{"id":"https://openalex.org/W4281680312","doi":"https://doi.org/10.3233/shti220167","title":"Identifying New COVID-19 Variants from Spike Proteins Using Novelty Detection","display_name":"Identifying New COVID-19 Variants from Spike Proteins Using Novelty Detection","publication_year":2022,"publication_date":"2022-06-06","ids":{"openalex":"https://openalex.org/W4281680312","doi":"https://doi.org/10.3233/shti220167","pmid":"https://pubmed.ncbi.nlm.nih.gov/35673106"},"language":"en","primary_location":{"id":"doi:10.3233/shti220167","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220167","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220167","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220167","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102386795","display_name":"Sayantani Basu","orcid":null},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sayantani Basu","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States","institution_ids":["https://openalex.org/I157725225"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065622216","display_name":"Roy H. Campbell","orcid":"https://orcid.org/0000-0002-3754-7777"},"institutions":[{"id":"https://openalex.org/I157725225","display_name":"University of Illinois Urbana-Champaign","ror":"https://ror.org/047426m28","country_code":"US","type":"education","lineage":["https://openalex.org/I157725225"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Roy H. Campbell","raw_affiliation_strings":["Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Illinois at Urbana-Champaign, Urbana, Illinois, United States","institution_ids":["https://openalex.org/I157725225"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I157725225"],"apc_list":null,"apc_paid":null,"fwci":0.4983,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.58403968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"290","issue":null,"first_page":"694","last_page":"698"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","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"}},"topics":[{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","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"}},{"id":"https://openalex.org/T12576","display_name":"vaccines and immunoinformatics approaches","score":0.9800000190734863,"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/T12946","display_name":"Fractal and DNA sequence analysis","score":0.9800000190734863,"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/novelty","display_name":"Novelty","score":0.8420071601867676},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.7353847026824951},{"id":"https://openalex.org/keywords/spike","display_name":"Spike (software development)","score":0.7298429608345032},{"id":"https://openalex.org/keywords/spike-protein","display_name":"Spike Protein","score":0.6835783123970032},{"id":"https://openalex.org/keywords/novelty-detection","display_name":"Novelty detection","score":0.6413284540176392},{"id":"https://openalex.org/keywords/pandemic","display_name":"Pandemic","score":0.5974544286727905},{"id":"https://openalex.org/keywords/severe-acute-respiratory-syndrome-coronavirus-2","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score":0.5558545589447021},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5531203746795654},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.526861310005188},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.49521008133888245},{"id":"https://openalex.org/keywords/2019-20-coronavirus-outbreak","display_name":"2019-20 coronavirus outbreak","score":0.4592260420322418},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.4566560983657837},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.43410539627075195},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4288971722126007},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.42882800102233887},{"id":"https://openalex.org/keywords/virology","display_name":"Virology","score":0.3333813548088074},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.26190465688705444},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1709287166595459}],"concepts":[{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.8420071601867676},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.7353847026824951},{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.7298429608345032},{"id":"https://openalex.org/C2909509916","wikidata":"https://www.wikidata.org/wiki/Q22329850","display_name":"Spike Protein","level":5,"score":0.6835783123970032},{"id":"https://openalex.org/C2778924833","wikidata":"https://www.wikidata.org/wiki/Q7064603","display_name":"Novelty detection","level":3,"score":0.6413284540176392},{"id":"https://openalex.org/C89623803","wikidata":"https://www.wikidata.org/wiki/Q12184","display_name":"Pandemic","level":5,"score":0.5974544286727905},{"id":"https://openalex.org/C3007834351","wikidata":"https://www.wikidata.org/wiki/Q82069695","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","level":5,"score":0.5558545589447021},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5531203746795654},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.526861310005188},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.49521008133888245},{"id":"https://openalex.org/C3006700255","wikidata":"https://www.wikidata.org/wiki/Q81068910","display_name":"2019-20 coronavirus outbreak","level":3,"score":0.4592260420322418},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.4566560983657837},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.43410539627075195},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4288971722126007},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.42882800102233887},{"id":"https://openalex.org/C159047783","wikidata":"https://www.wikidata.org/wiki/Q7215","display_name":"Virology","level":1,"score":0.3333813548088074},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.26190465688705444},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1709287166595459},{"id":"https://openalex.org/C116675565","wikidata":"https://www.wikidata.org/wiki/Q3241045","display_name":"Outbreak","level":2,"score":0.0},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0},{"id":"https://openalex.org/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086382","descriptor_name":"COVID-19","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","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":"D058873","descriptor_name":"Pandemics","qualifier_ui":"Q000517","qualifier_name":"prevention & control","is_major_topic":false},{"descriptor_ui":"D058873","descriptor_name":"Pandemics","qualifier_ui":"Q000517","qualifier_name":"prevention & control","is_major_topic":false},{"descriptor_ui":"D058873","descriptor_name":"Pandemics","qualifier_ui":"Q000517","qualifier_name":"prevention & control","is_major_topic":false},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false},{"descriptor_ui":"D064370","descriptor_name":"Spike Glycoprotein, Coronavirus","qualifier_ui":"Q000378","qualifier_name":"metabolism","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/shti220167","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220167","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220167","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:35673106","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35673106","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":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":{"id":"doi:10.3233/shti220167","is_oa":true,"landing_page_url":"https://doi.org/10.3233/shti220167","pdf_url":"https://ebooks.iospress.nl/pdf/doi/10.3233/SHTI220167","source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":"cc-by-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8299999833106995,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4281680312.pdf","grobid_xml":"https://content.openalex.org/works/W4281680312.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1501531009","https://openalex.org/W1995443851","https://openalex.org/W2101234009","https://openalex.org/W2125027820","https://openalex.org/W2127774996","https://openalex.org/W2132870739","https://openalex.org/W2181616869","https://openalex.org/W2943878969","https://openalex.org/W2952045272","https://openalex.org/W3003415212","https://openalex.org/W3013019084","https://openalex.org/W3016767494","https://openalex.org/W3017855299","https://openalex.org/W3019119825","https://openalex.org/W3035119815","https://openalex.org/W3044543952","https://openalex.org/W3095432437","https://openalex.org/W3207987129","https://openalex.org/W4243563432","https://openalex.org/W4398748092","https://openalex.org/W6600280466","https://openalex.org/W6600310816","https://openalex.org/W6603562897","https://openalex.org/W6605179812","https://openalex.org/W6605305367","https://openalex.org/W6631783900","https://openalex.org/W6634682946","https://openalex.org/W6686700731"],"related_works":["https://openalex.org/W3032320397","https://openalex.org/W3152606407","https://openalex.org/W4280491013","https://openalex.org/W3025176011","https://openalex.org/W4308017287","https://openalex.org/W3107152225","https://openalex.org/W3027835066","https://openalex.org/W3017171836","https://openalex.org/W3033635008","https://openalex.org/W3183300108"],"abstract_inverted_index":{"The":[0],"COVID-19":[1,65,85],"pandemic":[2],"has":[3],"caused":[4],"millions":[5],"of":[6,18,22,53,63,71,106,119],"infections":[7],"and":[8,30,40,57,73,78,103,114,121],"deaths":[9],"worldwide":[10],"in":[11,36,117],"an":[12],"ongoing":[13],"pandemic.":[14],"With":[15],"the":[16,38,61,76,127],"passage":[17],"time,":[19],"several":[20],"variants":[21,80,107],"this":[23,46],"virus":[24,39],"have":[25,32,49],"surfaced.":[26],"Machine":[27],"learning":[28],"methods":[29],"algorithms":[31,56],"been":[33],"very":[34],"useful":[35],"understanding":[37],"its":[41],"implications":[42],"so":[43],"far.":[44],"In":[45],"paper,":[47],"we":[48],"studied":[50],"a":[51,99],"set":[52],"novelty":[54],"detection":[55,105],"applied":[58],"it":[59],"to":[60],"problem":[62],"detecting":[64],"variants.":[66,129],"Our":[67],"results":[68],"show":[69],"accuracies":[70],"79.64%":[72],"82.43%":[74],"on":[75,82],"B.1.1.7":[77],"B.1.351":[79],"respectively":[81],"ProtVec":[83],"unaligned":[84],"spike":[86],"protein":[87],"sequences":[88],"using":[89],"One":[90],"Class":[91],"SVM":[92],"with":[93],"fine-tuned":[94],"parameters.":[95],"We":[96],"believe":[97],"that":[98,123],"system":[100],"for":[101],"automated":[102],"timely":[104],"will":[108],"help":[109],"countries":[110],"formulate":[111],"mitigation":[112],"measures":[113],"study":[115],"remedies":[116],"terms":[118],"medicines":[120],"vaccines":[122],"can":[124],"protect":[125],"against":[126],"new":[128]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}
