{"id":"https://openalex.org/W4415427648","doi":"https://doi.org/10.3233/faia251439","title":"Predicting Protein Functions with Ensemble Deep Learning and Protein Language Models","display_name":"Predicting Protein Functions with Ensemble Deep Learning and Protein Language Models","publication_year":2025,"publication_date":"2025-10-21","ids":{"openalex":"https://openalex.org/W4415427648","doi":"https://doi.org/10.3233/faia251439"},"language":"en","primary_location":{"id":"doi:10.3233/faia251439","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251439","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.3233/faia251439","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5030361899","display_name":"Giacomo Frisoni","orcid":"https://orcid.org/0000-0002-9845-0231"},"institutions":[{"id":"https://openalex.org/I4210136873","display_name":"Azienda-Unita' Sanitaria Locale Di Cesena","ror":"https://ror.org/04kgp1379","country_code":"IT","type":"government","lineage":["https://openalex.org/I4210136873"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Giacomo Frisoni","raw_affiliation_strings":["Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy","institution_ids":["https://openalex.org/I4210136873"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5120092040","display_name":"Marcello Fuschi","orcid":"https://orcid.org/0000-0002-1834-953X"},"institutions":[{"id":"https://openalex.org/I4210136873","display_name":"Azienda-Unita' Sanitaria Locale Di Cesena","ror":"https://ror.org/04kgp1379","country_code":"IT","type":"government","lineage":["https://openalex.org/I4210136873"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Marcello Fuschi","raw_affiliation_strings":["Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy","institution_ids":["https://openalex.org/I4210136873"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5079648393","display_name":"Gianluca Moro","orcid":"https://orcid.org/0000-0002-3663-7877"},"institutions":[{"id":"https://openalex.org/I4210136873","display_name":"Azienda-Unita' Sanitaria Locale Di Cesena","ror":"https://ror.org/04kgp1379","country_code":"IT","type":"government","lineage":["https://openalex.org/I4210136873"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Gianluca Moro","raw_affiliation_strings":["Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering (DISI), University of Bologna, Cesena Campus, Via dell\u2019Universit\u00e0 50, I-47522 Cesena, Italy","institution_ids":["https://openalex.org/I4210136873"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5030361899"],"corresponding_institution_ids":["https://openalex.org/I4210136873"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.51904471,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"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":0.9932000041007996,"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":0.9932000041007996,"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":0.9682999849319458,"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":0.9333000183105469,"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/deep-learning","display_name":"Deep learning","score":0.6399000287055969},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.4878999888896942},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.44040000438690186},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.4147000014781952},{"id":"https://openalex.org/keywords/ensemble-forecasting","display_name":"Ensemble forecasting","score":0.36309999227523804},{"id":"https://openalex.org/keywords/protein-function-prediction","display_name":"Protein function prediction","score":0.36160001158714294},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.35760000348091125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7218000292778015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6995000243186951},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6399000287055969},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.4878999888896942},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.44040000438690186},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4147000014781952},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4081000089645386},{"id":"https://openalex.org/C119898033","wikidata":"https://www.wikidata.org/wiki/Q3433888","display_name":"Ensemble forecasting","level":2,"score":0.36309999227523804},{"id":"https://openalex.org/C207060522","wikidata":"https://www.wikidata.org/wiki/Q7251473","display_name":"Protein function prediction","level":4,"score":0.36160001158714294},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.35760000348091125},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3440999984741211},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3310999870300293},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.3025999963283539},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2987000048160553},{"id":"https://openalex.org/C2986374874","wikidata":"https://www.wikidata.org/wiki/Q8054","display_name":"Protein function","level":3,"score":0.29600000381469727},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.2957000136375427},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.28870001435279846},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.26249998807907104},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.25119999051094055}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3233/faia251439","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251439","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},{"id":"pmh:oai:cris.unibo.it:11585/1027335","is_oa":true,"landing_page_url":"https://ebooks.iospress.nl/doi/10.3233/FAIA251439","pdf_url":null,"source":{"id":"https://openalex.org/S4306402579","display_name":"Archivio istituzionale della ricerca (Alma Mater Studiorum Universit\u00e0 di Bologna)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210117483","host_organization_name":"Istituto di Ematologia di Bologna","host_organization_lineage":["https://openalex.org/I4210117483"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":{"id":"doi:10.3233/faia251439","is_oa":true,"landing_page_url":"https://doi.org/10.3233/faia251439","pdf_url":null,"source":{"id":"https://openalex.org/S4210201731","display_name":"Frontiers in artificial intelligence and applications","issn_l":"0922-6389","issn":["0922-6389","1879-8314"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Frontiers in Artificial Intelligence and Applications","raw_type":"book-chapter"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Understanding":[0],"protein":[1,47],"functions":[2,27],"enables":[3],"deciphering":[4],"cellular":[5],"mechanisms":[6],"and":[7,46,68],"improving":[8],"healthcare":[9],"outcomes,":[10],"from":[11],"disease":[12],"diagnosis":[13],"to":[14],"targeted":[15],"therapy.":[16],"We":[17],"present":[18],"GOMIX,":[19],"an":[20,34],"ensemble":[21],"learning":[22],"method":[23],"for":[24],"predicting":[25],"the":[26,57],"of":[28],"newly":[29],"discovered":[30],"proteins,":[31],"packaged":[32],"within":[33],"easy-to-use":[35],"web":[36],"application.":[37],"By":[38],"combining":[39],"seven":[40],"complementary":[41],"base":[42],"predictors\u2013including":[43],"sequence":[44],"homology":[45],"language":[48],"models,":[49],"GOMIX":[50,63],"achieves":[51],"competitive":[52],"or":[53],"state-of-the-art":[54],"performance":[55],"in":[56],"CAFA-3":[58],"challenge.":[59],"Unlike":[60],"existing":[61],"solutions,":[62],"is":[64,73],"entirely":[65],"open-source,":[66],"modular,":[67],"computationally":[69],"low-resource.":[70],"The":[71],"code":[72],"publicly":[74],"available":[75],"at":[76],"https://github.com/disi-unibo-nlp/gomix":[77],"(MIT":[78],"License).":[79]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-24T00:00:00"}