{"id":"https://openalex.org/W7135066094","doi":"https://doi.org/10.1109/clei67442.2025.11420541","title":"An Empirical Study of Remote Homology Detection using Protein Language Models","display_name":"An Empirical Study of Remote Homology Detection using Protein Language Models","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W7135066094","doi":"https://doi.org/10.1109/clei67442.2025.11420541"},"language":null,"primary_location":{"id":"doi:10.1109/clei67442.2025.11420541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clei67442.2025.11420541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 LI Latin American Computer Conference (CLEI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5128835185","display_name":"Ruben Jimenez","orcid":null},"institutions":[{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Ruben Jimenez","raw_affiliation_strings":["Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I44202434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5107112915","display_name":"Aldo Galeano","orcid":null},"institutions":[{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Aldo Galeano","raw_affiliation_strings":["Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I44202434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5117572127","display_name":"Marcelo Baez","orcid":null},"institutions":[{"id":"https://openalex.org/I4210126406","display_name":"Xuzhou Construction Machinery Group (China)","ror":"https://ror.org/02y5rmj89","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210126406"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Marcelo B\u00e1ez","raw_affiliation_strings":["Universidad Católica \"Nuestra Señora de la Asunción\",Departamento de Electrónica e Informática,Asunción,Paraguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Católica \"Nuestra Señora de la Asunción\",Departamento de Electrónica e Informática,Asunción,Paraguay","institution_ids":["https://openalex.org/I4210126406"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5081616777","display_name":"Santiago Ferreyra","orcid":null},"institutions":[{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Santiago Ferreyra","raw_affiliation_strings":["Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I44202434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5128852500","display_name":"Guilherme Melo","orcid":null},"institutions":[{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Guilherme Melo","raw_affiliation_strings":["Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I44202434"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126722004","display_name":"Giorgio Valentini","orcid":null},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Giorgio Valentini","raw_affiliation_strings":["Università Degli Studi di Milano,Dipartimento di Informatica,Milan,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Degli Studi di Milano,Dipartimento di Informatica,Milan,Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079939753","display_name":"Elena Casiraghi","orcid":"https://orcid.org/0000-0003-2024-7572"},"institutions":[{"id":"https://openalex.org/I189158943","display_name":"University of Milan","ror":"https://ror.org/00wjc7c48","country_code":"IT","type":"education","lineage":["https://openalex.org/I189158943"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Elena Casiraghi","raw_affiliation_strings":["Università Degli Studi di Milano,Dipartimento di Informatica,Milan,Italy"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Università Degli Studi di Milano,Dipartimento di Informatica,Milan,Italy","institution_ids":["https://openalex.org/I189158943"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034166026","display_name":"Luca Cernuzzi","orcid":"https://orcid.org/0000-0001-7803-1067"},"institutions":[{"id":"https://openalex.org/I2799978770","display_name":"X-Fab (Germany)","ror":"https://ror.org/030bh9196","country_code":"DE","type":"company","lineage":["https://openalex.org/I2799978770"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Luca Cernuzzi","raw_affiliation_strings":["Universidad Católica \"Nuestra Señora de la Asunción\" Centro de Ingeniería Para la Investigación Desarrollo e Innovación Tecnológica,Departamento de Electrónica e Informática,Asunción,Paraguay"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universidad Católica \"Nuestra Señora de la Asunción\" Centro de Ingeniería Para la Investigación Desarrollo e Innovación Tecnológica,Departamento de Electrónica e Informática,Asunción,Paraguay","institution_ids":["https://openalex.org/I2799978770"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030607460","display_name":"Alberto Paccanaro","orcid":"https://orcid.org/0000-0001-8059-1346"},"institutions":[{"id":"https://openalex.org/I44202434","display_name":"Funda\u00e7\u00e3o Getulio Vargas","ror":"https://ror.org/01evzkn27","country_code":"BR","type":"education","lineage":["https://openalex.org/I44202434"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Alberto Paccanaro","raw_affiliation_strings":["Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Fundação Getúlio Vargas,Escola de Matemática Aplicada,Rio de Janeiro,Brazil","institution_ids":["https://openalex.org/I44202434"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":9,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.61196604,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3522000014781952,"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/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.3522000014781952,"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":0.31529998779296875,"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/T11642","display_name":"Genomics and Rare Diseases","score":0.1257999986410141,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/classifier","display_name":"Classifier (UML)","score":0.6833999752998352},{"id":"https://openalex.org/keywords/structural-classification-of-proteins-database","display_name":"Structural Classification of Proteins database","score":0.640999972820282},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.5091000199317932},{"id":"https://openalex.org/keywords/homology","display_name":"Homology (biology)","score":0.46140000224113464},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4074999988079071},{"id":"https://openalex.org/keywords/empirical-research","display_name":"Empirical research","score":0.40059998631477356},{"id":"https://openalex.org/keywords/protein-sequencing","display_name":"Protein sequencing","score":0.39730000495910645},{"id":"https://openalex.org/keywords/structural-alignment","display_name":"Structural alignment","score":0.3702999949455261},{"id":"https://openalex.org/keywords/scope","display_name":"Scope (computer science)","score":0.3634999990463257}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6869999766349792},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.6833999752998352},{"id":"https://openalex.org/C58773245","wikidata":"https://www.wikidata.org/wiki/Q4832556","display_name":"Structural Classification of Proteins database","level":3,"score":0.640999972820282},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237999796867371},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.5091000199317932},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4821000099182129},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.46140000224113464},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4090000092983246},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4074999988079071},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.40059998631477356},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.39730000495910645},{"id":"https://openalex.org/C4668613","wikidata":"https://www.wikidata.org/wiki/Q4116110","display_name":"Structural alignment","level":5,"score":0.3702999949455261},{"id":"https://openalex.org/C2778012447","wikidata":"https://www.wikidata.org/wiki/Q1034415","display_name":"Scope (computer science)","level":2,"score":0.3634999990463257},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.36169999837875366},{"id":"https://openalex.org/C88031987","wikidata":"https://www.wikidata.org/wiki/Q1377767","display_name":"Multiple sequence alignment","level":5,"score":0.3601999878883362},{"id":"https://openalex.org/C200307862","wikidata":"https://www.wikidata.org/wiki/Q7797175","display_name":"Threading (protein sequence)","level":3,"score":0.3479999899864197},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3472000062465668},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.34470000863075256},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.3386000096797943},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.3249000012874603},{"id":"https://openalex.org/C18051474","wikidata":"https://www.wikidata.org/wiki/Q899656","display_name":"Protein structure prediction","level":3,"score":0.3248000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.31709998846054077},{"id":"https://openalex.org/C92028520","wikidata":"https://www.wikidata.org/wiki/Q7395025","display_name":"SUPERFAMILY","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C2911029443","wikidata":"https://www.wikidata.org/wiki/Q21296145","display_name":"Human proteins","level":3,"score":0.2872999906539917},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2854999899864197},{"id":"https://openalex.org/C47701112","wikidata":"https://www.wikidata.org/wiki/Q735188","display_name":"Protein structure","level":2,"score":0.2728999853134155},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.2718999981880188},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.2581999897956848},{"id":"https://openalex.org/C69131567","wikidata":"https://www.wikidata.org/wiki/Q2068215","display_name":"Structural bioinformatics","level":3,"score":0.2578999996185303},{"id":"https://openalex.org/C60644358","wikidata":"https://www.wikidata.org/wiki/Q128570","display_name":"Bioinformatics","level":1,"score":0.2549000084400177}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/clei67442.2025.11420541","is_oa":false,"landing_page_url":"https://doi.org/10.1109/clei67442.2025.11420541","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 LI Latin American Computer Conference (CLEI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.5402015447616577}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1491063910","https://openalex.org/W2059185913","https://openalex.org/W2100161738","https://openalex.org/W2101220662","https://openalex.org/W2102122585","https://openalex.org/W2108067237","https://openalex.org/W2110412254","https://openalex.org/W2130695501","https://openalex.org/W2133657429","https://openalex.org/W2138122982","https://openalex.org/W2145268834","https://openalex.org/W2161072217","https://openalex.org/W2510820101","https://openalex.org/W2550969987","https://openalex.org/W2730472814","https://openalex.org/W3085898256","https://openalex.org/W3139397034","https://openalex.org/W3146944767","https://openalex.org/W4205192056","https://openalex.org/W4235848672","https://openalex.org/W4236236547","https://openalex.org/W4282984452","https://openalex.org/W4327550249","https://openalex.org/W4362471278","https://openalex.org/W4375858802","https://openalex.org/W4385737488","https://openalex.org/W4388052750","https://openalex.org/W4393342758","https://openalex.org/W4393620727","https://openalex.org/W4400493769"],"related_works":[],"abstract_inverted_index":{"Detecting":[0],"remote":[1,48,116],"homologs,":[2],"proteins":[3],"that":[4,78,104,120],"share":[5],"evolutionary":[6],"ancestry":[7],"despite":[8],"low":[9,130],"sequence":[10,110,131],"similarity,":[11],"remains":[12],"a":[13,43,74,84],"central":[14],"challenge":[15],"in":[16,128],"computational":[17],"biology.":[18],"The":[19],"Structural":[20],"Classification":[21],"of":[22,38,58],"Proteins":[23],"extended":[24],"(SCOPe)":[25],"database":[26],"organizes":[27],"protein":[28,59],"domains":[29],"into":[30],"superfamilies":[31,67],"based":[32],"on":[33],"structural":[34],"and":[35,90,112,119],"functional":[36],"evidence":[37],"common":[39],"origin,":[40],"making":[41],"it":[42],"widely":[44],"used":[45],"benchmark":[46],"for":[47,64,115],"homology":[49,117],"detection.":[50],"In":[51],"this":[52],"study,":[53],"we":[54],"investigate":[55],"the":[56],"effectiveness":[57],"language":[60],"model":[61],"(PLM)":[62],"embeddings":[63,107],"predicting":[65],"SCOPe":[66,97],"directly":[68],"from":[69],"sequence.":[70],"We":[71],"introduce":[72],"DOMCLASS,":[73],"deep":[75],"learning":[76,82,122],"framework":[77],"combines":[79],"supervised":[80],"contrastive":[81,121],"with":[83,96],"distance-weighted":[85],"K-NN":[86],"classifier":[87],"to":[88],"learn":[89],"exploit":[91],"an":[92],"embedding":[93],"space":[94],"aligned":[95],"superfamily":[98],"annotations.":[99],"Our":[100],"empirical":[101],"results":[102],"show":[103],"general-purpose":[105],"PLM":[106],"already":[108],"outperform":[109],"similarity-":[111],"profile-based":[113],"methods":[114],"detection,":[118],"can":[123],"further":[124],"improve":[125],"performance,":[126],"even":[127],"challenging":[129],"identity":[132],"settings.":[133]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-13T00:00:00"}