Skip to main content
. 2016 Aug 25;2016:8527435. doi: 10.1155/2016/8527435

Table 2.

Results on benchmark dataset for different predictors proposed in the current study.

Predictor Test method Se (%) Sp (%) Acc (%) MCC
SVM-Kmera Jackknife 75.92 86.29 81.59 0.628
SVM-DACCb Jackknife 76.12 87.99 82.61 0.649
SVM-PseDNCc Jackknife 72.04 90.69 82.24 0.644
SVM-EL Jackknife 76.33 88.33 82.89 0.654

aThe parameters used are k = 6 for SVM-Kmer and C = 27 and γ = 2 for LIBSVM [18].

bThe parameters used are lag = 6 for SVM-DACC and C = 23 and γ = 2−3 for LIBSVM [18].

cThe parameters used are λ = 7 and w = 0.3 for SVM-PseDNC and C = 213 and γ = 23 for LIBSVM [18].