Skip to main content

Table 3 AUPRs 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

0.9054

0.8431

0.8216

0.6999

0.8321

Fold 2

0.9214

0.8189

0.8200

0.7287

0.8240

Fold 3

0.9502

0.8302

0.8120

0.7398

0.8258

Fold 4

0.9046

0.8334

0.8205

0.7301

0.8377

Fold 5

0.9246

0.8024

0.8261

0.7119

0.8387

Mean

0.9212

0.8256

0.8200

0.7220

0.8317

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us