Skip to main content

Table 2 AUCs of HMCDA under fivefold cross validation compared with four previous models

From: HMCDA: a novel method based on the heterogeneous graph neural network and metapath for circRNA-disease associations prediction

 

HMCDA

GATCL2CD

iCircDA-MF

GCNCDA

GATNNCDA

Fold 1

0.8913

0.8322

0.8111

0.7307

0.8222

Fold 2

0.9096

0.8419

0.8095

0.7347

0.8191

Fold 3

0.9474

0.8404

0.8005

0.7389

0.8107

Fold 4

0.8977

0.8457

0.8199

0.7392

0.8270

Fold 5

0.9217

0.8104

0.8262

0.7235

0.8383

Mean

0.9135

0.83412

0.8134

0.7334

0.8234

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us