{"id":"https://openalex.org/W2012019831","doi":"https://doi.org/10.1145/2506583.2506630","title":"Classifying Proteins by Amino Acid Variations of Sequential Patterns","display_name":"Classifying Proteins by Amino Acid Variations of Sequential Patterns","publication_year":2013,"publication_date":"2013-09-22","ids":{"openalex":"https://openalex.org/W2012019831","doi":"https://doi.org/10.1145/2506583.2506630","mag":"2012019831"},"language":"en","primary_location":{"id":"doi:10.1145/2506583.2506630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2506583.2506630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics","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/A5054354683","display_name":"En-Shiun Annie Lee","orcid":null},"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":"En-Shiun Annie Lee","raw_affiliation_strings":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, Waterloo, Ontario, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, 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":["University of Waterloo, Waterloo, Ontario, Canada","University of Waterloo, Waterloo, Ontario, CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, Canada","institution_ids":["https://openalex.org/I151746483"]},{"raw_affiliation_string":"University of Waterloo, Waterloo, Ontario, 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":0.2992,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.61417506,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"276","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9983999729156494,"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":0.998199999332428,"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/entropy","display_name":"Entropy (arrow of time)","score":0.5704806447029114},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5669602751731873},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5601314306259155},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5344628095626831},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4771553874015808},{"id":"https://openalex.org/keywords/mutual-information","display_name":"Mutual information","score":0.46057912707328796},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.4329332113265991},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.35968631505966187},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34379255771636963}],"concepts":[{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5704806447029114},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5669602751731873},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5601314306259155},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5344628095626831},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4771553874015808},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.46057912707328796},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.4329332113265991},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.35968631505966187},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34379255771636963},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2506583.2506630","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2506583.2506630","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Conference on Bioinformatics, Computational Biology and Biomedical Informatics","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W1912673154","https://openalex.org/W1967305892","https://openalex.org/W1974771527","https://openalex.org/W1994400985","https://openalex.org/W1995918845","https://openalex.org/W2041404167","https://openalex.org/W2047304481","https://openalex.org/W2051664277","https://openalex.org/W2065200208","https://openalex.org/W2072325671","https://openalex.org/W2079436643","https://openalex.org/W2080553628","https://openalex.org/W2101090646","https://openalex.org/W2119290215","https://openalex.org/W2126625758","https://openalex.org/W2140244239","https://openalex.org/W2151831732","https://openalex.org/W2170960297","https://openalex.org/W2951351205","https://openalex.org/W2978725006","https://openalex.org/W3008624235","https://openalex.org/W3150158916"],"related_works":["https://openalex.org/W2036846997","https://openalex.org/W2112223184","https://openalex.org/W2347586617","https://openalex.org/W2161963661","https://openalex.org/W2125614474","https://openalex.org/W2295845123","https://openalex.org/W2358054814","https://openalex.org/W2090882960","https://openalex.org/W2889544313","https://openalex.org/W2165061339"],"abstract_inverted_index":{"Similarities":[0],"and":[1,13,38,50,53,83,90,105,125,131,172,195,225,234,245,257,286],"differences":[2],"in":[3,128,152,208,294],"protein":[4,17,176,206],"sequence":[5,48,240],"patterns":[6,33,49,82,241],"can":[7,252],"be":[8,253,259],"used":[9],"to":[10,35],"reveal":[11,31,238],"essential":[12],"class-specific":[14],"functionality":[15,37],"of":[16,135,144,183,185,221,242,281,289],"families.":[18,177],"Traditional":[19],"supervised":[20],"learning":[21],"methods":[22],"require":[23,72],"class":[24,73,78,92,101,112,256,271],"labels":[25,74],"for":[26,44,81,96,261],"classifying":[27],"sequences":[28],"but":[29],"cannot":[30],"embedded":[32],"related":[34],"inherent":[36],"taxonomical":[39],"variations.":[40],"We":[41,61,155],"develop":[42],"algorithm":[43],"discovering":[45],"statistically":[46],"significant":[47],"then":[51],"aligning":[52],"clustering":[54],"them":[55],"into":[56],"Aligned":[57,158],"Patterns":[58],"Clusters":[59],"(APCs).":[60],"measure":[62,108,224],"APC's":[63],"classification":[64,181],"ability:":[65],"1)":[66],"with":[67,147,232,255],"semi-supervised":[68],"information":[69,93],"measures":[70,188],"that":[71,120],"such":[75,114],"as:":[76,115],"a)":[77,116,163],"entropy":[79],"(H)":[80],"each":[84,97,184,222,250],"amino":[85,102,122,246,262],"acid":[86,103,123,127,247,263],"on":[87,111,202,249,270],"a":[88,129,145,190,209],"column;":[89],"b)":[91,132,168],"gain":[94],"(IG)":[95],"column":[98,130,146,251],"based":[99],"its":[100],"distribution":[104,248],"2)":[106],"unsupervised":[107],"without":[109],"relying":[110],"labels,":[113],"Entropy":[117],"Redundancy":[118,138],"(R1)":[119],"reflects":[121],"conservation":[124],"diversity":[126],"Normalized":[133],"Sum":[134],"Mutual":[136],"Information":[137],"(SR2)":[139],"which":[140,273],"characterizes":[141],"the":[142,149,153,169,174,180,186,196,203,219,227,230,243,268,282,290,295],"dependence":[143],"all":[148,213],"other":[150,204],"columns":[151],"APC.":[154],"applied":[156],"our":[157,214],"Pattern":[159],"Synthesis":[160],"Process":[161],"on:":[162],"spermidine":[164],"/":[165],"spermine-N1-acetyltransferase":[166],"(SSAT),":[167],"cytochrome":[170],"c,":[171],"c)":[173],"ubiquitin":[175],"After":[178],"validating":[179],"ability":[182,220],"proposed":[187,223],"through":[189],"simple":[191],"synthetic":[192],"data":[193],"set":[194],"SAAT":[197],"data,":[198],"we":[199,216],"present":[200],"results":[201],"two":[205],"families":[207],"selective":[210],"manner.":[211],"In":[212],"experiments,":[215],"have":[217],"demonstrated":[218],"confirm":[226],"correlation":[228],"between":[229],"SR2":[231],"R1":[233],"IG.":[235],"Our":[236],"experiments":[237],"how":[239],"rows":[244],"associated":[254],"will":[258],"useful":[260],"substitution":[264],"study,":[265],"thus":[266],"avoiding":[267],"dependencies":[269],"label,":[272],"are":[274,292],"often":[275],"unavailable,":[276],"inaccurate,":[277],"or":[278],"unbalanced.":[279],"Properties":[280],"measures,":[283],"computational":[284],"efficiency":[285],"biological":[287],"impact":[288],"algorithms":[291],"discussed":[293],"paper.":[296]},"counts_by_year":[{"year":2014,"cited_by_count":1},{"year":2013,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}