{"id":"https://openalex.org/W3118986139","doi":"https://doi.org/10.1093/bioinformatics/btaa1081","title":"Accurate, scalable cohort variant calls using DeepVariant and GLnexus","display_name":"Accurate, scalable cohort variant calls using DeepVariant and GLnexus","publication_year":2020,"publication_date":"2020-12-15","ids":{"openalex":"https://openalex.org/W3118986139","doi":"https://doi.org/10.1093/bioinformatics/btaa1081","mag":"3118986139","pmid":"https://pubmed.ncbi.nlm.nih.gov/33399819"},"language":"en","primary_location":{"id":"doi:10.1093/bioinformatics/btaa1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1081","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/24/5582/36899470/btaa1081.pdf","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","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://academic.oup.com/bioinformatics/article-pdf/36/24/5582/36899470/btaa1081.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5091102480","display_name":"Taedong Yun","orcid":"https://orcid.org/0000-0002-6242-5536"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Taedong Yun","raw_affiliation_strings":["Google Health , Cambridge, MA 02142, USA"],"raw_orcid":"https://orcid.org/0000-0002-6242-5536","affiliations":[{"raw_affiliation_string":"Google Health , Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100753432","display_name":"Helen Li","orcid":"https://orcid.org/0000-0002-1145-6527"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Helen Li","raw_affiliation_strings":["Google Health , Palo Alto, CA 94304, USA"],"raw_orcid":"https://orcid.org/0000-0002-1145-6527","affiliations":[{"raw_affiliation_string":"Google Health , Palo Alto, CA 94304, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056695196","display_name":"Pi-Chuan Chang","orcid":"https://orcid.org/0000-0003-3021-6446"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Pi-Chuan Chang","raw_affiliation_strings":["Google Health , Palo Alto, CA 94304, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Google Health , Palo Alto, CA 94304, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013977055","display_name":"Michael Lin","orcid":"https://orcid.org/0000-0003-4447-1683"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Michael F Lin","raw_affiliation_strings":["mlin.net LLC , Honolulu, HI 96816, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"mlin.net LLC , Honolulu, HI 96816, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071154269","display_name":"Andrew Carroll","orcid":"https://orcid.org/0000-0002-4824-6689"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Andrew Carroll","raw_affiliation_strings":["Google Health , Palo Alto, CA 94304, USA"],"raw_orcid":"https://orcid.org/0000-0002-4824-6689","affiliations":[{"raw_affiliation_string":"Google Health , Palo Alto, CA 94304, USA","institution_ids":["https://openalex.org/I1291425158"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5021644000","display_name":"Cory Y. McLean","orcid":"https://orcid.org/0000-0001-9928-8216"},"institutions":[{"id":"https://openalex.org/I1291425158","display_name":"Google (United States)","ror":"https://ror.org/00njsd438","country_code":"US","type":"company","lineage":["https://openalex.org/I1291425158","https://openalex.org/I4210128969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Cory Y McLean","raw_affiliation_strings":["Google Health , Cambridge, MA 02142, USA"],"raw_orcid":"https://orcid.org/0000-0001-9928-8216","affiliations":[{"raw_affiliation_string":"Google Health , Cambridge, MA 02142, USA","institution_ids":["https://openalex.org/I1291425158"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5021644000"],"corresponding_institution_ids":["https://openalex.org/I1291425158"],"apc_list":{"value":3618,"currency":"USD","value_usd":3618},"apc_paid":{"value":3618,"currency":"USD","value_usd":3618},"fwci":16.2149,"has_fulltext":false,"cited_by_count":264,"citation_normalized_percentile":{"value":0.99417716,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":100},"biblio":{"volume":"36","issue":"24","first_page":"5582","last_page":"5589"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10261","display_name":"Genetic Associations and Epidemiology","score":0.886900007724762,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10261","display_name":"Genetic Associations and Epidemiology","score":0.886900007724762,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T11642","display_name":"Genomics and Rare Diseases","score":0.09210000187158585,"subfield":{"id":"https://openalex.org/subfields/1311","display_name":"Genetics"},"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/T10269","display_name":"Epigenetics and DNA Methylation","score":0.0034000000450760126,"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/computer-science","display_name":"Computer science","score":0.6702245473861694},{"id":"https://openalex.org/keywords/1000-genomes-project","display_name":"1000 Genomes Project","score":0.6045728921890259},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5887861251831055},{"id":"https://openalex.org/keywords/cohort","display_name":"Cohort","score":0.55185467004776},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.546202540397644},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.5281170606613159},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39721208810806274},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3828660845756531},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.25041714310646057},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.23135125637054443},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.21793314814567566},{"id":"https://openalex.org/keywords/genetics","display_name":"Genetics","score":0.21296623349189758},{"id":"https://openalex.org/keywords/biology","display_name":"Biology","score":0.2117348611354828},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.16803660988807678},{"id":"https://openalex.org/keywords/single-nucleotide-polymorphism","display_name":"Single-nucleotide polymorphism","score":0.1260119080543518}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6702245473861694},{"id":"https://openalex.org/C97425143","wikidata":"https://www.wikidata.org/wiki/Q164786","display_name":"1000 Genomes Project","level":5,"score":0.6045728921890259},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5887861251831055},{"id":"https://openalex.org/C72563966","wikidata":"https://www.wikidata.org/wiki/Q1303415","display_name":"Cohort","level":2,"score":0.55185467004776},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.546202540397644},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.5281170606613159},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39721208810806274},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3828660845756531},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.25041714310646057},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.23135125637054443},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.21793314814567566},{"id":"https://openalex.org/C54355233","wikidata":"https://www.wikidata.org/wiki/Q7162","display_name":"Genetics","level":1,"score":0.21296623349189758},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.2117348611354828},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.16803660988807678},{"id":"https://openalex.org/C153209595","wikidata":"https://www.wikidata.org/wiki/Q501128","display_name":"Single-nucleotide polymorphism","level":4,"score":0.1260119080543518},{"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/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C135763542","wikidata":"https://www.wikidata.org/wiki/Q106016","display_name":"Genotype","level":3,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1093/bioinformatics/btaa1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1081","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/24/5582/36899470/btaa1081.pdf","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},{"id":"pmid:33399819","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/33399819","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:8023681","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/8023681","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":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Bioinformatics","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1093/bioinformatics/btaa1081","is_oa":true,"landing_page_url":"https://doi.org/10.1093/bioinformatics/btaa1081","pdf_url":"https://academic.oup.com/bioinformatics/article-pdf/36/24/5582/36899470/btaa1081.pdf","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-nc","license_id":"https://openalex.org/licenses/cc-by-nc","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Bioinformatics","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2332256532","display_name":null,"funder_award_id":"U01 HG007301","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G3520747131","display_name":null,"funder_award_id":"UM1 HG008901","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"},{"id":"https://openalex.org/G5296202576","display_name":null,"funder_award_id":"U01 HG007417","funder_id":"https://openalex.org/F4320337348","funder_display_name":"National Human Genome Research Institute"}],"funders":[{"id":"https://openalex.org/F4320309327","display_name":"Google","ror":"https://ror.org/00njsd438"},{"id":"https://openalex.org/F4320337348","display_name":"National Human Genome Research Institute","ror":"https://ror.org/00baak391"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":59,"referenced_works":["https://openalex.org/W783262033","https://openalex.org/W1596062789","https://openalex.org/W2009171533","https://openalex.org/W2046952982","https://openalex.org/W2058598374","https://openalex.org/W2069769149","https://openalex.org/W2073241381","https://openalex.org/W2084396669","https://openalex.org/W2095680943","https://openalex.org/W2095859808","https://openalex.org/W2104549677","https://openalex.org/W2107862628","https://openalex.org/W2108234281","https://openalex.org/W2116868464","https://openalex.org/W2119180969","https://openalex.org/W2119818111","https://openalex.org/W2122732537","https://openalex.org/W2134638008","https://openalex.org/W2147733682","https://openalex.org/W2149992227","https://openalex.org/W2168133698","https://openalex.org/W2171777347","https://openalex.org/W2238851414","https://openalex.org/W2256016639","https://openalex.org/W2280860630","https://openalex.org/W2417483443","https://openalex.org/W2524054538","https://openalex.org/W2529241974","https://openalex.org/W2562408240","https://openalex.org/W2584596997","https://openalex.org/W2595956553","https://openalex.org/W2604937811","https://openalex.org/W2742539294","https://openalex.org/W2770095154","https://openalex.org/W2789839305","https://openalex.org/W2806567602","https://openalex.org/W2867868648","https://openalex.org/W2885727518","https://openalex.org/W2889664156","https://openalex.org/W2891925439","https://openalex.org/W2895486342","https://openalex.org/W2919717584","https://openalex.org/W2922257230","https://openalex.org/W2929354011","https://openalex.org/W2935917243","https://openalex.org/W2951331911","https://openalex.org/W2952113787","https://openalex.org/W2968499116","https://openalex.org/W2971662497","https://openalex.org/W3029661147","https://openalex.org/W3098304617","https://openalex.org/W3113234297","https://openalex.org/W4394666350","https://openalex.org/W6635813232","https://openalex.org/W6674561012","https://openalex.org/W6727855413","https://openalex.org/W6746163975","https://openalex.org/W6752217974","https://openalex.org/W6761439770"],"related_works":["https://openalex.org/W4286002085","https://openalex.org/W2122946544","https://openalex.org/W2178628622","https://openalex.org/W4381248205","https://openalex.org/W4387141664","https://openalex.org/W4317801964","https://openalex.org/W1968654496","https://openalex.org/W2216458865","https://openalex.org/W1989743336","https://openalex.org/W3095727366"],"abstract_inverted_index":{"MOTIVATION:":[0],"Population-scale":[1],"sequenced":[2,98],"cohorts":[3],"are":[4,163,188],"foundational":[5],"resources":[6],"for":[7],"genetic":[8,155],"analyses,":[9],"but":[10],"processing":[11],"raw":[12],"reads":[13],"into":[14,177],"analysis-ready":[15],"cohort-level":[16],"variants":[17],"remains":[18],"challenging.":[19],"RESULTS:":[20],"We":[21,90,127],"introduce":[22],"an":[23,117],"open-source":[24],"cohort-calling":[25],"method":[26,61],"that":[27],"uses":[28],"the":[29,60,96,130,166],"highly":[30],"accurate":[31],"caller":[32],"DeepVariant":[33,158],"and":[34,47,52,70,104,110,135,143,160,165,182],"scalable":[35],"merging":[36,147],"tool":[37],"GLnexus.":[38],"Using":[39],"callset":[40,107,137],"quality":[41,78,108],"metrics":[42,109],"based":[43],"on":[44],"variant":[45,133],"recall":[46],"precision":[48],"in":[49,55,95,171],"benchmark":[50],"samples":[51,103],"Mendelian":[53],"consistency":[54],"father-mother-child":[56],"trios,":[57],"we":[58],"optimize":[59],"across":[62],"a":[63],"range":[64],"of":[65,145,154],"cohort":[66,136,146],"sizes,":[67],"sequencing":[68,71],"methods":[69,148],"depths.":[72],"The":[73],"resulting":[74],"callsets":[75],"show":[76,105],"consistent":[77],"improvements":[79],"over":[80],"those":[81],"generated":[82,119],"using":[83],"existing":[84],"best":[85],"practices":[86],"with":[87],"reduced":[88],"cost.":[89],"further":[91],"evaluate":[92],"our":[93],"pipeline":[94],"deeply":[97],"1000":[99],"Genomes":[100],"Project":[101],"(1KGP)":[102],"superior":[106],"imputation":[111],"reference":[112],"panel":[113],"performance":[114],"compared":[115],"to":[116,139],"independently":[118],"GATK":[120],"Best":[121],"Practices":[122],"pipeline.":[123],"AVAILABILITY":[124],"AND":[125],"IMPLEMENTATION:":[126],"publicly":[128],"release":[129],"1KGP":[131],"individual-level":[132],"calls":[134],"(https://console.cloud.google.com/storage/browser/brain-genomics-public/research/cohort/1KGP)":[138],"foster":[140],"additional":[141],"development":[142],"evaluation":[144],"as":[149,151],"well":[150],"broad":[152],"studies":[153],"variation.":[156],"Both":[157],"(https://github.com/google/deepvariant)":[159],"GLnexus":[161,168,178],"(https://github.com/dnanexus-rnd/GLnexus)":[162],"open-source,":[164],"optimized":[167],"setup":[169],"discovered":[170],"this":[172],"study":[173],"is":[174],"also":[175],"integrated":[176],"public":[179],"releases":[180],"v1.2.2":[181],"later.":[183],"SUPPLEMENTARY":[184],"INFORMATION:":[185],"Supplementary":[186],"data":[187],"available":[189],"at":[190],"Bioinformatics":[191],"online.":[192]},"counts_by_year":[{"year":2026,"cited_by_count":36},{"year":2025,"cited_by_count":73},{"year":2024,"cited_by_count":63},{"year":2023,"cited_by_count":37},{"year":2022,"cited_by_count":35},{"year":2021,"cited_by_count":18},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-25T08:15:23.626066","created_date":"2025-10-10T00:00:00"}
