A scalable and portable framework for massively parallel variable selection in genetic association studies
Author:
Open Access
- 11 January 2012
- journal article
- research article
- Published by Oxford University Press (OUP) in Bioinformatics
- Vol. 28 (5) , 719-720
Abstract
Summary: The deluge of data emerging from high-throughput sequencing technologies poses large analytical challenges when testing for association to disease. We introduce a scalable framework for variable selection, implemented in C++ and OpenCL, that fits regularized regression across multiple Graphics Processing Units. Open source code and documentation can be found at a Google Code repository under the URL http://bioinformatics.oxfordjournals.org/content/early/2012/01/10/bioinformatics.bts015. Contact:gary.k.chen@usc.edu Supplementary information: Supplementary data are available at Bioinformatics online.Keywords
This publication has 8 references indexed in Scilit:
- Genome-wide association study identifies new prostate cancer susceptibility lociHuman Molecular Genetics, 2011
- Genome-wide association study of prostate cancer in men of African ancestry identifies a susceptibility locus at 17q21Nature Genetics, 2011
- Association screening of common and rare genetic variants by penalized regressionBioinformatics, 2010
- Stability SelectionJournal of the Royal Statistical Society Series B: Statistical Methodology, 2010
- Regularization Paths for Generalized Linear Models via Coordinate Descent2010
- A genome-wide association study of breast and prostate cancer in the NHLBI's Framingham Heart StudyBMC Medical Genetics, 2007
- Least angle regressionThe Annals of Statistics, 2004
- Regression Shrinkage and Selection Via the LassoJournal of the Royal Statistical Society Series B: Statistical Methodology, 1996