Table 5

Prediction accuracy of the proposed PBF11CBF-PSSE for four datasets and comparison with the competing prediction methods
Dataset Method Prediction accuracy (%)
All-α All-β α/β α+β Overall
25PDB RKS-PPSC [42] 92.8 83.3 85.8 70.1 82.9
Liu and Jia [26] 92.6 81.3 81.5 76.0 82.9
Zhang et al. [27] 95.0 85.6 81.5 73.2 83.9
Ding et al. [42] 95.03 81.26 83.24 77.55 84.34
Proposed PBF11CBF-PSSE 98.65 85.78 79.19 79.82 86.25
640 RKS-PPSC [41] 89.1 85.1 88.1 71.4 83.1
Ding et al. [42] 94.93 76.62 89.27 74.27 83.44
Proposed PBF11CBF-PSSE 97.1 81.17 89.27 79.53 86.41
FC699 Liu and Jia [26] 97.7 88.0 89.1 84.2 89.6
Proposed PBF11CBF-PSSE 100 97.03 96.55 73.17 94.99
1189 RKS-PPSC [41] 89.2 86.7 82.6 65.6 81.3
Zhang et al. [27] 92.4 87.4 82.0 71.0 83.2
Ding et al. [42] 93.72 84.01 83.53 66.39 81.96
Proposed PBF11CBF-PSSE 97.76 86.39 84.73 70.54 84.71

The accuracy of each class and overall accuracy of the proposed PBF11CBF-PSSE for four datasets, and comparison with the competing prediction methods based on protein prediction secondary structures.

Dai et al.

Dai et al. BMC Bioinformatics 2013 14:152   doi:10.1186/1471-2105-14-152

Open Data