Skip to main content
Fig. 1 | Algorithms for Molecular Biology

Fig. 1

From: Identification of donor splice sites using support vector machine: a computational approach based on positional, compositional and dependency features

Fig. 1

a ROC curves of SVM with linear, polynomial, sigmoid and RBF kernels in fivefold of the cross validation b Bar plots of AUC-ROC values for SVM with RBF kernel for different values of gamma (shown over each bar) in fivefold of the cross validation. SVM with polynomial and RBF kernels performed almost equally. Further, it can be seen that the AUC-ROC value of SVM with RBF kernel almost stabilized after 0.2 (value of gamma) in all the fivefold of the cross validation

Back to article page