{"id":"https://openalex.org/W2128786211","doi":"https://doi.org/10.1109/bibe.2003.1188976","title":"An assessment of a metric space database index to support sequence homology","display_name":"An assessment of a metric space database index to support sequence homology","publication_year":2003,"publication_date":"2003-11-20","ids":{"openalex":"https://openalex.org/W2128786211","doi":"https://doi.org/10.1109/bibe.2003.1188976","mag":"2128786211"},"language":"en","primary_location":{"id":"doi:10.1109/bibe.2003.1188976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2003.1188976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE Symposium on Bioinformatics and Bioengineering, 2003. Proceedings.","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/A5101724957","display_name":"Rui Mao","orcid":"https://orcid.org/0000-0002-3645-5520"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Rui Mao","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, USA","Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101883722","display_name":"Weijia Xu","orcid":"https://orcid.org/0000-0002-5134-6381"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weijia Xu","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, USA","Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069783174","display_name":"Neha Singh","orcid":"https://orcid.org/0000-0002-9412-8528"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neha Singh","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, USA","Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#","institution_ids":["https://openalex.org/I86519309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083499808","display_name":"Daniel P. Miranker","orcid":"https://orcid.org/0009-0003-8838-2890"},"institutions":[{"id":"https://openalex.org/I86519309","display_name":"The University of Texas at Austin","ror":"https://ror.org/00hj54h04","country_code":"US","type":"education","lineage":["https://openalex.org/I86519309"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"D.P. Miranker","raw_affiliation_strings":["Department of Computer Sciences, University of Texas, Austin, Austin, USA","Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Sciences, University of Texas, Austin, Austin, USA","institution_ids":["https://openalex.org/I86519309"]},{"raw_affiliation_string":"Department of Computer Sciences, The University of Texas at Austin, 1 University Station, C0500 Austin, TX 78712-0233, USA#TAB#","institution_ids":["https://openalex.org/I86519309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5101724957"],"corresponding_institution_ids":["https://openalex.org/I86519309"],"apc_list":null,"apc_paid":null,"fwci":2.0741,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.8840211,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"5","issue":null,"first_page":"375","last_page":"382"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10519","display_name":"Advanced Proteomics Techniques and Applications","score":0.9954000115394592,"subfield":{"id":"https://openalex.org/subfields/1607","display_name":"Spectroscopy"},"field":{"id":"https://openalex.org/fields/16","display_name":"Chemistry"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9785000085830688,"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/computer-science","display_name":"Computer science","score":0.7360294461250305},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6509157419204712},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6330704689025879},{"id":"https://openalex.org/keywords/curse-of-dimensionality","display_name":"Curse of dimensionality","score":0.575387179851532},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.5666148662567139},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.543308436870575},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5274291634559631},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.4777997136116028},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.39421507716178894},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.34840327501296997},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.3152139186859131},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.20432454347610474}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7360294461250305},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6509157419204712},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6330704689025879},{"id":"https://openalex.org/C111030470","wikidata":"https://www.wikidata.org/wiki/Q1430460","display_name":"Curse of dimensionality","level":2,"score":0.575387179851532},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.5666148662567139},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.543308436870575},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5274291634559631},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.4777997136116028},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.39421507716178894},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.34840327501296997},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3152139186859131},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.20432454347610474},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibe.2003.1188976","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibe.2003.1188976","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Third IEEE Symposium on Bioinformatics and Bioengineering, 2003. Proceedings.","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":37,"referenced_works":["https://openalex.org/W125925666","https://openalex.org/W938539187","https://openalex.org/W1509426348","https://openalex.org/W1554174647","https://openalex.org/W1971927246","https://openalex.org/W1974434915","https://openalex.org/W1990061958","https://openalex.org/W1994529543","https://openalex.org/W2006122215","https://openalex.org/W2012481064","https://openalex.org/W2038044292","https://openalex.org/W2049644877","https://openalex.org/W2055391790","https://openalex.org/W2072391778","https://openalex.org/W2073583237","https://openalex.org/W2074231493","https://openalex.org/W2087286364","https://openalex.org/W2091967195","https://openalex.org/W2106642566","https://openalex.org/W2107302432","https://openalex.org/W2118269922","https://openalex.org/W2136145671","https://openalex.org/W2143642163","https://openalex.org/W2157092487","https://openalex.org/W2165156013","https://openalex.org/W2169036209","https://openalex.org/W2320748401","https://openalex.org/W2600349519","https://openalex.org/W2601913882","https://openalex.org/W4252546523","https://openalex.org/W4285719527","https://openalex.org/W6605063754","https://openalex.org/W6606249707","https://openalex.org/W6630456963","https://openalex.org/W6632963374","https://openalex.org/W6675880266","https://openalex.org/W6682969285"],"related_works":["https://openalex.org/W1583922594","https://openalex.org/W2998448420","https://openalex.org/W1974038726","https://openalex.org/W1953626159","https://openalex.org/W1598224733","https://openalex.org/W4304731099","https://openalex.org/W4280502676","https://openalex.org/W2000769876","https://openalex.org/W3095240633","https://openalex.org/W75168880"],"abstract_inverted_index":{"Hierarchical":[0],"metric-space":[1,95],"clustering":[2,20,135],"methods":[3],"have":[4],"been":[5],"commonly":[6],"used":[7],"to":[8,63,99,113,136],"organize":[9,81],"proteomes":[10],"into":[11],"taxonomies.":[12],"Consequently,":[13],"it":[14],"is":[15,42,111],"often":[16],"anticipated":[17],"that":[18,129],"hierarchical":[19,126],"can":[21],"be":[22],"leveraged":[23],"as":[24,84],"a":[25,73,149],"basis":[26],"for":[27,48],"scalable":[28],"database":[29,83],"index":[30,110,152],"structures":[31],"capable":[32],"of":[33,38,51,61,68,86,102,108,116,120],"managing":[34],"the":[35,49,59,64,82,105,114,117,121,138,141,144,154],"hyper-exponential":[36],"growth":[37],"sequence":[39,70],"data.":[40,71],"M-tree":[41,156],"one":[43],"such":[44],"data":[45,53],"structure":[46],"specialized":[47],"management":[50],"large":[52],"sets":[54],"on":[55],"disk.":[56],"We":[57,123],"explore":[58],"application":[60],"M-trees":[62],"storage":[65],"and":[66,104,133],"retrieval":[67],"peptide":[69],"Exploiting":[72],"technique":[74],"first":[75],"suggested":[76],"by":[77],"Myers":[78],"(1994),":[79],"we":[80],"records":[85],"fixed":[87],"length":[88],"substrings.":[89],"Empirical":[90],"results":[91],"are":[92,97],"promising.":[93],"However,":[94],"indexes":[96],"subject":[98],"\"the":[100],"curse":[101],"dimensionality\"":[103],"ultimate":[106],"performance":[107],"an":[109],"sensitive":[112],"quality":[115],"initial":[118],"construction":[119],"index.":[122,139],"introduce":[124],"new":[125],"bulk-load":[127],"algorithm":[128],"alternates":[130],"between":[131],"top-down":[132],"bottom-up":[134],"initialize":[137],"Using":[140],"Yeast":[142],"Proteomes,":[143],"bi-directional":[145],"bulk":[146],"load":[147],"produces":[148],"more":[150],"effective":[151],"than":[153],"existing":[155],"initialization":[157],"algorithms.":[158]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}