{"id":"https://openalex.org/W2145468550","doi":"https://doi.org/10.1093/bioinformatics/btp679","title":"A novel method for accurate one-dimensional protein structure prediction based on fragment matching","display_name":"A novel method for accurate one-dimensional protein structure prediction based on fragment matching","publication_year":2009,"publication_date":"2009-12-09","ids":{"openalex":"https://openalex.org/W2145468550","doi":"https://doi.org/10.1093/bioinformatics/btp679","mag":"2145468550","pmid":"https://pubmed.ncbi.nlm.nih.gov/20007252"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btp679","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp679","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/4/470/16896756/btp679.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,"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":true,"oa_status":"bronze","oa_url":"https://academic.oup.com/bioinformatics/article-pdf/26/4/470/16896756/btp679.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109806922","display_name":"Tuping Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Tuping Zhou","raw_affiliation_strings":["Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101420205","display_name":"Nanjiang Shu","orcid":"https://orcid.org/0000-0002-3537-2387"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Nanjiang Shu","raw_affiliation_strings":["Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden","institution_ids":["https://openalex.org/I161593684"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5075675047","display_name":"Sven Hovm\u00f6ller","orcid":"https://orcid.org/0000-0003-1717-0455"},"institutions":[{"id":"https://openalex.org/I161593684","display_name":"Stockholm University","ror":"https://ror.org/05f0yaq80","country_code":"SE","type":"education","lineage":["https://openalex.org/I161593684"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Sven Hovm\u00f6ller","raw_affiliation_strings":["Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Division of Structural Chemistry, Stockholm University, Stockholm SE-106 91, Sweden","institution_ids":["https://openalex.org/I161593684"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5109806922"],"corresponding_institution_ids":["https://openalex.org/I161593684"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":1.3513,"has_fulltext":false,"cited_by_count":26,"citation_normalized_percentile":{"value":0.80397466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"26","issue":"4","first_page":"470","last_page":"477"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.928600013256073,"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":0.928600013256073,"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":0.0421999990940094,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.006399999838322401,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/protein-secondary-structure","display_name":"Protein secondary structure","score":0.6998986005783081},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.596752405166626},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5709245800971985},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5564313530921936},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.506632387638092},{"id":"https://openalex.org/keywords/fragment","display_name":"Fragment (logic)","score":0.5035812258720398},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.49499720335006714},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4463731050491333},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4372140169143677},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3625554144382477},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30459389090538025},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.12210813164710999},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.11878716945648193},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.09015083312988281}],"concepts":[{"id":"https://openalex.org/C62614982","wikidata":"https://www.wikidata.org/wiki/Q904984","display_name":"Protein secondary structure","level":2,"score":0.6998986005783081},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.596752405166626},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5709245800971985},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5564313530921936},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.506632387638092},{"id":"https://openalex.org/C2776235265","wikidata":"https://www.wikidata.org/wiki/Q18392052","display_name":"Fragment (logic)","level":2,"score":0.5035812258720398},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.49499720335006714},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4463731050491333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4372140169143677},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3625554144382477},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30459389090538025},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.12210813164710999},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.11878716945648193},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.09015083312988281},{"id":"https://openalex.org/C46141821","wikidata":"https://www.wikidata.org/wiki/Q209402","display_name":"Nuclear magnetic resonance","level":1,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D008958","descriptor_name":"Models, Molecular","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":"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":"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":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017433","descriptor_name":"Protein Structure, Secondary","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":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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},{"descriptor_ui":"D020539","descriptor_name":"Sequence Analysis, Protein","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btp679","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp679","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/4/470/16896756/btp679.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,"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:20007252","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/20007252","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}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btp679","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btp679","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/26/4/470/16896756/btp679.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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2145468550.pdf","grobid_xml":"https://content.openalex.org/works/W2145468550.grobid-xml"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W255996521","https://openalex.org/W1490138956","https://openalex.org/W1969621320","https://openalex.org/W1978520289","https://openalex.org/W1981132436","https://openalex.org/W1985818354","https://openalex.org/W2008708467","https://openalex.org/W2008807736","https://openalex.org/W2011495938","https://openalex.org/W2013136212","https://openalex.org/W2035066314","https://openalex.org/W2041369927","https://openalex.org/W2047544230","https://openalex.org/W2047962024","https://openalex.org/W2049695588","https://openalex.org/W2060178110","https://openalex.org/W2062693912","https://openalex.org/W2086403919","https://openalex.org/W2091194233","https://openalex.org/W2107538253","https://openalex.org/W2114520383","https://openalex.org/W2116268847","https://openalex.org/W2116689128","https://openalex.org/W2118836759","https://openalex.org/W2124919568","https://openalex.org/W2125725297","https://openalex.org/W2130479394","https://openalex.org/W2135079066","https://openalex.org/W2139753312","https://openalex.org/W2142013909","https://openalex.org/W2144483796","https://openalex.org/W2144727125","https://openalex.org/W2145268834","https://openalex.org/W2147905080","https://openalex.org/W2148557779","https://openalex.org/W2153026148","https://openalex.org/W2153153865","https://openalex.org/W2153187042","https://openalex.org/W2158714788","https://openalex.org/W2164886928","https://openalex.org/W3147254695","https://openalex.org/W4246356731"],"related_works":["https://openalex.org/W2928838901","https://openalex.org/W2574528486","https://openalex.org/W2494604670","https://openalex.org/W1578077690","https://openalex.org/W1998289425","https://openalex.org/W2303656598","https://openalex.org/W1510508486","https://openalex.org/W4206825711","https://openalex.org/W2114568928","https://openalex.org/W3086268169"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,143],"precise":[2],"prediction":[3,34,51,68,103,173,239],"of":[4,19,22,35,69,72,121,168,232,252],"one-dimensional":[5],"(1D)":[6],"protein":[7,13,92,95,130],"structure":[8,15,38,50,96,172,238],"as":[9,39,41,210],"represented":[10],"by":[11,112,212,246],"the":[12,32,67,77,90,106,132,165,188,205,230,243,253],"secondary":[14,80,171],"and":[16,62,83,94,149,155,174,208],"1D":[17,49,73,237],"string":[18],"discrete":[20],"state":[21],"dihedral":[23],"angles":[24],"(i.e.":[25],"Shape":[26,85,151,193,225],"Strings)":[27],"is":[28,141],"a":[29,47,57,113,118,200],"prerequisite":[30],"for":[31,136,147,170,223],"successful":[33],"three-dimensional":[36],"(3D)":[37],"well":[40],"protein-protein":[42],"interaction.":[43],"We":[44,158],"have":[45,100,159],"developed":[46],"novel":[48],"method,":[52],"called":[53],"Frag1D,":[54],"based":[55],"on":[56,117,184,236],"straightforward":[58],"fragment":[59],"matching":[60],"algorithm":[61],"demonstrated":[63],"its":[64],"success":[65],"in":[66,180,221],"three":[70],"sets":[71],"structural":[74],"alphabets,":[75],"i.e.":[76,139],"classical":[78],"three-state":[79,224],"structure,":[81],"three-":[82,148],"eight-state":[84,150],"Strings.":[86,226],"RESULTS:":[87],"By":[88,227],"exploiting":[89],"vast":[91],"sequence":[93,126],"data":[97,233],"available,":[98],"we":[99,195,240],"brought":[101],"secondary-structure":[102,137],"closer":[104],"to":[105],"expected":[107],"theoretical":[108],"limit.":[109],"When":[110],"tested":[111,183],"leave-one-out":[114],"cross":[115],"validation":[116],"non-redundant":[119],"set":[120],"PDB":[122],"cutting":[123],"at":[124,218],"30%":[125],"identity":[127],"containing":[128],"5860":[129],"chains,":[131],"overall":[133,144],"per-residue":[134,145],"accuracy":[135,146,222,244],"prediction,":[138],"Q3":[140,181],"82.9%.":[142],"Strings":[152],"are":[153],"85.1":[154],"71.5%,":[156],"respectively.":[157],"also":[160],"benchmarked":[161],"our":[162,175,197],"program":[163,176,216],"with":[164,187,199,204,249],"latest":[166],"version":[167],"PSIPRED":[169],"predicted":[177,217],"0.3%":[178],"better":[179,220],"when":[182],"2241":[185],"chains":[186],"same":[189,206],"training":[190],"set.":[191],"For":[192],"Strings,":[194],"compared":[196],"method":[198,203],"recently":[201],"published":[202],"dataset":[207],"definition":[209],"used":[211],"that":[213,242],"method.":[214],"Our":[215],"2.2%":[219],"quantitatively":[228],"investigating":[229],"effect":[231],"base":[234],"size":[235],"show":[241],"increases":[245],"approximately":[247],"1%":[248],"every":[250],"doubling":[251],"database":[254],"size.":[255]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":4},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":2},{"year":2013,"cited_by_count":3},{"year":2012,"cited_by_count":5}],"updated_date":"2026-04-29T09:16:38.111599","created_date":"2025-10-10T00:00:00"}