{"id":"https://openalex.org/W7225808691","doi":"https://doi.org/10.64898/2026.11.09.765411","title":"Assessing the Capacity of Genomic Language Models to Generate Informative Embeddings of Viral Genome Fragments","display_name":"Assessing the Capacity of Genomic Language Models to Generate Informative Embeddings of Viral Genome Fragments","publication_year":2026,"publication_date":"2026-11-11","ids":{"openalex":"https://openalex.org/W7225808691","doi":"https://doi.org/10.64898/2026.11.09.765411"},"language":"en","primary_location":{"id":"doi:10.64898/2026.11.09.765411","doi":"https://doi.org/10.64898/2026.11.09.765411","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765411","pdf_url":null,"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://doi.org/10.64898/2026.11.09.765411","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5161470949","display_name":"Alexandr Kladchenko","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Alexandr Kladchenko","raw_affiliation_strings":["Moscow Center for Advanced Studies;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Moscow Center for Advanced Studies;","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5161493315","display_name":"Alexander Manolov","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I64264942","display_name":"Federal Medical-Biological Agency","ror":"https://ror.org/052ay8m85","country_code":"RU","type":"government","lineage":["https://openalex.org/I64264942"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Alexander Manolov","raw_affiliation_strings":["Federal Research and Clinical Center of Physical-Chemical Medicine of Federal Medical Biological Age;"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Federal Research and Clinical Center of Physical-Chemical Medicine of Federal Medical Biological Age;","institution_ids":["https://openalex.org/I64264942"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040521252","display_name":"\u041f\u043e\u043f\u043e\u0432 \u041d\u0438\u043a\u043e\u043b\u0430\u0439 \u0421\u0435\u0440\u0433\u0435\u0435\u0432\u0438\u0447","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210099575","display_name":"InSysBio (Russia)","ror":"https://ror.org/011fdmv87","country_code":"RU","type":"company","lineage":["https://openalex.org/I4210099575"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Nikolay Sergeevich Popov","raw_affiliation_strings":["Research Institute for Systems Biology and Medicine (RISBM), Moscow, Russia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Research Institute for Systems Biology and Medicine (RISBM), Moscow, Russia","institution_ids":["https://openalex.org/I4210099575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5161493315"],"corresponding_institution_ids":["https://openalex.org/I64264942"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"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":0.8134999871253967,"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":0.8134999871253967,"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/T11048","display_name":"Bacteriophages and microbial interactions","score":0.06870000064373016,"subfield":{"id":"https://openalex.org/subfields/2406","display_name":"Virology"},"field":{"id":"https://openalex.org/fields/24","display_name":"Immunology and Microbiology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.0406000018119812,"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":[],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5504000186920166},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5422000288963318},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.5321999788284302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5073999762535095},{"id":"https://openalex.org/C189430467","wikidata":"https://www.wikidata.org/wiki/Q7293293","display_name":"Ranking (information retrieval)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.4887000024318695},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.487199991941452},{"id":"https://openalex.org/C111442797","wikidata":"https://www.wikidata.org/wiki/Q7291446","display_name":"Rand index","level":3,"score":0.44449999928474426},{"id":"https://openalex.org/C93518851","wikidata":"https://www.wikidata.org/wiki/Q180160","display_name":"Metadata","level":2,"score":0.4316999912261963},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4047999978065491},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.392300009727478},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.3896999955177307},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.3601999878883362},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.34369999170303345},{"id":"https://openalex.org/C12426560","wikidata":"https://www.wikidata.org/wiki/Q189569","display_name":"Basis (linear algebra)","level":2,"score":0.33629998564720154},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33329999446868896},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.319599986076355},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.27630001306533813},{"id":"https://openalex.org/C41587187","wikidata":"https://www.wikidata.org/wiki/Q1501882","display_name":"Generalized linear model","level":2,"score":0.27379998564720154},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.26420000195503235},{"id":"https://openalex.org/C106208931","wikidata":"https://www.wikidata.org/wiki/Q1098876","display_name":"Genome-wide association study","level":5,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.64898/2026.11.09.765411","doi":"https://doi.org/10.64898/2026.11.09.765411","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765411","pdf_url":null,"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:10.64898/2026.11.09.765411","doi":"https://doi.org/10.64898/2026.11.09.765411","is_oa":true,"landing_page_url":"https://doi.org/10.64898/2026.11.09.765411","pdf_url":null,"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":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Genomic":[0],"language":[1],"models":[2,240],"(gLMs)":[3],"trained":[4],"on":[5,62,141,161,178,182,217],"large":[6],"volumes":[7],"of":[8,34,48,59,100,110,197,227,233],"nucleotide":[9],"sequences":[10],"are":[11,241],"becoming":[12],"an":[13],"alternative":[14],"to":[15,42],"classical":[16],"methods":[17,140],"in":[18,108],"metagenomic":[19],"analysis,":[20],"particularly":[21],"for":[22,246],"studying":[23],"genomic":[24],"\"dark":[25],"matter\".":[26],"In":[27],"this":[28],"work,":[29],"we":[30],"investigate":[31],"the":[32,63,70,96,101,105,115,139,150,162,167,195,207,218],"ability":[33],"four":[35,102],"gLMs":[36,74,103,209],"(DNABERT-2,":[37],"DNABERT-S,":[38],"ViraLM,":[39],"and":[40,68,79,84,92,112,146,156,180,202,220,236],"Evo2-7B)":[41],"generate":[43],"taxonomically":[44,248],"informative":[45,249],"vector":[46],"representations":[47,71,198],"short":[49],"viral":[50,143],"genome":[51],"fragments.":[52],"We":[53,136,192],"constructed":[54],"a":[55,230],"balanced":[56],"reference":[57,97,151,163],"dataset":[58,219],"viruses":[60],"based":[61],"ICTV":[64],"Virus":[65],"Metadata":[66],"Resource":[67],"compared":[69],"generated":[72],"by":[73,125],"with":[75,153,187],"conventional":[76,211],"k-mer":[77,130,157,185],"profiles":[78,131,186],"MinHash":[80,134],"sketches":[81],"using":[82],"clustering":[83],"neighborhood-based":[85],"metrics":[86],"(adjusted":[87],"Rand":[88],"index":[89],"(ARI),":[90],"precision@k,":[91],"CROSS":[93],"precision@k).":[94],"On":[95],"dataset,":[98,152],"three":[99],"outperformed":[104,133],"4-mer":[106],"profile":[107],"terms":[109],"ARI":[111],"precision@5":[113],"under":[114],"same":[116],"evaluation":[117,221],"protocol.":[118],"The":[119,223],"best":[120],"performance":[121,171,226],"was":[122],"generally":[123],"achieved":[124],"intermediate":[126],"model":[127,154],"layers.":[128],"Conventional":[129],"consistently":[132,169,224],"sketches.":[135],"further":[137],"evaluated":[138],"two":[142,174],"orders":[144],"(egoviruses":[145],"mriyaviruses)":[147],"absent":[148],"from":[149],"layers":[155],"lengths":[158],"selected":[159],"exclusively":[160],"dataset.":[164],"DNABERT-S":[165,228],"showed":[166],"most":[168],"strong":[170,225],"across":[172],"these":[173],"orders,":[175],"ranking":[176],"first":[177],"mriyaviruses":[179],"second":[181],"egoviruses,":[183],"while":[184],"Jensen-Shannon":[188],"distance":[189],"remained":[190],"competitive.":[191],"also":[193],"observed":[194],"consistency":[196],"between":[199],"forward":[200],"fragments":[201],"their":[203,214],"reverse":[204],"complements.":[205],"Overall,":[206],"best-performing":[208],"surpassed":[210],"baselines,":[212],"although":[213],"advantage":[215],"depended":[216],"metric.":[222],"suggests":[229],"potential":[231],"benefit":[232],"contrastive":[234],"fine-tuning":[235],"indicates":[237],"that":[238],"larger":[239],"not":[242],"necessarily":[243],"more":[244],"effective":[245],"generating":[247],"representations.":[250]},"counts_by_year":[],"updated_date":"2026-11-12T12:28:57.059296","created_date":"2026-11-12T00:00:00"}