Skip to main content

Table 1 The mean absolute error of different feature combinations with ResNet 5-100-3 on TS1267

From: RaptorX-Angle: real-value prediction of protein backbone dihedral angles through a hybrid method of clustering and deep learning

Feature combination Phi Psi Phi_H Psi_H Phi_E Psi_E Phi_C Psi_C
basic1=PSSM+aa 19.97 31.97 9.82 17.57 20.70 26.97 29.84 49.66
basic2=PSFM+aa 20.02 31.78 9.86 17.68 20.46 26.38 30.10 49.39
basic=PSSM+PSFM+aa 19.27 30.04 9.11 15.58 19.70 24.64 29.35 48.02
basic+ACC 19.08 29.30 9.07 15.44 19.36 23.18 29.11 47.10
basic+SS 19.19 28.73 8.56 13.76 19.29 22.43 31.00 47.95
basic+ACC+SS 18.58 27.98 8.45 13.37 19.03 22.14 28.61 46.21
  1. Phi and Psi denote MAE for all residues Phi_H and Psi_H denote MAE for residues in helix region Phi_E and Psi_E denote MAE for residues in beta strand region Phi_C and Psi_C denote MAE for residues in coil region