Optimization of a parallel permutation testing function for the SPRINT R package

Savvas Petrou; Terence Sloan; Muriel Mewissen; Thorsten Forster; Michal Piotrowski; Bartosz Dobrzelecki

doi:10.1145/1851476.1851551

Optimization of a parallel permutation testing function for the SPRINT R package

Savvas Petrou, Terence Sloan, Muriel Mewissen, Thorsten Forster, Michal Piotrowski, Bartosz Dobrzelecki

Research output: Contribution to conference › Paper › peer-review

Abstract / Description of output

The statistical language R and Bioconductor package are
favoured by many biostatisticians for processing microarray
data. The amount of data produced by these analyses has
reached the limits of many common bioinformatics computing
infrastructures. High Performance Computing (HPC)
systems offer a solution to this issue. The Simple Parallel R
INTerface (SPRINT) is a package that provides biostatisticians
with easy access to HPC systems and allows the addition
of parallelized functions to R. This paper will present
how we added a parallelized permutation testing function
in R using SPRINT and how this function performs on a
supercomputer for executions of up to 512 processes.

Original language	English
Pages	516-521
Number of pages	6
DOIs	https://doi.org/10.1145/1851476.1851551
Publication status	Published - 1 Jan 2010
Event	19th ACM International Symposium on High Performance Distributed Computing - Chicago, United States Duration: 20 Jun 2010 → 25 Jun 2010

Conference

Conference	19th ACM International Symposium on High Performance Distributed Computing
Country/Territory	United States
City	Chicago
Period	20/06/10 → 25/06/10

Access to Document

10.1145/1851476.1851551

sprint_hpdc_2010
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee.
Final published version, 91.5 KB

http://portal.acm.org/citation.cfm?doid=1851476.1851551

SPRINTing with HECToR
Sloan, T., Mewissen, M. & Petrou, S.
1/10/09 → 31/03/10
Project: Awarded Facility Time
HPC Enabling of R Application Software
Sloan, T. & Ghazal, P.
UK-based charities
1/04/09 → 31/03/11
Project: Research

Cite this

@conference{0cd26306fd504c10b0890ef1bcdc7957,

title = "Optimization of a parallel permutation testing function for the SPRINT R package",

abstract = "The statistical language R and Bioconductor package arefavoured by many biostatisticians for processing microarraydata. The amount of data produced by these analyses hasreached the limits of many common bioinformatics computinginfrastructures. High Performance Computing (HPC)systems offer a solution to this issue. The Simple Parallel RINTerface (SPRINT) is a package that provides biostatisticianswith easy access to HPC systems and allows the additionof parallelized functions to R. This paper will presenthow we added a parallelized permutation testing functionin R using SPRINT and how this function performs on asupercomputer for executions of up to 512 processes.",

author = "Savvas Petrou and Terence Sloan and Muriel Mewissen and Thorsten Forster and Michal Piotrowski and Bartosz Dobrzelecki",

year = "2010",

month = jan,

day = "1",

doi = "10.1145/1851476.1851551",

language = "English",

pages = "516--521",

note = "19th ACM International Symposium on High Performance Distributed Computing ; Conference date: 20-06-2010 Through 25-06-2010",

}

TY - CONF

T1 - Optimization of a parallel permutation testing function for the SPRINT R package

AU - Petrou, Savvas

AU - Sloan, Terence

AU - Mewissen, Muriel

AU - Forster, Thorsten

AU - Piotrowski, Michal

AU - Dobrzelecki, Bartosz

PY - 2010/1/1

Y1 - 2010/1/1

N2 - The statistical language R and Bioconductor package arefavoured by many biostatisticians for processing microarraydata. The amount of data produced by these analyses hasreached the limits of many common bioinformatics computinginfrastructures. High Performance Computing (HPC)systems offer a solution to this issue. The Simple Parallel RINTerface (SPRINT) is a package that provides biostatisticianswith easy access to HPC systems and allows the additionof parallelized functions to R. This paper will presenthow we added a parallelized permutation testing functionin R using SPRINT and how this function performs on asupercomputer for executions of up to 512 processes.

AB - The statistical language R and Bioconductor package arefavoured by many biostatisticians for processing microarraydata. The amount of data produced by these analyses hasreached the limits of many common bioinformatics computinginfrastructures. High Performance Computing (HPC)systems offer a solution to this issue. The Simple Parallel RINTerface (SPRINT) is a package that provides biostatisticianswith easy access to HPC systems and allows the additionof parallelized functions to R. This paper will presenthow we added a parallelized permutation testing functionin R using SPRINT and how this function performs on asupercomputer for executions of up to 512 processes.

U2 - 10.1145/1851476.1851551

DO - 10.1145/1851476.1851551

M3 - Paper

SP - 516

EP - 521

T2 - 19th ACM International Symposium on High Performance Distributed Computing

Y2 - 20 June 2010 through 25 June 2010

ER -

Optimization of a parallel permutation testing function for the SPRINT R package

Abstract / Description of output

Conference

Access to Document

Fingerprint

Projects

SPRINTing with HECToR

HPC Enabling of R Application Software

Cite this