{"id":"https://openalex.org/W4282926623","doi":"https://doi.org/10.1093/bib/bbac204","title":"ViBE: a hierarchical BERT model to identify eukaryotic viruses using metagenome sequencing data","display_name":"ViBE: a hierarchical BERT model to identify eukaryotic viruses using metagenome sequencing data","publication_year":2022,"publication_date":"2022-05-04","ids":{"openalex":"https://openalex.org/W4282926623","doi":"https://doi.org/10.1093/bib/bbac204","pmid":"https://pubmed.ncbi.nlm.nih.gov/35667011"},"language":"en","primary_location":{"id":"doi:10.1093/bib/bbac204","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac204","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"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/A5088681657","display_name":"Ho\u2010Jin Gwak","orcid":"https://orcid.org/0000-0001-7765-0827"},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Ho-Jin Gwak","raw_affiliation_strings":["Department of Computer Science, Hanyang University , Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hanyang University , Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078928762","display_name":"Mina Rho","orcid":null},"institutions":[{"id":"https://openalex.org/I4575257","display_name":"Hanyang University","ror":"https://ror.org/046865y68","country_code":"KR","type":"education","lineage":["https://openalex.org/I4575257"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Mina Rho","raw_affiliation_strings":["Department of Biomedical Informatics, Hanyang University , Seoul, Korea","Department of Computer Science, Hanyang University , Seoul, Korea"],"affiliations":[{"raw_affiliation_string":"Department of Biomedical Informatics, Hanyang University , Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]},{"raw_affiliation_string":"Department of Computer Science, Hanyang University , Seoul, Korea","institution_ids":["https://openalex.org/I4575257"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078928762"],"corresponding_institution_ids":["https://openalex.org/I4575257"],"apc_list":{"value":4011,"currency":"USD","value_usd":4011},"apc_paid":null,"fwci":4.8556,"has_fulltext":false,"cited_by_count":31,"citation_normalized_percentile":{"value":0.95340354,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"23","issue":"4","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9997000098228455,"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"}},"topics":[{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9997000098228455,"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/T13220","display_name":"Plant and Fungal Interactions Research","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1310","display_name":"Endocrinology"},"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":0.998199999332428,"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/metagenomics","display_name":"Metagenomics","score":0.8887436389923096},{"id":"https://openalex.org/keywords/human-virome","display_name":"Human virome","score":0.8518173694610596},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.735312819480896},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.7263478636741638},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.551542341709137},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4526888132095337},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.35535532236099243},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.31492578983306885},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.29352670907974243}],"concepts":[{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.8887436389923096},{"id":"https://openalex.org/C190743605","wikidata":"https://www.wikidata.org/wiki/Q17027885","display_name":"Human virome","level":4,"score":0.8518173694610596},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.735312819480896},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.7263478636741638},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.551542341709137},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4526888132095337},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.35535532236099243},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.31492578983306885},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.29352670907974243}],"mesh":[{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016415","descriptor_name":"Sequence Alignment","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056186","descriptor_name":"Metagenomics","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D056890","descriptor_name":"Eukaryota","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.1093/bib/bbac204","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bib/bbac204","pdf_url":null,"source":{"id":"https://openalex.org/S91767247","display_name":"Briefings in Bioinformatics","issn_l":"1467-5463","issn":["1467-5463","1477-4054"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35667011","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35667011","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Briefings in bioinformatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6299999952316284,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[{"id":"https://openalex.org/G5323172026","display_name":null,"funder_award_id":"2020-0-01373","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W1968872877","https://openalex.org/W1971876518","https://openalex.org/W1998989757","https://openalex.org/W2021210077","https://openalex.org/W2072022921","https://openalex.org/W2101234009","https://openalex.org/W2108234281","https://openalex.org/W2116934424","https://openalex.org/W2132598047","https://openalex.org/W2149017136","https://openalex.org/W2152885278","https://openalex.org/W2159954944","https://openalex.org/W2170551349","https://openalex.org/W2289294330","https://openalex.org/W2467114126","https://openalex.org/W2530132666","https://openalex.org/W2562468253","https://openalex.org/W2575057819","https://openalex.org/W2605595174","https://openalex.org/W2610784236","https://openalex.org/W2783928952","https://openalex.org/W2805517687","https://openalex.org/W2890665816","https://openalex.org/W2892181857","https://openalex.org/W2949759087","https://openalex.org/W2950044547","https://openalex.org/W2952631022","https://openalex.org/W2968063528","https://openalex.org/W2980450195","https://openalex.org/W2990618091","https://openalex.org/W3003110834","https://openalex.org/W3027189436","https://openalex.org/W3120018424","https://openalex.org/W3120883648","https://openalex.org/W3127238141","https://openalex.org/W3127482714","https://openalex.org/W3127656915","https://openalex.org/W3133451990","https://openalex.org/W3148807116","https://openalex.org/W3159504416","https://openalex.org/W6675354045","https://openalex.org/W6682691769","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766673545","https://openalex.org/W6778883912"],"related_works":["https://openalex.org/W2519363532","https://openalex.org/W3182597671","https://openalex.org/W4220807255","https://openalex.org/W3216950677","https://openalex.org/W4293040420","https://openalex.org/W2254157384","https://openalex.org/W2289294330","https://openalex.org/W3133222449","https://openalex.org/W2210738511","https://openalex.org/W2474302342"],"abstract_inverted_index":{"Viruses":[0],"are":[1,70],"ubiquitous":[2],"in":[3,14,77],"humans":[4],"and":[5,8,28,100,119,135],"various":[6],"environments":[7],"continually":[9],"mutate":[10],"themselves.":[11],"Identifying":[12],"viruses":[13,27,41,95,134],"an":[15],"environment":[16],"without":[17],"cultivation":[18],"is":[19,35],"challenging;":[20],"however,":[21],"promoting":[22],"the":[23,30,58,74,78,104,115,173],"screening":[24],"of":[25,32,57,163],"novel":[26],"expanding":[29],"knowledge":[31],"viral":[33,44,64,79],"space":[34],"essential.":[36],"Homology-based":[37],"methods":[38,147,156],"that":[39,124],"identify":[40],"using":[42,110,168],"known":[43,59],"genomes":[45,118],"rely":[46],"on":[47],"sequence":[48],"alignments,":[49],"making":[50],"it":[51],"difficult":[52],"to":[53,72,92,128],"capture":[54,63],"remote":[55],"homologs":[56],"viruses.":[60,139],"To":[61],"accurately":[62],"signals":[65],"from":[66,96,114],"metagenomic":[67],"samples,":[68],"models":[69,123],"needed":[71],"understand":[73],"patterns":[75],"encoded":[76],"genomes.":[80],"In":[81],"this":[82],"study,":[83],"we":[84],"developed":[85],"a":[86],"hierarchical":[87],"BERT":[88],"model":[89],"named":[90],"ViBE":[91,109,140,152,164],"detect":[93],"eukaryotic":[94,131,136],"metagenome":[97],"sequencing":[98,170],"data":[99],"classify":[101,125],"them":[102],"at":[103],"order":[105],"level.":[106],"We":[107],"pre-trained":[108],"read-like":[111],"sequences":[112],"generated":[113],"virus":[116],"reference":[117],"derived":[120],"three":[121],"fine-tuned":[122],"paired-end":[126],"reads":[127],"orders":[129],"for":[130,157],"deoxyribonucleic":[132],"acid":[133,138],"ribonucleic":[137],"achieved":[141],"higher":[142],"recall":[143],"than":[144],"state-of-the-art":[145,154],"alignment-based":[146],"while":[148],"maintaining":[149],"comparable":[150],"precision.":[151],"outperformed":[153],"alignment-free":[155],"all":[158],"test":[159],"cases.":[160],"The":[161],"performance":[162],"was":[165],"also":[166],"verified":[167],"real":[169],"datasets,":[171],"including":[172],"vaginal":[174],"virome.":[175]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":14},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
