Bioinformatics is challenged by the fact that traditional analysis tools have difficulty in processing large-scale data from high-throughput sequencing. The open source Apache Hadoop project, which adopts the MapReduce framework and a distributed file system, has recently given bioinformatics researchers an opportunity to achieve scalable, efficient and reliable computing performance on Linux clusters and on cloud computing services. In this article, we present MapReduce frame-based applications that can be employed in the next-generation sequencing and other biological domains. In addition, we discuss the challenges faced by this field as well as the future works on parallel computing in bioinformatics.
%0 Journal Article
%1 zou2013survey
%A Zou, Quan
%A Li, Xu-Bin
%A Jiang, Wen-Rui
%A Lin, Zi-Yu
%A Li, Gui-Lin
%A Chen, Ke
%D 2013
%J Briefings in Bioinformatics
%K bioinformatics
%T Survey of MapReduce frame operation in bioinformatics
%U http://bib.oxfordjournals.org/content/early/2013/02/07/bib.bbs088.full
%X Bioinformatics is challenged by the fact that traditional analysis tools have difficulty in processing large-scale data from high-throughput sequencing. The open source Apache Hadoop project, which adopts the MapReduce framework and a distributed file system, has recently given bioinformatics researchers an opportunity to achieve scalable, efficient and reliable computing performance on Linux clusters and on cloud computing services. In this article, we present MapReduce frame-based applications that can be employed in the next-generation sequencing and other biological domains. In addition, we discuss the challenges faced by this field as well as the future works on parallel computing in bioinformatics.
@article{zou2013survey,
abstract = {Bioinformatics is challenged by the fact that traditional analysis tools have difficulty in processing large-scale data from high-throughput sequencing. The open source Apache Hadoop project, which adopts the MapReduce framework and a distributed file system, has recently given bioinformatics researchers an opportunity to achieve scalable, efficient and reliable computing performance on Linux clusters and on cloud computing services. In this article, we present MapReduce frame-based applications that can be employed in the next-generation sequencing and other biological domains. In addition, we discuss the challenges faced by this field as well as the future works on parallel computing in bioinformatics.},
added-at = {2013-04-30T20:03:11.000+0200},
author = {Zou, Quan and Li, Xu-Bin and Jiang, Wen-Rui and Lin, Zi-Yu and Li, Gui-Lin and Chen, Ke},
biburl = {https://www.bibsonomy.org/bibtex/25d297bd5eda232ed8c4c2bfc4f0193a4/legaultdenis},
interhash = {c472fcc16c910d4432002ee8d6c1e9f9},
intrahash = {5d297bd5eda232ed8c4c2bfc4f0193a4},
journal = {Briefings in Bioinformatics},
keywords = {bioinformatics},
timestamp = {2013-04-30T20:03:11.000+0200},
title = {Survey of MapReduce frame operation in bioinformatics},
url = {http://bib.oxfordjournals.org/content/early/2013/02/07/bib.bbs088.full},
year = 2013
}