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.

ModelTesting setAccu (%)Sens (%)Prec (%)MCC (%)

Guo [41]ACC89.33 ± 2.6789.93 ± 3.6888.87 ± 6.16N/A
AC87.36 ± 1.3887.30 ± 4.6887.82 ± 4.33N/A

Yang [32]Code175.08 ± 1.1375.81 ± 1.2074.75 ± 1.23N/A
Code280.04 ± 1.0676.77 ± 0.6982.17 ± 1.35N/A
Code380.41 ± 0.4778.14 ± 0.9081.66 ± 0.99N/A
Code486.15 ± 1.1781.03 ± 1.7490.24 ± 1.34N/A

You [74]PCA-EELM87.00 ± 0.2986.15 ± 0.4387.59 ± 0.3277.36 ± 0.44

Wong [75]PR-LPQ + RF93.92 ± 0.3691.10 ± 0.3196.45 ± 0.4588.56 ± 0.63

Proposed methodPCVM96.55 ± 0.297.23 ± 0.395.84 ± 0.593.25 ± 0.3