{"id":"https://openalex.org/W4249872424","doi":"https://doi.org/10.1109/icpr.2004.1334254","title":"An efficient technique for protein sequence clustering and classification","display_name":"An efficient technique for protein sequence clustering and classification","publication_year":2004,"publication_date":"2004-01-01","ids":{"openalex":"https://openalex.org/W4249872424","doi":"https://doi.org/10.1109/icpr.2004.1334254"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2004.1334254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334254","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","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/A5086823033","display_name":"P.A. Vijaya","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"P.A. Vijaya","raw_affiliation_strings":["Department of Computer Science Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073470852","display_name":"M.N. Murty","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"M.N. Murty","raw_affiliation_strings":["Department of Computer Science Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045191039","display_name":"Dhinakaran Subramanian","orcid":null},"institutions":[{"id":"https://openalex.org/I59270414","display_name":"Indian Institute of Science Bangalore","ror":"https://ror.org/04dese585","country_code":"IN","type":"education","lineage":["https://openalex.org/I59270414"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"D.K. Subramanian","raw_affiliation_strings":["Department of Computer Science Automation, Indian Institute of Science, Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science Automation, Indian Institute of Science, Bangalore, India","institution_ids":["https://openalex.org/I59270414"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5086823033"],"corresponding_institution_ids":["https://openalex.org/I59270414"],"apc_list":null,"apc_paid":null,"fwci":0.9224,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.78587699,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"29","issue":null,"first_page":"447","last_page":"450 Vol.2"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9991999864578247,"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":0.9991999864578247,"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":0.9969000220298767,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9961000084877014,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7531557679176331},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.7013294696807861},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.6554887294769287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6159303784370422},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6146773099899292},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5988403558731079},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5289832353591919},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.46455663442611694},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.43609240651130676},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.4112459421157837},{"id":"https://openalex.org/keywords/peptide-sequence","display_name":"Peptide sequence","score":0.12066051363945007},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.0723787248134613}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7531557679176331},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.7013294696807861},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6554887294769287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6159303784370422},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6146773099899292},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5988403558731079},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5289832353591919},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.46455663442611694},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.43609240651130676},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.4112459421157837},{"id":"https://openalex.org/C167625842","wikidata":"https://www.wikidata.org/wiki/Q899763","display_name":"Peptide sequence","level":3,"score":0.12066051363945007},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0723787248134613},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"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/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icpr.2004.1334254","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2004.1334254","pdf_url":null,"source":{"id":"https://openalex.org/S4363608750","display_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004.","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W1505171204","https://openalex.org/W1554135376","https://openalex.org/W1769049279","https://openalex.org/W1992419399","https://openalex.org/W1992648037","https://openalex.org/W1997268601","https://openalex.org/W2008841836","https://openalex.org/W2008907996","https://openalex.org/W2031810922","https://openalex.org/W2076223365","https://openalex.org/W2086403919","https://openalex.org/W2086770662","https://openalex.org/W2122111042","https://openalex.org/W2146827656","https://openalex.org/W6630238339","https://openalex.org/W6637940469"],"related_works":["https://openalex.org/W2981877337","https://openalex.org/W3203938600","https://openalex.org/W2169074127","https://openalex.org/W2163707935","https://openalex.org/W83146503","https://openalex.org/W202723009","https://openalex.org/W2188612292","https://openalex.org/W4206462905","https://openalex.org/W2165396616","https://openalex.org/W2058882606"],"abstract_inverted_index":{"A":[0],"technique":[1],"to":[2],"reduce":[3],"time":[4,81],"and":[5,11,17,79,127],"space":[6,112],"during":[7,116],"protein":[8],"sequence":[9,37,52,105],"clustering":[10],"classification":[12,65],"is":[13,29,44,114],"presented.":[14],"During":[15],"training":[16,78],"testing":[18,80],"phase,":[19],"the":[20,36,40,59,64,69,77,86,91,100,104],"similarity":[21,92],"score":[22,93],"value":[23],"between":[24],"a":[25,33,47,108],"pair":[26],"of":[27,35,39,49,58,103],"sequences":[28],"determined":[30],"by":[31,98],"selecting":[32,46],"portion":[34],"instead":[38],"entire":[41,101],"sequence.":[42],"It":[43],"like":[45],"subset":[48],"features":[50],"for":[51,106],"data":[53],"sets.":[54],"The":[55],"experimental":[56,87],"results":[57,88],"proposed":[60],"method":[61],"show":[62],"that":[63,90],"accuracy":[66],"(CA)":[67],"using":[68,123],"prototypes":[70],"generated/used":[71],"does":[72],"not":[73,95],"degrade":[74],"much":[75],"but":[76],"are":[82],"reduced":[83,115],"significantly.":[84],"Thus":[85],"indicate":[89],"need":[94],"be":[96],"calculated":[97],"considering":[99],"length":[102],"achieving":[107],"good":[109],"CA.":[110],"Even":[111],"requirement":[113],"execution":[117],"phase.":[118],"We":[119],"have":[120],"tested":[121],"this":[122],"K-medians,":[124],"supervised":[125],"K-medians":[126],"nearest":[128],"neighbour":[129],"classifier":[130],"(NNC)":[131],"techniques.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}