{"id":"https://openalex.org/W7214769017","doi":"https://doi.org/10.64898/2026.09.25.754388","title":"Analyzing Genomic Foundation Models for Viral Sequence Identification","display_name":"Analyzing Genomic Foundation Models for Viral Sequence Identification","publication_year":2026,"publication_date":"2026-09-28","ids":{"openalex":"https://openalex.org/W7214769017","doi":"https://doi.org/10.64898/2026.09.25.754388"},"language":"en","primary_location":{"id":"doi:10.64898/2026.09.25.754388","doi":"https://doi.org/10.64898/2026.09.25.754388","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754388","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.25.754388.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":"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/2026/09/28/2026.09.25.754388.full.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5144473850","display_name":"Veronika B\u016f\u017ekov\u00e1","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Veronika B\u016f\u017ekov\u00e1","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077363792","display_name":"Bohuslav Dvorsk\u00fd","orcid":"https://orcid.org/0009-0000-4517-0570","observed_orcids":["https://orcid.org/0009-0000-4517-0570"]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Bohuslav Dvorsk\u00fd","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0000-4517-0570","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121118698","display_name":"Mariana Kom\u00e1rkov\u00e1","orcid":"https://orcid.org/0009-0000-5492-9104","observed_orcids":["https://orcid.org/0009-0000-5492-9104"]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Mariana Kom\u00e1rkov\u00e1","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0000-5492-9104","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121024916","display_name":"Kate\u0159ina Kollinov\u00e1","orcid":"https://orcid.org/0009-0000-1653-7919","observed_orcids":["https://orcid.org/0009-0000-1653-7919"]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Kate\u0159ina Kollinov\u00e1","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":"https://orcid.org/0009-0000-1653-7919","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047383339","display_name":"Radim Krupi\u010dka","orcid":"https://orcid.org/0000-0002-0280-215X","observed_orcids":["https://orcid.org/0000-0002-0280-215X"]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":false,"raw_author_name":"Radim Krupi\u010dka","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0002-0280-215X","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5074567563","display_name":"Ond\u0159ej Klemp\u00ed\u0159","orcid":"https://orcid.org/0000-0003-0773-5360","observed_orcids":["https://orcid.org/0000-0003-0773-5360"]},"institutions":[{"id":"https://openalex.org/I44504214","display_name":"Czech Technical University in Prague","ror":"https://ror.org/03kqpb082","country_code":"CZ","type":"education","lineage":["https://openalex.org/I44504214"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Ond\u0159ej Klemp\u00ed\u0159","raw_affiliation_strings":["Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic"],"raw_orcid":"https://orcid.org/0000-0003-0773-5360","affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Faculty of Biomedical Engineering, Czech Technical University in Prague, Sitna Square 3105, Kladno, Czech Republic","institution_ids":["https://openalex.org/I44504214"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5074567563"],"corresponding_institution_ids":["https://openalex.org/I44504214"],"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4684999883174896,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.4684999883174896,"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":0.34060001373291016,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.16040000319480896,"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/genomic-foundation-models","display_name":"genomic foundation models","score":0.9819999933242798},{"id":"https://openalex.org/keywords/viral-sequence-classification","display_name":"viral sequence classification","score":0.8849999904632568},{"id":"https://openalex.org/keywords/nucleotide-transformer","display_name":"Nucleotide Transformer","score":0.8429999947547913},{"id":"https://openalex.org/keywords/dnabert","display_name":"DNABERT","score":0.996999979019165},{"id":"https://openalex.org/keywords/blast-comparison","display_name":"BLAST comparison","score":0.8690000176429749},{"id":"https://openalex.org/keywords/sequence-embeddings","display_name":"sequence embeddings","score":0.675000011920929}],"concepts":[{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5494999885559082},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5241000056266785},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5142999887466431},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.503000020980835},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4893999993801117},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C192953774","wikidata":"https://www.wikidata.org/wiki/Q7307127","display_name":"Reference genome","level":4,"score":0.33169999718666077},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.3312999904155731},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.3296999931335449},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3140999972820282},{"id":"https://openalex.org/C2984717058","wikidata":"https://www.wikidata.org/wiki/Q1789476","display_name":"Reference database","level":2,"score":0.29109999537467957},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.28040000796318054},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2759999930858612},{"id":"https://openalex.org/C2994067223","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"Genomic sequencing","level":4,"score":0.275299996137619},{"id":"https://openalex.org/C2279292","wikidata":"https://www.wikidata.org/wiki/Q6322851","display_name":"k-mer","level":4,"score":0.271699994802475},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.26109999418258667},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.2567000091075897},{"id":"https://openalex.org/C45484198","wikidata":"https://www.wikidata.org/wiki/Q827246","display_name":"Sequence alignment","level":4,"score":0.25540000200271606}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.09.25.754388","doi":"https://doi.org/10.64898/2026.09.25.754388","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754388","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.25.754388.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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"bioRxiv","raw_type":"posted-content"}],"best_oa_location":{"id":"doi:10.64898/2026.09.25.754388","doi":"https://doi.org/10.64898/2026.09.25.754388","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.09.25.754388","pdf_url":"https://www.biorxiv.org/content/biorxiv/early/2026/09/28/2026.09.25.754388.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":"submittedVersion","is_accepted":false,"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/W7214769017.pdf","grobid_xml":"https://content.openalex.org/works/W7214769017.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2024847513","https://openalex.org/W2608965099","https://openalex.org/W3105816068","https://openalex.org/W3154674552","https://openalex.org/W4211107894","https://openalex.org/W4317436847","https://openalex.org/W4382490702","https://openalex.org/W4390889686","https://openalex.org/W4394808305","https://openalex.org/W4404251131","https://openalex.org/W4404403425","https://openalex.org/W4404617447","https://openalex.org/W4404644013","https://openalex.org/W4404821554","https://openalex.org/W4411538442","https://openalex.org/W4412454127","https://openalex.org/W4413395449","https://openalex.org/W4416795380","https://openalex.org/W6893234797","https://openalex.org/W7126223888","https://openalex.org/W7133517058","https://openalex.org/W7162319355","https://openalex.org/W7162507345","https://openalex.org/W7167850975","https://openalex.org/W7207735844"],"related_works":["https://openalex.org/W7199040093","https://openalex.org/W4404403425","https://openalex.org/W7162507345","https://openalex.org/W7207735844","https://openalex.org/W4417303333","https://openalex.org/W7169516937","https://openalex.org/W4407265890","https://openalex.org/W4409585627","https://openalex.org/W7126071320","https://openalex.org/W4410510686"],"abstract_inverted_index":{"Abstract":[0],"Rapid":[1],"and":[2,13,78,102,113,224,260],"accurate":[3],"identification":[4],"of":[5,17,160,170],"viral":[6,82],"sequences":[7,142,159],"underpins":[8],"clinical":[9],"diagnostics,":[10],"epidemiological":[11],"surveillance,":[12],"the":[14,21,43,74,90,139,163,173,189,219,232,253],"safety":[15],"testing":[16],"biological":[18],"products,":[19],"yet":[20],"established":[22],"alignment-based":[23],"methods":[24,66,217],"such":[25],"as":[26,117,129,252],"BLAST":[27,116,121,225],"are":[28],"inherently":[29],"closed-set,":[30],"with":[31,99,115,193,228],"accuracy":[32,169],"tied":[33],"to":[34,57,64,211],"how":[35],"well":[36],"a":[37,86,118,123,130,146,184,247],"query":[38,136],"is":[39,246],"already":[40],"represented":[41],"in":[42,48,109,262],"reference":[44,141,222],"database.":[45],"Recent":[46],"advances":[47],"genomic":[49,180],"foundation":[50,147],"models":[51],"(GFMs)":[52],"have":[53],"enabled":[54],"alignment-free":[55],"approaches":[56],"sequence":[58,83],"classification.":[59],"However,":[60],"their":[61],"performance":[62],"relative":[63],"traditional":[65],"remains":[67],"incompletely":[68],"characterised.":[69],"We":[70],"evaluated":[71,182],"GFMs,":[72],"specifically":[73],"Nucleotide":[75],"Transformer":[76],"(NT)":[77],"DNABERT":[79],"families,":[80],"for":[81,199,257],"classification":[84],"using":[85],"dataset":[87],"derived":[88],"from":[89,238],"Reference":[91],"Viral":[92],"Database":[93],"(RVDB).":[94],"Sequence":[95],"embeddings":[96],"were":[97,207],"generated":[98],"mean,":[100],"max,":[101],"CLS":[103],"pooling,":[104],"classified":[105],"by":[106,154,176],"nearest-neighbour":[107],"search":[108],"an":[110,168],"embedding":[111],"index":[112],"compared":[114,226],"reference.":[119],"Matching":[120],"provided":[122],"particularly":[124],"stringent":[125],"benchmark":[126],"here,":[127],"because":[128],"closed-set":[131],"method":[132],"it":[133,143,237],"compares":[134],"each":[135],"directly":[137,230],"against":[138,197],"exact":[140],"stores,":[144],"whereas":[145],"model":[148],"must":[149],"rely":[150],"on":[151,183],"representations":[152,241],"shaped":[153],"broad,":[155],"general-purpose":[156,240],"pre-training.":[157],"On":[158,178],"standard":[161],"length,":[162],"best":[164],"model,":[165],"NTv3-650M,":[166],"reached":[167],"0.93,":[171],"approaching":[172,236],"0.97":[174],"achieved":[175],"BLAST.":[177,200,215],"long":[179],"sequences,":[181,223],"much":[185],"smaller":[186],"test":[187],"set,":[188],"difference":[190],"narrowed":[191],"further,":[192],"NTv3-650M":[194,250],"reaching":[195],"0.95":[196],"0.98":[198],"Robustness":[201],"analyses":[202],"showed":[203],"that":[204],"all":[205],"GFMs":[206],"markedly":[208],"more":[209],"sensitive":[210],"base":[212],"masking":[213],"than":[214],"Both":[216],"indexed":[218],"same":[220],"labelled":[221],"queries":[227],"them":[229],"at":[231],"nucleotide":[233],"level,":[234],"so":[235],"frozen,":[239],"without":[242],"any":[243],"parameter":[244],"update":[245],"meaningful":[248],"result.":[249],"emerged":[251],"most":[254],"promising":[255],"candidate":[256],"further":[258],"optimisation":[259],"deployment":[261],"bioinformatics":[263],"applications.":[264]},"counts_by_year":[],"updated_date":"2026-11-09T13:22:03.289127","created_date":"2026-09-30T00:00:00"}