Table 7 Results of the experimental comparison between the proposed MODAS method and competing structural class prediction methods on the 25PDB dataset.
Classifier used (name of the method, if any) | Feature vector (# features) | Reference | Accuracy | MCC | GC2 | |||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|
|  |  |  | α | β | α/β | α+β | overal l | α | β | α/β | α+β |  |
SVM with 1st order polyn. kernel | autocorrelation (30) | 73 | 50.1 | 49.4 | 28.8 | 29.5 | 34.2 | 0.16 | 0.16 | 0.05 | 0.05 | 0.02 |
Multinomial logistic regression | custom dipeptides (16) | 58 | 56.2 | 44.5 | 41.3 | 18.8 | 40.2 | 0.23 | 0.20 | 0.31 | 0.06 | 0.05 |
Bagging with random tree | CV (20) | 54 | 58.7 | 47.0 | 35.5 | 24.7 | 41.8 | 0.33 | 0.26 | 0.22 | 0.06 | 0.06 |
Information discrepancy | tripeptides (8000) | 59, 60 | 45.8 | 48.5 | 51.7 | 32.5 | 44.7 | 0.39 | 0.39 | 0.25 | 0.06 | 0.11 |
LogicBoost with decision tree | CV (20) | 46 | 56.9 | 51.5 | 45.4 | 30.2 | 46.0 | 0.41 | 0.32 | 0.32 | 0.06 | 0.10 |
Information discrepancy | dipeptides (400) | 59, 60 | 59.6 | 54.2 | 47.1 | 23.5 | 47.0 | 0.46 | 0.40 | 0.24 | 0.04 | 0.12 |
LogitBoost with decision stump | CV (20) | 54 | 62.8 | 52.6 | 50.0 | 32.4 | 49.4 | 0.49 | 0.35 | 0.34 | 0.11 | 0.13 |
SVM with 3rd order polyn. kernel | CV (20) | 54 | 61.2 | 53.5 | 57.2 | 27.7 | 49.5 | 0.46 | 0.35 | 0.39 | 0.11 | 0.13 |
SVM with Gaussian kernel | CV (20) | 47 | 68.6 | 59.6 | 59.8 | 28.6 | 53.9 | 0.52 | 0.42 | 0.43 | 0.15 | 0.17 |
Multinomial logistic regression | custom (66) | 73 | 69.1 | 61.6 | 60.1 | 38.3 | 57.1 | 0.56 | 0.44 | 0.48 | 0.21 | 0.21 |
Nearest neighbor | Composition of tripeptides (8000) | 52 | 60.6 | 60.7 | 67.9 | 44.3 | 58.6 | --- | --- | --- | --- | --- |
SVM with RBF kernel | custom (34) | 72 | 69.7 | 62.1 | 67.1 | 39.3 | 59.5 | 0.60 | 0.50 | 0.53 | 0.21 | 0.25 |
Multinomial logistic regression | custom (34) | 72 | 71.1 | 65.3 | 66.5 | 37.3 | 60.0 | 0.61 | 0.51 | 0.51 | 0.22 | 0.25 |
StackingC ensemble | custom (34) | 72 | 74.6 | 67.9 | 70.2 | 32.4 | 61.3 | 0.62 | 0.53 | 0.55 | 0.22 | 0.26 |
Linear logistic regression | custom (58) | 30 | 75.2 | 67.5 | 62.1 | 44.0 | 62.2 | 0.63 | 0.54 | 0.54 | 0.27 | 0.27 |
SVM with 1st order polyn. kernel | custom (58) | 30 | 77.4 | 66.4 | 61.3 | 45.4 | 62.7 | 0.65 | 0.54 | 0.55 | 0.27 | 0.28 |
SVM with RBF kernel | custom (56) | 61 | 76.5 | 67.3 | 66.8 | 45.8 | 64.0 | 0.62 | 0.51 | 0.50 | 0.28 | --- |
Discriminant analysis | custom (16) | 78 | 64.3 | 65.0 | 61.7 | 65.0 | 64.0 | --- | --- | --- | --- | --- |
SVM with Gaussian kernel | custom (8 PSI Pred based) | 79 | 92.6 | 80.6 | 73.4 | 68.5 | 79.1 | 0.87 | 0.79 | 0.67 | 0.54 | 0.54 |
SVM with Gaussian kernel | PSI Pred based (13) | 79 | 92.6 | 79.8 | 74.9 | 69.0 | 79.3 | 0.87 | 0.79 | 0.68 | 0.55 | 0.55 |
SVM with RBF kernel (SCPRED) | custom (9) | 79 | 92.6 | 80.1 | 74.0 | 71.0 | 79.7 | 0.87 | 0.79 | 0.69 | 0.57 | 0.55 |
SVM with polynomial or RBF kernels (MODAS) | custom(117, 53, 46, 163) | this paper | 92.3 | 83.7 | 81.2 | 68.3 | 81.4 | 0.88 | 0.79 | 0.76 | 0.58 | 0.58 |