{"id":"https://openalex.org/W4414924541","doi":"https://doi.org/10.1186/s12859-026-06491-3","title":"Protein language models are accidental taxonomists","display_name":"Protein language models are accidental taxonomists","publication_year":2026,"publication_date":"2026-06-12","ids":{"openalex":"https://openalex.org/W4414924541","doi":"https://doi.org/10.1186/s12859-026-06491-3","pmid":"https://pubmed.ncbi.nlm.nih.gov/41279532","pmcid":"https://www.ncbi.nlm.nih.gov/pmc/articles/12632502"},"language":"en","primary_location":{"id":"doi:10.1186/s12859-026-06491-3","doi":"https://doi.org/10.1186/s12859-026-06491-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06491-3","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1186/s12859-026-06491-3","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5051261338","display_name":"Logan Hallee","orcid":"https://orcid.org/0000-0002-0426-3508","observed_orcids":["https://orcid.org/0000-0002-0426-3508"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Logan Hallee","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Delaware","Synthyra, PBLLC","University of Delware"],"raw_orcid":"https://orcid.org/0000-0002-0426-3508","affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Delaware","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Synthyra, PBLLC","institution_ids":[]},{"raw_affiliation_string":"University of Delware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Tamar Peleg","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tamar Peleg","raw_affiliation_strings":["Department of Medical and Molecular Sciences, University of Delaware","University of Delaware"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Medical and Molecular Sciences, University of Delaware","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5092890826","display_name":"Nikolaos Rafailidis","orcid":"https://orcid.org/0009-0002-2988-7533","observed_orcids":["https://orcid.org/0009-0002-2988-7533"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nikolaos Rafailidis","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Delaware","University of Delaware"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Delaware","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026075148","display_name":"Jason P. Gleghorn","orcid":"https://orcid.org/0000-0003-1283-2966","observed_orcids":["https://orcid.org/0000-0003-1283-2966"]},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jason P. Gleghorn","raw_affiliation_strings":["Center for Bioinformatics and Computational Biology, University of Delaware","Department of Biomedical Engineering, University of Delaware","Synthyra, PBLLC","University of Delaware"],"raw_orcid":"https://orcid.org/0000-0003-1283-2966","affiliations":[{"raw_affiliation_string":"Center for Bioinformatics and Computational Biology, University of Delaware","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Department of Biomedical Engineering, University of Delaware","institution_ids":["https://openalex.org/I86501945"]},{"raw_affiliation_string":"Synthyra, PBLLC","institution_ids":[]},{"raw_affiliation_string":"University of Delaware","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5026075148"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":16.2503,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.99376941,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":99},"biblio":{"volume":"27","issue":"1","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10887","display_name":"Bioinformatics and Genomic Networks","score":0.7261000275611877,"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":0.7261000275611877,"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":0.25999999046325684,"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":0.001500000013038516,"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/protein-protein-interaction","display_name":"protein-protein interaction","score":0.8299999833106995},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.9980000257492065},{"id":"https://openalex.org/keywords/phylogenetic-bias","display_name":"phylogenetic bias","score":0.7940000295639038},{"id":"https://openalex.org/keywords/negative-sampling","display_name":"negative sampling","score":0.6600000262260437},{"id":"https://openalex.org/keywords/protein-embeddings","display_name":"protein embeddings","score":0.7960000038146973},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.5099999904632568}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6385999917984009},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5194000005722046},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.508400022983551},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.4521999955177307},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.45210000872612},{"id":"https://openalex.org/C126965237","wikidata":"https://www.wikidata.org/wiki/Q816335","display_name":"Accidental","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3677000105381012},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C90132467","wikidata":"https://www.wikidata.org/wiki/Q171184","display_name":"Phylogenetics","level":3,"score":0.3441999852657318},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31540000438690186},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3082999885082245},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.2919999957084656},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C171268870","wikidata":"https://www.wikidata.org/wiki/Q1486676","display_name":"GRASP","level":2,"score":0.2879999876022339},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.27390000224113464},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.267300009727478},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.2660999894142151},{"id":"https://openalex.org/C11804247","wikidata":"https://www.wikidata.org/wiki/Q896177","display_name":"Protein\u2013protein interaction","level":2,"score":0.26010000705718994},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.2583000063896179},{"id":"https://openalex.org/C201797286","wikidata":"https://www.wikidata.org/wiki/Q4914986","display_name":"Biological data","level":2,"score":0.2581000030040741},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2522999942302704},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.25060001015663147}],"mesh":[],"locations_count":7,"locations":[{"id":"doi:10.1186/s12859-026-06491-3","doi":"https://doi.org/10.1186/s12859-026-06491-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06491-3","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},{"id":"doi:10.1101/2025.10.07.681002","doi":"https://doi.org/10.1101/2025.10.07.681002","is_oa":true,"landing_page_url":"https://doi.org/10.1101/2025.10.07.681002","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2025/10/07/2025.10.07.681002.full.pdf","source":{"id":"https://openalex.org/S4306402567","display_name":"bioRxiv (Cold Spring Harbor Laboratory)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2750212522","host_organization_name":"Cold Spring Harbor Laboratory","host_organization_lineage":["https://openalex.org/I2750212522"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},{"id":"pmid:41279532","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41279532","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,"listed_in":[],"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":"bioRxiv : the preprint server for biology","raw_type":"Journal Article"},{"id":"pmid:42286461","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/42286461","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,"listed_in":[],"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":"BMC bioinformatics","raw_type":"Journal Article"},{"id":"pmh:oai:pubmedcentral.nih.gov:13487993","doi":null,"is_oa":true,"landing_page_url":"https://pmc.ncbi.nlm.nih.gov/articles/PMC13487993/","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"Text"},{"id":"pmh:oai:europepmc.org:11440078","doi":null,"is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12632502","pdf_url":null,"source":{"id":"https://openalex.org/S4306400806","display_name":"Europe PMC (PubMed Central)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I1303153112","host_organization_name":"European Bioinformatics Institute","host_organization_lineage":["https://openalex.org/I1303153112"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nd","license_id":"https://openalex.org/licenses/cc-by-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"},{"id":"pmh:oai:doaj.org/article:6ac3d2d9cf854a13ad83f2ff5b877413","doi":null,"is_oa":false,"landing_page_url":"https://doaj.org/article/6ac3d2d9cf854a13ad83f2ff5b877413","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BMC Bioinformatics, Vol 27, Iss 1 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1186/s12859-026-06491-3","doi":"https://doi.org/10.1186/s12859-026-06491-3","is_oa":true,"landing_page_url":"https://doi.org/10.1186/s12859-026-06491-3","pdf_url":null,"source":{"id":"https://openalex.org/S19032547","display_name":"BMC Bioinformatics","issn_l":"1471-2105","issn":["1471-2105"],"is_oa":true,"is_in_doaj":true,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","ccf-c","cwts-core","doaj","dongbi-c","doyens","jufo-1","ki-jl-1","medline","norway-2","oarl","poland-100","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320256","host_organization_name":"BioMed Central","host_organization_lineage":["https://openalex.org/P4310320256","https://openalex.org/P4310319965"],"host_organization_lineage_names":["BioMed Central","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"BMC Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G7130690183","display_name":null,"funder_award_id":"NAIRR 240064","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G7226622218","display_name":"Mechanical Control of Cell Proliferation and Branching Morphogenesis in the Embryonic Lung","funder_award_id":"R01HL145147","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G8141840742","display_name":"Pressure in lung development and congenital diaphragmatic hernia","funder_award_id":"R01HL133163","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G9000874348","display_name":"Dissecting the Protective Role of Cardiac Hsp90\u00df Ablation/Inhibition","funder_award_id":"R01HL178817","funder_id":"https://openalex.org/F4320337338","funder_display_name":"National Heart, Lung, and Blood Institute"},{"id":"https://openalex.org/G9000911971","display_name":"Graduate Training Program in Computational Biology, Bioinformatics and Biomedical Data Science (CBB)","funder_award_id":"T32GM142603","funder_id":"https://openalex.org/F4320337354","funder_display_name":"National Institute of General Medical Sciences"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"},{"id":"https://openalex.org/F4320337338","display_name":"National Heart, Lung, and Blood Institute","ror":"https://ror.org/012pb6c26"},{"id":"https://openalex.org/F4320337354","display_name":"National Institute of General Medical Sciences","ror":"https://ror.org/04q48ey07"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4414924541.pdf","grobid_xml":"https://content.openalex.org/works/W4414924541.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W1904365287","https://openalex.org/W2008840001","https://openalex.org/W2024103356","https://openalex.org/W2117407746","https://openalex.org/W2128084896","https://openalex.org/W2131562240","https://openalex.org/W2148958646","https://openalex.org/W2156125289","https://openalex.org/W2161922860","https://openalex.org/W2626778328","https://openalex.org/W2792643794","https://openalex.org/W2908510526","https://openalex.org/W2947149365","https://openalex.org/W3045699526","https://openalex.org/W3093053585","https://openalex.org/W3177500196","https://openalex.org/W3199468887","https://openalex.org/W4200025610","https://openalex.org/W4200310257","https://openalex.org/W4225264859","https://openalex.org/W4242765109","https://openalex.org/W4281710911","https://openalex.org/W4283586679","https://openalex.org/W4296293027","https://openalex.org/W4307068738","https://openalex.org/W4308834893","https://openalex.org/W4317374308","https://openalex.org/W4319298372","https://openalex.org/W4319339817","https://openalex.org/W4327550249","https://openalex.org/W4380153748","https://openalex.org/W4386811611","https://openalex.org/W4389686956","https://openalex.org/W4391629225","https://openalex.org/W4392500220","https://openalex.org/W4392633839","https://openalex.org/W4400664797","https://openalex.org/W4400984795","https://openalex.org/W4401178127","https://openalex.org/W4401794303","https://openalex.org/W4404343151","https://openalex.org/W4404458588","https://openalex.org/W4404792828","https://openalex.org/W4406090237","https://openalex.org/W4406465794","https://openalex.org/W4407867672","https://openalex.org/W4409722910","https://openalex.org/W4409958938","https://openalex.org/W4410270211","https://openalex.org/W4410827740","https://openalex.org/W4410975694","https://openalex.org/W4412392503","https://openalex.org/W4412454121","https://openalex.org/W4415348682","https://openalex.org/W4417256350","https://openalex.org/W6935797875","https://openalex.org/W7128820983","https://openalex.org/W7134806761","https://openalex.org/W7135063183","https://openalex.org/W7148951193","https://openalex.org/W7168137441"],"related_works":["https://openalex.org/W4380153748","https://openalex.org/W4404141244","https://openalex.org/W7161814920","https://openalex.org/W7128820983","https://openalex.org/W4416392486","https://openalex.org/W4402458171","https://openalex.org/W7118534871","https://openalex.org/W4392686654","https://openalex.org/W4408524736","https://openalex.org/W7134971468"],"abstract_inverted_index":{"Protein-protein":[0],"interactions":[1],"(PPIs)":[2],"are":[3,81],"fundamental":[4],"to":[5,105,117,137,194],"nearly":[6],"all":[7],"biological":[8],"processes,":[9],"yet":[10],"their":[11],"experimental":[12],"characterization":[13],"remains":[14],"costly":[15],"and":[16,188],"time-consuming.":[17],"While":[18],"computational":[19],"methods,":[20],"particularly":[21,183],"those":[22],"using":[23],"protein":[24,59,76,138,197],"language":[25],"models":[26,116,159],"(pLMs),":[27],"offer":[28],"higher-throughput":[29],"solutions,":[30],"they":[31],"often":[32],"report":[33],"unexpectedly":[34],"high":[35],"performance":[36,170],"on":[37],"multi-species":[38,166],"datasets.":[39],"Here,":[40],"we":[41,144],"introduce":[42],"the":[43,53,85,141],"accidental":[44,178],"taxonomist":[45,179],"hypothesis,":[46],"proposing":[47],"that":[48,68,99,133,165,177],"neural":[49],"networks":[50],"can":[51,102,168],"exploit":[52],"phylogenetic":[54],"distances":[55],"across":[56],"labels":[57],"in":[58,69,149],"datasets":[60,71],"rather":[61],"than":[62],"genuine":[63,124],"interaction":[64],"features.":[65,126],"We":[66,96],"show":[67],"PPI":[70,125],"with":[72],"random":[73],"negative":[74,135],"sampling,":[75],"pairs":[77,139],"for":[78,186],"real":[79],"PPIs":[80],"almost":[82,90],"exclusively":[83],"from":[84,93,140],"same":[86,142],"species,":[87,143],"while":[88],"negatives":[89],"always":[91],"originate":[92],"different":[94],"species.":[95],"then":[97],"demonstrate":[98],"pLM":[100],"embeddings":[101],"be":[103],"used":[104],"accurately":[106],"distinguish":[107],"whether":[108],"two":[109],"proteins":[110],"share":[111],"a":[112,129,146,182],"taxonomic":[113],"origin,":[114],"allowing":[115],"\"cheat\"":[118],"by":[119],"learning":[120],"phylogeny":[121],"instead":[122],"of":[123],"By":[127],"employing":[128],"strategic":[130],"sampling":[131],"strategy":[132],"restricts":[134],"examples":[136],"reveal":[145],"marked":[147],"drop":[148],"model":[150],"performance,":[151],"confirming":[152],"our":[153],"hypothesis.":[154],"Compellingly,":[155],"these":[156],"strategically":[157],"trained":[158],"still":[160],"outperform":[161],"single-species":[162],"models,":[163],"suggesting":[164],"data":[167],"improve":[169],"if":[171],"carefully":[172],"curated.":[173],"These":[174],"findings":[175],"suggest":[176],"behavior":[180],"is":[181,190],"influential":[184],"confounder":[185],"PPI,":[187],"it":[189],"also":[191],"broadly":[192],"applicable":[193],"any":[195],"supervised-learning":[196],"dataset.":[198]},"counts_by_year":[{"year":2026,"cited_by_count":11}],"updated_date":"2026-11-08T12:12:28.789561","created_date":"2025-10-10T00:00:00"}