Skip to main content

Table 4 Performance comparison between MMPCC and SMOTE under different percentage of pseudo-negative samples

From: How to balance the bioinformatics data: pseudo-negative sampling

Percentage(%)MethodsClassifiersSen(%)Spe(%)Acc(%)MCC
10MMPCCRF17.1399.4492.460.333
  NN17.0599.2392.250.312
 SMOTERF16.0198.2791.340.235
  NN5.299.6991.680.16
20MMPCCRF17.2899.4591.840.337
  NN24.699.2292.310.405
 SMOTERF17.0798.1490.750.246
  NN8.0599.4991.160.2
30MMPCCRF18.1899.4491.290.351
  NN30.3899.1692.270.464
 SMOTERF17.6997.9590.080.25
  NN10.1699.2390.50.216
40MMPCCRF19.0999.4390.750.363
  NN35.9499.0892.260.513
 SMOTERF18.5497.889.50.258
  NN12.0799.1490.020.243
50MMPCCRF19.5699.3990.160.367
  NN38.8299.1392.150.543
 SMOTERF18.597.7288.90.258
  NN14.0599.0189.550.266