Skip to main content

Table 2 The prediction performances in 5CV,10CV and denovo validation, the best results are in the bold face

From: DDIGIP: predicting drug-drug interactions based on Gaussian interaction profile kernels

 

The prediction performances(AUC)

   

Method

Feature

5CV

10CV

Denovo

WAE

Chemical data, biological data, phenotypic data

0.9502

0.9530

0.9073

L1E

Chemical data, biological data, phenotypic data

0.9570

0.9599

∅

L2E

Chemical data, biological data, phenotypic data

0.9561

0.9594

∅

LP

Drug-sub

0.9356

0.9359

0.8993

 

Drug-Label

0.9364

0.9368

0.8994

 

Drug-Off Label

0.9374

0.9378

0.8997

DDIGIP

Chemical data, biological data, phenotypic data

0.9600

0.9636

0.9262

  1. The ∅ represents that we did not compute the prediction performance because the prediction limit for new drugs.
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us