{"id":"https://openalex.org/W7140387086","doi":"https://doi.org/10.1093/bioinformatics/btag146","title":"STAR-GO: improving protein function prediction by learning to hierarchically integrate ontology-informed semantic embeddings","display_name":"STAR-GO: improving protein function prediction by learning to hierarchically integrate ontology-informed semantic embeddings","publication_year":2026,"publication_date":"2026-03-24","ids":{"openalex":"https://openalex.org/W7140387086","doi":"https://doi.org/10.1093/bioinformatics/btag146","pmid":"https://pubmed.ncbi.nlm.nih.gov/41883139"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btag146","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag146","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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":"gold","oa_url":"https://doi.org/10.1093/bioinformatics/btag146","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5116620305","display_name":"Mehmet Efe Ak\u00e7a","orcid":null},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Mehmet Efe Ak\u00e7a","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044882535","display_name":"G\u00f6k\u00e7e Uludo\u011fan","orcid":"https://orcid.org/0000-0002-8684-2457"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"G\u00f6k\u00e7e Uludo\u011fan","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye"],"raw_orcid":"https://orcid.org/0000-0002-8684-2457","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030252794","display_name":"Arzucan \u00d6zg\u00fcr","orcid":"https://orcid.org/0000-0001-8376-1056"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Arzucan \u00d6zg\u00fcr","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye"],"raw_orcid":"https://orcid.org/0000-0001-8376-1056","affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye","institution_ids":["https://openalex.org/I4405392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014649156","display_name":"\u0130nci M. Bayta\u015f","orcid":"https://orcid.org/0000-0003-4765-2615"},"institutions":[{"id":"https://openalex.org/I4405392","display_name":"Bo\u011fazi\u00e7i University","ror":"https://ror.org/03z9tma90","country_code":"TR","type":"education","lineage":["https://openalex.org/I4405392"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"\u0130nci M Bayta\u015f","raw_affiliation_strings":["Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Bogazici University , Bebek, Istanbul 34342, Turkiye","institution_ids":["https://openalex.org/I4405392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5014649156","https://openalex.org/A5030252794"],"corresponding_institution_ids":["https://openalex.org/I4405392"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32314432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"42","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4936000108718872,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.4936000108718872,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.22210000455379486,"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/T11710","display_name":"Biomedical Text Mining and Ontologies","score":0.19249999523162842,"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/code","display_name":"Code (set theory)","score":0.5963000059127808},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5274999737739563},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4449000060558319},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.3903999924659729},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.3434999883174896},{"id":"https://openalex.org/keywords/protein-function","display_name":"Protein function","score":0.3368000090122223}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8105999827384949},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6305999755859375},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5963000059127808},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5274999737739563},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4449000060558319},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.3903999924659729},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35740000009536743},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3434999883174896},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3425000011920929},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.3368000090122223},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3059999942779541},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.29980000853538513},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2980000078678131}],"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":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","is_major_topic":true},{"descriptor_ui":"D011506","descriptor_name":"Proteins","qualifier_ui":"Q000502","qualifier_name":"physiology","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":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012660","descriptor_name":"Semantics","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012660","descriptor_name":"Semantics","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":true},{"descriptor_ui":"D012984","descriptor_name":"Software","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":"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},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D063990","descriptor_name":"Gene Ontology","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btag146","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag146","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:41883139","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41883139","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/btag146","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btag146","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Zero hunger","id":"https://metadata.un.org/sdg/2","score":0.412945419549942}],"awards":[{"id":"https://openalex.org/G3159938427","display_name":"Understanding the Language of Life: Identifying and Characterizing the Language Units in Protein Sequences","funder_award_id":"101089287","funder_id":"https://openalex.org/F4320338453","funder_display_name":"HORIZON EUROPE European Research Council"}],"funders":[{"id":"https://openalex.org/F4320338453","display_name":"HORIZON EUROPE European Research Council","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W2018661561","https://openalex.org/W2055043387","https://openalex.org/W2103017472","https://openalex.org/W2156125289","https://openalex.org/W2911489562","https://openalex.org/W2965778154","https://openalex.org/W3112376646","https://openalex.org/W3137270128","https://openalex.org/W3146944767","https://openalex.org/W3164046276","https://openalex.org/W3166265964","https://openalex.org/W3177500196","https://openalex.org/W3179436811","https://openalex.org/W4210584212","https://openalex.org/W4225687252","https://openalex.org/W4236358448","https://openalex.org/W4288384170","https://openalex.org/W4320933419","https://openalex.org/W4322494707","https://openalex.org/W4323036511","https://openalex.org/W4391821988","https://openalex.org/W4401660139","https://openalex.org/W4402253370"],"related_works":[],"abstract_inverted_index":{"MOTIVATION:":[0],"Accurate":[1],"prediction":[2],"of":[3,27,106,166],"protein":[4,28,112,148,175],"function":[5,113,176],"is":[6],"essential":[7],"for":[8,171],"elucidating":[9],"molecular":[10],"mechanisms":[11],"and":[12,15,51,84,103,159,169,173,180],"advancing":[13],"biological":[14],"therapeutic":[16],"discovery.":[17],"Yet":[18],"experimental":[19],"annotation":[20],"lags":[21],"far":[22],"behind":[23],"the":[24,62,81,86,101,164],"rapid":[25],"growth":[26],"sequence":[29,149],"data.":[30],"Computational":[31],"approaches":[32],"address":[33],"this":[34],"gap":[35],"by":[36],"associating":[37],"proteins":[38],"with":[39,119,147],"Gene":[40],"Ontology":[41],"(GO)":[42],"terms,":[43],"which":[44,128],"encode":[45],"functional":[46],"knowledge":[47],"through":[48],"hierarchical":[49,132],"relations":[50],"textual":[52,117],"definitions.":[53],"However,":[54],"existing":[55],"models":[56,89,100,182],"often":[57],"emphasize":[58],"one":[59],"modality":[60],"over":[61],"other,":[63],"limiting":[64],"their":[65],"ability":[66],"to":[67,70,109,123,134,139,151],"generalize,":[68],"particularly":[69],"unseen":[71],"or":[72],"newly":[73],"introduced":[74],"GO":[75,107,126],"terms":[76,108],"that":[77,98],"frequently":[78],"arise":[79],"as":[80],"ontology":[82,120],"evolves,":[83],"making":[85],"previously":[87],"trained":[88],"outdated.":[90],"RESULTS:":[91],"We":[92],"present":[93],"STAR-GO,":[94],"a":[95],"Transformer-based":[96],"framework":[97],"jointly":[99],"semantic":[102],"structural":[104],"characteristics":[105],"enhance":[110],"zero-shot":[111,161],"prediction.":[114,177],"STAR-GO":[115,155],"integrates":[116],"definitions":[118],"graph":[121],"structure":[122,170],"learn":[124],"unified":[125],"representations,":[127],"are":[129,144,183],"processed":[130],"in":[131],"order":[133],"propagate":[135],"information":[136],"from":[137],"general":[138],"specific":[140],"terms.":[141],"These":[142],"representations":[143],"then":[145],"aligned":[146],"embeddings":[150],"capture":[152],"sequence-function":[153],"relationships.":[154],"achieves":[156],"state-of-the-art":[157],"performance":[158],"superior":[160],"generalization,":[162],"demonstrating":[163],"utility":[165],"integrating":[167],"semantics":[168],"robust":[172],"adaptable":[174],"AVAILABILITY:":[178],"Code":[179],"pre-trained":[181],"available":[184],"at":[185],"https://github.com/boun-tabi-lifelu/stargo,":[186],"https://doi.org/10.5281/zenodo.18643082.":[187]},"counts_by_year":[],"updated_date":"2026-07-12T07:33:03.550515","created_date":"2026-03-27T00:00:00"}
