Skip to main content

Table 2 Prediction performance for different patch types.

From: Exploiting structural and topological information to improve prediction of RNA-protein binding sites

Classifier Patch type AUC δ 95 MCC SN[%] SP[%]
NB sequential 0.77 0.016 0.30 73.6 66.8
NB topological 0.78 0.016 0.31 75.4 65.7
NB spatial 0.79 0.016 0.32 75.4 67.1
SVM sequential 0.79 0.021 0.34 78.4 65.8
SVM topological 0.80 0.021 0.34 79.9 64.4
SVM spatial 0.80 0.021 0.36 80.0 65.6
  1. Prediction performance for different patch types (sequential, topological, spatial) and classifiers (NB, SVM) on RB144 data set, tested by five-fold cross-validation. C-value for SVM was 1.0 and γ-value of RBF-kernel was 0.01. Cost factor was assigned as 5.7 to compensate for the unbalanced class distribution.
\