{"id":"https://openalex.org/W2105099387","doi":"https://doi.org/10.1093/bioinformatics/btl102","title":"A machine learning information retrieval approach to protein fold recognition","display_name":"A machine learning information retrieval approach to protein fold recognition","publication_year":2006,"publication_date":"2006-03-17","ids":{"openalex":"https://openalex.org/W2105099387","doi":"https://doi.org/10.1093/bioinformatics/btl102","mag":"2105099387","pmid":"https://pubmed.ncbi.nlm.nih.gov/16547073"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btl102","doi":"https://doi.org/10.1093/bioinformatics/btl102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/12/1456/48838580/bioinformatics_22_12_1456.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"volume":null,"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/22/12/1456/48838580/bioinformatics_22_12_1456.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5044354277","display_name":"Jianlin Jack Cheng","orcid":"https://orcid.org/0000-0003-0305-2853","observed_orcids":["https://orcid.org/0000-0003-0305-2853"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jianlin Cheng","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California \u00a0 Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California \u00a0 Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5088813478","display_name":"Pierre Baldi","orcid":"https://orcid.org/0000-0001-8752-4664","observed_orcids":["https://orcid.org/0000-0001-8752-4664"]},"institutions":[{"id":"https://openalex.org/I204250578","display_name":"University of California, Irvine","ror":"https://ror.org/04gyf1771","country_code":"US","type":"education","lineage":["https://openalex.org/I204250578"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Pierre Baldi","raw_affiliation_strings":["Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California \u00a0 Irvine, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute for Genomics and Bioinformatics, School of Information and Computer Sciences, University of California \u00a0 Irvine, CA, USA","institution_ids":["https://openalex.org/I204250578"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5088813478"],"corresponding_institution_ids":["https://openalex.org/I204250578"],"apc_list":{"value":3989,"currency":"USD","value_usd":3989},"apc_paid":null,"fwci":10.7323,"has_fulltext":true,"cited_by_count":230,"citation_normalized_percentile":{"value":0.99239582,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":100},"biblio":{"volume":"22","issue":"12","first_page":"1456","last_page":"1463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.989300012588501,"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":0.989300012588501,"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":0.004399999976158142,"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":0.0038999998942017555,"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/protein-fold-recognition","display_name":"protein fold recognition","score":0.9990000128746033},{"id":"https://openalex.org/keywords/template-based-protein-structure-prediction","display_name":"template-based protein structure prediction","score":0.902999997138977},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"information retrieval","score":0.8399999737739563},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"support vector machine","score":0.7960000038146973},{"id":"https://openalex.org/keywords/profile-profile-alignment","display_name":"profile-profile alignment","score":0.7329999804496765},{"id":"https://openalex.org/keywords/protein-tertiary-structure","display_name":"protein tertiary structure","score":0.414000004529953}],"concepts":[{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7039262056350708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6844640374183655},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5854127407073975},{"id":"https://openalex.org/C82714645","wikidata":"https://www.wikidata.org/wiki/Q438331","display_name":"Template","level":2,"score":0.5506762862205505},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.5253122448921204},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49551641941070557},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.47843411564826965},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4205930829048157},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.346259742975235},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09285187721252441},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000818","descriptor_name":"Animals","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001185","descriptor_name":"Artificial Intelligence","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","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":"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":"D015233","descriptor_name":"Models, Statistical","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016011","descriptor_name":"Normal Distribution","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":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017510","descriptor_name":"Protein Folding","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btl102","doi":"https://doi.org/10.1093/bioinformatics/btl102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/12/1456/48838580/bioinformatics_22_12_1456.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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:16547073","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/16547073","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,"listed_in":[],"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":"Journal Article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.129.9831","doi":null,"is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.129.9831","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://bioinformatics.oxfordjournals.org/cgi/reprint/btl102v1.pdf","raw_type":"text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btl102","doi":"https://doi.org/10.1093/bioinformatics/btl102","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btl102","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/22/12/1456/48838580/bioinformatics_22_12_1456.pdf","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,"listed_in":["abdc-a","anvur-class-a","anvur-scientific","ccf-a","cwts-core","doaj","dongbi-b","doyens","jufo-3","ki-jl-2","medline","norway-2","oarl","poland-200","russia-white-list-1","vabb-shw"],"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"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2105099387.pdf","grobid_xml":"https://content.openalex.org/works/W2105099387.grobid-xml"},"referenced_works_count":86,"referenced_works":["https://openalex.org/W1500214331","https://openalex.org/W1518942907","https://openalex.org/W1560724230","https://openalex.org/W1576520375","https://openalex.org/W1604938182","https://openalex.org/W1854214752","https://openalex.org/W1963726977","https://openalex.org/W1966017044","https://openalex.org/W1971596502","https://openalex.org/W1971751969","https://openalex.org/W1975989487","https://openalex.org/W1978496948","https://openalex.org/W1986949826","https://openalex.org/W1991538681","https://openalex.org/W1995186828","https://openalex.org/W1996357466","https://openalex.org/W2003853681","https://openalex.org/W2004228538","https://openalex.org/W2011495938","https://openalex.org/W2013570924","https://openalex.org/W2015292449","https://openalex.org/W2032737594","https://openalex.org/W2033496784","https://openalex.org/W2036009566","https://openalex.org/W2037960865","https://openalex.org/W2047515553","https://openalex.org/W2051969447","https://openalex.org/W2052711770","https://openalex.org/W2055043387","https://openalex.org/W2057447180","https://openalex.org/W2058336694","https://openalex.org/W2059886402","https://openalex.org/W2060035159","https://openalex.org/W2062123114","https://openalex.org/W2062327179","https://openalex.org/W2062693912","https://openalex.org/W2063389953","https://openalex.org/W2074231493","https://openalex.org/W2083445888","https://openalex.org/W2084466582","https://openalex.org/W2085277871","https://openalex.org/W2087064593","https://openalex.org/W2094051420","https://openalex.org/W2096495474","https://openalex.org/W2097555181","https://openalex.org/W2099075703","https://openalex.org/W2099946731","https://openalex.org/W2102122585","https://openalex.org/W2102677343","https://openalex.org/W2105118494","https://openalex.org/W2106116715","https://openalex.org/W2106882534","https://openalex.org/W2118836759","https://openalex.org/W2127122014","https://openalex.org/W2136739161","https://openalex.org/W2139279375","https://openalex.org/W2139621307","https://openalex.org/W2140244239","https://openalex.org/W2141783940","https://openalex.org/W2143210482","https://openalex.org/W2144281817","https://openalex.org/W2144319229","https://openalex.org/W2144357990","https://openalex.org/W2144362290","https://openalex.org/W2144483796","https://openalex.org/W2145268834","https://openalex.org/W2147667050","https://openalex.org/W2148603752","https://openalex.org/W2150434184","https://openalex.org/W2151831732","https://openalex.org/W2152064613","https://openalex.org/W2156798505","https://openalex.org/W2158714788","https://openalex.org/W2164583490","https://openalex.org/W2164652663","https://openalex.org/W2164843630","https://openalex.org/W2164886928","https://openalex.org/W2168508791","https://openalex.org/W2169097687","https://openalex.org/W2170409750","https://openalex.org/W2283504545","https://openalex.org/W2435251607","https://openalex.org/W3144619878","https://openalex.org/W3201413583","https://openalex.org/W4246356731","https://openalex.org/W4317929372"],"related_works":["https://openalex.org/W7097302592","https://openalex.org/W7097573192","https://openalex.org/W2999310752","https://openalex.org/W2103082682","https://openalex.org/W2163957306","https://openalex.org/W2566498094","https://openalex.org/W41702196","https://openalex.org/W2747370968","https://openalex.org/W2914272550","https://openalex.org/W7100515552"],"abstract_inverted_index":{"MOTIVATION:":[0],"Recognizing":[1],"proteins":[2],"that":[3],"have":[4,64],"similar":[5,28],"tertiary":[6],"structure":[7,15],"is":[8,185,220],"the":[9,76,155,160,166,172,180,199,215,218,227,235,239],"key":[10],"step":[11],"of":[12,21,79,165,214],"template-based":[13],"protein":[14,69,116],"prediction":[16],"methods.":[17],"Traditionally,":[18],"a":[19,82,86,94,208],"variety":[20],"alignment":[22,107],"methods":[23,39,52,63,108],"are":[24,40,176],"used":[25,66,177],"to":[26,101,109,138,150,153,178,242],"identify":[27],"folds,":[29],"based":[30],"on":[31,207],"sequence":[32],"similarity":[33,112],"and":[34,70,135,188,224,230,245],"sequence-structure":[35],"compatibility.":[36],"Although":[37],"these":[38,62,151],"complementary,":[41],"their":[42],"integration":[43],"has":[44],"not":[45],"been":[46,65],"thoroughly":[47],"exploited.":[48],"Statistical":[49],"machine":[50,96],"learning":[51],"provide":[53],"tools":[54],"for":[55,68,85,114],"integrating":[56],"multiple":[57],"features,":[58],"but":[59],"so":[60],"far":[61],"primarily":[67],"fold":[71,80,102,162,194,231],"classification,":[72],"rather":[73],"than":[74],"addressing":[75],"retrieval":[77],"problem":[78],"recognition-finding":[81],"proper":[83],"template":[84],"given":[87],"query":[88],"protein.":[89],"RESULTS:":[90],"Here":[91],"we":[92,105,145],"present":[93],"two-stage":[95],"learning,":[97],"information":[98],"retrieval,":[99],"approach":[100,184],"recognition.":[103],"First,":[104],"use":[106,120],"derive":[110],"pairwise":[111,140],"features":[113,152],"query-template":[115,167],"pairs.":[117,168],"We":[118],"also":[119],"global":[121],"profile-profile":[122],"alignments":[123],"in":[124,159,202],"combination":[125],"with":[126,191],"predicted":[127],"secondary":[128],"structure,":[129],"relative":[130],"solvent":[131],"accessibility,":[132],"contact":[133],"map":[134],"beta-strand":[136],"pairing":[137],"extract":[139],"structural":[141,156],"compatibility":[142],"features.":[143],"Second,":[144],"apply":[146],"support":[147],"vector":[148],"machines":[149],"predict":[154],"relevance":[157,174],"(i.e.":[158],"same":[161],"or":[163],"not)":[164],"For":[169],"each":[170],"query,":[171],"continuous":[173],"scores":[175],"rank":[179],"templates.":[181],"The":[182],"FOLDpro":[183,197],"modular,":[186],"scalable":[187],"effective.":[189],"Compared":[190],"11":[192],"other":[193],"recognition":[195],"methods,":[196],"yields":[198],"best":[200],"results":[201],"almost":[203],"all":[204],"standard":[205],"categories":[206],"comprehensive":[209],"benchmark":[210],"dataset.":[211],"Using":[212,234],"predictions":[213],"top-ranked":[216,237],"template,":[217],"sensitivity":[219,240],"approximately":[221],"85,":[222],"56,":[223],"27%":[225],"at":[226],"family,":[228],"superfamily":[229],"levels":[232],"respectively.":[233],"5":[236],"templates,":[238],"increases":[241],"90,":[243],"70,":[244],"48%.":[246]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":19},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":7},{"year":2018,"cited_by_count":9},{"year":2017,"cited_by_count":11},{"year":2016,"cited_by_count":7},{"year":2015,"cited_by_count":6},{"year":2014,"cited_by_count":5},{"year":2013,"cited_by_count":10},{"year":2012,"cited_by_count":6}],"updated_date":"2026-10-31T12:09:11.096373","created_date":"2016-06-24T00:00:00"}