gkmSVM: an R package for gapped-kmer SVM

作     者：Ghandi, Mahmoud Mohammad-Noori, Morteza Ghareghani, Narges Lee, Dongwon Garraway, Levi Beer, Michael A. 

作者机构：Broad Inst MIT & Harvard Cambridge MA 02142 USA Univ Tehran Coll Sci Sch Math Stat & Comp Sci Tehran Iran Univ Tehran Coll Engn Dept Engn Sci Tehran Iran Inst Res Fundamental Sci IPM Tehran Iran Johns Hopkins Univ McKusick Nathans Inst Genet Med Baltimore MD USA Harvard Univ Sch Med Dana Farber Canc Inst 44 Binney St Boston MA 02115 USA Johns Hopkins Univ Dept Biomed Engn Baltimore MD USA 

出 版 物：《BIOINFORMATICS》 (生物信息学)

年 卷 期：2016年第32卷第14期

页      面：2205-2207页

核心收录：

学科分类：0710[理学-生物学] 08[工学] 0714[理学-统计学（可授理学、经济学学位）] 0836[工学-生物工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：NIH [R01 HG0007348] IPM [CS1391-4-02, 94050016] 

主　　题：AMINO acid sequence DNA sequencing KERNEL functions COMPUTER algorithms BIOLOGICAL systems 

摘      要：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 ***/gkmsvm