Skip to main content

Table 7 Comparison with existing PPI prediction methods on different data sets

From: Protein–protein interaction prediction based on ordinal regression and recurrent convolutional neural networks

Data set

S. cerevisiae

Homo sapiens

Methods

MAE(\(\times 10^{-2}\))

MSE(\(\times 10^{-2}\))

MAE(\(\times 10^{-2}\))

MSE(\(\times 10^{-2}\))

RF-AC

12.427

2.835

18.979

5.218

RF-CTD

12.210

2.707

18.850

5.163

XGBoost-AC

13.575

3.147

23.875

7.571

XGBoost-CTD

13.076

3.051

23.951

7.630

SVM-AC

24.466

8.025

SVM-CTD

31.174

14.435

OR-RCNN

6.131

1.155

10.476

2.543

  1. The values in each column represents the experimental results for each criterion of performance. Minimal values in each column is shown in bold