{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,16]],"date-time":"2026-01-16T19:37:48Z","timestamp":1768592268234,"version":"3.49.0"},"reference-count":16,"publisher":"Oxford University Press (OUP)","issue":"6","license":[{"start":{"date-parts":[[2023,5,19]],"date-time":"2023-05-19T00:00:00Z","timestamp":1684454400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["5U24CA180996"],"award-info":[{"award-number":["5U24CA180996"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>The RaggedExperiment R \/ Bioconductor package provides lossless representation of disparate genomic ranges across multiple specimens or cells, in conjunction with efficient and flexible calculations of rectangular-shaped summaries for downstream analysis. Applications include statistical analysis of somatic mutations, copy number, methylation, and open chromatin data. RaggedExperiment is compatible with multimodal data analysis as a component of MultiAssayExperiment data objects, and simplifies data representation and transformation for software developers and analysts.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Motivation and Results<\/jats:title>\n                  <jats:p>Measurement of copy number, mutation, single nucleotide polymorphism, and other genomic attributes that may be stored as VCF files produce \u201cragged\u201d genomic ranges data: i.e. across different genomic coordinates in each sample. Ragged data are not rectangular or matrix-like, presenting informatics challenges for downstream statistical analyses. We present the RaggedExperiment R\/Bioconductor data structure for lossless representation of ragged genomic data, with associated reshaping tools for flexible and efficient calculation of tabular representations to support a wide range of downstream statistical analyses. We demonstrate its applicability to copy number and somatic mutation data across 33 TCGA cancer datasets.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btad330","type":"journal-article","created":{"date-parts":[[2023,5,20]],"date-time":"2023-05-20T01:36:00Z","timestamp":1684546560000},"source":"Crossref","is-referenced-by-count":1,"title":["RaggedExperiment: the missing link between genomic ranges and matrices in Bioconductor"],"prefix":"10.1093","volume":"39","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3242-0582","authenticated-orcid":false,"given":"Marcel","family":"Ramos","sequence":"first","affiliation":[{"name":"Epidemiology and Biostatistics, Graduate School of Public Health and Health Policy, City University of New York , New York, NY 10027, United States"},{"name":"Institute for Implementation Science and Population Health, City University of New York , New York, NY 10027, United States"},{"name":"Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center , Buffalo, NY 14203, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martin","family":"Morgan","sequence":"additional","affiliation":[{"name":"Biostatistics and Bioinformatics, Roswell Park Comprehensive Cancer Center , Buffalo, NY 14203, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2495-5464","authenticated-orcid":false,"given":"Ludwig","family":"Geistlinger","sequence":"additional","affiliation":[{"name":"Epidemiology and Biostatistics, Graduate School of Public Health and Health Policy, City University of New York , New York, NY 10027, United States"},{"name":"Institute for Implementation Science and Population Health, City University of New York , New York, NY 10027, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vincent J","family":"Carey","sequence":"additional","affiliation":[{"name":"Channing Division of Network Medicine, Brigham and Women\u2019s Hospital and Harvard Medical School , Boston, MA 02115, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2725-0694","authenticated-orcid":false,"given":"Levi","family":"Waldron","sequence":"additional","affiliation":[{"name":"Epidemiology and Biostatistics, Graduate School of Public Health and Health Policy, City University of New York , New York, NY 10027, United States"},{"name":"Institute for Implementation Science and Population Health, City University of New York , New York, NY 10027, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2023,5,19]]},"reference":[{"key":"2023061606244138900_btad330-B1","author":"Bates"},{"key":"2023061606244138900_btad330-B2","doi-asserted-by":"crossref","first-page":"2156","DOI":"10.1093\/bioinformatics\/btr330","article-title":"The variant call format and VCFtools","volume":"27","author":"Danecek","year":"2011","journal-title":"Bioinformatics"},{"key":"2023061606244138900_btad330-B3","doi-asserted-by":"crossref","first-page":"l1","DOI":"10.1126\/scisignal.2004088","article-title":"Integrative analysis of complex cancer genomics and clinical profiles using the cBioPortal","volume":"6","author":"Gao","year":"2013","journal-title":"Sci Signal"},{"key":"2023061606244138900_btad330-B4","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1186\/s12859-016-1455-1","article-title":"MultiDataSet: an R package for encapsulating multiple data sets with application to omic data integration","volume":"18","author":"Hernandez-Ferrer","year":"2017","journal-title":"BMC Bioinformatics"},{"key":"2023061606244138900_btad330-B5","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1038\/nmeth.3252","article-title":"Orchestrating high-throughput genomic analysis with bioconductor","volume":"12","author":"Huber","year":"2015","journal-title":"Nat Methods"},{"key":"2023061606244138900_btad330-B6","doi-asserted-by":"crossref","first-page":"2142","DOI":"10.1093\/bioinformatics\/bty062","article-title":"omicsPrint: detection of data linkage errors in multiple omics studies","volume":"34","author":"van Iterson","year":"2018","journal-title":"Bioinformatics"},{"key":"2023061606244138900_btad330-B7","doi-asserted-by":"crossref","first-page":"e1003118","DOI":"10.1371\/journal.pcbi.1003118","article-title":"Software for computing and annotating genomic ranges","volume":"9","author":"Lawrence","year":"2013","journal-title":"PLoS Comput Biol"},{"key":"2023061606244138900_btad330-B8","doi-asserted-by":"crossref","first-page":"519","DOI":"10.1038\/nmeth.3370","article-title":"G&T-seq: parallel sequencing of single-cell genomes and transcriptomes","volume":"12","author":"Macaulay","year":"2015","journal-title":"Nat Methods"},{"key":"2023061606244138900_btad330-B9","doi-asserted-by":"crossref","first-page":"1747","DOI":"10.1101\/gr.239244.118","article-title":"Maftools: efficient and comprehensive analysis of somatic variants in cancer","volume":"28","author":"Mayakonda","year":"2018","journal-title":"Genome Res"},{"key":"2023061606244138900_btad330-B10","author":"Morgan"},{"key":"2023061606244138900_btad330-B11","author":"Ramos"},{"key":"2023061606244138900_btad330-B12","doi-asserted-by":"crossref","first-page":"958","DOI":"10.1200\/CCI.19.00119","article-title":"Multiomic integration of public oncology databases in bioconductor","volume":"4","author":"Ramos","year":"2020","journal-title":"JCO Clin Cancer Inform"},{"key":"2023061606244138900_btad330-B13","doi-asserted-by":"crossref","first-page":"e39","DOI":"10.1158\/0008-5472.CAN-17-0344","article-title":"Software for the integration of multiomics experiments in bioconductor","volume":"77","author":"Ramos","year":"2017","journal-title":"Cancer Res"},{"key":"2023061606244138900_btad330-B14","author":"Ramos"},{"key":"2023061606244138900_btad330-B15","doi-asserted-by":"crossref","first-page":"e106397","DOI":"10.1371\/journal.pone.0106397","article-title":"RTCGAToolbox: a new tool for exporting TCGA firehose data","volume":"9","author":"Samur","year":"2014","journal-title":"PLoS One"},{"key":"2023061606244138900_btad330-B16","doi-asserted-by":"crossref","first-page":"972","DOI":"10.1093\/bioinformatics\/btz632","article-title":"CNVRanger: association analysis of CNVs with gene expression and quantitative phenotypes","volume":"36","author":"da Silva","year":"2020","journal-title":"Bioinformatics"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btad330\/50402317\/btad330.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad330\/50625339\/btad330.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/39\/6\/btad330\/50625339\/btad330.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T06:25:23Z","timestamp":1686896723000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btad330\/7174143"}},"subtitle":[],"editor":[{"given":"Peter","family":"Robinson","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2023,5,19]]},"references-count":16,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btad330","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2023,6,1]]},"published":{"date-parts":[[2023,5,19]]},"article-number":"btad330"}}