{"id":"https://openalex.org/W3010889593","doi":"https://doi.org/10.1093/bioinformatics/btaa196","title":"Redundancy-weighting the PDB for detailed secondary structure prediction using deep-learning models","display_name":"Redundancy-weighting the PDB for detailed secondary structure prediction using deep-learning models","publication_year":2020,"publication_date":"2020-03-16","ids":{"openalex":"https://openalex.org/W3010889593","doi":"https://doi.org/10.1093/bioinformatics/btaa196","mag":"3010889593","pmid":"https://pubmed.ncbi.nlm.nih.gov/32186698"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa196","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa196","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/A5043433500","display_name":"Tomer Sidi","orcid":"https://orcid.org/0000-0002-9713-8289"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Tomer Sidi","raw_affiliation_strings":["Department of Computer Science , Ben-Gurion University, P.O.B 653, Be'er Sheva 84105, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Ben-Gurion University, P.O.B 653, Be'er Sheva 84105, Israel","institution_ids":["https://openalex.org/I124227911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5072753313","display_name":"Chen Keasar","orcid":"https://orcid.org/0000-0003-0994-1520"},"institutions":[{"id":"https://openalex.org/I124227911","display_name":"Ben-Gurion University of the Negev","ror":"https://ror.org/05tkyf982","country_code":"IL","type":"education","lineage":["https://openalex.org/I124227911"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Chen Keasar","raw_affiliation_strings":["Department of Computer Science , Ben-Gurion University, P.O.B 653, Be'er Sheva 84105, Israel"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science , Ben-Gurion University, P.O.B 653, Be'er Sheva 84105, Israel","institution_ids":["https://openalex.org/I124227911"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5043433500","https://openalex.org/A5072753313"],"corresponding_institution_ids":["https://openalex.org/I124227911"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":null,"fwci":0.5835,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.64418099,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":"36","issue":"12","first_page":"3733","last_page":"3738"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.6044999957084656,"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":0.6044999957084656,"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":0.21690000593662262,"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":0.07569999992847443,"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/weighting","display_name":"Weighting","score":0.7133647203445435},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank (RCSB PDB)","score":0.704387366771698},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6054986119270325},{"id":"https://openalex.org/keywords/protein-data-bank","display_name":"Protein Data Bank","score":0.5567950010299683},{"id":"https://openalex.org/keywords/mit-license","display_name":"MIT License","score":0.5516968369483948},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.5393857955932617},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5234596133232117},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5086613297462463},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4476449191570282},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4147678315639496},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3601672649383545},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.22480592131614685},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.19620370864868164},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.1941038966178894},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.0749589204788208}],"concepts":[{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.7133647203445435},{"id":"https://openalex.org/C65556437","wikidata":"https://www.wikidata.org/wiki/Q766195","display_name":"Protein Data Bank (RCSB PDB)","level":2,"score":0.704387366771698},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6054986119270325},{"id":"https://openalex.org/C119145174","wikidata":"https://www.wikidata.org/wiki/Q7251429","display_name":"Protein Data Bank","level":3,"score":0.5567950010299683},{"id":"https://openalex.org/C174183944","wikidata":"https://www.wikidata.org/wiki/Q334661","display_name":"MIT License","level":3,"score":0.5516968369483948},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.5393857955932617},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5234596133232117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5086613297462463},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4476449191570282},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4147678315639496},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3601672649383545},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.22480592131614685},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.19620370864868164},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.1941038966178894},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0749589204788208},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","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},{"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/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","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":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":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","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},{"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/btaa196","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa196","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:32186698","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32186698","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":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4609973417","display_name":null,"funder_award_id":"1122/14","funder_id":"https://openalex.org/F4320313643","funder_display_name":"Iowa Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320313643","display_name":"Iowa Science Foundation","ror":null},{"id":"https://openalex.org/F4320322252","display_name":"Israel Science Foundation","ror":"https://ror.org/04sazxf24"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1533958831","https://openalex.org/W1548178570","https://openalex.org/W1596947964","https://openalex.org/W1966041739","https://openalex.org/W1975017420","https://openalex.org/W1981132436","https://openalex.org/W1985818354","https://openalex.org/W2008708467","https://openalex.org/W2033354942","https://openalex.org/W2049695588","https://openalex.org/W2059136964","https://openalex.org/W2064675550","https://openalex.org/W2095450147","https://openalex.org/W2102677343","https://openalex.org/W2105801262","https://openalex.org/W2110821410","https://openalex.org/W2119068667","https://openalex.org/W2123085274","https://openalex.org/W2142678478","https://openalex.org/W2145268834","https://openalex.org/W2148488210","https://openalex.org/W2150705899","https://openalex.org/W2153187042","https://openalex.org/W2156125289","https://openalex.org/W2157540858","https://openalex.org/W2160718424","https://openalex.org/W2168267323","https://openalex.org/W2171546617","https://openalex.org/W2171572477","https://openalex.org/W2271840356","https://openalex.org/W2273396394","https://openalex.org/W2342838938","https://openalex.org/W2606314633","https://openalex.org/W2900952222","https://openalex.org/W2949867299","https://openalex.org/W2950374603","https://openalex.org/W2969644707","https://openalex.org/W2993302057","https://openalex.org/W3136918052","https://openalex.org/W3184998487","https://openalex.org/W6694517276","https://openalex.org/W6756396466","https://openalex.org/W7038994942"],"related_works":["https://openalex.org/W2090630809","https://openalex.org/W2106612397","https://openalex.org/W4387804157","https://openalex.org/W2518314460","https://openalex.org/W2119891507","https://openalex.org/W2089869950","https://openalex.org/W2047544230","https://openalex.org/W2589205199","https://openalex.org/W2952811294","https://openalex.org/W4386448451"],"abstract_inverted_index":{"MOTIVATION:":[0],"The":[1,166],"Protein":[2],"Data":[3],"Bank":[4],"(PDB),":[5],"the":[6,30,38,66,83,114,128,169],"ultimate":[7],"source":[8,70],"for":[9,60,71,74,92,172,182],"data":[10,198],"in":[11,150,193],"structural":[12,22],"biology,":[13],"is":[14],"inherently":[15],"imbalanced.":[16],"To":[17],"alleviate":[18],"biases,":[19],"virtually":[20],"all":[21],"biology":[23],"studies":[24,87],"use":[25,65],"nonredundant":[26],"(NR)":[27],"subsets":[28],"of":[29,37,131,153],"PDB,":[31],"which":[32],"include":[33],"only":[34],"a":[35,178],"fraction":[36],"available":[39,189,200],"data.":[40,72],"An":[41],"alternative":[42],"approach,":[43],"dubbed":[44],"redundancy-weighting":[45],"(RW),":[46],"down-weights":[47],"redundant":[48],"entries":[49],"rather":[50],"than":[51],"discarding":[52],"them.":[53],"This":[54,125],"approach":[55],"may":[56],"be":[57],"particularly":[58],"helpful":[59],"machine-learning":[61],"(ML)":[62],"methods":[63,98],"that":[64,143],"PDB":[67],"as":[68,110,112],"their":[69,173],"Methods":[73],"secondary":[75,121,161],"structure":[76,122],"prediction":[77,152],"(SSP)":[78],"have":[79],"greatly":[80],"improved":[81],"over":[82],"years":[84],"with":[85],"recent":[86],"achieving":[88],"above":[89],"70%":[90],"accuracy":[91],"eight-class":[93],"(DSSP)":[94,157],"prediction.":[95],"As":[96],"these":[97],"typically":[99],"incorporate":[100],"ML":[101,167],"techniques,":[102],"training":[103,144],"on":[104,135,145],"RW":[105,137,146],"datasets":[106,170],"might":[107],"improve":[108],"accuracy,":[109],"well":[111],"pave":[113],"way":[115],"toward":[116],"larger":[117],"and":[118,158,175,177,184],"more":[119],"informative":[120],"classes.":[123],"RESULTS:":[124],"study":[126],"compares":[127],"SSP":[129,180],"performances":[130],"deep-learning":[132],"models":[133],"trained":[134],"either":[136],"or":[138],"NR":[139],"datasets.":[140],"We":[141],"show":[142],"sets":[147],"consistently":[148],"results":[149],"better":[151],"3-":[154],"(HCE),":[155],"8-":[156],"13-class":[159],"(STR2)":[160],"structures.":[162],"AVAILABILITY":[163],"AND":[164],"IMPLEMENTATION:":[165],"models,":[168],"used":[171],"derivation":[174],"testing,":[176],"stand-alone":[179],"program":[181],"DSSP":[183],"STR2":[185],"predictions,":[186],"are":[187,199],"freely":[188],"under":[190],"LGPL":[191],"license":[192],"http://meshi1.cs.bgu.ac.il/rw.":[194],"SUPPLEMENTARY":[195],"INFORMATION:":[196],"Supplementary":[197],"at":[201],"Bioinformatics":[202],"online.":[203]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
