Table 3.

The performance of different kinds of feature descriptors in non-redundant dataset by SVM method

Features	ACC	SN	SP	AUC	MCC	F1
OAAC	0.802	0.801	0.811	0.858	0.505	0.870
Dipeptide = 0	0.797	0.798	0.795	0.870	0.490	0.867
Dipeptide = 1	0.810	0.814	0.791	0.884	0.506	0.877
Dipeptide = 2	0.792	0.801	0.750	0.859	0.459	0.865
AAindex	0.792	0.795	0.779	0.857	0.473	0.864
PSSM	0.795	0.797	0.790	0.863	0.484	0.866
All features	0.860	0.863	0.845	0.923	0.615	0.911