{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T20:34:43Z","timestamp":1772138083988,"version":"3.50.1"},"reference-count":38,"publisher":"Oxford University Press (OUP)","issue":"23","funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1P50HL083800"],"award-info":[{"award-number":["1P50HL083800"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["1R01HL101388"],"award-info":[{"award-number":["1R01HL101388"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017,12,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Motivation<\/jats:title>\n                    <jats:p>Large scale genomic sequencing is now widely used to decipher questions in diverse realms such as biological function, human diseases, evolution, ecosystems, and agriculture. With the quantity and diversity these data harbor, a robust and scalable data handling and analysis solution is desired.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>We present interactive analytics using a cloud-based columnar database built on Dremel to perform information compression, comprehensive quality controls, and biological information retrieval in large volumes of genomic data. We demonstrate such Big Data computing paradigms can provide orders of magnitude faster turnaround for common genomic analyses, transforming long-running batch jobs submitted via a Linux shell into questions that can be asked from a web browser in seconds. Using this method, we assessed a study population of 475 deeply sequenced human genomes for genomic call rate, genotype and allele frequency distribution, variant density across the genome, and pharmacogenomic information.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>Our analysis framework is implemented in Google Cloud Platform and BigQuery. Codes are available at https:\/\/github.com\/StanfordBioinformatics\/mvp_aaa_codelabs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Supplementary information<\/jats:title>\n                    <jats:p>Supplementary data are available at Bioinformatics online.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btx468","type":"journal-article","created":{"date-parts":[[2017,7,25]],"date-time":"2017-07-25T15:11:15Z","timestamp":1500995475000},"page":"3709-3715","source":"Crossref","is-referenced-by-count":8,"title":["Cloud-based interactive analytics for terabytes of genomic variants data"],"prefix":"10.1093","volume":"33","author":[{"given":"Cuiping","family":"Pan","sequence":"first","affiliation":[{"name":"VA Palo Alto Health Care System, Palo Alto Epidemiology Research and Information Center for Genomics, CA, USA"},{"name":"Department of Genetics, Stanford University, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregory","family":"McInnes","sequence":"additional","affiliation":[{"name":"VA Palo Alto Health Care System, Palo Alto Epidemiology Research and Information Center for Genomics, CA, USA"},{"name":"Stanford Center for Genomics and Personalized Medicine, Stanford University, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicole","family":"Deflaux","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"},{"name":"Verily Life Sciences, South San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Snyder","sequence":"additional","affiliation":[{"name":"Department of Genetics, Stanford University, CA, USA"},{"name":"Stanford Center for Genomics and Personalized Medicine, Stanford University, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Bingham","sequence":"additional","affiliation":[{"name":"Google, Mountain View, CA, USA"},{"name":"Verily Life Sciences, South San Francisco, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Somalee","family":"Datta","sequence":"additional","affiliation":[{"name":"VA Palo Alto Health Care System, Palo Alto Epidemiology Research and Information Center for Genomics, CA, USA"},{"name":"Stanford Center for Genomics and Personalized Medicine, Stanford University, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Philip S","family":"Tsao","sequence":"additional","affiliation":[{"name":"VA Palo Alto Health Care System, Palo Alto Epidemiology Research and Information Center for Genomics, CA, USA"},{"name":"Division of Cardiovascular Medicine, Stanford University, Stanford, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2017,7,26]]},"reference":[{"key":"2023020207004434800_btx468-B1","doi-asserted-by":"crossref","first-page":"68","DOI":"10.1038\/nature15393","article-title":"A global reference for human genetic variation","volume":"526","author":"1000 Genomes Project Consortium","year":"2015","journal-title":"Nature"},{"key":"2023020207004434800_btx468-B2","doi-asserted-by":"crossref","DOI":"10.1126\/science.aaf7000","article-title":"Genetic identification of familial hypercholesterolemia within a single U.S. health care system","volume":"354","author":"Abul-Husn","year":"2016","journal-title":"Science (New York, N.Y.)"},{"key":"2023020207004434800_btx468-B3","doi-asserted-by":"crossref","first-page":"e0140829.","DOI":"10.1371\/journal.pone.0140829","article-title":"Genomics virtual laboratory: a practical bioinformatics workbench for the cloud","volume":"10","author":"Afgan","year":"2015","journal-title":"PloS One"},{"key":"2023020207004434800_btx468-B4","doi-asserted-by":"crossref","first-page":"3887.","DOI":"10.1038\/ncomms4887","article-title":"A pan-cancer proteomic perspective on The Cancer Genome Atlas","volume":"5","author":"Akbani","year":"2014","journal-title":"Nat. Commun"},{"key":"2023020207004434800_btx468-B5","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1016\/j.bbi.2016.11.026","article-title":"A genetic association study of CSMD1 and CSMD2 with cognitive function","volume":"61","author":"Athanasiu","year":"2017","journal-title":"Brain Behav. Immun"},{"key":"2023020207004434800_btx468-B6","doi-asserted-by":"crossref","first-page":"10.","DOI":"10.1186\/gm527","article-title":"Harvard Personal Genome Project: lessons from participatory public research","volume":"6","author":"Ball","year":"2014","journal-title":"Genome Med"},{"key":"2023020207004434800_btx468-B7","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1007\/7651_2015_236","article-title":"Bioinformatics and microarray data analysis on the cloud","volume":"1375","author":"Calabrese","year":"2016","journal-title":"Methods Mol. Biol. (Clifton, N.J.)"},{"key":"2023020207004434800_btx468-B8","doi-asserted-by":"crossref","first-page":"215","DOI":"10.1038\/gim.2016.87","article-title":"Standardizing terms for clinical pharmacogenetic test results: consensus terms from the Clinical Pharmacogenetics Implementation Consortium (CPIC)","volume":"19","author":"Caudle","year":"2017","journal-title":"Genet. Med"},{"key":"2023020207004434800_btx468-B9","doi-asserted-by":"crossref","first-page":"1977","DOI":"10.2146\/ajhp150977","article-title":"Evidence and resources to implement pharmacogenetic knowledge for precision medicine","volume":"73","author":"Caudle","year":"2016","journal-title":"Am. J. Health Syst. Pharm"},{"key":"2023020207004434800_btx468-B10","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1007\/s12016-012-8303-5","article-title":"The genetics of psoriasis and psoriatic arthritis","volume":"44","author":"Chandran","year":"2013","journal-title":"Clin. Rev. Allergy Immunol"},{"key":"2023020207004434800_btx468-B12","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1038\/nbt.3496","article-title":"Secure cloud computing for genomic data","volume":"34","author":"Datta","year":"2016","journal-title":"Nat. Biotechnol"},{"key":"2023020207004434800_btx468-B13","doi-asserted-by":"crossref","first-page":"491","DOI":"10.1038\/ng.806","article-title":"A framework for variation discovery and genotyping using next-generation DNA sequencing data","volume":"43","author":"DePristo","year":"2011","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B14","doi-asserted-by":"crossref","first-page":"1035","DOI":"10.1001\/jama.2014.1717","article-title":"Clinical interpretation and implications of whole-genome sequencing","volume":"311","author":"Dewey","year":"2014","journal-title":"JAMA"},{"key":"2023020207004434800_btx468-B16","doi-asserted-by":"crossref","first-page":"76920","DOI":"10.18632\/oncotarget.12729","article-title":"Complement inhibitor CSMD1 acts as tumor suppressor in human breast cancer","volume":"7","author":"Escudero-Esparza","year":"2016","journal-title":"Oncotarget"},{"key":"2023020207004434800_btx468-B17","doi-asserted-by":"crossref","first-page":"e1005728.","DOI":"10.1371\/journal.pgen.1005728","article-title":"Genome-wide scan informed by age-related disease identifies loci for exceptional human longevity","volume":"11","author":"Fortney","year":"2015","journal-title":"PLoS Genet"},{"key":"2023020207004434800_btx468-B18","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1038\/nature18642","article-title":"The genetic architecture of type 2 diabetes","volume":"536","author":"Fuchsberger","year":"2016","journal-title":"Nature"},{"key":"2023020207004434800_btx468-B19","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1038\/ng.3021","article-title":"Whole-genome sequence variation, population structure and demographic history of the Dutch population","volume":"46","author":"Genome of the Netherlands Consortium","year":"2014","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B20","doi-asserted-by":"crossref","first-page":"648","DOI":"10.1126\/science.1262110","article-title":"Human genomics. The Genotype-Tissue Expression (GTEx) pilot analysis: multitissue gene regulation in humans","volume":"348","author":"GTEx Consortium","year":"2015","journal-title":"Science (New York, N.Y.)"},{"key":"2023020207004434800_btx468-B21","doi-asserted-by":"crossref","first-page":"435","DOI":"10.1038\/ng.3247","article-title":"Large-scale whole-genome sequencing of the Icelandic population","volume":"47","author":"Gudbjartsson","year":"2015","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B22","doi-asserted-by":"crossref","first-page":"E327","DOI":"10.1073\/pnas.1619052114","article-title":"Comprehensive population-based genome sequencing provides insight into hematopoietic regulatory mechanisms","volume":"114","author":"Guo","year":"2017","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"2023020207004434800_btx468-B23","first-page":"49","author":"Huang","year":"2013"},{"key":"2023020207004434800_btx468-B24","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1038\/gim.2016.190","article-title":"Recommendations for reporting of secondary findings in clinical exome and genome sequencing, 2016 update (ACMG SF v2.0): a policy statement of the American College of Medical Genetics and Genomics","volume":"19","author":"Kalia","year":"2017","journal-title":"Genet. Med"},{"key":"2023020207004434800_btx468-B25","doi-asserted-by":"crossref","first-page":"e84860.","DOI":"10.1371\/journal.pone.0084860","article-title":"STORMSeq: an open-source, user-friendly pipeline for processing personal genomics data in the cloud","volume":"9","author":"Karczewski","year":"2014","journal-title":"PloS One"},{"key":"2023020207004434800_btx468-B26","doi-asserted-by":"crossref","first-page":"1037","DOI":"10.1038\/ng.3626","article-title":"NEK1 variants confer susceptibility to amyotrophic lateral sclerosis","volume":"48","author":"Kenna","year":"2016","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B27","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1038\/nbt.2065","article-title":"Performance comparison of whole-genome sequencing platforms","volume":"30","author":"Lam","year":"2011","journal-title":"Nat. Biotechnol"},{"key":"2023020207004434800_btx468-B41","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1145\/1953122.1953148","article-title":"Dremel: Interactive Analysis of Web-Scale Datasets","volume":"54","author":"Melnik","year":"2011","journal-title":"Commun. ACM"},{"key":"2023020207004434800_btx468-B28","doi-asserted-by":"crossref","first-page":"8018.","DOI":"10.1038\/ncomms9018","article-title":"Rare variant discovery by deep whole-genome sequencing of 1,070 Japanese individuals","volume":"6","author":"Nagasaki","year":"2015","journal-title":"Nat. Commun"},{"key":"2023020207004434800_btx468-B29","doi-asserted-by":"crossref","first-page":"30.","DOI":"10.1186\/1471-2105-15-30","article-title":"Launching genomics into the cloud: deployment of Mercury, a next generation sequence analysis pipeline","volume":"15","author":"Reid","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023020207004434800_btx468-B30","doi-asserted-by":"crossref","first-page":"e0129277.","DOI":"10.1371\/journal.pone.0129277","article-title":"Inexpensive and highly reproducible cloud-based variant calling of 2,535 human genomes","volume":"10","author":"Shringarpure","year":"2015","journal-title":"PloS One"},{"key":"2023020207004434800_btx468-B31","doi-asserted-by":"crossref","first-page":"64.","DOI":"10.1186\/s12920-015-0134-9","article-title":"Scalable and cost-effective NGS genotyping in the cloud","volume":"8","author":"Souilmi","year":"2015","journal-title":"BMC Med. Genomics"},{"key":"2023020207004434800_btx468-B32","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1006\/geno.2001.6587","article-title":"Transcript map of the 8p23 putative tumor suppressor region","volume":"75","author":"Sun","year":"2001","journal-title":"Genomics"},{"key":"2023020207004434800_btx468-B33","doi-asserted-by":"crossref","first-page":"11901","DOI":"10.1073\/pnas.1613365113","article-title":"Deep sequencing of 10,000 human genomes","volume":"113","author":"Telenti","year":"2016","journal-title":"Proc. Natl. Acad. Sci. U.S.A"},{"key":"2023020207004434800_btx468-B34","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1038\/ng.2854","article-title":"Application of a 5-tiered scheme for standardized classification of 2,360 unique mismatch repair gene variants in the InSiGHT locus-specific database","volume":"46","author":"Thompson","year":"2014","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B35","author":"Turner","year":"2011"},{"key":"2023020207004434800_btx468-B36","doi-asserted-by":"crossref","first-page":"1043","DOI":"10.1038\/ng.3622","article-title":"Genome-wide association analyses identify new risk variants and the genetic architecture of amyotrophic lateral sclerosis","volume":"48","author":"van Rheenen","year":"2016","journal-title":"Nat. Genet"},{"key":"2023020207004434800_btx468-B38","doi-asserted-by":"crossref","first-page":"176","DOI":"10.1186\/1471-2105-15-176","article-title":"QMachine: commodity supercomputing in web browsers","volume":"15","author":"Wilkinson","year":"2014","journal-title":"BMC Bioinformatics"},{"key":"2023020207004434800_btx468-B39","doi-asserted-by":"crossref","first-page":"52","DOI":"10.1016\/j.ajhg.2012.12.005","article-title":"Deep whole-genome sequencing of 100 southeast Asian Malays","volume":"92","author":"Wong","year":"2013","journal-title":"Am. J. Hum. Genet"},{"key":"2023020207004434800_btx468-B40","doi-asserted-by":"crossref","first-page":"602","DOI":"10.1038\/nn.4524","article-title":"Whole genome sequencing resource identifies 18 new candidate genes for autism spectrum disorder","volume":"20","author":"Yuan","year":"2017","journal-title":"Nature Neuroscience"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/23\/3709\/49041998\/bioinformatics_33_23_3709.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/33\/23\/3709\/49041998\/bioinformatics_33_23_3709.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,2]],"date-time":"2023-02-02T02:01:58Z","timestamp":1675303318000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/33\/23\/3709\/4036385"}},"subtitle":[],"editor":[{"given":"Inanc","family":"Birol","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2017,7,26]]},"references-count":38,"journal-issue":{"issue":"23","published-print":{"date-parts":[[2017,12,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btx468","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/035295","asserted-by":"object"}]},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2017,12,1]]},"published":{"date-parts":[[2017,7,26]]}}}