{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T21:42:24Z","timestamp":1781732544746,"version":"3.54.5"},"reference-count":8,"publisher":"Oxford University Press (OUP)","issue":"1","license":[{"start":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T00:00:00Z","timestamp":1705017600000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100008730","name":"Norwegian Cancer Society","doi-asserted-by":"publisher","award":["216137"],"award-info":[{"award-number":["216137"]}],"id":[{"id":"10.13039\/100008730","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,2]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:sec>\n                  <jats:title>Motivation<\/jats:title>\n                  <jats:p>methyLImp, a method we recently introduced for the missing value estimation of DNA methylation data, has demonstrated competitive performance in data imputation compared to the existing, general-purpose, approaches. However, imputation running time was considerably long and unfeasible in case of large datasets with numerous missing values.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Results<\/jats:title>\n                  <jats:p>methyLImp2 made possible computations that were previously unfeasible. We achieved this by introducing two important modifications that have significantly reduced the original running time without sacrificing prediction performance. First, we implemented a chromosome-wise parallel version of methyLImp. This parallelization reduced the runtime by several 10-fold in our experiments. Then, to handle large datasets, we also introduced a mini-batch approach that uses only a subset of the samples for the imputation. Thus, it further reduces the running time from days to hours or even minutes in large datasets.<\/jats:p>\n               <\/jats:sec>\n               <jats:sec>\n                  <jats:title>Availability and implementation<\/jats:title>\n                  <jats:p>The R package methyLImp2 is under review for Bioconductor. It is currently freely available on Github https:\/\/github.com\/annaplaksienko\/methyLImp2.<\/jats:p>\n               <\/jats:sec>","DOI":"10.1093\/bioinformatics\/btae001","type":"journal-article","created":{"date-parts":[[2024,1,12]],"date-time":"2024-01-12T06:04:48Z","timestamp":1705039488000},"source":"Crossref","is-referenced-by-count":12,"title":["methyLImp2: faster missing value estimation for DNA methylation data"],"prefix":"10.1093","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9607-057X","authenticated-orcid":false,"given":"Anna","family":"Plaksienko","sequence":"first","affiliation":[{"name":"Oslo Centre for Biostatistics and Epidemiology, Department of Biostatistics, University of Oslo , Oslo 0317, Norway"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1838-8918","authenticated-orcid":false,"given":"Pietro","family":"Di Lena","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, University of Bologna , Bologna 40126, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7601-321X","authenticated-orcid":false,"given":"Christine","family":"Nardini","sequence":"additional","affiliation":[{"name":"Institute for Applied Mathematics (IAC) \u201cMauro Picone\u201d, National Research Council (CNR) Rome , Rome 00185, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8350-8464","authenticated-orcid":false,"given":"Claudia","family":"Angelini","sequence":"additional","affiliation":[{"name":"Institute for Applied Mathematics (IAC) \u201cMauro Picone\u201d, National Research Council (CNR) Naples , Naples 80131, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"286","published-online":{"date-parts":[[2024,1,11]]},"reference":[{"key":"2024021216484810900_btae001-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":"2024021216484810900_btae001-B2","doi-asserted-by":"crossref","first-page":"3786","DOI":"10.1093\/bioinformatics\/btz134","article-title":"Missing value estimation methods for DNA methylation data","volume":"35","author":"Di Lena","year":"2019","journal-title":"Bioinformatics"},{"key":"2024021216484810900_btae001-B3","doi-asserted-by":"crossref","first-page":"268","DOI":"10.1186\/s12859-020-03592-5","article-title":"Methylation data imputation performances under different representations and missingness patterns","volume":"21","author":"Lena","year":"2020","journal-title":"BMC Bioinformatics"},{"key":"2024021216484810900_btae001-B4","doi-asserted-by":"crossref","first-page":"e1008625","DOI":"10.1371\/journal.pcbi.1008625","article-title":"Fast clustering for single cell data using mini-batch k-means","volume":"17","author":"Hicks","year":"2021","journal-title":"PLoS Comput Biol"},{"key":"2024021216484810900_btae001-B5","author":"Morgan","year":"2023"},{"key":"2024021216484810900_btae001-B6","author":"Schafer","year":"2021"},{"key":"2024021216484810900_btae001-B7","first-page":"1177","author":"Sculley","year":"2010"},{"key":"2024021216484810900_btae001-B8","doi-asserted-by":"crossref","first-page":"e1000438","DOI":"10.1371\/journal.pgen.1000438","article-title":"DNA methylation analysis of chromosome 21 gene promoters at single base pair and single allele resolution","volume":"5","author":"Zhang","year":"2009","journal-title":"PLoS Genet"}],"container-title":["Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/1\/btae001\/56664429\/btae001.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/advance-article-pdf\/doi\/10.1093\/bioinformatics\/btae001\/55520221\/btae001.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article-pdf\/40\/1\/btae001\/56664429\/btae001.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,12]],"date-time":"2024-02-12T16:49:04Z","timestamp":1707756544000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/bioinformatics\/article\/doi\/10.1093\/bioinformatics\/btae001\/7517106"}},"subtitle":[],"editor":[{"given":"Macha","family":"Nikolski","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,1,1]]},"references-count":8,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1,2]]}},"URL":"https:\/\/doi.org\/10.1093\/bioinformatics\/btae001","relation":{},"ISSN":["1367-4803","1367-4811"],"issn-type":[{"value":"1367-4803","type":"print"},{"value":"1367-4811","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2024,1,1]]},"published":{"date-parts":[[2024,1,1]]},"article-number":"btae001"}}