gkmSVM: an R package for gapped-kmer SVM

Mahmoud Ghandi; Morteza Mohammad-Noori; Narges Ghareghani; Dongwon Lee; Levi Garraway; Michael A Beer

doi:10.1093/bioinformatics/btw203

gkmSVM: an R package for gapped-kmer SVM

Bioinformatics. 2016 Jul 15;32(14):2205-7. doi: 10.1093/bioinformatics/btw203. Epub 2016 Apr 19.

Authors

Mahmoud Ghandi¹, Morteza Mohammad-Noori², Narges Ghareghani³, Dongwon Lee⁴, Levi Garraway⁵, Michael A Beer⁶

Affiliations

¹ The Broad Institute of MIT and Harvard, Cambridge, MA, USA.
² School of Mathematics, Statistics, and Computer Science, College of Science, University of Tehran, Tehran, Iran.
³ Department of Engineering Science, College of Engineering, University of Tehran, and Institute for Research in Fundamental Sciences (IPM), Tehran, Iran.
⁴ McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University, Baltimore, MD, USA.
⁵ The Broad Institute of MIT and Harvard, Cambridge, MA, USA Dana-Farber Cancer Institute, Harvard Medical School, Boston, MA, USA.
⁶ McKusick-Nathans Institute of Genetic Medicine, Johns Hopkins University, Baltimore, MD, USA Department of Biomedical Engineering, Johns Hopkins University, Baltimore, MD, USA.

Abstract

We present a new R package for training gapped-kmer SVM classifiers for DNA and protein sequences. We describe an improved algorithm for kernel matrix calculation that speeds run time by about 2 to 5-fold over our original gkmSVM algorithm. This package supports several sequence kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.

Availability and implementation: gkmSVM package is freely available through the Comprehensive R Archive Network (CRAN), for Linux, Mac OS and Windows platforms. The C ++ implementation is available at www.beerlab.org/gkmsvm

Contact: mghandi@gmail.com or mbeer@jhu.edu

Supplementary information: Supplementary data are available at Bioinformatics online.

MeSH terms

Algorithms
Sequence Analysis, DNA / methods*
Sequence Analysis, Protein / methods*
Software*
Support Vector Machine*

Grants and funding

R01 HG007348/HG/NHGRI NIH HHS/United States