{"id":"https://openalex.org/W7214918458","doi":"https://doi.org/10.64898/2026.09.17.752359","title":"A moving target: non-stationary selection governs unsupervised prediction of viral fitness","display_name":"A moving target: non-stationary selection governs unsupervised prediction of viral fitness","publication_year":2026,"publication_date":"2026-09-30","ids":{"openalex":"https://openalex.org/W7214918458","doi":"https://doi.org/10.64898/2026.09.17.752359"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.17.752359","doi":"https://doi.org/10.64898/2026.09.17.752359","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752359","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.17.752359.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.17.752359.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068557724","display_name":"St\u00e9phane Aris\u2010Brosou","orcid":"https://orcid.org/0000-0003-4987-0296","observed_orcids":["https://orcid.org/0000-0003-4987-0296"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Stephane Aris-Brosou","raw_affiliation_strings":["University of Ottawa"],"raw_orcid":"https://orcid.org/0000-0003-4987-0296","affiliations":[{"raw_affiliation_string":"University of Ottawa","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021631132","display_name":"Matthieu Vilain","orcid":"https://orcid.org/0009-0004-4870-3853","observed_orcids":["https://orcid.org/0009-0004-4870-3853"]},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Matthieu Vilain","raw_affiliation_strings":["University of Ottawa"],"raw_orcid":"https://orcid.org/0009-0004-4870-3853","affiliations":[{"raw_affiliation_string":"University of Ottawa","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5068557724"],"corresponding_institution_ids":["https://openalex.org/I153718931"],"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/T11764","display_name":"Evolution and Genetic Dynamics","score":0.92330002784729,"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"}},"topics":[{"id":"https://openalex.org/T11764","display_name":"Evolution and Genetic Dynamics","score":0.92330002784729,"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"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.022700000554323196,"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/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.017500000074505806,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"unsupervised learning","score":0.7689999938011169},{"id":"https://openalex.org/keywords/protein-language-models","display_name":"protein language models","score":0.8130000233650208},{"id":"https://openalex.org/keywords/protein-multiple-sequence-alignment","display_name":"protein multiple sequence alignment","score":0.7310000061988831},{"id":"https://openalex.org/keywords/antigen-escape","display_name":"antigen escape","score":0.7450000047683716},{"id":"https://openalex.org/keywords/deep-mutational-scanning","display_name":"deep mutational scanning","score":0.8190000057220459},{"id":"https://openalex.org/keywords/sars-cov-2-spike-protein","display_name":"SARS-CoV-2 spike protein","score":0.8970000147819519},{"id":"https://openalex.org/keywords/protein-structure","display_name":"protein structure","score":0.40299999713897705},{"id":"https://openalex.org/keywords/emerging-pathogens","display_name":"emerging pathogens","score":0.5770000219345093}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.566100001335144},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5390999913215637},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.4997999966144562},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44620001316070557},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4375999867916107},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4172999858856201},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.41499999165534973},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.412200003862381},{"id":"https://openalex.org/C501734568","wikidata":"https://www.wikidata.org/wiki/Q42918","display_name":"Mutation","level":3,"score":0.412200003862381},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3930000066757202},{"id":"https://openalex.org/C2910387474","wikidata":"https://www.wikidata.org/wiki/Q331710","display_name":"Genetic Fitness","level":3,"score":0.3880000114440918},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.38499999046325684},{"id":"https://openalex.org/C193252679","wikidata":"https://www.wikidata.org/wiki/Q242125","display_name":"Phylogenetic tree","level":3,"score":0.38339999318122864},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3765000104904175},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.3749000132083893},{"id":"https://openalex.org/C93959086","wikidata":"https://www.wikidata.org/wiki/Q6888345","display_name":"Model selection","level":2,"score":0.36320000886917114},{"id":"https://openalex.org/C8769409","wikidata":"https://www.wikidata.org/wiki/Q2066554","display_name":"Viral evolution","level":4,"score":0.3546000123023987},{"id":"https://openalex.org/C91852762","wikidata":"https://www.wikidata.org/wiki/Q3307742","display_name":"Fitness landscape","level":3,"score":0.3172000050544739},{"id":"https://openalex.org/C114289077","wikidata":"https://www.wikidata.org/wiki/Q3284399","display_name":"Statistical model","level":2,"score":0.31450000405311584},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.3142000138759613},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.3028999865055084},{"id":"https://openalex.org/C3007834351","wikidata":"https://www.wikidata.org/wiki/Q82069695","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","level":5,"score":0.29660001397132874},{"id":"https://openalex.org/C2779714256","wikidata":"https://www.wikidata.org/wiki/Q25305062","display_name":"Multiple Models","level":2,"score":0.2892000079154968},{"id":"https://openalex.org/C2780879997","wikidata":"https://www.wikidata.org/wiki/Q952587","display_name":"Viral protein","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.28119999170303345},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.27059999108314514},{"id":"https://openalex.org/C90329073","wikidata":"https://www.wikidata.org/wiki/Q914232","display_name":"Ask price","level":2,"score":0.25619998574256897},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.25450000166893005},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.17.752359","doi":"https://doi.org/10.64898/2026.09.17.752359","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752359","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.17.752359.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.17.752359","doi":"https://doi.org/10.64898/2026.09.17.752359","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.17.752359","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/30/2026.09.17.752359.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-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.5683000087738037,"display_name":"Good health and well-being"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320310630","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7214918458.pdf","grobid_xml":"https://content.openalex.org/works/W7214918458.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4410325217","https://openalex.org/W7134847968","https://openalex.org/W7213398897","https://openalex.org/W4413768906","https://openalex.org/W4413345420","https://openalex.org/W4403165127","https://openalex.org/W7212555430","https://openalex.org/W7167929289","https://openalex.org/W7219845977","https://openalex.org/W4318452921"],"abstract_inverted_index":{"Anticipating":[0],"how":[1,35],"mutations":[2],"change":[3],"viral":[4,102,122,187,267],"fitness":[5,89,188,248,268],"is":[6,25,32,79,117,189,201,221,232,240,270],"central":[7,199],"to":[8,185],"genomic":[9],"surveillance":[10],"and":[11,48,74,209,255],"vaccine":[12],"design.":[13],"However,":[14],"the":[15,19,88,97,135,140,147,150,153,165,169,177,181,190,216,219,252],"phenotypic":[16],"data":[17],"behind":[18],"most":[20,28,182],"accurate":[21],"supervised":[22],"variant-effect":[23],"predictors":[24],"unavailable":[26],"for":[27,139],"emerging":[29],"pathogens.":[30],"It":[31],"therefore":[33],"unclear":[34],"a":[36,59,92,110,118,125,223,233,237,277],"label-free,":[37],"unsupervised":[38,62,266],"approach":[39],"would":[40],"perform":[41],"using":[42,203],"only":[43],"sequences,":[44],"their":[45,49],"evolutionary":[46,274],"history,":[47],"protein":[50,113,159,191],"structure.":[51],"To":[52],"address":[53],"this":[54,262],"outstanding":[55],"question,":[56],"we":[57,107,213],"assemble":[58],"modular,":[60],"fully":[61],"pipeline":[63],"that":[64,87,109,215,230,239,265],"estimates":[65],"key":[66],"interpretable":[67],"terms:":[68],"intrinsic":[69,98],"replicative":[70],"fitness,":[71,123],"antigenic":[72,141],"escape,":[73],"realized":[75],"growth.":[76],"Each":[77],"term":[78,99],"produced":[80],"by":[81],"more":[82,130],"than":[83,131],"one":[84],"estimator,":[85],"so":[86],"predictor":[90,120],"becomes":[91],"testable":[93],"model":[94,115,129,194],"choice.":[95],"Benchmarking":[96],"on":[100,158],"21":[101],"deep-mutational-scanning":[103],"assays":[104],"from":[105],"ProteinGym,":[106],"find":[108,214],"650-million-parameter":[111],"single-sequence":[112,170],"language":[114],"(PLM)":[116],"weak":[119],"of":[121,149,206,218,226,247],"whereas":[124],"simple":[126,178],"site-independent":[127],"alignment":[128,160,220,259],"doubles":[132],"performance,":[133],"with":[134,168],"largest":[136],"gains":[137],"obtained":[138],"surface":[142],"proteins":[143],"not":[144,174,193,250],"included":[145],"in":[146,236],"training":[148],"PLM.":[151],"On":[152],"other":[154],"hand,":[155],"PMLs":[156],"based":[157],"(MSA":[161],"Transformer,":[162],"Tranception)":[163],"regain":[164],"accuracy":[166],"lost":[167],"PML,":[171],"but":[172],"do":[173],"significantly":[175],"exceed":[176],"alignment.":[179],"Therefore,":[180],"important":[183],"feature":[184],"predict":[186],"alignment,":[192],"scale":[195],"or":[196],"architecture.":[197],"Our":[198],"result":[200],"evolutionary:":[202],"dated":[204],"sequences":[205],"SARS-CoV-2":[207],"spike":[208],"influenza":[210],"H3N2":[211],"hemagglutinin,":[212],"epoch":[217],"itself":[222,241],"virus-specific":[224],"determinant":[225],"accuracy.":[227],"This":[228],"demonstrates":[229],"selection":[231],"non-stationary":[234],"process,":[235],"manner":[238],"virus-specific.":[242],"A":[243],"phylogenetic":[244],"mutation-selection":[245],"estimator":[246],"does":[249],"match":[251],"far":[253],"simpler":[254],"less":[256],"computationally":[257],"expensive":[258],"model.":[260],"Altogether,":[261],"work":[263],"shows":[264],"prediction":[269],"as":[271,276],"much":[272],"an":[273],"problem":[275],"modeling":[278],"one.":[279]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-10-01T00:00:00"}