{"id":"https://openalex.org/W3032757820","doi":"https://doi.org/10.1371/journal.pcbi.1007894","title":"Predicting host taxonomic information from viral genomes: A comparison of feature representations","display_name":"Predicting host taxonomic information from viral genomes: A comparison of feature representations","publication_year":2020,"publication_date":"2020-05-26","ids":{"openalex":"https://openalex.org/W3032757820","doi":"https://doi.org/10.1371/journal.pcbi.1007894","mag":"3032757820","pmid":"https://pubmed.ncbi.nlm.nih.gov/32453718"},"language":"en","primary_location":{"id":"doi:10.1371/journal.pcbi.1007894","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1007894","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1007894&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1007894&type=printable","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5057178535","display_name":"Francesca Young","orcid":"https://orcid.org/0000-0002-5236-1145"},"institutions":[{"id":"https://openalex.org/I4210146449","display_name":"MRC University of Glasgow Centre for Virus Research","ror":"https://ror.org/03vaer060","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210146449","https://openalex.org/I7882870","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Francesca Young","raw_affiliation_strings":["MRC-University of Glasgow Centre For Virus Research, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"MRC-University of Glasgow Centre For Virus Research, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I4210146449"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060432668","display_name":"Simon Rogers","orcid":"https://orcid.org/0000-0003-3578-4477"},"institutions":[{"id":"https://openalex.org/I7882870","display_name":"University of Glasgow","ror":"https://ror.org/00vtgdb53","country_code":"GB","type":"education","lineage":["https://openalex.org/I7882870"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Simon Rogers","raw_affiliation_strings":["School of Computing Science, University of Glasgow, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"School of Computing Science, University of Glasgow, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I7882870"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5082064376","display_name":"David L. Robertson","orcid":"https://orcid.org/0000-0001-6338-0221"},"institutions":[{"id":"https://openalex.org/I4210146449","display_name":"MRC University of Glasgow Centre for Virus Research","ror":"https://ror.org/03vaer060","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210087105","https://openalex.org/I4210146449","https://openalex.org/I7882870","https://openalex.org/I90344618"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"David L. Robertson","raw_affiliation_strings":["MRC-University of Glasgow Centre For Virus Research, Glasgow, United Kingdom"],"affiliations":[{"raw_affiliation_string":"MRC-University of Glasgow Centre For Virus Research, Glasgow, United Kingdom","institution_ids":["https://openalex.org/I4210146449"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5082064376"],"corresponding_institution_ids":["https://openalex.org/I4210146449"],"apc_list":{"value":2655,"currency":"USD","value_usd":2655},"apc_paid":{"value":2655,"currency":"USD","value_usd":2655},"fwci":5.4623,"has_fulltext":true,"cited_by_count":62,"citation_normalized_percentile":{"value":0.96202411,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":100},"biblio":{"volume":"16","issue":"5","first_page":"e1007894","last_page":"e1007894"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11048","display_name":"Bacteriophages and microbial interactions","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9983000159263611,"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/T10494","display_name":"Plant Virus Research Studies","score":0.9976000189781189,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.7866673469543457},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.64078688621521},{"id":"https://openalex.org/keywords/metagenomics","display_name":"Metagenomics","score":0.5738745331764221},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5543321371078491},{"id":"https://openalex.org/keywords/host","display_name":"Host (biology)","score":0.490251362323761},{"id":"https://openalex.org/keywords/prokaryote","display_name":"Prokaryote","score":0.48066246509552},{"id":"https://openalex.org/keywords/genomics","display_name":"Genomics","score":0.4451582729816437},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3488422632217407},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.28061118721961975},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.23485520482063293},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.21671411395072937}],"concepts":[{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.7866673469543457},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.64078688621521},{"id":"https://openalex.org/C15151743","wikidata":"https://www.wikidata.org/wiki/Q903778","display_name":"Metagenomics","level":3,"score":0.5738745331764221},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5543321371078491},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.490251362323761},{"id":"https://openalex.org/C2780918051","wikidata":"https://www.wikidata.org/wiki/Q19081","display_name":"Prokaryote","level":3,"score":0.48066246509552},{"id":"https://openalex.org/C189206191","wikidata":"https://www.wikidata.org/wiki/Q222046","display_name":"Genomics","level":4,"score":0.4451582729816437},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3488422632217407},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.28061118721961975},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.23485520482063293},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.21671411395072937}],"mesh":[{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D000465","descriptor_name":"Algorithms","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D001419","descriptor_name":"Bacteria","qualifier_ui":"Q000821","qualifier_name":"virology","is_major_topic":false},{"descriptor_ui":"D009711","descriptor_name":"Nucleotides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D009711","descriptor_name":"Nucleotides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D009711","descriptor_name":"Nucleotides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D009711","descriptor_name":"Nucleotides","qualifier_ui":"Q000032","qualifier_name":"analysis","is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010802","descriptor_name":"Phylogeny","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":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D014780","descriptor_name":"Viruses","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016014","descriptor_name":"Linear Models","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016208","descriptor_name":"Databases, Factual","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D016679","descriptor_name":"Genome, Viral","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017899","descriptor_name":"Caudovirales","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017899","descriptor_name":"Caudovirales","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017899","descriptor_name":"Caudovirales","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D017899","descriptor_name":"Caudovirales","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019295","descriptor_name":"Computational Biology","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D019540","descriptor_name":"Area Under Curve","qualifier_ui":null,"qualifier_name":null,"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":"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":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D060388","descriptor_name":"Support Vector Machine","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true}],"locations_count":5,"locations":[{"id":"doi:10.1371/journal.pcbi.1007894","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1007894","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1007894&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},{"id":"pmid:32453718","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/32453718","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":"PLoS computational biology","raw_type":null},{"id":"pmh:oai:eprints.gla.ac.uk:217218","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4210235606","display_name":"ENLIGHTEN (Jurnal Bimbingan dan Konseling Islam)","issn_l":"2622-8912","issn":["2622-8912","2622-8920"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Articles"},{"id":"pmh:oai:doaj.org/article:1139adc897314dcb9d7f708011c82e86","is_oa":true,"landing_page_url":"https://doaj.org/article/1139adc897314dcb9d7f708011c82e86","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Computational Biology, Vol 16, Iss 5, p e1007894 (2020)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:7307784","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/7307784","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"PLoS Comput Biol","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1371/journal.pcbi.1007894","is_oa":true,"landing_page_url":"https://doi.org/10.1371/journal.pcbi.1007894","pdf_url":"https://journals.plos.org/ploscompbiol/article/file?id=10.1371/journal.pcbi.1007894&type=printable","source":{"id":"https://openalex.org/S86033158","display_name":"PLoS Computational Biology","issn_l":"1553-734X","issn":["1553-734X","1553-7358"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310315706","host_organization_name":"Public Library of Science","host_organization_lineage":["https://openalex.org/P4310315706"],"host_organization_lineage_names":["Public Library of Science"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"PLOS Computational Biology","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2206474454","display_name":null,"funder_award_id":"MC_UU_12014","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G5126738005","display_name":null,"funder_award_id":"MC_UU_1201412","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G5566807808","display_name":null,"funder_award_id":"MC_UU_","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"},{"id":"https://openalex.org/G8128754418","display_name":null,"funder_award_id":"1201412","funder_id":"https://openalex.org/F4320334626","funder_display_name":"Medical Research Council"}],"funders":[{"id":"https://openalex.org/F4320334626","display_name":"Medical Research Council","ror":"https://ror.org/03x94j517"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3032757820.pdf","grobid_xml":"https://content.openalex.org/works/W3032757820.grobid-xml"},"referenced_works_count":67,"referenced_works":["https://openalex.org/W995630646","https://openalex.org/W1505191356","https://openalex.org/W1508259457","https://openalex.org/W1552724685","https://openalex.org/W1663973292","https://openalex.org/W1964514974","https://openalex.org/W1966912927","https://openalex.org/W1978006472","https://openalex.org/W1979601325","https://openalex.org/W1982267716","https://openalex.org/W1982763078","https://openalex.org/W1982809731","https://openalex.org/W1989895278","https://openalex.org/W1991310235","https://openalex.org/W1998092469","https://openalex.org/W2024014229","https://openalex.org/W2038195617","https://openalex.org/W2043974064","https://openalex.org/W2057088297","https://openalex.org/W2079635715","https://openalex.org/W2083804674","https://openalex.org/W2084241014","https://openalex.org/W2097231226","https://openalex.org/W2101234009","https://openalex.org/W2108982334","https://openalex.org/W2119821739","https://openalex.org/W2122281839","https://openalex.org/W2124236601","https://openalex.org/W2125957866","https://openalex.org/W2129994773","https://openalex.org/W2131186249","https://openalex.org/W2135621733","https://openalex.org/W2138122982","https://openalex.org/W2145295623","https://openalex.org/W2169899471","https://openalex.org/W2238100083","https://openalex.org/W2245444176","https://openalex.org/W2277953252","https://openalex.org/W2291003811","https://openalex.org/W2345960958","https://openalex.org/W2559100382","https://openalex.org/W2574133781","https://openalex.org/W2583527348","https://openalex.org/W2594364047","https://openalex.org/W2603067364","https://openalex.org/W2734399491","https://openalex.org/W2749147866","https://openalex.org/W2758167635","https://openalex.org/W2763934336","https://openalex.org/W2769959144","https://openalex.org/W2788604517","https://openalex.org/W2791552377","https://openalex.org/W2802028237","https://openalex.org/W2810889556","https://openalex.org/W2899317755","https://openalex.org/W2900402284","https://openalex.org/W2901212243","https://openalex.org/W2904384071","https://openalex.org/W2905286853","https://openalex.org/W2919326595","https://openalex.org/W2946028192","https://openalex.org/W2950044547","https://openalex.org/W2951254987","https://openalex.org/W4239510810","https://openalex.org/W6647673380","https://openalex.org/W6661409852","https://openalex.org/W6675354045"],"related_works":["https://openalex.org/W638577851","https://openalex.org/W2605583263","https://openalex.org/W2968354375","https://openalex.org/W2194508283","https://openalex.org/W2359440920","https://openalex.org/W2889550857","https://openalex.org/W2276314549","https://openalex.org/W2071178303","https://openalex.org/W2090384119","https://openalex.org/W4288427168"],"abstract_inverted_index":{"The":[0,110],"rise":[1],"in":[2,10,82],"metagenomics":[3],"has":[4],"led":[5],"to":[6,29,37,146,235],"an":[7],"exponential":[8],"growth":[9],"virus":[11,19,31,84,231,242],"discovery.":[12],"However,":[13],"the":[14,51,78,83,116,148,199,207,211],"majority":[15],"of":[16,45,54,61,102,120,151,153,166,172,225,241,249],"these":[17,154],"new":[18],"sequences":[20],"have":[21,34],"no":[22],"assigned":[23],"host.":[24],"Current":[25],"machine":[26],"learning":[27],"approaches":[28],"predicting":[30],"host":[32,173,243,250],"interactions":[33],"a":[35,87,191,223,239],"tendency":[36],"focus":[38],"on":[39],"nucleotide":[40],"features,":[41,227],"ignoring":[42],"other":[43],"representations":[44],"genomic":[46],"information.":[47,252],"Here":[48],"we":[49,196],"investigate":[50],"predictive":[52,149,171,200],"potential":[53],"features":[55],"generated":[56,128,228],"from":[57,230],"four":[58,117],"different":[59,118],"'levels'":[60],"viral":[62,111],"genome":[63,121,167,232],"representation:":[64],"nucleotide,":[65],"amino":[66,68],"acid,":[67],"acid":[69],"properties":[70],"and":[71,89,105,123,133,139,175,216],"protein":[72,135],"domains.":[73,136],"This":[74],"more":[75],"fully":[76],"exploits":[77],"biological":[79],"information":[80],"present":[81],"genomes.":[85],"Over":[86],"hundred":[88],"eighty":[90],"binary":[91],"datasets":[92],"for":[93,157,185,238],"infecting":[94,213],"versus":[95],"non-infecting":[96],"viruses":[97,212],"at":[98],"all":[99,164,186],"taxonomic":[100,251],"ranks":[101],"both":[103,206],"eukaryote":[104],"prokaryote":[106],"hosts":[107],"were":[108,113,127],"compiled.":[109],"genomes":[112],"converted":[114],"into":[115],"levels":[119,165],"representation":[122,168],"twenty":[124],"feature":[125,155,201],"sets":[126,156,202],"by":[129],"extracting":[130],"k-mer":[131,178,183,187],"compositions":[132],"predicted":[134],"We":[137],"trained":[138],"tested":[140],"Support":[141],"Vector":[142],"Machine,":[143],"SVM,":[144],"classifiers":[145],"compare":[147],"capacity":[150],"each":[152,158],"dataset.":[159],"Our":[160,218],"results":[161,219],"show":[162],"that":[163,176,198,221],"are":[169],"consistently":[170],"taxonomy":[174],"prediction":[177,244],"composition":[179],"improves":[180],"with":[181],"increasing":[182],"length":[184],"based":[188],"features.":[189],"Using":[190],"phylogenetically":[192],"aware":[193],"holdout":[194],"method,":[195],"demonstrate":[197,220],"contain":[203],"signals":[204],"reflecting":[205],"evolutionary":[208],"relationship":[209],"between":[210],"related":[214],"hosts,":[215],"host-mimicry.":[217],"incorporating":[222],"range":[224,240],"complementary":[226],"purely":[229],"sequences,":[233],"leads":[234],"improved":[236],"accuracy":[237],"tasks":[245],"enabling":[246],"computational":[247],"assignment":[248]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":15},{"year":2024,"cited_by_count":9},{"year":2023,"cited_by_count":10},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":10},{"year":2020,"cited_by_count":4}],"updated_date":"2026-04-01T17:29:45.350535","created_date":"2025-10-10T00:00:00"}
