{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:23:07Z","timestamp":1780608187604,"version":"3.54.1"},"reference-count":10,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2018,10,23]],"date-time":"2018-10-23T00:00:00Z","timestamp":1540252800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U54-AG052427"],"award-info":[{"award-number":["U54-AG052427"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U01-AG032984"],"award-info":[{"award-number":["U01-AG032984"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000049","name":"National Institute on Aging","doi-asserted-by":"publisher","award":["U24-AG041689"],"award-info":[{"award-number":["U24-AG041689"]}],"id":[{"id":"10.13039\/100000049","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5,15]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Summary<\/jats:title>\n                    <jats:p>We report VCPA, our SNP\/Indel Variant Calling Pipeline and data management tool used for the analysis of whole genome and exome sequencing (WGS\/WES) for the Alzheimer\u2019s Disease Sequencing Project. VCPA consists of two independent but linkable components: pipeline and tracking database. The pipeline, implemented using the Workflow Description Language and fully optimized for the Amazon elastic compute cloud environment, includes steps from aligning raw sequence reads to variant calling using GATK. The tracking database allows users to view job running status in real time and visualize &amp;gt;100 quality metrics per genome. VCPA is functionally equivalent to the CCDG\/TOPMed pipeline. Users can use the pipeline and the dockerized database to process large WGS\/WES datasets on Amazon cloud with minimal configuration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Availability and implementation<\/jats:title>\n                    <jats:p>VCPA is released under the MIT license and is available for academic and nonprofit use for free. The pipeline source code and step-by-step instructions are available from the National Institute on Aging Genetics of Alzheimer\u2019s Disease Data Storage Site (http:\/\/www.niagads.org\/VCPA).<\/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\/bty894","type":"journal-article","created":{"date-parts":[[2018,10,22]],"date-time":"2018-10-22T15:42:39Z","timestamp":1540222959000},"page":"1768-1770","source":"Crossref","is-referenced-by-count":55,"title":["VCPA: genomic variant calling pipeline and data management tool for Alzheimer\u2019s Disease Sequencing Project"],"prefix":"10.1093","volume":"35","author":[{"given":"Yuk Yee","family":"Leung","sequence":"first","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Otto","family":"Valladares","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi-Fan","family":"Chou","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Han-Jen","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Amanda B","family":"Kuzma","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Cantwell","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liming","family":"Qu","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Prabhakaran","family":"Gangadharan","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"William J","family":"Salerno","sequence":"additional","affiliation":[{"name":"Human Genome Sequencing Center, Baylor College of Medicine, Houston, TX, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gerard D","family":"Schellenberg","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Li-San","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Pathology and Laboratory Medicine, Perelman School of Medicine at the University of Pennsylvania, Penn Neurodegeneration Genomics Center, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2018,10,23]]},"reference":[{"key":"2023013107490273900_bty894-B1","author":"Chandran","year":"2018"},{"key":"2023013107490273900_bty894-B2","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":"2023013107490273900_bty894-B3","article-title":"xAtlas: scalable small variant calling across heterogeneous next-generation sequencing experiments.","author":"Farek","year":"2018","journal-title":"bioRxiv"},{"key":"2023013107490273900_bty894-B4","doi-asserted-by":"crossref","first-page":"2503","DOI":"10.1093\/bioinformatics\/btu314","article-title":"SAMBLASTER: fast duplicate marking and structural variant read extraction","volume":"30","author":"Faust","year":"2014","journal-title":"Bioinformatics"},{"key":"2023013107490273900_bty894-B5","first-page":"3997","article-title":"Aligning sequence reads, clone sequences and assembly contigs with BWA-MEM","volume":"1303","author":"Li","year":"2013","journal-title":"arXiv preprint"},{"key":"2023013107490273900_bty894-B6","doi-asserted-by":"crossref","first-page":"2078","DOI":"10.1093\/bioinformatics\/btp352","article-title":"The Sequence Alignment\/Map format and SAMtools","volume":"25","author":"Li","year":"2009","journal-title":"Bioinformatics"},{"key":"2023013107490273900_bty894-B7","doi-asserted-by":"crossref","first-page":"1297","DOI":"10.1101\/gr.107524.110","article-title":"The Genome Analysis Toolkit: a MapReduce framework for analyzing next-generation DNA sequencing data","volume":"20","author":"McKenna","year":"2010","journal-title":"Genome Res."},{"key":"2023013107490273900_bty894-B8","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.1093\/bioinformatics\/btv098","article-title":"Sambamba: fast processing of NGS alignment formats","volume":"31","author":"Tarasov","year":"2015","journal-title":"Bioinformatics"},{"key":"2023013107490273900_bty894-B9","first-page":"1379","article-title":"Full-stack genomics pipelining with GATK4\u2009+\u2009WDL\u2009+\u2009Cromwell","volume":"6","author":"Voss","year":"2017","journal-title":"F1000Res."},{"key":"2023013107490273900_bty894-B10","article-title":"Functional equivalence of genome sequencing analysis pipelines enables harmonized variant calling across human genetics projects.","author":"Regier","year":"2018","journal-title":"bioRxiv"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/bty894\/28388605\/bty894.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/10\/1768\/48970241\/bioinformatics_35_10_1768.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/35\/10\/1768\/48970241\/bioinformatics_35_10_1768.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T05:51:23Z","timestamp":1675144283000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/35\/10\/1768\/5142723"}},"subtitle":[],"editor":[{"given":"John","family":"Hancock","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2018,10,23]]},"references-count":10,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,5,15]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/bty894","relation":{"has-preprint":[{"id-type":"doi","id":"10.1101\/327395","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":[[2019,5,15]]},"published":{"date-parts":[[2018,10,23]]}}}