are compared. As given in Table 2, the predictive performances of three representative kinases in KinasePhos 2.0 are comparable with PredPhospho, GPS, PPSP and KinasePhos 1.0. In particular, KinasePhos 2.0 provides the predictive model for phosphohistidine, whose predictive accuracy is 93%. The overall predictive accuracy of the kinase-specific groups with at least 20 phosphorylation sites of the proposed method is 91%. However, as given in Table S4, the overall predictive accuracy of the kinase groups which are smaller than 20 experimental phosphorylation sites is 94%. Table 2.The comparison among KinasePhos 2.0, DISPHOS, PredPhospho, GPS, PPSP and KinasePhos 1.0ToolsDISPHOSPredPhosphoGPSPPSPKinasePhos 1.0KinasePhos 2.0MethodLogistic regressionSVMMCL+GPSBDTMDD+HMMCP+SVMNumber of kinases–4 groups71 groups68 groups1858Kinase PKA–Sn = 0.88Sn = 0.89Sn = 0.90Sn = 0.91Sn = 0.92Sp = 0.91Sp = 0.91Sp = 0.92Sp = 0.86Sp = 0.89Kinase PKC–Sn = 0.79Sn = 0.82Sn = 0.82Sn = 0.80Sn = 0.84Sp = 0.86Sp = 0.83Sp = 0.86Sp = 0.87Sp = 0.86Kinase CK2–Sn = 0.84Sn = 0.83Sn = 0.83Sn = 0.87Sn = 0.87Sp = 0.96Sp = 0.88Sp = 0.90Sp = 0.85Sp = 0.86SerineAcc = 0.76Acc = 0.81––Acc = 0.86Acc = 0.90ThreonineAcc = 0.81Acc = 0.77––Acc = 0.91Acc = 0.93TyrosineAcc = 0.83–––Acc = 0.84Acc = 0.88Histidine–––––Acc = 0.93Overall performance–Acc = 0.76 ∼ 0.91––Acc = 0.87Acc
