Skip to main content

Table 3 Performance of new feature representations over the ten-fold cross-validation and independent tests

From: M3S-GRPred: a novel ensemble learning approach for the interpretable prediction of glucocorticoid receptor antagonists using a multi-step stacking strategy

Evaluation strategy

Feature

ACC

BACC

SN

SP

MCC

AUC

Cross-validation

PFV

0.900

0.903

0.908

0.898

0.713

0.965

 

PFV_FS

0.898

0.900

0.903

0.897

0.708

0.964

Independent test

PFV

0.862

0.882

0.913

0.851

0.643

0.944

 

PFV_FS

0.867

0.891

0.928

0.854

0.658

0.953