{"id":"https://openalex.org/W4280508019","doi":"https://doi.org/10.1093/bioinformatics/btac311","title":"ReadItAndKeep: rapid decontamination of SARS-CoV-2 sequencing reads","display_name":"ReadItAndKeep: rapid decontamination of SARS-CoV-2 sequencing reads","publication_year":2022,"publication_date":"2022-05-10","ids":{"openalex":"https://openalex.org/W4280508019","doi":"https://doi.org/10.1093/bioinformatics/btac311","pmid":"https://pubmed.ncbi.nlm.nih.gov/35551365"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btac311","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac311","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1093/bioinformatics/btac311","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5053101311","display_name":"Martin Hunt","orcid":"https://orcid.org/0000-0002-8060-4335"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]},{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Martin Hunt","raw_affiliation_strings":["EMBL-EBI , Cambridge CB10 1SD, UK","Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"EMBL-EBI , Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]},{"raw_affiliation_string":"Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064078365","display_name":"Jeremy Swann","orcid":"https://orcid.org/0000-0002-1475-8248"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Jeremy Swann","raw_affiliation_strings":["Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088001432","display_name":"Bede Constantinides","orcid":"https://orcid.org/0000-0002-3480-3819"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Bede Constantinides","raw_affiliation_strings":["Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025309888","display_name":"Philip W. Fowler","orcid":"https://orcid.org/0000-0003-0912-4483"},"institutions":[{"id":"https://openalex.org/I40120149","display_name":"University of Oxford","ror":"https://ror.org/052gg0110","country_code":"GB","type":"education","lineage":["https://openalex.org/I40120149"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Philip W Fowler","raw_affiliation_strings":["Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nuffield Department of Medicine, University of Oxford , Oxford OX3 9DU, UK","institution_ids":["https://openalex.org/I40120149"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078769186","display_name":"Zamin Iqbal","orcid":"https://orcid.org/0000-0001-8466-7547"},"institutions":[{"id":"https://openalex.org/I1303153112","display_name":"European Bioinformatics Institute","ror":"https://ror.org/02catss52","country_code":"GB","type":"facility","lineage":["https://openalex.org/I1303153112","https://openalex.org/I4210138560"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Zamin Iqbal","raw_affiliation_strings":["EMBL-EBI , Cambridge CB10 1SD, UK"],"raw_orcid":"https://orcid.org/0000-0001-8466-7547","affiliations":[{"raw_affiliation_string":"EMBL-EBI , Cambridge CB10 1SD, UK","institution_ids":["https://openalex.org/I1303153112"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5053101311","https://openalex.org/A5078769186"],"corresponding_institution_ids":["https://openalex.org/I1303153112","https://openalex.org/I40120149"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":1.1089,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.78207951,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"38","issue":"12","first_page":"3291","last_page":"3293"},"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":0.7694000005722046,"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":0.7694000005722046,"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":0.1371999979019165,"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/T10015","display_name":"Genomics and Phylogenetic Studies","score":0.007699999958276749,"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/nanopore-sequencing","display_name":"Nanopore sequencing","score":0.6877835988998413},{"id":"https://openalex.org/keywords/human-genome","display_name":"Human genome","score":0.6076784133911133},{"id":"https://openalex.org/keywords/genome","display_name":"Genome","score":0.6044285297393799},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5842394232749939},{"id":"https://openalex.org/keywords/computational-biology","display_name":"Computational biology","score":0.5074500441551208},{"id":"https://openalex.org/keywords/severe-acute-respiratory-syndrome-coronavirus-2","display_name":"Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2)","score":0.49687460064888},{"id":"https://openalex.org/keywords/minion","display_name":"Minion","score":0.4542137384414673},{"id":"https://openalex.org/keywords/coronavirus-disease-2019","display_name":"Coronavirus disease 2019 (COVID-19)","score":0.4289093017578125},{"id":"https://openalex.org/keywords/1000-genomes-project","display_name":"1000 Genomes Project","score":0.41562899947166443},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.34422773122787476},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.2467135488986969},{"id":"https://openalex.org/keywords/gene","display_name":"Gene","score":0.10541874170303345},{"id":"https://openalex.org/keywords/genotype","display_name":"Genotype","score":0.09938907623291016},{"id":"https://openalex.org/keywords/medicine","display_name":"Medicine","score":0.08236220479011536}],"concepts":[{"id":"https://openalex.org/C126513998","wikidata":"https://www.wikidata.org/wiki/Q8973627","display_name":"Nanopore sequencing","level":4,"score":0.6877835988998413},{"id":"https://openalex.org/C197077220","wikidata":"https://www.wikidata.org/wiki/Q720988","display_name":"Human genome","level":4,"score":0.6076784133911133},{"id":"https://openalex.org/C141231307","wikidata":"https://www.wikidata.org/wiki/Q7020","display_name":"Genome","level":3,"score":0.6044285297393799},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5842394232749939},{"id":"https://openalex.org/C70721500","wikidata":"https://www.wikidata.org/wiki/Q177005","display_name":"Computational biology","level":1,"score":0.5074500441551208},{"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":0.49687460064888},{"id":"https://openalex.org/C2779927696","wikidata":"https://www.wikidata.org/wiki/Q6865654","display_name":"Minion","level":5,"score":0.4542137384414673},{"id":"https://openalex.org/C3008058167","wikidata":"https://www.wikidata.org/wiki/Q84263196","display_name":"Coronavirus disease 2019 (COVID-19)","level":4,"score":0.4289093017578125},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.41562899947166443},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.34422773122787476},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.2467135488986969},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.10541874170303345},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.09938907623291016},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.08236220479011536},{"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},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"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":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D000086402","descriptor_name":"SARS-CoV-2","qualifier_ui":"Q000235","qualifier_name":"genetics","is_major_topic":false},{"descriptor_ui":"D003666","descriptor_name":"Decontamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003666","descriptor_name":"Decontamination","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D003666","descriptor_name":"Decontamination","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":"D006801","descriptor_name":"Humans","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D012984","descriptor_name":"Software","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D015894","descriptor_name":"Genome, Human","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D017422","descriptor_name":"Sequence Analysis, DNA","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D059014","descriptor_name":"High-Throughput Nucleotide Sequencing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false}],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btac311","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac311","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:35551365","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/35551365","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":"Bioinformatics (Oxford, England)","raw_type":null},{"id":"pmh:oai:pubmedcentral.nih.gov:9191204","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/9191204","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":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btac311","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btac311","pdf_url":null,"source":{"id":"https://openalex.org/S52395412","display_name":"Bioinformatics","issn_l":"1367-4803","issn":["1367-4803","1367-4811"],"is_oa":false,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310311648","host_organization_name":"Oxford University Press","host_organization_lineage":["https://openalex.org/P4310311648","https://openalex.org/P4310311647"],"host_organization_lineage_names":["Oxford University Press","University of Oxford"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":6,"referenced_works":["https://openalex.org/W2170551349","https://openalex.org/W2607669908","https://openalex.org/W2990618091","https://openalex.org/W3036067368","https://openalex.org/W3180301457","https://openalex.org/W4294012180"],"related_works":["https://openalex.org/W2749851556","https://openalex.org/W2765793069","https://openalex.org/W4200050032","https://openalex.org/W2550586733","https://openalex.org/W2515795842","https://openalex.org/W1855401909","https://openalex.org/W3138936383","https://openalex.org/W2324462508","https://openalex.org/W2601089939","https://openalex.org/W2907400852"],"abstract_inverted_index":{"SUMMARY:":[0],"Viral":[1],"sequence":[2],"data":[3,32,47,123,157],"from":[4,78,107,113,152],"clinical":[5],"samples":[6,112],"frequently":[7],"contain":[8],"contaminating":[9],"human":[10,86,92,109,111],"reads,":[11,87],"which":[12],"must":[13],"be":[14,133],"removed":[15],"prior":[16],"to":[17,90],"sharing":[18],"for":[19,29,43,135],"legal":[20],"and":[21,45,64,124,150],"ethical":[22],"reasons.":[23],"To":[24],"enable":[25],"host":[26],"read":[27],"removal":[28],"SARS-CoV-2":[30,54,129],"sequencing":[31],"on":[33],"low-specification":[34],"laptops,":[35],"we":[36],"developed":[37],"ReadItAndKeep,":[38],"a":[39,125],"fast":[40],"lightweight":[41],"tool":[42],"Illumina":[44],"nanopore":[46],"that":[48,72],"only":[49],"keeps":[50],"reads":[51,96,106],"matching":[52],"the":[53,75,79,91,108,116,120,147],"genome.":[55],"Peak":[56],"RAM":[57],"usage":[58],"is":[59,141],"typically":[60],"below":[61],"10":[62],"MB,":[63],"runtime":[65],"less":[66],"than":[67],"1":[68],"min.":[69],"We":[70,98],"show":[71],"by":[73],"excluding":[74],"polyA":[76],"tail":[77],"viral":[80],"reference,":[81],"ReadItAndKeep":[82,140],"prevents":[83],"bleed-through":[84],"of":[85,115,128],"whereas":[88],"mapping":[89],"genome":[93],"lets":[94],"some":[95],"escape.":[97],"believe":[99],"our":[100],"test":[101],"approach":[102],"(including":[103],"all":[104],"possible":[105],"genome,":[110],"each":[114],"26":[117],"populations":[118],"in":[119,143],"1000":[121],"genomes":[122],"diverse":[126],"set":[127],"genomes)":[130],"will":[131],"also":[132],"useful":[134],"others.":[136],"AVAILABILITY":[137],"AND":[138],"IMPLEMENTATION:":[139],"implemented":[142],"C++,":[144],"released":[145],"under":[146],"MIT":[148],"license,":[149],"available":[151,159],"https://github.com/GenomePathogenAnalysisService/read-it-and-keep.":[153],"SUPPLEMENTARY":[154],"INFORMATION:":[155],"Supplementary":[156],"are":[158],"at":[160],"Bioinformatics":[161],"online.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":2}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
