{"id":"https://openalex.org/W4226483197","doi":"https://doi.org/10.1109/bibm52615.2021.9669612","title":"Unsupervised clustering analysis of SARS-Cov-2 population structure reveals six major subtypes at early stage across the world","display_name":"Unsupervised clustering analysis of SARS-Cov-2 population structure reveals six major subtypes at early stage across the world","publication_year":2021,"publication_date":"2021-12-09","ids":{"openalex":"https://openalex.org/W4226483197","doi":"https://doi.org/10.1109/bibm52615.2021.9669612"},"language":"en","primary_location":{"id":"doi:10.1109/bibm52615.2021.9669612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"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/A5100377378","display_name":"Yawei Li","orcid":"https://orcid.org/0000-0001-9699-5118"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yawei Li","raw_affiliation_strings":["Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100713357","display_name":"Qingyun Liu","orcid":"https://orcid.org/0000-0002-2284-5050"},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Qingyun Liu","raw_affiliation_strings":["Department of Immunology and Infectious Diseases, Harvard T. H. Chan School of Public Health, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Immunology and Infectious Diseases, Harvard T. H. Chan School of Public Health, Boston, MA, USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051021402","display_name":"Zexian Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I4210117453","display_name":"Dana-Farber Cancer Institute","ror":"https://ror.org/02jzgtq86","country_code":"US","type":"facility","lineage":["https://openalex.org/I4210117453"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zexian Zeng","raw_affiliation_strings":["Department of Data Science, Harvard T. H. Chan School of Public Health, Dana Farber Cancer Institute, Boston, MA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Data Science, Harvard T. H. Chan School of Public Health, Dana Farber Cancer Institute, Boston, MA, USA","institution_ids":["https://openalex.org/I4210117453"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452550","display_name":"Yuan Luo","orcid":"https://orcid.org/0000-0003-0195-7456"},"institutions":[{"id":"https://openalex.org/I111979921","display_name":"Northwestern University","ror":"https://ror.org/000e0be47","country_code":"US","type":"education","lineage":["https://openalex.org/I111979921"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yuan Luo","raw_affiliation_strings":["Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Preventive Medicine, Feinberg School of Medicine, Northwestern University, Chicago, IL, USA","institution_ids":["https://openalex.org/I111979921"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7135,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.87694013,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"48","issue":null,"first_page":"58","last_page":"63"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10118","display_name":"SARS-CoV-2 and COVID-19 Research","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"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/T11754","display_name":"SARS-CoV-2 detection and testing","score":0.995199978351593,"subfield":{"id":"https://openalex.org/subfields/2725","display_name":"Infectious Diseases"},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.994700014591217,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8442888259887695},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.7578860521316528},{"id":"https://openalex.org/keywords/population","display_name":"Population","score":0.6326632499694824},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.5688263177871704},{"id":"https://openalex.org/keywords/cluster","display_name":"Cluster (spacecraft)","score":0.49177172780036926},{"id":"https://openalex.org/keywords/identification","display_name":"Identification (biology)","score":0.47261810302734375},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.4545038342475891},{"id":"https://openalex.org/keywords/coronavirus","display_name":"Coronavirus","score":0.4543229937553406},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.4118445813655853},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.39711982011795044},{"id":"https://openalex.org/keywords/evolutionary-biology","display_name":"Evolutionary biology","score":0.3920169770717621},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3607214689254761},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3577544093132019},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.32261162996292114},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.29565513134002686},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.09066459536552429},{"id":"https://openalex.org/keywords/ecology","display_name":"Ecology","score":0.07611769437789917}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8442888259887695},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.7578860521316528},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.6326632499694824},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.5688263177871704},{"id":"https://openalex.org/C164866538","wikidata":"https://www.wikidata.org/wiki/Q367351","display_name":"Cluster (spacecraft)","level":2,"score":0.49177172780036926},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.47261810302734375},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.4545038342475891},{"id":"https://openalex.org/C2777648638","wikidata":"https://www.wikidata.org/wiki/Q57751738","display_name":"Coronavirus","level":5,"score":0.4543229937553406},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.4118445813655853},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.39711982011795044},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.3920169770717621},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3607214689254761},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3577544093132019},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.32261162996292114},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.29565513134002686},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.09066459536552429},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.07611769437789917},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C99454951","wikidata":"https://www.wikidata.org/wiki/Q932068","display_name":"Environmental health","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/C524204448","wikidata":"https://www.wikidata.org/wiki/Q788926","display_name":"Infectious disease (medical specialty)","level":3,"score":0.0},{"id":"https://openalex.org/C2779134260","wikidata":"https://www.wikidata.org/wiki/Q12136","display_name":"Disease","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bibm52615.2021.9669612","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bibm52615.2021.9669612","pdf_url":null,"source":{"id":"https://openalex.org/S4363607735","display_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.6499999761581421,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":43,"referenced_works":["https://openalex.org/W1128809682","https://openalex.org/W1852605861","https://openalex.org/W1973264045","https://openalex.org/W1996881001","https://openalex.org/W2019952619","https://openalex.org/W2031611770","https://openalex.org/W2095897464","https://openalex.org/W2099086577","https://openalex.org/W2115489189","https://openalex.org/W2124967403","https://openalex.org/W2126714764","https://openalex.org/W2127218421","https://openalex.org/W2137015675","https://openalex.org/W2141245797","https://openalex.org/W2145191876","https://openalex.org/W2156521045","https://openalex.org/W2168175751","https://openalex.org/W2400732335","https://openalex.org/W2586952891","https://openalex.org/W2800078342","https://openalex.org/W2800328275","https://openalex.org/W2952045272","https://openalex.org/W2954745675","https://openalex.org/W2963776453","https://openalex.org/W2964074409","https://openalex.org/W3001897055","https://openalex.org/W3002539152","https://openalex.org/W3004280078","https://openalex.org/W3004826757","https://openalex.org/W3009906937","https://openalex.org/W3012841297","https://openalex.org/W3012944241","https://openalex.org/W3015444032","https://openalex.org/W3023943624","https://openalex.org/W3048831848","https://openalex.org/W3082351255","https://openalex.org/W3082463691","https://openalex.org/W3093806642","https://openalex.org/W3096263877","https://openalex.org/W3111071089","https://openalex.org/W6678914141","https://openalex.org/W6685380521","https://openalex.org/W6786745205"],"related_works":["https://openalex.org/W2487162673","https://openalex.org/W2942366970","https://openalex.org/W2793211469","https://openalex.org/W2949152769","https://openalex.org/W4372354731","https://openalex.org/W2562400057","https://openalex.org/W1692008701","https://openalex.org/W2597588799","https://openalex.org/W4360593462","https://openalex.org/W2194570607"],"abstract_inverted_index":{"the":[0,4,32,35,39,43,48,67,91,96,104,115,125,143,148,165,172],"population":[1,36,174,190],"structure":[2,37,71,175],"of":[3,34,38,69,76,90,124,167,176,188,195],"newly":[5,49],"emerged":[6,50],"coronavirus":[7],"SARS-CoV-2":[8,20,62],"has":[9],"significant":[10],"potential":[11],"to":[12,42,58,170],"inform":[13],"public":[14],"health":[15],"management":[16],"and":[17,113],"diagnosis.":[18],"As":[19],"sequencing":[21],"data":[22],"accrued,":[23],"grouping":[24],"them":[25],"into":[26,153],"clusters":[27,80,127],"is":[28],"important":[29],"for":[30,72,164,185],"organizing":[31],"landscape":[33],"virus.":[40],"Due":[41],"limited":[44],"prior":[45],"information":[46],"on":[47,146],"coronavirus,":[51],"we":[52],"utilized":[53],"four":[54,97],"different":[55,129],"clustering":[56,92,109,168,180],"algorithms":[57,98],"group":[59],"16,":[60],"S73":[61],"strains,":[63],"which":[64,147],"automatically":[65],"enables":[66],"identification":[68],"spatial":[70],"SARS-CoV-2.":[73,177],"A":[74],"total":[75],"six":[77,126,154],"distinct":[78],"genomic":[79],"were":[81,150],"identified":[82],"using":[83],"mutation":[84],"profiles":[85],"as":[86],"input":[87],"features.":[88],"Comparison":[89],"results":[93],"reveals":[94],"that":[95,140],"produced":[99,114],"highly":[100],"consistent":[101],"results,":[102],"but":[103],"state-of-the-art":[105],"unsupervised":[106],"deep":[107],"learning":[108],"algorithm":[110],"performed":[111],"best":[112],"smallest":[116],"intra-cluster":[117],"pairwise":[118],"genetic":[119],"distances.":[120],"The":[121],"varied":[122],"proportions":[123],"within":[128],"continents":[130],"revealed":[131],"specific":[132,193],"geographical":[133],"distributions.":[134],"In":[135,156,178],"particular,":[136],"our":[137],"analysis":[138],"found":[139],"Oceania":[141],"was":[142],"only":[144],"continent":[145],"strains":[149],"dispersively":[151],"distributed":[152],"clusters.":[155],"summary,":[157],"this":[158],"study":[159,171],"provides":[160],"a":[161],"concrete":[162],"framework":[163],"use":[166],"methods":[169,181],"global":[173],"addition,":[179],"can":[182],"be":[183],"used":[184],"future":[186],"studies":[187],"variant":[189],"structures":[191],"in":[192],"regions":[194],"these":[196],"fast-growing":[197],"viruses.":[198]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}