Skip to main content

Table 3 ROC scores

From: Phylogenetic tree information aids supervised learning for predicting protein-protein interaction based on distance matrices

Classification

Data Representation

ROC

Unsupervised (Pearson CC)

MirrorTree

0.6587

   
 

TreeSec

0.6731

   

Gaussian Kernel SVM

MirrorTree

0.7067

   
 

TreeSec

0.7436

   
 

TreeSec × 10

0.8446

   
 

TreeSec × 10 (no NJ)

0.7196

   
 

TreeSec × 10 (random tree)

0.5368

   
 

Polynomial degree

2

3

4

5

Polynomial Kernel SVM

MirrorTree

0.7212

0.5353

0.7003

0.5577

 

TreeSec

0.7196

0.5657

0.7179

0.6074

 

TreeSec × 10

0.7051

0.6426

0.7468

0.6619

 

TreeSec × 10 (no NJ)

0.6987

0.5865

0.6907

0.6554

 

TreeSec × 10 (random tree)

0.4696

0.4583

0.4503

0.5048

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us