Summary of SVM results for different classifiers.

The table summarizes the SVM results for four different classifiers: RBPs vs. NNBPs (40 parameters), RBPs vs. NNBPs (10 top parameters), RBPs vs. NNBPs including only electrostatic patch features (34 parameters), RBP vs. large-patch NNBPs, and RBP vs. DBP. TP, true positives; TN, true negatives; FP, false positive; FN, false negatives; AUC, area under the curve. Sensitivity, specificity, accuracy, and MCC (Matthew's correlation coefficient) were calculated as described in Materials and Methods section.