{"id":"https://openalex.org/W4289779552","doi":"https://doi.org/10.1016/j.biosystems.2022.104740","title":"Dive into machine learning algorithms for influenza virus host prediction with hemagglutinin sequences","display_name":"Dive into machine learning algorithms for influenza virus host prediction with hemagglutinin sequences","publication_year":2022,"publication_date":"2022-08-04","ids":{"openalex":"https://openalex.org/W4289779552","doi":"https://doi.org/10.1016/j.biosystems.2022.104740","pmid":"https://pubmed.ncbi.nlm.nih.gov/35934256"},"language":"en","primary_location":{"id":"doi:10.1016/j.biosystems.2022.104740","doi":"https://doi.org/10.1016/j.biosystems.2022.104740","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.biosystems.2022.104740","pdf_url":"https://www.sciencedirect.com/science/article/pii/S030326472200123X/pdf","source":{"id":"https://openalex.org/S99347777","display_name":"Biosystems","issn_l":"0303-2647","issn":["0303-2647","1872-8324"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biosystems","raw_type":"journal-article"},"volume":null,"type":"article","is_traditional":true,"indexed_in":["arxiv","crossref","datacite","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://www.sciencedirect.com/science/article/pii/S030326472200123X/pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5007408738","display_name":"Yanhua Xu","orcid":"https://orcid.org/0000-0003-1028-9023","observed_orcids":["https://orcid.org/0000-0003-1028-9023"]},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Yanhua Xu","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK. Electronic address: Y.XU137@liverpool.ac.uk","Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK"],"raw_orcid":"https://orcid.org/0000-0003-1028-9023","affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK. Electronic address: Y.XU137@liverpool.ac.uk","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001234060","display_name":"Dominik Wojtczak","orcid":"https://orcid.org/0000-0001-5560-0546","observed_orcids":["https://orcid.org/0000-0001-5560-0546"]},"institutions":[{"id":"https://openalex.org/I146655781","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96","country_code":"GB","type":"education","lineage":["https://openalex.org/I146655781"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Dominik Wojtczak","raw_affiliation_strings":["Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK. Electronic address: D.Wojtczak@liverpool.ac.uk","Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK. Electronic address: D.Wojtczak@liverpool.ac.uk","institution_ids":["https://openalex.org/I146655781"]},{"raw_affiliation_string":"Department of Computer Science, University of Liverpool, Liverpool, L69 3BX, UK","institution_ids":["https://openalex.org/I146655781"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5007408738"],"corresponding_institution_ids":["https://openalex.org/I146655781"],"apc_list":{"value":2280,"currency":"USD","value_usd":2280},"apc_paid":{"value":2280,"currency":"USD","value_usd":2280},"fwci":1.9118,"has_fulltext":true,"cited_by_count":30,"citation_normalized_percentile":{"value":0.87411384,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":"220","issue":null,"first_page":"104740","last_page":"104740"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9312000274658203,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9312000274658203,"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/T10167","display_name":"Influenza Virus Research Studies","score":0.02019999921321869,"subfield":{"id":"https://openalex.org/subfields/2713","display_name":"Epidemiology"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T12946","display_name":"Fractal and DNA sequence analysis","score":0.012299999594688416,"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/influenza-a-virus","display_name":"influenza A virus","score":0.9210000038146973},{"id":"https://openalex.org/keywords/hemagglutinin","display_name":"hemagglutinin","score":0.796999990940094},{"id":"https://openalex.org/keywords/host-prediction","display_name":"host prediction","score":0.7319999933242798},{"id":"https://openalex.org/keywords/machine-learning","display_name":"machine learning","score":0.49799999594688416},{"id":"https://openalex.org/keywords/position-specific-scoring-matrix","display_name":"position weight matrices","score":0.8790000081062317},{"id":"https://openalex.org/keywords/word-embeddings","display_name":"word embeddings","score":0.8809999823570251},{"id":"https://openalex.org/keywords/virus-taxonomy","display_name":"virus taxonomy","score":0.4449999928474426}],"concepts":[{"id":"https://openalex.org/C2778692840","wikidata":"https://www.wikidata.org/wiki/Q9136673","display_name":"Hemagglutinin (influenza)","level":3,"score":0.683087170124054},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5304450392723083},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.510066568851471},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43878331780433655},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.43261247873306274},{"id":"https://openalex.org/C126831891","wikidata":"https://www.wikidata.org/wiki/Q221673","display_name":"Host (biology)","level":2,"score":0.4305024743080139},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4304346740245819},{"id":"https://openalex.org/C2522874641","wikidata":"https://www.wikidata.org/wiki/Q808","display_name":"Virus","level":2,"score":0.4243679642677307},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2916030287742615},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.08737853169441223}],"mesh":[{"descriptor_ui":"D000069550","descriptor_name":"Machine Learning","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":"D006388","descriptor_name":"Hemagglutinins","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D009975","descriptor_name":"Orthomyxoviridae","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D009980","descriptor_name":"Influenza A virus","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":true}],"locations_count":4,"locations":[{"id":"doi:10.1016/j.biosystems.2022.104740","doi":"https://doi.org/10.1016/j.biosystems.2022.104740","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.biosystems.2022.104740","pdf_url":"https://www.sciencedirect.com/science/article/pii/S030326472200123X/pdf","source":{"id":"https://openalex.org/S99347777","display_name":"Biosystems","issn_l":"0303-2647","issn":["0303-2647","1872-8324"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biosystems","raw_type":"journal-article"},{"id":"pmid:35934256","doi":null,"is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35934256","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,"listed_in":[],"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":"Bio Systems","raw_type":"Journal Article"},{"id":"pmh:oai:arXiv.org:2207.13842","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2207.13842","pdf_url":"https://arxiv.org/pdf/2207.13842","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2207.13842","doi":"https://doi.org/10.48550/arxiv.2207.13842","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2207.13842","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1016/j.biosystems.2022.104740","doi":"https://doi.org/10.1016/j.biosystems.2022.104740","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.biosystems.2022.104740","pdf_url":"https://www.sciencedirect.com/science/article/pii/S030326472200123X/pdf","source":{"id":"https://openalex.org/S99347777","display_name":"Biosystems","issn_l":"0303-2647","issn":["0303-2647","1872-8324"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["anvur-class-a","anvur-scientific","cwts-core","jufo-1","ki-jl-1","medline","norway-1","poland-70","russia-white-list-1","vabb-shw"],"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Biosystems","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.6240000128746033,"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3"}],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320320323","display_name":"University of Liverpool","ror":"https://ror.org/04xs57h96"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4289779552.pdf","grobid_xml":"https://content.openalex.org/works/W4289779552.grobid-xml"},"referenced_works_count":50,"referenced_works":["https://openalex.org/W63710172","https://openalex.org/W1563938718","https://openalex.org/W1614298861","https://openalex.org/W1930624869","https://openalex.org/W1975670646","https://openalex.org/W1983941241","https://openalex.org/W2005584594","https://openalex.org/W2015359732","https://openalex.org/W2015403041","https://openalex.org/W2021312899","https://openalex.org/W2029436281","https://openalex.org/W2030793934","https://openalex.org/W2041753380","https://openalex.org/W2045934762","https://openalex.org/W2068361619","https://openalex.org/W2086789740","https://openalex.org/W2101234009","https://openalex.org/W2111359724","https://openalex.org/W2112114816","https://openalex.org/W2119611042","https://openalex.org/W2121009566","https://openalex.org/W2135107501","https://openalex.org/W2137378887","https://openalex.org/W2147863530","https://openalex.org/W2147901189","https://openalex.org/W2154776925","https://openalex.org/W2158714788","https://openalex.org/W2160881014","https://openalex.org/W2164759261","https://openalex.org/W2164860726","https://openalex.org/W2295598076","https://openalex.org/W2490420619","https://openalex.org/W2521200999","https://openalex.org/W2557112659","https://openalex.org/W2626778328","https://openalex.org/W2736736208","https://openalex.org/W2767813829","https://openalex.org/W2890347237","https://openalex.org/W2899053251","https://openalex.org/W2903201721","https://openalex.org/W2914874661","https://openalex.org/W2987073966","https://openalex.org/W2996470210","https://openalex.org/W3048846953","https://openalex.org/W4237959566","https://openalex.org/W4239613409","https://openalex.org/W4292893847","https://openalex.org/W4300294292","https://openalex.org/W4300829895","https://openalex.org/W6910681941"],"related_works":["https://openalex.org/W4414529035","https://openalex.org/W7212343829","https://openalex.org/W1504771313","https://openalex.org/W4402898471","https://openalex.org/W7167349364","https://openalex.org/W2736736208","https://openalex.org/W3206330457","https://openalex.org/W4415933731","https://openalex.org/W3190978111","https://openalex.org/W4281656273"],"abstract_inverted_index":{"Influenza":[0],"viruses":[1,22],"mutate":[2],"rapidly":[3],"and":[4,62,75,107,113,141,149,156],"can":[5],"pose":[6],"a":[7,37,76,145,160],"threat":[8],"to":[9,13,32,41,59,83],"public":[10],"health,":[11],"especially":[12],"those":[14],"in":[15,39,54,98],"vulnerable":[16],"groups.":[17],"Throughout":[18],"history,":[19],"influenza":[20],"A":[21],"have":[23],"caused":[24],"pandemics":[25],"between":[26],"different":[27,89],"species.":[28],"It":[29],"is":[30,94,124],"important":[31],"identify":[33],"the":[34,43,95,99,120,125],"origin":[35],"of":[36,45,78],"virus":[38],"order":[40],"prevent":[42],"spread":[44],"an":[46],"outbreak.":[47],"Recently,":[48],"there":[49],"has":[50],"been":[51],"increasing":[52],"interest":[53],"using":[55],"machine":[56,85],"learning":[57,86],"algorithms":[58,87],"provide":[60],"fast":[61],"accurate":[63],"predictions":[64],"for":[65,129],"viral":[66,131],"sequences.":[67],"In":[68],"this":[69],"study,":[70],"real":[71],"testing":[72],"data":[73],"sets":[74],"variety":[77],"evaluation":[79],"metrics":[80],"were":[81,105],"used":[82,106],"evaluate":[84],"at":[88,144,159],"taxonomic":[90],"levels.":[91],"As":[92],"hemagglutinin":[93,103],"major":[96],"protein":[97],"immune":[100],"response,":[101],"only":[102],"sequences":[104],"represented":[108],"by":[109],"position-specific":[110],"scoring":[111],"matrix":[112],"word":[114],"embedding.":[115],"The":[116],"results":[117],"suggest":[118],"that":[119],"5-grams-transformer":[121],"neural":[122],"network":[123],"most":[126],"effective":[127],"algorithm":[128],"predicting":[130],"sequence":[132],"origins,":[133],"with":[134],"approximately":[135,150],"99.54%":[136],"AUCPR,":[137,152],"98.01%":[138],"F1":[139,154],"score":[140,155],"96.60%":[142],"MCC":[143,158],"higher":[146],"classification":[147,162],"level,":[148],"94.74%":[151],"87.41%":[153],"80.79%":[157],"lower":[161],"level.":[163]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":7},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":1}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2022-08-04T00:00:00"}
