Skip to main content

Table 3 Comparison of classical SVM and LUPI-SVM on the external independent validation dataset with training on affinity benchmark dataset

From: Learning protein binding affinity using privileged information

 

Input features

 

2-mer

Blosum (Protein)

 

ROC

PR

S r

ROC

PR

S r

 

Classical SVM

 

0.63

0.38

− 0.28

0.61

0.39

−0.19

Privileged features

LUPI-SVM

 NIRP

0.66

0.42

−0.30

0.64

0.40

−0.28

 Moal descriptors

0.71

0.46

−0.39

0.69

0.48

−0.30

 Dias descriptors

0.65

0.41

−0.29

0.64

0.44

−0.20

 Blosum (Interface)

0.64

0.40

−0.26

0.64

0.46

−0.22

  1. Bold faced values indicate best performance for each model
  2. ROC Area under the ROC curve, PR Area under the precision-recall curve, Sr Spearman correlation coefficient
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us