{"id":"https://openalex.org/W4220691739","doi":"https://doi.org/10.1186/s12859-022-04623-z","title":"Lightweight ProteinUnet2 network for protein secondary structure prediction: a step towards proper evaluation","display_name":"Lightweight ProteinUnet2 network for protein secondary structure prediction: a step towards proper evaluation","publication_year":2022,"publication_date":"2022-03-22","ids":{"openalex":"https://openalex.org/W4220691739","doi":"https://doi.org/10.1186/s12859-022-04623-z","pmid":"https://pubmed.ncbi.nlm.nih.gov/35317722"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-022-04623-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04623-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-022-04623-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-022-04623-z","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5045740283","display_name":"Katarzyna St\u0105por","orcid":"https://orcid.org/0000-0003-3003-6592"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":true,"raw_author_name":"Katarzyna Stapor","raw_affiliation_strings":["Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland. Katarzyna.Stapor@polsl.pl","Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland. Katarzyna.Stapor@polsl.pl","institution_ids":[]},{"raw_affiliation_string":"Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069610379","display_name":"Krzysztof Kotowski","orcid":"https://orcid.org/0000-0003-2596-6517"},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Krzysztof Kotowski","raw_affiliation_strings":["Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070421166","display_name":"Tomasz Smolarczyk","orcid":null},"institutions":[{"id":"https://openalex.org/I119004910","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442","country_code":"PL","type":"education","lineage":["https://openalex.org/I119004910"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Tomasz Smolarczyk","raw_affiliation_strings":["Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Applied Informatics, Silesian University of Technology, Akademicka 16, 44-100, Gliwice, Poland","institution_ids":["https://openalex.org/I119004910"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087239926","display_name":"Irena Roterman","orcid":"https://orcid.org/0000-0003-3652-9099"},"institutions":[{"id":"https://openalex.org/I126596746","display_name":"Jagiellonian University","ror":"https://ror.org/03bqmcz70","country_code":"PL","type":"education","lineage":["https://openalex.org/I126596746"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Irena Roterman","raw_affiliation_strings":["Department of Bioinformatics and Telemedicine, Jagiellonian University Medical College, Medyczna 7, 30-688, Krak\u00f3w, Poland"],"affiliations":[{"raw_affiliation_string":"Department of Bioinformatics and Telemedicine, Jagiellonian University Medical College, Medyczna 7, 30-688, Krak\u00f3w, Poland","institution_ids":["https://openalex.org/I126596746"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5045740283"],"corresponding_institution_ids":["https://openalex.org/I119004910"],"apc_list":{"value":1690,"currency":"GBP","value_usd":2072},"apc_paid":{"value":1690,"currency":"GBP","value_usd":2072},"fwci":0.3466,"has_fulltext":true,"cited_by_count":6,"citation_normalized_percentile":{"value":0.54089779,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"23","issue":"1","first_page":"100","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10044","display_name":"Protein Structure and Dynamics","score":0.9997000098228455,"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":0.9997000098228455,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9994999766349792,"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/T10521","display_name":"RNA and protein synthesis mechanisms","score":0.9980000257492065,"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":0.5877695679664612},{"id":"https://openalex.org/keywords/dna-microarray","display_name":"DNA microarray","score":0.5188261866569519},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.488901287317276},{"id":"https://openalex.org/keywords/protein-structure-prediction","display_name":"Protein structure prediction","score":0.46648290753364563},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3681667447090149},{"id":"https://openalex.org/keywords/bioinformatics","display_name":"Bioinformatics","score":0.333404004573822},{"id":"https://openalex.org/keywords/protein-structure","display_name":"Protein structure","score":0.29718542098999023},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2297491431236267},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.1534324586391449},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.09079280495643616}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5877695679664612},{"id":"https://openalex.org/C95371953","wikidata":"https://www.wikidata.org/wiki/Q591745","display_name":"DNA microarray","level":4,"score":0.5188261866569519},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.488901287317276},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.46648290753364563},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3681667447090149},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.333404004573822},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.29718542098999023},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2297491431236267},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.1534324586391449},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.09079280495643616},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","level":3,"score":0.0}],"mesh":[{"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","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":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","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},{"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":5,"locations":[{"id":"doi:10.1186/s12859-022-04623-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04623-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-022-04623-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35317722","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35317722","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":"BMC bioinformatics","raw_type":null},{"id":"pmh:oai:doaj.org/article:b7928a31b15a42be8b44f1f25fd1c79c","is_oa":true,"landing_page_url":"https://doaj.org/article/b7928a31b15a42be8b44f1f25fd1c79c","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 23, Iss 1, Pp 1-16 (2022)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:8939211","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8939211","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:ruj.uj.edu.pl:item/291611","is_oa":true,"landing_page_url":"https://bmcbioinformatics.biomedcentral.com/articles/10.1186/s12859-022-04623-z","pdf_url":null,"source":{"id":"https://openalex.org/S4306401249","display_name":"Jagiellonian University Repository (Jagiellonian University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I126596746","host_organization_name":"Jagiellonian University","host_organization_lineage":["https://openalex.org/I126596746"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"doi:10.1186/s12859-022-04623-z","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-022-04623-z","pdf_url":"https://bmcbioinformatics.biomedcentral.com/track/pdf/10.1186/s12859-022-04623-z","source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G7078362746","display_name":null,"funder_award_id":"02/100/BK_21/0008","funder_id":"https://openalex.org/F4320324727","funder_display_name":"Silesian University of Technology"}],"funders":[{"id":"https://openalex.org/F4320324727","display_name":"Silesian University of Technology","ror":"https://ror.org/02dyjk442"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4220691739.pdf","grobid_xml":"https://content.openalex.org/works/W4220691739.grobid-xml"},"referenced_works_count":48,"referenced_works":["https://openalex.org/W1556779599","https://openalex.org/W1569736468","https://openalex.org/W1965895350","https://openalex.org/W1985854865","https://openalex.org/W1996073320","https://openalex.org/W2008708467","https://openalex.org/W2016707108","https://openalex.org/W2034223735","https://openalex.org/W2041369927","https://openalex.org/W2045777307","https://openalex.org/W2049695588","https://openalex.org/W2051210555","https://openalex.org/W2061500593","https://openalex.org/W2095450147","https://openalex.org/W2130479394","https://openalex.org/W2143197682","https://openalex.org/W2147905080","https://openalex.org/W2149024119","https://openalex.org/W2153187042","https://openalex.org/W2548307244","https://openalex.org/W2567587907","https://openalex.org/W2613869537","https://openalex.org/W2739202500","https://openalex.org/W2751476102","https://openalex.org/W2807692668","https://openalex.org/W2808950571","https://openalex.org/W2905446269","https://openalex.org/W2950374603","https://openalex.org/W2963457143","https://openalex.org/W2980699342","https://openalex.org/W2995514860","https://openalex.org/W3014974815","https://openalex.org/W3025484814","https://openalex.org/W3027554922","https://openalex.org/W3028467215","https://openalex.org/W3037888463","https://openalex.org/W3093108887","https://openalex.org/W3112701542","https://openalex.org/W3133820354","https://openalex.org/W3144701084","https://openalex.org/W3146944767","https://openalex.org/W3157437194","https://openalex.org/W3159719254","https://openalex.org/W3177500196","https://openalex.org/W3177828909","https://openalex.org/W3203475177","https://openalex.org/W4245883783","https://openalex.org/W4300870773"],"related_works":["https://openalex.org/W2415545834","https://openalex.org/W2069695727","https://openalex.org/W2118505788","https://openalex.org/W4254166511","https://openalex.org/W2150084125","https://openalex.org/W1542823905","https://openalex.org/W1490878237","https://openalex.org/W2990314835","https://openalex.org/W2131319730","https://openalex.org/W1975122118"],"abstract_inverted_index":{"Our":[0],"results":[1,15,69],"suggest":[2],"that":[3,57],"ProteinUnet2":[4],"architecture":[5],"has":[6],"much":[7],"shorter":[8],"training":[9],"and":[10,19,73],"inference":[11],"times":[12,28],"while":[13],"maintaining":[14],"similar":[16],"to":[17],"SAINT":[18],"SPOT-1D":[20],"predictors.":[21],"Taking":[22],"into":[23],"account":[24],"the":[25,42,52,64,79],"relatively":[26],"long":[27],"of":[29,66],"calculating":[30],"evolutionary-based":[31],"features":[32,50],"(from":[33],"PSSM":[34],"in":[35,51],"particular),":[36],"it":[37],"would":[38],"be":[39,71],"worth":[40],"conducting":[41],"predictive":[43],"ability":[44],"tests":[45],"on":[46],"embeddings":[47],"as":[48],"input":[49],"future.":[53],"We":[54],"strongly":[55],"believe":[56],"our":[58],"proposed":[59],"here":[60],"statistical":[61],"methodology":[62],"for":[63],"evaluation":[65],"SS":[67],"prediction":[68],"will":[70],"adopted":[72],"used":[74],"(and":[75],"even":[76],"expanded)":[77],"by":[78],"research":[80],"community.":[81]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":3}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}