Research Article
Detecting Protein-Protein Interactions with a Novel Matrix-Based Protein Sequence Representation and Support Vector Machines
Table 2
Comparing the prediction performance by the proposed method and some state-of-the-art works on the yeast dataset. Here, N/A means not available.
| Model | Test set | SN (%) | PPV (%) | ACC (%) | MCC (%) |
| Proposed method | SVM | 85.74 ± 0.94 | 93.84 ± 0.98 | 90.06 ± 0.64 | 82.03 ± 1.03 |
| Guos’ work | ACC | 89.93 ± 3.68 | 88.87 ± 6.16 | 89.33 ± 2.67 | N/A | AC | 87.30 ± 4.68 | 87.82 ± 4.33 | 87.36 ± 1.38 | N/A |
| Zhous’ work | SVM + LD | 87.37 ± 0.22 | 89.50 ± 0.60 | 88.56 ± 0.33 | 77.15 ± 0.68 |
| Yangs’ work | Cod1 | 75.81 ± 1.20 | 74.75 ± 1.23 | 75.08 ± 1.13 | N/A | Cod2 | 76.77 ± 0.69 | 82.17 ± 1.35 | 80.04 ± 1.06 | N/A | Cod3 | 78.14 ± 0.90 | 81.86 ± 0.99 | 80.41 ± 0.47 | N/A | Cod4 | 81.03 ± 1.74 | 90.24 ± 1.34 | 86.15 ± 1.17 | N/A |
|
|