{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,17]],"date-time":"2025-10-17T00:20:03Z","timestamp":1760660403533,"version":"build-2065373602"},"reference-count":24,"publisher":"Oxford University Press (OUP)","issue":"10","license":[{"start":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T00:00:00Z","timestamp":1759104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Office of Basic Energy Sciences of the U.S. Department of Energy","award":["DE-AC02-05CH11231"],"award-info":[{"award-number":["DE-AC02-05CH11231"]}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5R24OD011883-12","5RM1HG010860-03","5R01HD103805-04","5U24HG011449-04"],"award-info":[{"award-number":["5R24OD011883-12","5RM1HG010860-03","5R01HD103805-04","5U24HG011449-04"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100005156","name":"Alexander von Humboldt foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100005156","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Lack of data integration remains a significant impediment to cancer research, and many analyses still require customized software to transform and prepare cancer data. We describe a software package to harmonize genetic and clinical cancer data into the GA4GH Phenopacket schema, an ISO standard for representing clinical case data. We integrated demographic, mutation, morphology, diagnosis, intervention, and survival data using case data from the National Cancer Institute for 12 cancer types. The Phenopacket standard provides a foundation for downstream use, including sophisticated statistical and AI\/ML analyses. We demonstrate fitness for purpose by using the integrated data to recapitulate a known association between mutations in the gene encoding isocitrate dehydrogenase 1 and survival time in brain cancer patients.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>Source code is freely available at: https:\/\/github.com\/monarch-initiative\/oncopacket (archived at 10.5281\/zenodo.15353125).<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btaf546","type":"journal-article","created":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T09:48:12Z","timestamp":1759139292000},"source":"Crossref","is-referenced-by-count":0,"title":["Oncopacket: integration of cancer research data using GA4GH phenopackets"],"prefix":"10.1093","volume":"41","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0657-0288","authenticated-orcid":false,"given":"Michael","family":"Sierk","sequence":"first","affiliation":[{"name":"Center for Biomedical Informatics & Information Technology, National Cancer Institute (NCI) Bethesda, MD 20850,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daniel","family":"Danis","sequence":"additional","affiliation":[{"name":"Berlin Institute of Health at Charit\u00e9 Universit\u00e4tsmedizin Berlin , Berlin 10117,","place":["Germany"]},{"name":"The Jackson Laboratory for Genomic Medicine , Farmington, CT 06032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6142-1106","authenticated-orcid":false,"given":"Sujay","family":"Patil","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory (LBNL) , Berkeley, CA, 94720,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nobal","family":"Kishor","sequence":"additional","affiliation":[{"name":"Elucidata , San Francisco, CA 94114,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rajdeep","family":"Mondal","sequence":"additional","affiliation":[{"name":"Elucidata , San Francisco, CA 94114,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhishek","family":"Jha","sequence":"additional","affiliation":[{"name":"Elucidata , San Francisco, CA 94114,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingrong","family":"Chen","sequence":"additional","affiliation":[{"name":"Center for Biomedical Informatics & Information Technology, National Cancer Institute (NCI) Bethesda, MD 20850,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunhua","family":"Yan","sequence":"additional","affiliation":[{"name":"Center for Biomedical Informatics & Information Technology, National Cancer Institute (NCI) Bethesda, MD 20850,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Monica","family":"Munoz-Torres","sequence":"additional","affiliation":[{"name":"Department of Biomedical Informatics, University of Colorado Anschutz Medical Campus , Aurora, CO 80045,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Daoud","family":"Meerzaman","sequence":"additional","affiliation":[{"name":"Center for Biomedical Informatics & Information Technology, National Cancer Institute (NCI) Bethesda, MD 20850,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0736-9199","authenticated-orcid":false,"given":"Peter N","family":"Robinson","sequence":"additional","affiliation":[{"name":"Berlin Institute of Health at Charit\u00e9 Universit\u00e4tsmedizin Berlin , Berlin 10117,","place":["Germany"]},{"name":"The Jackson Laboratory for Genomic Medicine , Farmington, CT 06032,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2170-2250","authenticated-orcid":false,"given":"Justin T","family":"Reese","sequence":"additional","affiliation":[{"name":"Division of Environmental Genomics and Systems Biology, Lawrence Berkeley National Laboratory (LBNL) , Berkeley, CA, 94720,","place":["United States"]}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2025,9,29]]},"reference":[{"key":"2025101607372945400_btaf546-B1","doi-asserted-by":"crossref","first-page":"e21929","DOI":"10.2196\/21929","article-title":"The fast health interoperability resources (FHIR) standard: systematic literature review of implementations, applications, challenges and opportunities","volume":"9","author":"Ayaz","year":"2021","journal-title":"JMIR Med Inform"},{"key":"2025101607372945400_btaf546-B2","doi-asserted-by":"crossref","first-page":"1095","DOI":"10.1001\/jamaoncol.2022.1572","article-title":"Maximizing cancer data\u2014the future of cancer is now","volume":"8","author":"Barnholtz-Sloan","year":"2022","journal-title":"JAMA Oncol"},{"key":"2025101607372945400_btaf546-B3","doi-asserted-by":"crossref","first-page":"1384","DOI":"10.1158\/0008-5472.CAN-23-2655","article-title":"NCI cancer research data commons: core standards and services","volume":"84","author":"Brady","year":"2024","journal-title":"Cancer Res"},{"year":"2024","author":"Cancer Data Aggregator","key":"2025101607372945400_btaf546-B4"},{"key":"2025101607372945400_btaf546-B5","first-page":"100371","article-title":"A corpus of GA4GH phenopackets: case-level phenotyping for genomic diagnostics and discovery","volume":"6","author":"Danis","year":"2025","journal-title":"HGG Adv"},{"key":"2025101607372945400_btaf546-B6","doi-asserted-by":"crossref","first-page":"e0285433","DOI":"10.1371\/journal.pone.0285433","article-title":"Phenopacket-tools: building and validating GA4GH phenopackets","volume":"18","author":"Danis","year":"2023","journal-title":"PLoS One"},{"key":"2025101607372945400_btaf546-B7","doi-asserted-by":"crossref","first-page":"1317","DOI":"10.21105\/joss.01317","article-title":"Lifelines: survival analysis in Python","volume":"4","author":"Davidson-Pilon","year":"2019","journal-title":"J Open Source Softw"},{"key":"2025101607372945400_btaf546-B8","doi-asserted-by":"crossref","first-page":"1749","DOI":"10.1001\/jamaoncol.2019.2996","article-title":"Global, regional, and national cancer incidence, mortality, years of life lost, years lived with disability, and Disability-Adjusted Life-Years for 29 cancer groups, 1990 to 2017: a systematic analysis for the global burden of disease study","volume":"5","author":"Fitzmaurice","year":"2019","journal-title":"JAMA Oncol"},{"year":"2024","author":"GA4GH","key":"2025101607372945400_btaf546-B9"},{"year":"2024","author":"GA4GH","key":"2025101607372945400_btaf546-B10"},{"key":"2025101607372945400_btaf546-B11","doi-asserted-by":"crossref","first-page":"1109","DOI":"10.1056\/NEJMp1607591","article-title":"Toward a shared vision for cancer genomic data","volume":"375","author":"Grossman","year":"2016","journal-title":"N Engl J Med"},{"key":"2025101607372945400_btaf546-B12","doi-asserted-by":"crossref","first-page":"83","DOI":"10.3389\/fcell.2017.00083","article-title":"A comprehensive infrastructure for big data in cancer research: accelerating cancer research and precision medicine","volume":"5","author":"Hinkson","year":"2017","journal-title":"Front Cell Dev Biol"},{"year":"2025","author":"ICGC ARGO\u2014Home","key":"2025101607372945400_btaf546-B13"},{"key":"2025101607372945400_btaf546-B14","doi-asserted-by":"crossref","first-page":"817","DOI":"10.1038\/s41587-022-01357-4","article-title":"The GA4GH phenopacket schema defines a computable representation of clinical data","volume":"40","author":"Jacobsen","year":"2022","journal-title":"Nat Biotechnol"},{"key":"2025101607372945400_btaf546-B15","doi-asserted-by":"crossref","first-page":"2200016","DOI":"10.1002\/ggn2.202200016","article-title":"GA4GH phenopackets: a practical introduction","volume":"4","author":"Ladewig","year":"2023","journal-title":"Adv Genet (Hoboken)"},{"key":"2025101607372945400_btaf546-B16","doi-asserted-by":"crossref","first-page":"98","DOI":"10.1038\/s41597-019-0096-4","article-title":"Barriers to accessing public cancer genomic data","volume":"6","author":"Learned","year":"2019","journal-title":"Sci Data"},{"key":"2025101607372945400_btaf546-B17","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1186\/s12859-024-05993-2","article-title":"Pheno-Ranker: a toolkit for comparison of phenotypic data stored in GA4GH standards and beyond","volume":"25","author":"Leist","year":"2024","journal-title":"BMC Bioinformatics"},{"year":"2025","author":"National Cancer Database","key":"2025101607372945400_btaf546-B18"},{"key":"2025101607372945400_btaf546-B19","doi-asserted-by":"crossref","first-page":"6002","DOI":"10.1158\/1078-0432.CCR-09-0715","article-title":"IDH1 mutations as molecular signature and predictive factor of secondary glioblastomas","volume":"15","author":"Nobusawa","year":"2009","journal-title":"Clin Cancer Res"},{"key":"2025101607372945400_btaf546-B20","doi-asserted-by":"crossref","first-page":"1405","DOI":"10.1038\/bjc.2015.341","article-title":"Big data: the challenge for small research groups in the era of cancer genomics","volume":"113","author":"Noor","year":"2015","journal-title":"Br J Cancer"},{"key":"2025101607372945400_btaf546-B21","doi-asserted-by":"crossref","first-page":"2004","DOI":"10.1038\/nprot.2015.124","article-title":"Next-generation diagnostics and disease\u2013gene discovery with the Exomiser","volume":"10","author":"Smedley","year":"2015","journal-title":"Nat Protoc"},{"year":"2025","author":"Standardizing Cancer Variant Knowledge to Enable Precision Oncology","key":"2025101607372945400_btaf546-B22"},{"year":"2025","author":"The Cancer Genome Atlas Program (TCGA) \u2013 NCI","key":"2025101607372945400_btaf546-B23"},{"key":"2025101607372945400_btaf546-B24","doi-asserted-by":"crossref","first-page":"1388","DOI":"10.1158\/0008-5472.CAN-23-2468","article-title":"NCI cancer research data commons: resources to share key cancer data","volume":"84","author":"Wang","year":"2024","journal-title":"Cancer Res"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btaf546\/64425876\/btaf546.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf546\/64425876\/btaf546.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/41\/10\/btaf546\/64425876\/btaf546.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T11:37:41Z","timestamp":1760614661000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btaf546\/8267715"}},"subtitle":[],"editor":[{"given":"Christina","family":"Kendziorski","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,9,29]]},"references-count":24,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btaf546","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"type":"print","value":"1367-4803"},{"type":"electronic","value":"1367-4811"}],"subject":[],"published-other":{"date-parts":[[2025,10]]},"published":{"date-parts":[[2025,9,29]]},"article-number":"btaf546"}}