{"id":"https://openalex.org/W7203550135","doi":"https://doi.org/10.64898/2026.08.14.744703","title":"Protein language models and the long tail of functional diversity","display_name":"Protein language models and the long tail of functional diversity","publication_year":2026,"publication_date":"2026-08-14","ids":{"openalex":"https://openalex.org/W7203550135","doi":"https://doi.org/10.64898/2026.08.14.744703"},"language":"en","primary_location":{"id":"doi:10.64898/2026.08.14.744703","doi":"https://doi.org/10.64898/2026.08.14.744703","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.14.744703","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.14.744703.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.14.744703.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015655299","display_name":"Ria Vinod","orcid":"https://orcid.org/0000-0002-6282-9741","observed_orcids":["https://orcid.org/0000-0002-6282-9741"]},"institutions":[{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ria Vinod","raw_affiliation_strings":["Center for Computational Molecular Biology, Brown University, Providence, RI, USA"],"raw_orcid":"https://orcid.org/0000-0002-6282-9741","affiliations":[{"raw_affiliation_string":"Center for Computational Molecular Biology, Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5147232712","display_name":"Samir Char","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I1290206253","display_name":"Microsoft (United States)","ror":"https://ror.org/00d0nc645","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Samir Char","raw_affiliation_strings":["Microsoft Cloud & AI, Redmond, WA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Cloud & AI, Redmond, WA","institution_ids":["https://openalex.org/I1290206253"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071306257","display_name":"Ava P. Amini","orcid":"https://orcid.org/0000-0002-8601-6040","observed_orcids":["https://orcid.org/0000-0002-8601-6040"]},"institutions":[{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ava P. Amini","raw_affiliation_strings":["Microsoft Research, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0002-8601-6040","affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4400600948"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033244104","display_name":"Lorin A. Crawford","orcid":"https://orcid.org/0000-0003-0178-8242","observed_orcids":["https://orcid.org/0000-0003-0178-8242"]},"institutions":[{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Lorin Crawford","raw_affiliation_strings":["Microsoft Research, Cambridge, MA, USA"],"raw_orcid":"https://orcid.org/0000-0003-0178-8242","affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4400600948"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060834723","display_name":"Kevin Yang","orcid":"https://orcid.org/0000-0001-9045-6826","observed_orcids":["https://orcid.org/0000-0001-9045-6826"]},"institutions":[{"id":"https://openalex.org/I4400600948","display_name":"Microsoft Research New England (United States)","ror":"https://ror.org/010wkqn50","country_code":"US","type":"company","lineage":["https://openalex.org/I1290206253","https://openalex.org/I4400600948"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Kevin K. Yang","raw_affiliation_strings":["Microsoft Research, Cambridge, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Microsoft Research, Cambridge, MA, USA","institution_ids":["https://openalex.org/I4400600948"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5060834723"],"corresponding_institution_ids":["https://openalex.org/I4400600948"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"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":0.625,"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":0.625,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.3375999927520752,"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":0.015799999237060547,"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-language-models","display_name":"protein language models","score":0.9990000128746033},{"id":"https://openalex.org/keywords/sequence-clustering","display_name":"sequence clustering","score":0.6029999852180481},{"id":"https://openalex.org/keywords/functional-diversity","display_name":"functional diversity","score":0.6859999895095825},{"id":"https://openalex.org/keywords/protein-domain-composition","display_name":"protein domain composition","score":0.6510000228881836},{"id":"https://openalex.org/keywords/homology-detection","display_name":"homology detection","score":0.597000002861023},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.6100000143051147},{"id":"https://openalex.org/keywords/data-curation","display_name":"data curation","score":0.7099999785423279}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7293999791145325},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5737000107765198},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.4885999858379364},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.46720001101493835},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.46239998936653137},{"id":"https://openalex.org/C144292202","wikidata":"https://www.wikidata.org/wiki/Q898273","display_name":"Protein domain","level":3,"score":0.42829999327659607},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.3953000009059906},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.38920000195503235},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.38600000739097595},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.3276999890804291},{"id":"https://openalex.org/C2988890453","wikidata":"https://www.wikidata.org/wiki/Q5508815","display_name":"Functional diversity","level":2,"score":0.3163999915122986},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.31380000710487366},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.30869999527931213},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3041999936103821},{"id":"https://openalex.org/C10010492","wikidata":"https://www.wikidata.org/wiki/Q3142557","display_name":"Protein sequencing","level":4,"score":0.3018999993801117},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C186767784","wikidata":"https://www.wikidata.org/wiki/Q5162841","display_name":"Consensus clustering","level":5,"score":0.2957000136375427},{"id":"https://openalex.org/C171897839","wikidata":"https://www.wikidata.org/wiki/Q417841","display_name":"Protein family","level":3,"score":0.29190000891685486},{"id":"https://openalex.org/C165525559","wikidata":"https://www.wikidata.org/wiki/Q224180","display_name":"Homology (biology)","level":3,"score":0.28519999980926514},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2757999897003174},{"id":"https://openalex.org/C2779315201","wikidata":"https://www.wikidata.org/wiki/Q414601","display_name":"Sequence homology","level":4,"score":0.2720000147819519},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.26980000734329224},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.25839999318122864},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.2578999996185303},{"id":"https://openalex.org/C48702757","wikidata":"https://www.wikidata.org/wiki/Q8269924","display_name":"Biological classification","level":2,"score":0.25270000100135803}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.08.14.744703","doi":"https://doi.org/10.64898/2026.08.14.744703","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.14.744703","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.14.744703.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.08.14.744703","doi":"https://doi.org/10.64898/2026.08.14.744703","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.08.14.744703","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/08/14/2026.08.14.744703.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","license_id":"https://openalex.org/licenses/cc-by","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7203550135.pdf","grobid_xml":"https://content.openalex.org/works/W7203550135.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4402100089","https://openalex.org/W7171818247","https://openalex.org/W7028714238","https://openalex.org/W4414800680","https://openalex.org/W3010254513","https://openalex.org/W4392686654","https://openalex.org/W4402821735","https://openalex.org/W4416260672","https://openalex.org/W4388024559","https://openalex.org/W4409579563"],"abstract_inverted_index":{"Abstract":[0],"Protein":[1],"language":[2,119],"model":[3,120],"performance":[4],"on":[5,9],"downstream":[6],"tasks":[7],"depends":[8],"the":[10,70,86,91],"pretraining":[11],"data,":[12],"motivating":[13],"recent":[14],"efforts":[15],"to":[16,47,64,136],"combine":[17],"genomic-":[18],"and":[19,38,58,76,105,123,146,170,202],"metagenomic-derived":[20],"protein":[21,118],"sequences":[22,32,89],"into":[23],"large-scale":[24,81,211],"atlases.":[25,214],"Because":[26],"these":[27,194],"datasets":[28,148],"are":[29,33,53,62,77,96],"highly":[30],"redundant,":[31],"typically":[34,54],"clustered":[35,163,184],"by":[36,107,168],"similarity":[37],"sampled":[39],"during":[40],"training.":[41,173],"Sequences":[42],"that":[43,131,144,157,189],"do":[44],"not":[45],"belong":[46,135],"any":[48],"cluster,":[49],"known":[50],"as":[51],"\u201csingletons\u201d,":[52],"excluded":[55],"from":[56,103],"training":[57,201],"evaluation":[59],"because":[60],"they":[61,127],"considered":[63],"be":[65],"artifacts.":[66],"However,":[67],"singletons":[68,101,134,158,176,198],"represent":[69],"long":[71],"tail":[72],"of":[73,85,207],"functional":[74],"diversity":[75],"abundant":[78],"in":[79,90,199,210],"many":[80,132],"atlases:":[82],"nearly":[83],"43%":[84],"3.34":[87],"billion":[88],"joint":[92],"genomic-metagenomic":[93],"dataset":[94],"GigaRef":[95,106,133],"singletons.":[97],"Here,":[98],"we":[99],"characterize":[100],"derived":[102],"UniRef":[104],"assessing":[108],"whether":[109],"clustering":[110,152,191],"missed":[111],"homologs,":[112],"how":[113],"much":[114],"their":[115],"exclusion":[116],"affects":[117],"(PLM)":[121],"training,":[122],"which":[124],"biological":[125],"domains":[126],"contain.":[128],"We":[129,154],"find":[130],"a":[137],"cluster":[138],"under":[139],"alternative":[140],"parameter":[141],"settings,":[142],"suggesting":[143],"genomic":[145],"metagenomic":[147,175],"may":[149],"require":[150],"dataset-specific":[151],"configurations.":[153],"also":[155],"show":[156],"share":[159],"mutual":[160],"information":[161],"with":[162],"sequences,":[164,185],"making":[165],"them":[166],"learnable":[167],"PLMs":[169],"useful":[171],"for":[172,204],"Finally,":[174],"carry":[177],"denser,":[178],"more":[179],"diverse":[180],"domain":[181],"content":[182],"than":[183],"including":[186,197],"domain-level":[187],"homology":[188],"sequence-identity":[190],"misses.":[192],"Together,":[193],"results":[195],"support":[196],"PLM":[200],"call":[203],"closer":[205],"examination":[206],"data":[208],"curation":[209],"integrated":[212],"sequence":[213]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-08-16T00:00:00"}