{"id":"https://openalex.org/W2099698841","doi":"https://doi.org/10.1093/bioinformatics/bth036","title":"Rapid 3D protein structure database searching using information retrieval techniques","display_name":"Rapid 3D protein structure database searching using information retrieval techniques","publication_year":2004,"publication_date":"2004-02-12","ids":{"openalex":"https://openalex.org/W2099698841","doi":"https://doi.org/10.1093/bioinformatics/bth036","mag":"2099698841","pmid":"https://pubmed.ncbi.nlm.nih.gov/14962928"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/bth036","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth036","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","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/A5005863795","display_name":"Zeyar Aung","orcid":"https://orcid.org/0000-0001-5990-9305"},"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":"Zeyar Aung","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, 3 Science Drive 2, Singapore 117543","Department of Computer Science, National University of Singapore, 3 Science Drive 2 Singapore 117543#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, 3 Science Drive 2, Singapore 117543","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, 3 Science Drive 2 Singapore 117543#TAB#","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5077593594","display_name":"Kian\u2010Lee Tan","orcid":"https://orcid.org/0000-0001-9315-4057"},"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":"Kian-Lee Tan","raw_affiliation_strings":["Department of Computer Science, National University of Singapore, 3 Science Drive 2, Singapore 117543","Department of Computer Science, National University of Singapore, 3 Science Drive 2 Singapore 117543#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, 3 Science Drive 2, Singapore 117543","institution_ids":["https://openalex.org/I165932596"]},{"raw_affiliation_string":"Department of Computer Science, National University of Singapore, 3 Science Drive 2 Singapore 117543#TAB#","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5005863795"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":2.0357,"has_fulltext":false,"cited_by_count":51,"citation_normalized_percentile":{"value":0.85982614,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"20","issue":"7","first_page":"1045","last_page":"1052"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.6761999726295471,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.6761999726295471,"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/T11162","display_name":"Enzyme Structure and Function","score":0.061000000685453415,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.05490000173449516,"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/computer-science","display_name":"Computer science","score":0.8027600646018982},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6039101481437683},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.5931414365768433},{"id":"https://openalex.org/keywords/protein-structure-database","display_name":"Protein structure database","score":0.5296050310134888},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.48733314871788025},{"id":"https://openalex.org/keywords/database-index","display_name":"Database index","score":0.48431602120399475},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4763084650039673},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4738274812698364},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4303862750530243},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.4246675968170166},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.2875153422355652},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.11804282665252686}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8027600646018982},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6039101481437683},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.5931414365768433},{"id":"https://openalex.org/C136475424","wikidata":"https://www.wikidata.org/wiki/Q7251500","display_name":"Protein structure database","level":4,"score":0.5296050310134888},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.48733314871788025},{"id":"https://openalex.org/C59276292","wikidata":"https://www.wikidata.org/wiki/Q580427","display_name":"Database index","level":3,"score":0.48431602120399475},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4763084650039673},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4738274812698364},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4303862750530243},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.4246675968170166},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.2875153422355652},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.11804282665252686},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000595","descriptor_name":"Amino Acid Sequence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003198","descriptor_name":"Computer Simulation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D003628","descriptor_name":"Database Management Systems","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008969","descriptor_name":"Molecular Sequence Data","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D011487","descriptor_name":"Protein Conformation","qualifier_ui":null,"qualifier_name":null,"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":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012680","descriptor_name":"Sensitivity and Specificity","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015203","descriptor_name":"Reproducibility of Results","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D016247","descriptor_name":"Information Storage and Retrieval","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/bth036","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/bth036","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:14962928","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/14962928","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:scholarbank.nus.edu.sg:10635/39164","is_oa":false,"landing_page_url":"http://scholarbank.nus.edu.sg/handle/10635/39164","pdf_url":null,"source":{"id":"https://openalex.org/S7407052290","display_name":"National University of Singapore","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":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Scopus","raw_type":"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/W1510161841","https://openalex.org/W1520321564","https://openalex.org/W1876353827","https://openalex.org/W1965910641","https://openalex.org/W2003415917","https://openalex.org/W2022058405","https://openalex.org/W2030428223","https://openalex.org/W2103264682","https://openalex.org/W2113563422","https://openalex.org/W2117077088","https://openalex.org/W2130479394","https://openalex.org/W2144453646","https://openalex.org/W2145358391","https://openalex.org/W2152024417","https://openalex.org/W2152326664","https://openalex.org/W2167120101"],"related_works":["https://openalex.org/W2413339343","https://openalex.org/W2357241418","https://openalex.org/W1681204582","https://openalex.org/W2086064646","https://openalex.org/W2119135658","https://openalex.org/W2115485936","https://openalex.org/W2389993829","https://openalex.org/W2555949133","https://openalex.org/W2199640993","https://openalex.org/W4285503973"],"abstract_inverted_index":{"MOTIVATION:":[0],"As":[1],"the":[2,31,50,72,80,85,89,92,99,104,148,151],"sizes":[3],"of":[4,88,97,114,150,169],"three-dimensional":[5],"(3D)":[6],"protein":[7,40,101,137],"structure":[8,22,29,41,70,94,138],"databases":[9],"are":[10],"growing":[11],"rapidly":[12],"nowadays,":[13],"exhaustive":[14],"database":[15,62],"searching,":[16],"in":[17,30,46,53,57,71,103,112],"which":[18,47],"a":[19,37,108,156],"3D":[20,39,69,100],"query":[21],"is":[23,77,107,130,163,174],"compared":[24],"to":[25,59,67],"each":[26],"and":[27,116,142],"every":[28,68],"database,":[32],"becomes":[33],"inefficient.":[34],"We":[35],"propose":[36],"rapid":[38,61],"retrieval":[42,55,75],"system":[43],"named":[44],"'ProtDex2',":[45],"we":[48],"adopt":[49],"techniques":[51],"used":[52],"information":[54],"systems":[56],"order":[58],"perform":[60],"searching":[63],"without":[64],"having":[65],"access":[66],"database.":[73,105],"The":[74,124,172],"process":[76],"based":[78],"on":[79,84,147],"inverted-file":[81],"index":[82],"constructed":[83],"feature":[86],"vectors":[87],"relationships":[90],"between":[91],"secondary":[93],"elements":[95],"(SSEs)":[96],"all":[98],"structures":[102],"ProtDex2":[106,129,162],"significant":[109],"improvement,":[110],"both":[111],"terms":[113],"speed":[115],"accuracy,":[117],"upon":[118],"its":[119],"predecessor":[120],"system,":[121],"ProtDex.":[122],"RESULTS:":[123],"experimental":[125],"results":[126],"show":[127],"that":[128],"very":[131],"much":[132,164],"faster":[133,165],"than":[134],"two":[135],"well-known":[136],"comparison":[139],"methods,":[140],"DALI":[141],"CE,":[143],"yet":[144],"not":[145],"sacrificing":[146],"accuracy":[149],"comparison.":[152],"When":[153],"comparing":[154],"with":[155,166],"similar":[157],"SSE-based":[158],"method,":[159],"namely":[160],"TopScan,":[161],"comparable":[167],"degree":[168],"accuracy.":[170],"AVAILABILITY:":[171],"software":[173],"available":[175],"at:":[176],"http://xena1.ddns.comp.nus.edu.sg/~genesis/PD2.htm":[177]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":2},{"year":2013,"cited_by_count":5},{"year":2012,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
