EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

methyLImp2: faster missing value estimation for DNA methylation data

Anna Plaksienko iD, Pietro Di Lena iD, Christine Nardini iD, Claudia Angelini iD

Bioinformatics · 02.01.2024 · 40 (1)

DOI: 10.1093/bioinformatics/btae001 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Bioinformatics, online erschienen am 11.01.2024. Verfasst von Anna Plaksienko und 3 weiteren Autor:innen. Beteiligte Einrichtung: Oslo Centre for Biostatistics and Epidemiology, Department of Biostatistics, University of Oslo, Oslo 0317, Norway. Hauptthemen laut MEDLINE: DNA Methylation, Computational Biology. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 8 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Norwegian Cancer Society.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Motivation 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. Results 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. Availability and implementation The R package methyLImp2 is under review for Bioconductor. It is currently freely available on Github https://github.com/annaplaksienko/methyLImp2.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

DNA MethylationComputational Biology

Autor:innen und Institutionen

  • Oslo Centre for Biostatistics and Epidemiology, Department of Biostatistics, University of Oslo, Oslo 0317, Norway.
  • Department of Computer Science and Engineering, University of Bologna, Bologna 40126, Italy.
  • Institute for Applied Mathematics (IAC) "Mauro Picone", National Research Council (CNR) Rome, Rome 00185, Italy.
  • Institute for Applied Mathematics (IAC) "Mauro Picone", National Research Council (CNR) Naples, Naples 80131, Italy.

ORCID-Profile: Anna Plaksienko, Pietro Di Lena, Christine Nardini, Claudia Angelini

Förderung

  • Norwegian Cancer Society

Zitieren

APA

Plaksienko, A., Di Lena, P., Nardini, C., & Angelini, C. (2024). methyLImp2: faster missing value estimation for DNA methylation data. Bioinformatics, 40(1). https://doi.org/10.1093/bioinformatics/btae001

Vancouver

Plaksienko A, Di Lena P, Nardini C, Angelini C. methyLImp2: faster missing value estimation for DNA methylation data. Bioinformatics. 2024;40(1). doi:10.1093/bioinformatics/btae001

BibTeX
@article{Plaksienko2024,
  author = {Plaksienko, Anna and Di Lena, Pietro and Nardini, Christine and Angelini, Claudia},
  title = {methyLImp2: faster missing value estimation for DNA methylation data},
  journal = {Bioinformatics},
  year = {2024},
  volume = {40},
  number = {1},
  doi = {10.1093/bioinformatics/btae001}
}
Kostenlos starten →