{"id":"https://openalex.org/W3207390797","doi":"https://doi.org/10.3390/a14120348","title":"Robust Representation and Efficient Feature Selection Allows for Effective Clustering of SARS-CoV-2 Variants","display_name":"Robust Representation and Efficient Feature Selection Allows for Effective Clustering of SARS-CoV-2 Variants","publication_year":2021,"publication_date":"2021-11-29","ids":{"openalex":"https://openalex.org/W3207390797","doi":"https://doi.org/10.3390/a14120348","mag":"3207390797"},"language":"en","primary_location":{"id":"doi:10.3390/a14120348","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14120348","pdf_url":"https://www.mdpi.com/1999-4893/14/12/348/pdf?version=1638348998","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref","datacite","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-4893/14/12/348/pdf?version=1638348998","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032474804","display_name":"Zahra Tayebi","orcid":null},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zahra Tayebi","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064858842","display_name":"Sarwan Ali","orcid":"https://orcid.org/0000-0001-8121-2168"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sarwan Ali","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA"],"raw_orcid":"https://orcid.org/0000-0001-8121-2168","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA","institution_ids":["https://openalex.org/I181565077"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026228482","display_name":"Murray Patterson","orcid":"https://orcid.org/0000-0002-4329-0234"},"institutions":[{"id":"https://openalex.org/I181565077","display_name":"Georgia State University","ror":"https://ror.org/03qt6ba18","country_code":"US","type":"education","lineage":["https://openalex.org/I181565077"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Murray Patterson","raw_affiliation_strings":["Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA"],"raw_orcid":"https://orcid.org/0000-0002-4329-0234","affiliations":[{"raw_affiliation_string":"Department of Computer Science, Georgia State University, Atlanta, GA 30303, USA","institution_ids":["https://openalex.org/I181565077"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I181565077"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":0.0619,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.41132845,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":"14","issue":"12","first_page":"348","last_page":"348"},"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":0.9991000294685364,"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":0.9991000294685364,"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/T11495","display_name":"Animal Virus Infections Studies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1103","display_name":"Animal Science and Zoology"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12254","display_name":"Machine Learning in Bioinformatics","score":0.993399977684021,"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/spike","display_name":"Spike (software development)","score":0.8110330104827881},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6696579456329346},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.574560284614563},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.516254186630249},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5096874237060547},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.49682310223579407},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.474448561668396},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4685904383659363},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3998526334762573},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3799763023853302},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3554103970527649},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2734004259109497},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.20417198538780212},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.15937820076942444}],"concepts":[{"id":"https://openalex.org/C2781390188","wikidata":"https://www.wikidata.org/wiki/Q25203449","display_name":"Spike (software development)","level":2,"score":0.8110330104827881},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6696579456329346},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.574560284614563},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.516254186630249},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5096874237060547},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.49682310223579407},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.474448561668396},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4685904383659363},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3998526334762573},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3799763023853302},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3554103970527649},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2734004259109497},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.20417198538780212},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.15937820076942444},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.3390/a14120348","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14120348","pdf_url":"https://www.mdpi.com/1999-4893/14/12/348/pdf?version=1638348998","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:2110.09622","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2110.09622","pdf_url":"https://arxiv.org/pdf/2110.09622","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,"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":"mag:3207390797","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2110.09622","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,"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":"arXiv (Cornell University)","raw_type":null},{"id":"pmh:oai:doaj.org/article:8dbe01dce3f84168a1d8452725532457","is_oa":true,"landing_page_url":"https://doaj.org/article/8dbe01dce3f84168a1d8452725532457","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Algorithms, Vol 14, Iss 12, p 348 (2021)","raw_type":"article"},{"id":"doi:10.48550/arxiv.2110.09622","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2110.09622","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,"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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.3390/a14120348","is_oa":true,"landing_page_url":"https://doi.org/10.3390/a14120348","pdf_url":"https://www.mdpi.com/1999-4893/14/12/348/pdf?version=1638348998","source":{"id":"https://openalex.org/S190629608","display_name":"Algorithms","issn_l":"1999-4893","issn":["1999-4893"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Algorithms","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/3","score":0.8199999928474426,"display_name":"Good health and well-being"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W3207390797.pdf"},"referenced_works_count":68,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1587362683","https://openalex.org/W1971318281","https://openalex.org/W1983835132","https://openalex.org/W1987971958","https://openalex.org/W1990130348","https://openalex.org/W1995450389","https://openalex.org/W2022201359","https://openalex.org/W2037299376","https://openalex.org/W2051224630","https://openalex.org/W2066796151","https://openalex.org/W2075117036","https://openalex.org/W2085487226","https://openalex.org/W2097749765","https://openalex.org/W2103914106","https://openalex.org/W2107427530","https://openalex.org/W2113586398","https://openalex.org/W2119479037","https://openalex.org/W2144902422","https://openalex.org/W2156665896","https://openalex.org/W2169931829","https://openalex.org/W2187089797","https://openalex.org/W2278188209","https://openalex.org/W2564443324","https://openalex.org/W2600746833","https://openalex.org/W2601243251","https://openalex.org/W2758442197","https://openalex.org/W2848642079","https://openalex.org/W2943491685","https://openalex.org/W2950815005","https://openalex.org/W2952045272","https://openalex.org/W2963008485","https://openalex.org/W2963722442","https://openalex.org/W2963953805","https://openalex.org/W2991300985","https://openalex.org/W2997636468","https://openalex.org/W2997987931","https://openalex.org/W2999010333","https://openalex.org/W2999797826","https://openalex.org/W3003464757","https://openalex.org/W3004318991","https://openalex.org/W3005510968","https://openalex.org/W3009335299","https://openalex.org/W3014067025","https://openalex.org/W3021378185","https://openalex.org/W3033734920","https://openalex.org/W3046463683","https://openalex.org/W3085065390","https://openalex.org/W3087224093","https://openalex.org/W3098754359","https://openalex.org/W3114206215","https://openalex.org/W3121365103","https://openalex.org/W3126641925","https://openalex.org/W3127156551","https://openalex.org/W3162765748","https://openalex.org/W3164973676","https://openalex.org/W3165479483","https://openalex.org/W3176294083","https://openalex.org/W3192104315","https://openalex.org/W3196141744","https://openalex.org/W3198971816","https://openalex.org/W3209047475","https://openalex.org/W3217347027","https://openalex.org/W4244230525","https://openalex.org/W6667299493","https://openalex.org/W6681302627","https://openalex.org/W7066667914","https://openalex.org/W7067627250"],"related_works":["https://openalex.org/W3025506670","https://openalex.org/W3166126515","https://openalex.org/W3196238276","https://openalex.org/W2183746069","https://openalex.org/W2129715565","https://openalex.org/W3037853531","https://openalex.org/W3092769748","https://openalex.org/W1560256746","https://openalex.org/W123743014","https://openalex.org/W2510906293","https://openalex.org/W2130138427","https://openalex.org/W2765633183","https://openalex.org/W1861897873","https://openalex.org/W2948308350","https://openalex.org/W2397522630","https://openalex.org/W2326364899","https://openalex.org/W2159936323","https://openalex.org/W1544288077","https://openalex.org/W3023591722","https://openalex.org/W1000189836"],"abstract_inverted_index":{"The":[0],"widespread":[1],"availability":[2],"of":[3,6,16,33,62,90,108,117,130,152,175,186,200,229,261,268],"large":[4],"amounts":[5],"genomic":[7],"data":[8,100],"on":[9,98,172,247],"the":[10,17,28,41,60,63,66,83,106,109,118,121,127,131,140,159,198,213,230,243,248,252,293],"SARS-CoV-2":[11,84,122,262],"virus,":[12],"as":[13],"a":[14,31,102,148,173,208,217,224,257],"result":[15],"COVID-19":[18],"pandemic,":[19],"has":[20],"created":[21],"an":[22,184],"opportunity":[23],"for":[24,139,292],"researchers":[25],"to":[26,52,58,73,169,189,196,222,302],"analyze":[27],"disease":[29],"at":[30,207],"level":[32],"detail,":[34],"unlike":[35],"any":[36,78,96],"virus":[37,85],"before":[38],"it.":[39],"On":[40,65],"one":[42],"hand,":[43,68],"this":[44,144],"will":[45,71],"help":[46,72],"biologists,":[47],"policymakers,":[48],"and":[49,55,240,274,278,295],"other":[50,67],"authorities":[51],"make":[53],"timely":[54],"appropriate":[56,160,253],"decisions":[57],"control":[59],"spread":[61],"coronavirus.":[64],"such":[69,99,180],"studies":[70],"more":[74],"effectively":[75,241],"deal":[76],"with":[77,158,183,251,281],"possible":[79],"future":[80],"pandemic.":[81],"Since":[82],"contains":[86],"different":[87,93,165,176,201,249],"variants,":[88],"each":[89],"them":[91],"having":[92],"mutations,":[94],"performing":[95],"analysis":[97],"becomes":[101],"difficult":[103],"task,":[104],"given":[105],"size":[107],"data.":[110],"It":[111],"is":[112],"well":[113,171],"known":[114,202],"that":[115,204,236],"much":[116],"variation":[119],"in":[120,126,194],"genome":[123,132],"happens":[124],"disproportionately":[125],"spike":[128,141,191,231,244,263],"region":[129,136],"sequence\u2014the":[133],"relatively":[134],"short":[135],"which":[137],"codes":[138],"protein(s).":[142],"In":[143],"paper,":[145],"we":[146,237,265,286],"propose":[147],"robust":[149],"feature-vector":[150],"representation":[151,228],"biological":[153],"sequences":[154,193,245,270],"that,":[155,280],"when":[156],"combined":[157],"feature":[161,226,254,283],"selection":[162,284],"method,":[163],"allows":[164],"downstream":[166],"clustering":[167,187,267,276,298],"approaches":[168],"perform":[170,266],"variety":[174],"measures.":[177],"We":[178,215,233],"use":[179,216],"proposed":[181],"approach":[182,220],"array":[185],"techniques":[188],"cluster":[190,242],"protein":[192],"order":[195],"study":[197],"behavior":[199],"variants":[203,250],"are":[205],"increasing":[206],"very":[209],"high":[210],"rate":[211],"throughout":[212],"world.":[214],"k-mers":[218],"based":[219,246],"first":[221],"generate":[223],"fixed-length":[225],"vector":[227],"sequences.":[232],"then":[234],"show":[235,279],"can":[238,287],"efficiently":[239],"selection.":[255],"Using":[256],"publicly":[258],"available":[259],"set":[260],"sequences,":[264],"these":[269],"using":[271],"both":[272],"hard":[273],"soft":[275],"methods":[277],"our":[282],"methods,":[285],"achieve":[288],"higher":[289],"F1":[290],"scores":[291],"clusters":[294],"also":[296],"better":[297],"quality":[299],"metrics":[300],"compared":[301],"baselines.":[303]},"counts_by_year":[{"year":2021,"cited_by_count":1}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}