{"id":"https://openalex.org/W4405754472","doi":"https://doi.org/10.1109/jbhi.2024.3520579","title":"PubLabeler: Enhancing Automatic Classification of Publications in UniProtKB Using Protein Textual Description and PubMedBERT","display_name":"PubLabeler: Enhancing Automatic Classification of Publications in UniProtKB Using Protein Textual Description and PubMedBERT","publication_year":2024,"publication_date":"2024-12-24","ids":{"openalex":"https://openalex.org/W4405754472","doi":"https://doi.org/10.1109/jbhi.2024.3520579","pmid":"https://pubmed.ncbi.nlm.nih.gov/40030652"},"language":"en","primary_location":{"id":"doi:10.1109/jbhi.2024.3520579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2024.3520579","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Shaojun Wang","orcid":"https://orcid.org/0000-0003-0467-8911"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shaojun Wang","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-0467-8911","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084369276","display_name":"Junyi Bian","orcid":"https://orcid.org/0009-0000-3329-8614"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyi Bian","raw_affiliation_strings":["School of Computer Science, Fudan University, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I24943067"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072380374","display_name":"Xiaodi Huang","orcid":"https://orcid.org/0000-0002-6084-1851"},"institutions":[{"id":"https://openalex.org/I153230381","display_name":"Charles Sturt University","ror":"https://ror.org/00wfvh315","country_code":"AU","type":"education","lineage":["https://openalex.org/I153230381"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xiaodi Huang","raw_affiliation_strings":["School of Computing, Mathematics and Engineering, Charles Sturt University, Albury, NSW, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6084-1851","affiliations":[{"raw_affiliation_string":"School of Computing, Mathematics and Engineering, Charles Sturt University, Albury, NSW, Australia","institution_ids":["https://openalex.org/I153230381"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112878209","display_name":"Hong Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I4210136643","display_name":"OpTek Systems (United Kingdom)","ror":"https://ror.org/02wtt8e62","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210136643"]},{"id":"https://openalex.org/I4210143644","display_name":"Oxford Research (Norway)","ror":"https://ror.org/03y2s5683","country_code":"NO","type":"company","lineage":["https://openalex.org/I4210143644"]}],"countries":["GB","NO"],"is_corresponding":false,"raw_author_name":"Hong Zhou","raw_affiliation_strings":["Atypon Systems, LLC, Oxford, U.K","Atypon Systems, LLC, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Atypon Systems, LLC, Oxford, U.K","institution_ids":["https://openalex.org/I4210143644"]},{"raw_affiliation_string":"Atypon Systems, LLC, UK","institution_ids":["https://openalex.org/I4210136643"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045866167","display_name":"Shanfeng Zhu","orcid":"https://orcid.org/0000-0002-6067-5312"},"institutions":[{"id":"https://openalex.org/I24943067","display_name":"Fudan University","ror":"https://ror.org/013q1eq08","country_code":"CN","type":"education","lineage":["https://openalex.org/I24943067"]},{"id":"https://openalex.org/I4210164150","display_name":"Shanghai Center for Brain Science and Brain-Inspired Technology","ror":"https://ror.org/0551a0y31","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210164150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shanfeng Zhu","raw_affiliation_strings":["Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China","Institute of Science and Technology for Brain Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-6067-5312","affiliations":[{"raw_affiliation_string":"Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]},{"raw_affiliation_string":"Institute of Science and Technology for Brain Inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University, Shanghai, China","institution_ids":["https://openalex.org/I4210164150","https://openalex.org/I24943067"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.9363,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.75165399,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":98},"biblio":{"volume":"29","issue":"5","first_page":"3782","last_page":"3791"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9947999715805054,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.9947999715805054,"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":0.978600025177002,"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/T13937","display_name":"Genetics, Bioinformatics, and Biomedical Research","score":0.9521999955177307,"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/uniprot","display_name":"UniProt","score":0.9427341222763062},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7826598882675171},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5448018908500671},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.39631298184394836},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39412921667099},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3751112222671509},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08077642321586609}],"concepts":[{"id":"https://openalex.org/C202264299","wikidata":"https://www.wikidata.org/wiki/Q905695","display_name":"UniProt","level":3,"score":0.9427341222763062},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7826598882675171},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5448018908500671},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.39631298184394836},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39412921667099},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3751112222671509},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08077642321586609},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","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":"D006801","descriptor_name":"Humans","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000145","qualifier_name":"classification","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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000737","qualifier_name":"chemistry","is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000145","qualifier_name":"classification","is_major_topic":true},{"descriptor_ui":"D011642","descriptor_name":"Publications","qualifier_ui":"Q000145","qualifier_name":"classification","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":"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":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D030562","descriptor_name":"Databases, Protein","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D039781","descriptor_name":"PubMed","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true},{"descriptor_ui":"D057225","descriptor_name":"Data Mining","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1109/jbhi.2024.3520579","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jbhi.2024.3520579","pdf_url":null,"source":{"id":"https://openalex.org/S2495854775","display_name":"IEEE Journal of Biomedical and Health Informatics","issn_l":"2168-2194","issn":["2168-2194","2168-2208"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal of Biomedical and Health Informatics","raw_type":"journal-article"},{"id":"pmid:40030652","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40030652","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":"IEEE journal of biomedical and health informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Zero hunger","score":0.44999998807907104,"id":"https://metadata.un.org/sdg/2"}],"awards":[{"id":"https://openalex.org/G6370758788","display_name":null,"funder_award_id":"B18015","funder_id":"https://openalex.org/F4320327912","funder_display_name":"Higher Education Discipline Innovation Project"},{"id":"https://openalex.org/G7370466132","display_name":null,"funder_award_id":"62272105","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320327912","display_name":"Higher Education Discipline Innovation Project","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W61851215","https://openalex.org/W2004006914","https://openalex.org/W2063828850","https://openalex.org/W2088382887","https://openalex.org/W2116475964","https://openalex.org/W2163922914","https://openalex.org/W2473077402","https://openalex.org/W2787247269","https://openalex.org/W2807567459","https://openalex.org/W2896457183","https://openalex.org/W2911489562","https://openalex.org/W2952894920","https://openalex.org/W2963351448","https://openalex.org/W2963912736","https://openalex.org/W2970771982","https://openalex.org/W2971092323","https://openalex.org/W2971330564","https://openalex.org/W3023417367","https://openalex.org/W3046375318","https://openalex.org/W3136918052","https://openalex.org/W3201658153","https://openalex.org/W4200139355","https://openalex.org/W4224261633","https://openalex.org/W4230985562","https://openalex.org/W4309506674","https://openalex.org/W4366163632","https://openalex.org/W4385245566","https://openalex.org/W4393936594","https://openalex.org/W6631190155","https://openalex.org/W6631943919","https://openalex.org/W6729999211","https://openalex.org/W6778883912","https://openalex.org/W6848511598","https://openalex.org/W6851507257"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W24553703","https://openalex.org/W4211000692","https://openalex.org/W4212920271","https://openalex.org/W2612240612","https://openalex.org/W4211208250","https://openalex.org/W4211054902","https://openalex.org/W4324018414","https://openalex.org/W2170381940","https://openalex.org/W3204019825"],"abstract_inverted_index":{"In":[0],"UniProtKB,":[1],"each":[2,63],"protein":[3,64,101],"is":[4,35,65],"linked":[5],"to":[6,55,114,132,138,176,196,207],"numerous":[7],"publications":[8,60,73],"covering":[9],"topics":[10,58],"such":[11],"as":[12,107,155],"sequence,":[13],"function,":[14],"and":[15,31,37,84,103,118,166,205,212],"structure,":[16],"which":[17,87,98],"are":[18],"annotated":[19,149],"manually":[20],"or":[21],"through":[22],"automated":[23,42,53,178,198],"methods.":[24],"Given":[25],"the":[26,57,111,124,136],"vast":[27],"number":[28],"of":[29,59],"proteins":[30],"literature,":[32],"manual":[33],"annotation":[34,179],"time-consuming":[36],"labour-intensive.":[38],"Although":[39],"UniProtKB":[40,75],"offers":[41],"annotations,":[43],"their":[44],"quality":[45],"often":[46],"falls":[47],"short.":[48],"Therefore,":[49],"developing":[50],"an":[51],"accurate":[52],"classifier":[54],"identify":[56],"associated":[61],"with":[62,143],"imperative":[66],"for":[67],"advancing":[68],"biomedical":[69],"knowledge":[70,213],"discovery.":[71,214],"Classifying":[72],"in":[74,153,163,173,187],"involves":[76],"protein-publication":[77],"pairs":[78],"characterized":[79],"by":[80],"multi-label,":[81],"label":[82,120],"co-occurrence,":[83],"class":[85],"imbalance,":[86],"increases":[88],"complexity.":[89],"This":[90],"paper":[91],"proposes":[92],"a":[93,144,156,170],"novel":[94],"method":[95],"called":[96],"PubLabeler,":[97],"simultaneously":[99],"considers":[100],"description":[102],"scientific":[104],"literature":[105,150],"texts":[106,117],"input.":[108],"PubLabeler":[109,159],"employs":[110],"PubMedBERT":[112],"model":[113,125,137],"encode":[115],"input":[116],"integrates":[119],"co-occurrence":[121],"information":[122,210],"into":[123],"parameters.":[126],"Additionally,":[127],"it":[128],"uses":[129],"focal":[130],"loss":[131],"update":[133],"parameters,":[134],"allowing":[135],"focus":[139],"more":[140],"on":[141],"classes":[142],"few":[145],"instances.":[146],"Using":[147],"newly":[148],"from":[151],"Swiss-Prot":[152],"2023":[154],"test":[157],"set,":[158],"achieved":[160],"superior":[161],"results":[162,194],"both":[164],"micro":[165],"macro":[167],"metrics,":[168],"showing":[169],"28.5%":[171],"improvement":[172],"macro-F1":[174],"compared":[175,195],"UniProtKB's":[177],"method,":[180],"UPCLASS.":[181],"Furthermore,":[182],"we":[183],"validated":[184],"PubLabeler's":[185,203],"effectiveness":[186],"TrEMBL":[188],"annotation,":[189],"showcasing":[190],"its":[191],"comprehensive":[192],"prediction":[193],"TrEMBL's":[197],"annotations.":[199],"These":[200],"findings":[201],"highlight":[202],"reliability":[204],"potential":[206],"advance":[208],"protein-related":[209],"extraction":[211]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4}],"updated_date":"2026-07-10T07:45:09.275182","created_date":"2025-10-10T00:00:00"}