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

Figure 5

The comparison of different predictors for hotspots/coldspots identification. The areas under ROC curves (AUC) of SVM-EL, SVM-DACC, SVM-Kmer, and SVM-PseDNC are 0.91, 0.90, 0.89, and 0.87, respectively.