{"id":"https://openalex.org/W7126025018","doi":"https://doi.org/10.1109/bibm66473.2025.11356134","title":"Evo2-Virus: Ultra-Short Viral Sequence Identification with EVO2","display_name":"Evo2-Virus: Ultra-Short Viral Sequence Identification with EVO2","publication_year":2025,"publication_date":"2025-12-15","ids":{"openalex":"https://openalex.org/W7126025018","doi":"https://doi.org/10.1109/bibm66473.2025.11356134"},"language":null,"primary_location":{"id":"doi:10.1109/bibm66473.2025.11356134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124168772","display_name":"Zhixiang Xu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130392","display_name":"Research Applications (United States)","ror":"https://ror.org/02q2v3574","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhixiang Xu","raw_affiliation_strings":["Beijing Institute of Mathematical Sciences and Applications,Beijing Key Laboratory of Topological Statistics and Applications for Complex Systems,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Mathematical Sciences and Applications,Beijing Key Laboratory of Topological Statistics and Applications for Complex Systems,Beijing,China","institution_ids":["https://openalex.org/I4210130392"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hankai Yang","orcid":null},"institutions":[{"id":"https://openalex.org/I107982497","display_name":"Dalian Ocean University","ror":"https://ror.org/0523b6g79","country_code":"CN","type":"education","lineage":["https://openalex.org/I107982497"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hankai Yang","raw_affiliation_strings":["School of Chemical Engineering, Dalian University of Technology,Ocean and Life Sciences,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Chemical Engineering, Dalian University of Technology,Ocean and Life Sciences,China","institution_ids":["https://openalex.org/I107982497"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5055305202","display_name":"Xiaoya Fan","orcid":"https://orcid.org/0000-0002-5002-6968"},"institutions":[{"id":"https://openalex.org/I27357992","display_name":"Dalian University of Technology","ror":"https://ror.org/023hj5876","country_code":"CN","type":"education","lineage":["https://openalex.org/I27357992"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoya Fan","raw_affiliation_strings":["School of Software Technology, Dalian University of Technology,Dalian,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software Technology, Dalian University of Technology,Dalian,China","institution_ids":["https://openalex.org/I27357992"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5124159622","display_name":"Zhong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210130392","display_name":"Research Applications (United States)","ror":"https://ror.org/02q2v3574","country_code":"US","type":"company","lineage":["https://openalex.org/I4210130392"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhong Wang","raw_affiliation_strings":["Beijing Institute of Mathematical Sciences and Applications,Beijing Key Laboratory of Topological Statistics and Applications for Complex Systems,Beijing,China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Beijing Institute of Mathematical Sciences and Applications,Beijing Key Laboratory of Topological Statistics and Applications for Complex Systems,Beijing,China","institution_ids":["https://openalex.org/I4210130392"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":"7237","last_page":"7242"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.5972999930381775,"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":0.5972999930381775,"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":0.05849999934434891,"subfield":{"id":"https://openalex.org/subfields/2303","display_name":"Ecology"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11289","display_name":"Single-cell and spatial transcriptomics","score":0.03669999912381172,"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/robustness","display_name":"Robustness (evolution)","score":0.5896999835968018},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5619999766349792},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.4925999939441681},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.4242999851703644},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.40220001339912415},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.3955000042915344},{"id":"https://openalex.org/keywords/sequence-motif","display_name":"Sequence motif","score":0.3628000020980835}],"concepts":[{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.6363000273704529},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5896999835968018},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5619999766349792},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.4925999939441681},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.4596000015735626},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.43230000138282776},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4244000017642975},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.4242999851703644},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.40220001339912415},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.3955000042915344},{"id":"https://openalex.org/C117745874","wikidata":"https://www.wikidata.org/wiki/Q901612","display_name":"Sequence motif","level":3,"score":0.3628000020980835},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.35910001397132874},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.34880000352859497},{"id":"https://openalex.org/C132917006","wikidata":"https://www.wikidata.org/wiki/Q5250436","display_name":"Deep sequencing","level":4,"score":0.31709998846054077},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.31360000371932983},{"id":"https://openalex.org/C61053724","wikidata":"https://www.wikidata.org/wiki/Q1154615","display_name":"Sequence analysis","level":3,"score":0.3025999963283539},{"id":"https://openalex.org/C2522874641","wikidata":"https://www.wikidata.org/wiki/Q808","display_name":"Virus","level":2,"score":0.2856999933719635},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2824999988079071},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.27559998631477356},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.27000001072883606},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.266400009393692},{"id":"https://openalex.org/C2994541485","wikidata":"https://www.wikidata.org/wiki/Q1928978","display_name":"Viral infection","level":3,"score":0.25200000405311584}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm66473.2025.11356134","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm66473.2025.11356134","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W2045204781","https://openalex.org/W2119859604","https://openalex.org/W2142678478","https://openalex.org/W2291003811","https://openalex.org/W2526038422","https://openalex.org/W2732139758","https://openalex.org/W2902664755","https://openalex.org/W2949831026","https://openalex.org/W3003110834","https://openalex.org/W3004280078","https://openalex.org/W3009993360","https://openalex.org/W3033129278","https://openalex.org/W3091956242","https://openalex.org/W3112703609","https://openalex.org/W3127238141","https://openalex.org/W3127656915","https://openalex.org/W4400132918","https://openalex.org/W4404644013"],"related_works":[],"abstract_inverted_index":{"The":[0,133],"accurate":[1],"identification":[2],"of":[3,127,131],"viral":[4,19,70,147,168],"sequences":[5],"in":[6,15,27,44,152],"sequencing":[7,46],"data":[8],"is":[9,98],"critical":[10],"for":[11,166,174],"pathogen":[12,176],"surveillance,":[13],"especially":[14],"metagenomic":[16],"environments":[17],"where":[18],"reads":[20],"are":[21,42],"ultra-short,":[22],"noisy,":[23],"and":[24,35,57,87,101,122,129,142,148,163,179],"deeply":[25],"embedded":[26],"host":[28],"material.":[29],"Existing":[30],"methods":[31],"struggle":[32],"with":[33,64,171],"generalizability":[34],"robustness,":[36],"particularly":[37],"on":[38],"short":[39,73],"fragments":[40,71],"that":[41,60,112],"common":[43],"real-world":[45,175],"data.":[47],"In":[48],"this":[49],"work,":[50],"we":[51],"present":[52],"Ev02-":[53,158],"Virus,":[54],"a":[55,79,88,161],"lightweight":[56],"scalable":[58],"framework":[59],"combines":[61],"autoregressive":[62],"pretraining":[63,81],"bidirectional":[65],"Transformer":[66],"fine-tuning":[67],"to":[68],"classify":[69],"as":[72,74,160],"105":[75],"bp.":[76],"We":[77],"curate":[78],"large-scale":[80],"corpus":[82],"from":[83,93],"the":[84],"Virus-Host":[85],"DB":[86],"balanced":[89],"classification":[90],"dataset":[91],"constructed":[92],"human":[94],"RNA-seq":[95],"samples.":[96],"Evo2-Virus":[97,113],"trained":[99],"end-to-end":[100],"requires":[102],"no":[103],"hand-crafted":[104],"features":[105],"or":[106],"sequence":[107,140,169],"alignment.":[108],"Extensive":[109],"experiments":[110],"show":[111],"significantly":[114],"outperforms":[115],"state-of-the-art":[116],"models":[117],"including":[118],"Seeker,":[119],"DeepVirFinder,":[120],"RNA-FM,":[121],"RNN-VirSeeker,":[123],"achieving":[124],"an":[125],"Fl-score":[126],"0.889":[128],"AUC":[130],"0.957.":[132],"model":[134],"demonstrates":[135],"remarkable":[136],"robustness":[137],"under":[138],"synthetic":[139],"noise":[141],"exhibits":[143],"clear":[144],"separability":[145],"between":[146],"non-viral":[149],"embed":[150],"dings":[151],"low-dimensional":[153],"space.":[154],"Our":[155],"results":[156],"highlight":[157],"Virus":[159],"practical":[162],"effective":[164],"solution":[165],"ultra-short":[167],"detection,":[170],"direct":[172],"implications":[173],"screening,":[177],"biosurveillance,":[178],"genomic":[180],"diagnostics.":[181]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-30T00:00:00"}
