Fig. 2From: SEPIa, a knowledge-driven algorithm for predicting conformational B-cell epitopes from the amino acid sequencePrediction performance of the individual features F1-13 and of their combination (F), estimated by the AUC and evaluated by 10-fold cross validation of the S85 set, using a sequence window size W = 9. The bold horizontal line indicates the level of random prediction. From least to best performing: intrinsically disordered regions (F8 and F7), flexibility (F5 and F6), evolutionary information (F13), energy-like (F9), secondary structure (F4), solvent accessibility (F10 and F11), solubility (F12), hydrophilicity (F3), and amino acid composition (F1 and F2)Back to article page