Table 9 Results of the experimental comparison between the proposed MODAS method and competing structural class prediction methods on the D675 dataset.
Classifier used (name of the method, if any) | Feature vector | Reference | Accuracy | ||||
|---|---|---|---|---|---|---|---|
|  |  |  | α | β | α/β | α+β | overall |
Bayesian classifier | AA composition | 81 | 53.5 | 42.3 | 68.3 | 28.3 | 48.0 |
IB1 | PSI Blast based collocated AA pairs | 75 | 54.9 | 47.4 | 68.9 | 35.0 | 51.5 |
SVM with RBF kernel (SCEC) | PSI Blast based collocated AA pairs | 75 | 74.3 | 59.6 | 79.7 | 34.5 | 61.5 |
SVM with RBF kernel (SCPRED) | custom | 79 | 89.1 | 81.8 | 90.4 | 58.2 | 79.5 |
SVM with polynomial or RBF kernels (MODAS) | custom | this paper | 89.9 | 81.8 | 84.2 | 65.9 | 80.0 |