[36,63,84],"overcome":[37],"these":[38],"shortcomings,":[39],"this":[40,100],"paper":[41,101],"presents":[42],"new":[44],"efficient":[46],"method":[47,68],"for":[48],"representing":[49],"in":[53,99,174],"compact":[55],"called":[57],"Aligned":[58],"Pattern":[59],"Cluster":[60],"(AP":[61],"Cluster).":[62],"tackle":[64],"runtime,":[66],"our":[67,81,92,114,152],"discovers":[69,170],"shortened":[71],"list":[72],"non-redundant":[74],"statistically":[75,129],"associations":[78],"based":[79],"on":[80],"previous":[82],"work.":[83],"address":[85],"functional":[90],"regions,":[91],"pattern":[93],"alignment":[94],"clustering":[96],"step,":[97],"presented":[98],"captures":[102],"conservations":[104],"aligned":[109],"patterns.":[110],"We":[111],"further":[112],"refine":[113],"solution":[115],"to":[116,132,140,166,191],"allow":[117],"coverage":[119],"sequences":[121],"via":[122],"extending":[123],"AP":[125,136,176],"Clusters":[126,177],"containing":[127],"only":[128],"Weak":[133],"Conserved":[135],"Clusters.":[137],"When":[138,164],"applied":[139],"cytochrome":[142],"c,":[143],"ubiquitin,":[145],"triosephosphate":[148],"isomerase":[149],"families,":[151],"algorithm":[153],"identifies":[154],"binding":[156,162,172],"segments":[157],"as":[158,160],"well":[159],"residues.":[163],"compared":[165],"other":[167],"methods,":[168],"ours":[169],"all":[171],"sites":[173],"superior":[179],"entropy":[180],"coverage.":[182],"The":[183],"identification":[184],"help":[189],"biologists":[190],"avoid":[192],"time-consuming":[193],"simulations":[194],"experimentations.":[196],"(Software":[197],"available":[198],"upon":[199],"request).":[200]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":2},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":4},{"year":2015,"cited_by_count":3},{"year":2014,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}