{"id":"https://openalex.org/W2110798090","doi":"https://doi.org/10.1109/tai.2003.1250166","title":"Order-sensitive clustering for remote homologous protein detection","display_name":"Order-sensitive clustering for remote homologous protein detection","publication_year":2004,"publication_date":"2004-03-01","ids":{"openalex":"https://openalex.org/W2110798090","doi":"https://doi.org/10.1109/tai.2003.1250166","mag":"2110798090"},"language":"en","primary_location":{"id":"doi:10.1109/tai.2003.1250166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2003.1250166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence","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/A5100457173","display_name":"Jin Chen","orcid":"https://orcid.org/0000-0002-6634-4397"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Jin Chen","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput., National Univ. of Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput., National Univ. of Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051209739","display_name":"Wynne Hsu","orcid":"https://orcid.org/0000-0002-4142-8893"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Wynne Hsu","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput., National Univ. of Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput., National Univ. of Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019988958","display_name":"Mong Li Lee","orcid":"https://orcid.org/0000-0002-9636-388X"},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Mong Li Lee","raw_affiliation_strings":["School of Computing, National University of Singapore, Singapore","Sch. of Comput., National Univ. of Singapore, Singapore#TAB#"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Sch. of Comput., National Univ. of Singapore, Singapore#TAB#","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5100457173"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.11215283,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"26","last_page":"30"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9993000030517578,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.9943000078201294,"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":0.7503048181533813},{"id":"https://openalex.org/keywords/protein-superfamily","display_name":"Protein superfamily","score":0.6466811895370483},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6427557468414307},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5561764240264893},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.50824373960495},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5070204734802246},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48888081312179565},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4882950782775879},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.4831397235393524},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.4136177897453308},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.34319359064102173},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32451194524765015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2638684809207916},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.24158182740211487},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.22596827149391174},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.12841004133224487},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10919997096061707},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.07384759187698364}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7503048181533813},{"id":"https://openalex.org/C178180057","wikidata":"https://www.wikidata.org/wiki/Q7251477","display_name":"Protein superfamily","level":3,"score":0.6466811895370483},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6427557468414307},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5561764240264893},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.50824373960495},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5070204734802246},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48888081312179565},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4882950782775879},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.4831397235393524},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.4136177897453308},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.34319359064102173},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32451194524765015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2638684809207916},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.24158182740211487},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.22596827149391174},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.12841004133224487},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10919997096061707},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.07384759187698364},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tai.2003.1250166","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tai.2003.1250166","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings. 15th IEEE International Conference on Tools with Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/40941","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/40941","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","issn_l":null,"issn":[],"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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"Conference Paper"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":21,"referenced_works":["https://openalex.org/W1488329660","https://openalex.org/W1560256746","https://openalex.org/W1641039719","https://openalex.org/W1833785989","https://openalex.org/W1956559956","https://openalex.org/W1971318281","https://openalex.org/W1996764654","https://openalex.org/W2013570924","https://openalex.org/W2085277871","https://openalex.org/W2087668094","https://openalex.org/W2124331814","https://openalex.org/W2129621613","https://openalex.org/W2130479394","https://openalex.org/W2145358391","https://openalex.org/W2147694185","https://openalex.org/W2158714788","https://openalex.org/W2325227998","https://openalex.org/W4241122026","https://openalex.org/W6633798638","https://openalex.org/W6636681434","https://openalex.org/W6679358911"],"related_works":["https://openalex.org/W2170171070","https://openalex.org/W1965827393","https://openalex.org/W4235848672","https://openalex.org/W2075451741","https://openalex.org/W2139240863","https://openalex.org/W1793342102","https://openalex.org/W1975591133","https://openalex.org/W2164753093","https://openalex.org/W2821108685","https://openalex.org/W646353556"],"abstract_inverted_index":{"Traditional":[0],"sequence":[1,101],"alignment":[2],"methods":[3],"are":[4,11,31,36,88,144],"effective":[5],"in":[6,64,74],"identifying":[7],"homologous":[8,23],"proteins":[9,27],"that":[10,25,42,47,132,143],"highly":[12],"similar.":[13],"However,":[14],"these":[15],"approaches":[16],"do":[17],"not":[18],"perform":[19,100],"well":[20],"for":[21],"remote":[22],"proteins,":[24],"is,":[26],"whose":[28],"3D":[29,50],"structures":[30],"similar":[32,145],"but":[33],"their":[34],"sequences":[35,44,118],"not.":[37],"Recent":[38],"biological":[39],"research":[40],"reveals":[41],"protein":[43,68,72,92,117],"contain":[45],"residues":[46,73],"determine":[48],"the":[49,65,75,85,91,96,105,120,151],"structure":[51],"of":[52,67,77],"proteins.":[53],"In":[54],"this":[55,60],"work,":[56],"we":[57,99,110],"investigate":[58],"incorporating":[59],"information":[61],"to":[62,103,115,138,146],"aid":[63],"clustering":[66],"databases.":[69],"We":[70],"capture":[71],"form":[76],"patterns":[78,87,121],"with":[79],"fixed":[80],"order":[81,106,123],"among":[82,107],"them.":[83,108],"First,":[84],"significant":[86],"extracted":[89,97],"from":[90],"sequences.":[93],"Based":[94],"on":[95,126],"patterns,":[98],"mining":[102],"generate":[104,139],"Finally,":[109],"adopt":[111],"a":[112],"partition-based":[113],"method":[114],"cluster":[116],"using":[119],"and":[122,128],"features.":[124],"Experiments":[125],"COG":[127],"SCOP40":[129],"datasets":[130],"show":[131],"our":[133],"new":[134],"approach":[135],"is":[136],"able":[137],"high":[140],"quality":[141],"clusters":[142],"those":[147],"determined":[148],"manually":[149],"by":[150],"biologists.":[152]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}