Recombination Hotspot/Coldspot Identification Combining Three Different Pseudocomponents via an Ensemble Learning Approach

Table 2

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

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

The parameters used are for SVM-Kmer and and for LIBSVM [18].
The parameters used are for SVM-DACC and and for LIBSVM [18].
The parameters used are and for SVM-PseDNC and and for LIBSVM [18].