{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T05:35:26Z","timestamp":1773293726433,"version":"3.50.1"},"reference-count":10,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2022,12,15]],"date-time":"2022-12-15T00:00:00Z","timestamp":1671062400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000054","name":"National Cancer Institute","doi-asserted-by":"publisher","award":["P30 CA008748"],"award-info":[{"award-number":["P30 CA008748"]}],"id":[{"id":"10.13039\/100000054","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100007052","name":"Memorial Sloan Kettering Cancer Center","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100007052","id-type":"DOI","asserted-by":"publisher"}]},{"name":"American Association for Cancer Research Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,1,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>Data from the American Association for Cancer Research Project Genomics Evidence Neoplasia Information Exchange Biopharma Collaborative (GENIE BPC) represent comprehensive clinical data linked to high-throughput sequencing data, providing a multi-institution, pan-cancer, publicly available data repository. GENIE BPC data provide detailed demographic, clinical, treatment, genomic and outcome data for patients with cancer. These data result in a unique observational database of molecularly characterized tumors with comprehensive clinical annotation that can be used for health outcomes and precision medicine research in oncology. Due to the inherently complex structure of the multiple phenomic and genomic datasets, the use of these data requires a robust process for data integration and preparation in order to build analytic models.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>We present the {genieBPC} package, a user-friendly data processing pipeline to facilitate the creation of analytic cohorts from the GENIE BPC data that are ready for clinico-genomic modeling and analyses.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>{genieBPC} is available on CRAN and GitHub.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btac796","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T23:56:33Z","timestamp":1671062193000},"source":"Crossref","is-referenced-by-count":8,"title":["A data processing pipeline for the AACR project GENIE biopharma collaborative data with the {genieBPC} R package"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2746-5647","authenticated-orcid":false,"given":"Jessica A","family":"Lavery","sequence":"first","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5352-974X","authenticated-orcid":false,"given":"Samantha","family":"Brown","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael A","family":"Curry","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Axel","family":"Martin","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel D","family":"Sjoberg","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Karissa","family":"Whiting","sequence":"additional","affiliation":[{"name":"Department of Epidemiology and Biostatistics, Memorial Sloan Kettering Cancer Center , 633 3rd Avenue New York, New York 10017, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2022,12,15]]},"reference":[{"key":"2023010620564630300_btac796-B1","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1158\/2159-8290.CD-17-0151","article-title":"AACR project GENIE: powering precision medicine through an international consortium","volume":"7","author":"AACR Project GENIE Consortium","year":"2017","journal-title":"Cancer Discov"},{"key":"2023010620564630300_btac796-B2","doi-asserted-by":"crossref","DOI":"10.1001\/jamaoncol.2021.5153","article-title":"Implications of selection bias due to delayed study entry in clinical genomic studies","author":"Brown","year":"2022","journal-title":"JAMA Oncol"},{"key":"2023010620564630300_btac796-B3","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1200\/CCI.20.00108","article-title":"OncoTree: a cancer classification system for precision oncology","volume":"5","author":"Kundra","year":"2021","journal-title":"JCO Clin. Cancer Inform"},{"key":"2023010620564630300_btac796-B4","doi-asserted-by":"crossref","first-page":"e2100105","DOI":"10.1200\/CCI.21.00105","article-title":"A scalable quality assurance process for curating oncology electronic health records: the project GENIE biopharma collaborative approach","volume":"6","author":"Lavery","year":"2022","journal-title":"JCO Clin. Cancer Inform"},{"key":"2023010620564630300_btac796-B5","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1158\/2159-8290.CD-17-0604","article-title":"The GENIE is out of the bottle: landmark cancer genomics dataset released","volume":"7","author":"Litchfield","year":"2017","journal-title":"Cancer Discov"},{"key":"2023010620564630300_btac796-B6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1200\/CCI.17.00083","article-title":"American association for cancer research project genomics evidence neoplasia information exchange: from inception to first data release and beyond\u2014lessons learned and member institutions\u2019 perspectives","volume":"2","author":"Micheel","year":"2018","journal-title":"JCO Clin. Cancer Inform"},{"key":"2023010620564630300_btac796-B7","author":"Bostock","year":"2021"},{"key":"2023010620564630300_btac796-B8","author":"Sage Bionetworks","year":"2022"},{"key":"2023010620564630300_btac796-B9","author":"Schrag","year":"2018"},{"key":"2023010620564630300_btac796-B10","doi-asserted-by":"crossref","first-page":"570","DOI":"10.32614\/RJ-2021-053","article-title":"Reproducible summary tables with the gtsummary package","volume":"13","author":"Sjoberg","year":"2021","journal-title":"R J"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btac796\/47915703\/btac796.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac796\/48482867\/btac796.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/1\/btac796\/48482867\/btac796.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T20:59:33Z","timestamp":1673038773000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btac796\/6909009"}},"subtitle":[],"editor":[{"given":"Jonathan","family":"Wren","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,12,15]]},"references-count":10,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,1,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btac796","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,1,1]]},"published":{"date-parts":[[2022,12,15]]},"article-number":"btac796"}}