{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T19:56:36Z","timestamp":1774727796511,"version":"3.50.1"},"reference-count":25,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2024,6,20]],"date-time":"2024-06-20T00:00:00Z","timestamp":1718841600000},"content-version":"vor","delay-in-days":1,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01HL161012"],"award-info":[{"award-number":["R01HL161012"]}],"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":["K99HL166700"],"award-info":[{"award-number":["K99HL166700"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Summary<\/jats:title>\n                  <jats:p>Genome-wide DNA methylation (DNAm) profiling is indispensable for unveiling how DNAm regulates biological pathways and individual phenotypes. However, managing and analyzing extensive DNAm data generated from large cohort studies present computational obstacles. Apache Parquet is a data file format that allows for efficient data storage, retrieval, and manipulation, alleviating computational hurdles associated with conventional row-based formats. We here introduce MethParquet, the first R package leveraging the columnar Parquet format for efficient DNAm data analysis. It can be used for data extraction, methylation risk score calculation, epigenome-wide association analyses, and other standard post-quality control tasks. The package flexibly implements diverse regression models. Via a public methylation dataset, we show the efficiency of this package in reducing running time and RAM usage in large-scale EWAS.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The MethParquet R package is publicly available on the GitHub repository https:\/\/github.com\/ZWangTen\/MethParquet. It includes a vignette and a toy dataset derived from a public resource.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae410","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T22:01:01Z","timestamp":1718748061000},"source":"Crossref","is-referenced-by-count":4,"title":["MethParquet: an R package for rapid and efficient DNA methylation association analysis adopting Apache Parquet"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4702-4681","authenticated-orcid":false,"given":"Ziqing","family":"Wang","sequence":"first","affiliation":[{"name":"Department of Medicine, Cardiovascular Institute, Beth Israel Deaconess Medical Center , Boston, MA, 02215, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Cassidy","sequence":"additional","affiliation":[{"name":"Department of Medicine, Cardiovascular Institute, Beth Israel Deaconess Medical Center , Boston, MA, 02215, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Danielle A","family":"Wallace","sequence":"additional","affiliation":[{"name":"Department of Medicine, Cardiovascular Institute, Beth Israel Deaconess Medical Center , Boston, MA, 02215, United States"},{"name":"Division of Sleep Medicine, Harvard Medical School , Boston, MA, 02115, United States"},{"name":"Division of Sleep and Circadian Disorders, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA, 02115, United States"},{"name":"Division of Sleep and Circadian Disorders, Department of Neurology, Brigham and Women\u2019s Hospital , Boston, MA, 02115, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8520-8860","authenticated-orcid":false,"given":"Tamar","family":"Sofer","sequence":"additional","affiliation":[{"name":"Department of Medicine, Cardiovascular Institute, Beth Israel Deaconess Medical Center , Boston, MA, 02215, United States"},{"name":"Division of Sleep Medicine, Harvard Medical School , Boston, MA, 02115, United States"},{"name":"Division of Sleep and Circadian Disorders, Department of Medicine, Brigham and Women\u2019s Hospital , Boston, MA, 02115, United States"},{"name":"Division of Sleep and Circadian Disorders, Department of Neurology, Brigham and Women\u2019s Hospital , Boston, MA, 02115, United States"},{"name":"Department of Biostatistics, Harvard T.H. Chan School of Public Health , Boston, MA, 02115, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2024,6,19]]},"reference":[{"key":"2024070305154821000_btae410-B1","doi-asserted-by":"crossref","first-page":"1363","DOI":"10.1093\/bioinformatics\/btu049","article-title":"Minfi: a flexible and comprehensive Bioconductor package for the analysis of Infinium DNA methylation microarrays","volume":"30","author":"Aryee","year":"2014","journal-title":"Bioinformatics"},{"key":"2024070305154821000_btae410-B2","doi-asserted-by":"crossref","first-page":"208","DOI":"10.32614\/RJ-2021-048","article-title":"A unifying framework for parallel and distributed processing in R using futures","volume":"13","author":"Bengtsson","year":"2021","journal-title":"R J"},{"key":"2024070305154821000_btae410-B3","author":"Benjamini","year":"1995"},{"key":"2024070305154821000_btae410-B4","author":"Draisma","year":"2019","journal-title":"methylSCOPA and META-methylSCOPA: Software for the Analysis and Aggregation of Epigenome-Wide Association Studies of Multiple Correlated Phenotypes"},{"key":"2024070305154821000_btae410-B5","doi-asserted-by":"crossref","first-page":"40","DOI":"10.18637\/jss.v040.i08","article-title":"Rcpp\u202f: seamless R and C++ integration","volume":"40","author":"Eddelbuettel","year":"2011","journal-title":"J Stat Soft"},{"key":"2024070305154821000_btae410-B6","volume-title":"An R Companion to Applied Regression","author":"Fox","year":"2019"},{"key":"2024070305154821000_btae410-B7","author":"Giner","year":"2016"},{"key":"2024070305154821000_btae410-B8","doi-asserted-by":"crossref","first-page":"5346","DOI":"10.1093\/bioinformatics\/btz567","article-title":"Genetic association testing using the GENESIS R\/Bioconductor package","volume":"35","author":"Gogarten","year":"2019","journal-title":"Bioinformatics"},{"key":"2024070305154821000_btae410-B9","doi-asserted-by":"crossref","first-page":"20110328","DOI":"10.1098\/rstb.2011.0328","article-title":"DNA methylation dynamics during the mammalian life cycle","volume":"368","author":"Hackett","year":"2013","journal-title":"Phil Trans R Soc B"},{"key":"2024070305154821000_btae410-B10","author":"Hillary","year":"2023"},{"key":"2024070305154821000_btae410-B11","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1080\/15592294.2019.1644879","article-title":"Methodological challenges in constructing DNA methylation risk scores","volume":"15","author":"H\u00fcls","year":"2020","journal-title":"Epigenetics"},{"key":"2024070305154821000_btae410-B12","author":"Leeper","year":"2020"},{"key":"2024070305154821000_btae410-B13","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1038\/nmeth.1681","article-title":"FaST linear mixed models for genome-wide association studies","volume":"8","author":"Lippert","year":"2011","journal-title":"Nat Methods"},{"key":"2024070305154821000_btae410-B14","author":"Quinn","year":"2017"},{"key":"2024070305154821000_btae410-B15","author":"R Core Team","year":"2023"},{"key":"2024070305154821000_btae410-B16","doi-asserted-by":"crossref","first-page":"1870","DOI":"10.1093\/bioinformatics\/btx059","article-title":"GLINT: a user-friendly toolset for the analysis of high-throughput DNA-methylation array data","volume":"33","author":"Rahmani","year":"2017","journal-title":"Bioinformatics"},{"key":"2024070305154821000_btae410-B17","author":"Richardson","year":"2023"},{"key":"2024070305154821000_btae410-B18","doi-asserted-by":"crossref","first-page":"e47","DOI":"10.1093\/nar\/gkv007","article-title":"Limma powers differential expression analyses for RNA-sequencing and microarray studies","volume":"43","author":"Ritchie","year":"2015","journal-title":"Nucleic Acids Res"},{"key":"2024070305154821000_btae410-B19","author":"Van Rossum","year":"1995"},{"key":"2024070305154821000_btae410-B20","author":"Vaughan","year":"2022"},{"key":"2024070305154821000_btae410-B21","doi-asserted-by":"crossref","DOI":"10.1007\/978-0-387-21706-2","volume-title":"Modern Applied Statistics with S. Fourth","author":"Venables","year":"2002"},{"key":"2024070305154821000_btae410-B22","author":"Wickham","year":"2023"},{"key":"2024070305154821000_btae410-B23","doi-asserted-by":"crossref","first-page":"D890","DOI":"10.1093\/nar\/gkz840","article-title":"EWAS data hub: a resource of DNA methylation array data and metadata","volume":"48","author":"Xiong","year":"2020","journal-title":"Nucleic Acids Res"},{"key":"2024070305154821000_btae410-B24","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1186\/s13072-016-0075-3","article-title":"Profiling genome-wide DNA methylation","volume":"9","author":"Yong","year":"2016","journal-title":"Epigenetics Chromatin"},{"key":"2024070305154821000_btae410-B25","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1038\/nmeth.2815","article-title":"Epigenome-wide association studies without the need for cell-type composition","volume":"11","author":"Zou","year":"2014","journal-title":"Nat Methods"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae410\/58280983\/btae410.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/7\/btae410\/58402073\/btae410.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/7\/btae410\/58402073\/btae410.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,3]],"date-time":"2024-07-03T05:40:11Z","timestamp":1719985211000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae410\/7696316"}},"subtitle":[],"editor":[{"given":"Russell","family":"Schwartz","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,6,19]]},"references-count":25,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,7,1]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae410","relation":{},"ISSN":["1367-4811"],"issn-type":[{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,7]]},"published":{"date-parts":[[2024,6,19]]},"article-number":"btae410"}}