Research Article
Predicting Protein Interactions Using a Deep Learning Method-Stacked Sparse Autoencoder Combined with a Probabilistic Classification Vector Machine
Table 7
Performance comparison of different methods on the S. cerevisiae dataset.
| Model | Testing set | Accu (%) | Sens (%) | Prec (%) | MCC (%) |
| Guo [41] | ACC | 89.33 ± 2.67 | 89.93 ± 3.68 | 88.87 ± 6.16 | N/A | AC | 87.36 ± 1.38 | 87.30 ± 4.68 | 87.82 ± 4.33 | N/A |
| Yang [32] | Code1 | 75.08 ± 1.13 | 75.81 ± 1.20 | 74.75 ± 1.23 | N/A | Code2 | 80.04 ± 1.06 | 76.77 ± 0.69 | 82.17 ± 1.35 | N/A | Code3 | 80.41 ± 0.47 | 78.14 ± 0.90 | 81.66 ± 0.99 | N/A | Code4 | 86.15 ± 1.17 | 81.03 ± 1.74 | 90.24 ± 1.34 | N/A |
| You [74] | PCA-EELM | 87.00 ± 0.29 | 86.15 ± 0.43 | 87.59 ± 0.32 | 77.36 ± 0.44 |
| Wong [75] | PR-LPQ + RF | 93.92 ± 0.36 | 91.10 ± 0.31 | 96.45 ± 0.45 | 88.56 ± 0.63 |
| Proposed method | PCVM | 96.55 ± 0.2 | 97.23 ± 0.3 | 95.84 ± 0.5 | 93.25 ± 0.3 |
|
|