{"id":"https://openalex.org/W4284708293","doi":"https://doi.org/10.1016/j.patter.2022.100562","title":"Efficient compression of SARS-CoV-2 genome data using Nucleotide Archival Format","display_name":"Efficient compression of SARS-CoV-2 genome data using Nucleotide Archival Format","publication_year":2022,"publication_date":"2022-07-07","ids":{"openalex":"https://openalex.org/W4284708293","doi":"https://doi.org/10.1016/j.patter.2022.100562","pmid":"https://pubmed.ncbi.nlm.nih.gov/35818472"},"language":"en","primary_location":{"id":"doi:10.1016/j.patter.2022.100562","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100562","pdf_url":null,"source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Patterns","raw_type":"journal-article"},"type":"review","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.patter.2022.100562","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5088370475","display_name":"Kirill Kryukov","orcid":"https://orcid.org/0000-0002-0286-0288"},"institutions":[{"id":"https://openalex.org/I113198587","display_name":"National Institute of Genetics","ror":"https://ror.org/02xg1m795","country_code":"JP","type":"facility","lineage":["https://openalex.org/I113198587","https://openalex.org/I1319490839","https://openalex.org/I4210158934"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kirill Kryukov","raw_affiliation_strings":["Department of Informatics, National Institute of Genetics, Mishima, Shizuoka 411-8540, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Informatics, National Institute of Genetics, Mishima, Shizuoka 411-8540, Japan","institution_ids":["https://openalex.org/I113198587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109245262","display_name":"Lihua Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lihua Jin","raw_affiliation_strings":["Genomus Co., Ltd., Sagamihara, Kanagawa 252-0226, Japan"],"affiliations":[{"raw_affiliation_string":"Genomus Co., Ltd., Sagamihara, Kanagawa 252-0226, Japan","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054739143","display_name":"So Nakagawa","orcid":"https://orcid.org/0000-0003-1760-3839"},"institutions":[{"id":"https://openalex.org/I1314466530","display_name":"Tokai University","ror":"https://ror.org/01p7qe739","country_code":"JP","type":"education","lineage":["https://openalex.org/I1314466530"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"So Nakagawa","raw_affiliation_strings":["Department of Molecular Life Science, Tokai University School of Medicine, Isehara, Kanagawa 259-1193, Japan"],"affiliations":[{"raw_affiliation_string":"Department of Molecular Life Science, Tokai University School of Medicine, Isehara, Kanagawa 259-1193, Japan","institution_ids":["https://openalex.org/I1314466530"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5054739143"],"corresponding_institution_ids":["https://openalex.org/I1314466530"],"apc_list":{"value":5200,"currency":"USD","value_usd":5200},"apc_paid":{"value":5200,"currency":"USD","value_usd":5200},"fwci":0.9083,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.74574282,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"3","issue":"9","first_page":"100562","last_page":"100562"},"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":0.9943000078201294,"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":0.9943000078201294,"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/T10207","display_name":"Advanced biosensing and bioanalysis techniques","score":0.9934999942779541,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.9901000261306763,"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/genbank","display_name":"GenBank","score":0.7934451699256897},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6083634495735168},{"id":"https://openalex.org/keywords/upload","display_name":"Upload","score":0.5958917140960693},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.5250917673110962},{"id":"https://openalex.org/keywords/severe-acute-respiratory-syndrome-coronavirus-2","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score":0.4961627423763275},{"id":"https://openalex.org/keywords/data-compression","display_name":"Data compression","score":0.4732654094696045},{"id":"https://openalex.org/keywords/sequence-assembly","display_name":"Sequence assembly","score":0.43807655572891235},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.4260002374649048},{"id":"https://openalex.org/keywords/dna-sequencing","display_name":"DNA sequencing","score":0.4238869547843933},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3867008090019226},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.3768007159233093},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.35440078377723694},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.24226728081703186},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.18678706884384155},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.17854413390159607},{"id":"https://openalex.org/keywords/dna","display_name":"DNA","score":0.1533893346786499},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.15175357460975647},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.1281183958053589}],"concepts":[{"id":"https://openalex.org/C79029880","wikidata":"https://www.wikidata.org/wiki/Q901755","display_name":"GenBank","level":3,"score":0.7934451699256897},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6083634495735168},{"id":"https://openalex.org/C71901391","wikidata":"https://www.wikidata.org/wiki/Q7126699","display_name":"Upload","level":2,"score":0.5958917140960693},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.5250917673110962},{"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":0.4961627423763275},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.4732654094696045},{"id":"https://openalex.org/C18949551","wikidata":"https://www.wikidata.org/wiki/Q740578","display_name":"Sequence assembly","level":5,"score":0.43807655572891235},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.4260002374649048},{"id":"https://openalex.org/C51679486","wikidata":"https://www.wikidata.org/wiki/Q380546","display_name":"DNA sequencing","level":3,"score":0.4238869547843933},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3867008090019226},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.3768007159233093},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.35440078377723694},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.24226728081703186},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.18678706884384155},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.17854413390159607},{"id":"https://openalex.org/C552990157","wikidata":"https://www.wikidata.org/wiki/Q7430","display_name":"DNA","level":2,"score":0.1533893346786499},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.15175357460975647},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.1281183958053589},{"id":"https://openalex.org/C162317418","wikidata":"https://www.wikidata.org/wiki/Q252857","display_name":"Transcriptome","level":4,"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/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0},{"id":"https://openalex.org/C150194340","wikidata":"https://www.wikidata.org/wiki/Q26972","display_name":"Gene expression","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":3,"locations":[{"id":"doi:10.1016/j.patter.2022.100562","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100562","pdf_url":null,"source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Patterns","raw_type":"journal-article"},{"id":"pmid:35818472","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35818472","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":"Patterns (New York, N.Y.)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9259476","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9259476","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"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":"Patterns (N Y)","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1016/j.patter.2022.100562","is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.patter.2022.100562","pdf_url":null,"source":{"id":"https://openalex.org/S4210198061","display_name":"Patterns","issn_l":"2666-3899","issn":["2666-3899"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"Patterns","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Good health and well-being","id":"https://metadata.un.org/sdg/3","score":0.8199999928474426}],"awards":[{"id":"https://openalex.org/G5931258489","display_name":null,"funder_award_id":"JPMJCR20H1","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"},{"id":"https://openalex.org/G7306959901","display_name":null,"funder_award_id":"20K06612","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G875881984","display_name":null,"funder_award_id":"JPMJCR20H6","funder_id":"https://openalex.org/F4320338075","funder_display_name":"Core Research for Evolutional Science and Technology"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"},{"id":"https://openalex.org/F4320334789","display_name":"Japan Science and Technology Agency","ror":"https://ror.org/00097mb19"},{"id":"https://openalex.org/F4320338075","display_name":"Core Research for Evolutional Science and Technology","ror":"https://ror.org/00097mb19"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W1931027898","https://openalex.org/W1982703709","https://openalex.org/W2028990382","https://openalex.org/W2029195137","https://openalex.org/W2055043387","https://openalex.org/W2092880969","https://openalex.org/W2111451722","https://openalex.org/W2120141270","https://openalex.org/W2131106408","https://openalex.org/W2136145671","https://openalex.org/W2138196010","https://openalex.org/W2144514096","https://openalex.org/W2157745386","https://openalex.org/W2158678815","https://openalex.org/W2166588423","https://openalex.org/W2167943254","https://openalex.org/W2207690983","https://openalex.org/W2538355508","https://openalex.org/W2561200699","https://openalex.org/W2764165465","https://openalex.org/W2765745983","https://openalex.org/W2781268828","https://openalex.org/W2899544675","https://openalex.org/W2905575949","https://openalex.org/W2922407406","https://openalex.org/W2951893579","https://openalex.org/W2976854536","https://openalex.org/W2983510300","https://openalex.org/W2986984493","https://openalex.org/W2998912266","https://openalex.org/W3012798837","https://openalex.org/W3038746171","https://openalex.org/W3092652421","https://openalex.org/W3098741556","https://openalex.org/W3113585926","https://openalex.org/W3119974917","https://openalex.org/W3165479483","https://openalex.org/W3200118936","https://openalex.org/W3213153027","https://openalex.org/W3215751839","https://openalex.org/W4200137031","https://openalex.org/W4200261040","https://openalex.org/W4200553915","https://openalex.org/W4210330831","https://openalex.org/W4224212256","https://openalex.org/W4224216303","https://openalex.org/W4239734004","https://openalex.org/W4293196852","https://openalex.org/W4306800008","https://openalex.org/W4323037726","https://openalex.org/W4365799926","https://openalex.org/W6678795934","https://openalex.org/W6681447482","https://openalex.org/W6681790542","https://openalex.org/W6730472500","https://openalex.org/W6765131264","https://openalex.org/W6787587555","https://openalex.org/W6810052710","https://openalex.org/W6842402754"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W1993070549","https://openalex.org/W4250169950","https://openalex.org/W1906885765","https://openalex.org/W4232951075","https://openalex.org/W4386946098","https://openalex.org/W4238968199","https://openalex.org/W4240231372","https://openalex.org/W3215016332","https://openalex.org/W1491924329"],"abstract_inverted_index":{"Severe":[0],"acute":[1],"respiratory":[2],"syndrome":[3],"coronavirus":[4],"2":[5],"(SARS-CoV-2)":[6],"genome":[7],"data":[8,87,119],"are":[9],"essential":[10],"for":[11,85,91,106,136],"epidemiology,":[12],"vaccine":[13],"development,":[14],"and":[15,37,52,88,111,138,157,160,163],"tracking":[16],"emerging":[17],"variants.":[18],"Millions":[19],"of":[20,44,97,124,154],"SARS-CoV-2":[21,31],"genomes":[22,32],"have":[23],"been":[24],"sequenced":[25],"during":[26],"the":[27,49],"pandemic.":[28],"However,":[29],"downloading":[30],"from":[33],"databases":[34,148],"is":[35],"slow":[36],"unreliable,":[38],"largely":[39],"due":[40],"to":[41],"suboptimal":[42],"choice":[43],"compression":[45],"method.":[46],"We":[47],"evaluated":[48],"available":[50],"compressors":[51],"found":[53],"that":[54],"Nucleotide":[55,113],"Archival":[56],"Format":[57],"(NAF)":[58],"would":[59,80,101,117,149],"provide":[60,150],"a":[61,122,134,142,151],"drastic":[62],"improvement":[63],"compared":[64,127],"with":[65,128],"current":[66],"methods.":[67],"For":[68,94,109],"Global":[69],"Initiative":[70],"on":[71],"Sharing":[72],"Avian":[73],"Flu":[74],"Data's":[75],"(GISAID)":[76],"pre-compressed":[77],"datasets,":[78],"NAF":[79,100,116,143],"increase":[81],"efficiency":[82],"52.2":[83],"times":[84,90,105,126],"gzip-compressed":[86,107],"3.7":[89],"xz-compressed":[92],"data.":[93,108],"DNA":[95],"DataBank":[96],"Japan":[98],"(DDBJ),":[99],"improve":[102],"throughput":[103],"40":[104],"GenBank":[110],"European":[112],"Archive":[114],"(ENA),":[115],"accelerate":[118,161],"distribution":[120],"by":[121],"factor":[123],"29.3":[125],"uncompressed":[129],"FASTA.":[130],"This":[131],"article":[132],"provides":[133],"tutorial":[135],"installing":[137],"using":[139],"NAF.":[140],"Offering":[141],"download":[144],"option":[145],"in":[146],"sequence":[147],"significant":[152],"saving":[153],"time,":[155],"bandwidth,":[156],"disk":[158],"space":[159],"biological":[162],"medical":[164],"research":[165],"worldwide.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":1}],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2025-10-10T00:00:00"}
