{"id":"https://openalex.org/W4405488670","doi":"https://doi.org/10.1109/embc53108.2024.10782139","title":"Integrating Transformers and AutoML for Protein Function Prediction","display_name":"Integrating Transformers and AutoML for Protein Function Prediction","publication_year":2024,"publication_date":"2024-07-15","ids":{"openalex":"https://openalex.org/W4405488670","doi":"https://doi.org/10.1109/embc53108.2024.10782139","pmid":"https://pubmed.ncbi.nlm.nih.gov/40039729"},"language":"en","primary_location":{"id":"doi:10.1109/embc53108.2024.10782139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-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":"https://openalex.org/A5065375346","display_name":"Gabriel Bianchin de Oliveira","orcid":"https://orcid.org/0000-0002-1238-4860"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":true,"raw_author_name":"Gabriel Bianchin de Oliveira","raw_affiliation_strings":["University of Campinas,Institute of Computing,Campinas,Brazil,13083-052"],"affiliations":[{"raw_affiliation_string":"University of Campinas,Institute of Computing,Campinas,Brazil,13083-052","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065725754","display_name":"H\u00e9lio Pedrini","orcid":"https://orcid.org/0000-0003-0125-630X"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Helio Pedrini","raw_affiliation_strings":["University of Campinas,Institute of Computing,Campinas,Brazil,13083-052"],"affiliations":[{"raw_affiliation_string":"University of Campinas,Institute of Computing,Campinas,Brazil,13083-052","institution_ids":["https://openalex.org/I181391015"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5042140271","display_name":"Zanoni Dias","orcid":"https://orcid.org/0000-0003-3333-6822"},"institutions":[{"id":"https://openalex.org/I181391015","display_name":"Universidade Estadual de Campinas (UNICAMP)","ror":"https://ror.org/04wffgt70","country_code":"BR","type":"education","lineage":["https://openalex.org/I181391015"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Zanoni Dias","raw_affiliation_strings":["University of Campinas,Institute of Computing,Campinas,Brazil,13083-052"],"affiliations":[{"raw_affiliation_string":"University of Campinas,Institute of Computing,Campinas,Brazil,13083-052","institution_ids":["https://openalex.org/I181391015"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5065375346"],"corresponding_institution_ids":["https://openalex.org/I181391015"],"apc_list":null,"apc_paid":null,"fwci":0.6843,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.71286611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"2024","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9987999796867371,"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":0.9987999796867371,"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/T10044","display_name":"Protein Structure and Dynamics","score":0.9970999956130981,"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":0.9958999752998352,"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":0.5249704718589783},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5195655822753906},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.28483664989471436},{"id":"https://openalex.org/keywords/electrical-engineering","display_name":"Electrical engineering","score":0.1478741466999054}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5249704718589783},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5195655822753906},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28483664989471436},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.1478741466999054},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"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":"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":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":"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":"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":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}],"locations_count":2,"locations":[{"id":"doi:10.1109/embc53108.2024.10782139","is_oa":false,"landing_page_url":"https://doi.org/10.1109/embc53108.2024.10782139","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 46th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)","raw_type":"proceedings-article"},{"id":"pmid:40039729","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40039729","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":"Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320326191","display_name":"Centro Nacional de Processamento de Alto Desempenho em S\u00e3o Paulo","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2000950277","https://openalex.org/W2103017472","https://openalex.org/W2158714788","https://openalex.org/W2615066396","https://openalex.org/W2980176690","https://openalex.org/W2989608901","https://openalex.org/W3137270128","https://openalex.org/W3143063265","https://openalex.org/W3146944767","https://openalex.org/W3177500196","https://openalex.org/W3210411940","https://openalex.org/W4220934922","https://openalex.org/W4236358448","https://openalex.org/W4312097792","https://openalex.org/W4327550249","https://openalex.org/W4366823175","https://openalex.org/W4379882058","https://openalex.org/W4385245566","https://openalex.org/W4389543134"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"next-generation":[1],"sequencing":[2],"technology":[3],"and":[4,34,65,67,81,90,97,107],"the":[5,14,32,102,113],"decreasing":[6],"cost":[7,33],"of":[8,11,16,71],"experimental":[9],"verification":[10],"proteins":[12,18],"made":[13],"accumulation":[15],"sequenced":[17],"in":[19],"recent":[20],"years":[21],"possible.":[22],"However,":[23],"determining":[24],"protein":[25],"function":[26],"is":[27],"still":[28],"difficult":[29],"due":[30],"to":[31,48,52,75],"time":[35],"required":[36],"for":[37],"this":[38,55,78],"analysis.":[39],"For":[40],"that":[41],"reason,":[42],"computational":[43],"methods":[44,85,92],"have":[45],"been":[46],"developed":[47],"automatically":[49],"assign":[50],"annotations":[51],"proteins.":[53],"In":[54],"work,":[56],"we":[57],"present":[58],"MAGO,":[59],"an":[60,69],"approach":[61],"based":[62,86,104],"on":[63,87,105],"Transformers":[64],"AutoML,":[66],"MAGO+,":[68],"ensemble":[70,91],"MAGO":[72,80],"with":[73,77,112],"BLASTp,":[74],"deal":[76],"task.":[79],"MAGO+":[82],"surpassed":[83],"state-of-the-art":[84],"machine":[88,98],"learning":[89,99],"combining":[93],"local":[94],"alignment":[95],"tools":[96],"algorithms,":[100],"improving":[101],"results":[103],"F<sub>max</sub>":[106],"presenting":[108],"statistically":[109],"significant":[110],"differences":[111],"compared":[114],"approaches.":[115]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
