{"id":"https://openalex.org/W4200505767","doi":"https://doi.org/10.1093/bioinformatics/btab845","title":"Virtifier: a deep learning-based identifier for viral sequences from metagenomes","display_name":"Virtifier: a deep learning-based identifier for viral sequences from metagenomes","publication_year":2021,"publication_date":"2021-12-13","ids":{"openalex":"https://openalex.org/W4200505767","doi":"https://doi.org/10.1093/bioinformatics/btab845","pmid":"https://pubmed.ncbi.nlm.nih.gov/34908121"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btab845","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab845","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"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/A5004933429","display_name":"Yan Miao","orcid":"https://orcid.org/0000-0001-7719-426X"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Miao","raw_affiliation_strings":["College of Communication Engineering, Jilin University , Changchun 130022, China"],"raw_orcid":"https://orcid.org/0000-0001-7719-426X","affiliations":[{"raw_affiliation_string":"College of Communication Engineering, Jilin University , Changchun 130022, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101683169","display_name":"Fu Liu","orcid":"https://orcid.org/0000-0003-4378-3140"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fu Liu","raw_affiliation_strings":["College of Communication Engineering, Jilin University , Changchun 130022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Communication Engineering, Jilin University , Changchun 130022, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101489188","display_name":"Tao Hou","orcid":"https://orcid.org/0000-0002-2707-0573"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Hou","raw_affiliation_strings":["College of Communication Engineering, Jilin University , Changchun 130022, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Communication Engineering, Jilin University , Changchun 130022, China","institution_ids":["https://openalex.org/I194450716"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100321988","display_name":"Yun Liu","orcid":"https://orcid.org/0000-0003-0883-2453"},"institutions":[{"id":"https://openalex.org/I194450716","display_name":"Jilin University","ror":"https://ror.org/00js3aw79","country_code":"CN","type":"education","lineage":["https://openalex.org/I194450716"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yun Liu","raw_affiliation_strings":["College of Communication Engineering, Jilin University , Changchun 130022, China"],"raw_orcid":"https://orcid.org/0000-0003-0883-2453","affiliations":[{"raw_affiliation_string":"College of Communication Engineering, Jilin University , Changchun 130022, China","institution_ids":["https://openalex.org/I194450716"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5100321988"],"corresponding_institution_ids":["https://openalex.org/I194450716"],"apc_list":{"value":3478,"currency":"USD","value_usd":3478},"apc_paid":null,"fwci":5.3795,"has_fulltext":false,"cited_by_count":50,"citation_normalized_percentile":{"value":0.96271102,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":100},"biblio":{"volume":"38","issue":"5","first_page":"1216","last_page":"1222"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.5372999906539917,"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":0.5372999906539917,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.1931000053882599,"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":0.15320000052452087,"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/identifier","display_name":"Identifier","score":0.8683366775512695},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6363773345947266},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5602859854698181},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5104073882102966},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5009686946868896},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.4893292784690857},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.420170396566391},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.31494778394699097},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.18794772028923035},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15683290362358093},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1228753924369812}],"concepts":[{"id":"https://openalex.org/C154504017","wikidata":"https://www.wikidata.org/wiki/Q853614","display_name":"Identifier","level":2,"score":0.8683366775512695},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6363773345947266},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5602859854698181},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5104073882102966},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5009686946868896},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.4893292784690857},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.420170396566391},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.31494778394699097},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.18794772028923035},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15683290362358093},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1228753924369812}],"mesh":[{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000077321","descriptor_name":"Deep Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"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":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016571","descriptor_name":"Neural Networks, Computer","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":false},{"descriptor_ui":"D054892","descriptor_name":"Metagenome","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":false},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D064307","descriptor_name":"Microbiota","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":2,"locations":[{"id":"doi:10.1093/bioinformatics/btab845","is_oa":false,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btab845","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"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":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:34908121","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/34908121","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":"Bioinformatics (Oxford, England)","raw_type":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Good health and well-being","score":0.8199999928474426,"id":"https://metadata.un.org/sdg/3"}],"awards":[{"id":"https://openalex.org/G6551191678","display_name":null,"funder_award_id":"2019M651204","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":41,"referenced_works":["https://openalex.org/W194249466","https://openalex.org/W1693165432","https://openalex.org/W1703384511","https://openalex.org/W1975375203","https://openalex.org/W1981617416","https://openalex.org/W1982265452","https://openalex.org/W2003347102","https://openalex.org/W2005129098","https://openalex.org/W2011297553","https://openalex.org/W2045204781","https://openalex.org/W2048818637","https://openalex.org/W2055043387","https://openalex.org/W2063089818","https://openalex.org/W2064675550","https://openalex.org/W2072000548","https://openalex.org/W2107878631","https://openalex.org/W2119859604","https://openalex.org/W2121472218","https://openalex.org/W2145537580","https://openalex.org/W2147152072","https://openalex.org/W2159954944","https://openalex.org/W2165612380","https://openalex.org/W2321452352","https://openalex.org/W2403288892","https://openalex.org/W2610214149","https://openalex.org/W2658246793","https://openalex.org/W2732139758","https://openalex.org/W2740966378","https://openalex.org/W2750954606","https://openalex.org/W2886112809","https://openalex.org/W2887749901","https://openalex.org/W2889042945","https://openalex.org/W2949831026","https://openalex.org/W2951160681","https://openalex.org/W2973098646","https://openalex.org/W3003110834","https://openalex.org/W3005477624","https://openalex.org/W3027189436","https://openalex.org/W6607862964","https://openalex.org/W6637660989","https://openalex.org/W6739979769"],"related_works":["https://openalex.org/W2210738511","https://openalex.org/W2487541429","https://openalex.org/W1910109602","https://openalex.org/W2080583581","https://openalex.org/W4297131566","https://openalex.org/W2017364432","https://openalex.org/W2329606903","https://openalex.org/W3156493549","https://openalex.org/W3195915274","https://openalex.org/W3158976456"],"abstract_inverted_index":{"MOTIVATION:":[0],"Viruses,":[1],"the":[2,125,139,146,151,156,209],"most":[3,51],"abundant":[4],"biological":[5],"entities":[6],"on":[7,219],"earth,":[8],"are":[9,21,46,64,228,258,266],"important":[10],"components":[11],"of":[12,30,43,161,206],"microbial":[13],"communities,":[14],"and":[15,26,55,97,149,185,208],"as":[16],"major":[17],"human":[18,24,252],"pathogens,":[19],"they":[20],"responsible":[22],"for":[23,37,80,213],"mortality":[25],"morbidity.":[27],"The":[28,222,234,250],"identification":[29],"viral":[31,38,68,78,100,172],"sequences":[32,45,81,173],"from":[33,82,176],"metagenomes":[34,254],"is":[35,85,244],"critical":[36],"analysis.":[39],"As":[40],"massive":[41],"quantities":[42],"short":[44,171],"generated":[47],"by":[48,193],"next-generation":[49],"sequencing,":[50],"methods":[52],"utilize":[53],"discrete":[54],"sparse":[56],"one-hot":[57],"vectors":[58],"to":[59,118,155],"encode":[60,119],"nucleotide":[61,91,132],"sequences,":[62],"which":[63],"usually":[65],"ineffective":[66],"in":[67,130,225,230,241,246,255],"identification.":[69],"RESULTS:":[70],"In":[71],"this":[72,214,226,242,256],"article,":[73],"Virtifier,":[74],"a":[75,89,98,113,131,188],"deep":[76],"learning-based":[77],"identifier":[79],"metagenomic":[83],"data":[84,265],"proposed.":[86],"It":[87],"includes":[88],"meaningful":[90],"sequence":[92,101],"encoding":[93],"method":[94],"named":[95],"Seq2Vec":[96,121],"variant":[99],"predictor":[102],"with":[103,135],"an":[104,136],"attention-based":[105],"long":[106],"short-term":[107],"memory":[108],"(LSTM)":[109],"network.":[110],"By":[111],"utilizing":[112],"fully":[114],"trained":[115],"embedding":[116],"matrix":[117],"codons,":[120],"can":[122,143,168],"efficiently":[123],"extract":[124],"relationships":[126,148],"among":[127],"those":[128],"codons":[129],"sequence.":[133],"Combined":[134],"attention":[137],"layer,":[138],"LSTM":[140],"neural":[141],"network":[142],"further":[144],"analyze":[145],"codon":[147],"sift":[150],"parts":[152],"that":[153,166],"contribute":[154],"final":[157],"features.":[158],"Experimental":[159],"results":[160],"three":[162,179],"datasets":[163],"have":[164,216],"shown":[165],"Virtifier":[167,194,207],"accurately":[169],"identify":[170],"(<500":[174],"bp)":[175],"metagenomes,":[177],"surpassing":[178],"widely":[180],"used":[181],"methods,":[182],"VirFinder,":[183],"DeepVirFinder":[184],"PPR-Meta.":[186],"Meanwhile,":[187],"comparable":[189],"performance":[190],"was":[191],"achieved":[192],"at":[195,232,248,260,268],"longer":[196],"lengths":[197],"(>5000":[198],"bp).":[199],"AVAILABILITY":[200],"AND":[201],"IMPLEMENTATION:":[202],"A":[203],"Python":[204,210],"implementation":[205],"code":[211],"developed":[212],"study":[215],"been":[217],"provided":[218],"Github":[220],"https://github.com/crazyinter/Seq2Vec.":[221],"RefSeq":[223],"genomes":[224],"article":[227,243,257],"available":[229,245,259,267],"VirFinder":[231],"https://dx.doi.org/10.1186/s40168-017-0283-5.":[233],"CAMI":[235,247],"Challenge":[236],"Dataset":[237],"3":[238],"CAMI_high":[239],"dataset":[240],"https://data.cami-challenge.org/participate.":[249],"real":[251],"gut":[253],"https://dx.doi.org/10.1101/gr.142315.112.":[261],"SUPPLEMENTARY":[262],"INFORMATION:":[263],"Supplementary":[264],"Bioinformatics":[269],"online.":[270]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":14},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}
