Skip to main content

Table 2 The AUCs, AUPRs, accuracy and F1-scores achieved by compared methods based on MDAD under fivefold CV

From: GACNNMDA: a computational model for predicting potential human microbe-drug associations based on graph attention network and CNN-based classifier

Methods

AUC

AUPR

Accuracy

F1-score

HMDAKATZ

0.8712 ± 0.0010

0.2327 ± 0.0068

0.9774

0.3546

GCNMDA

0.9427 ± 0.0002

0.9133 ± 0.0031

0.9905

0.6672

EGATMDA

0.9585 ± 0.0053

0.9268 ± 0.0142

0.9081

0.6871

Graph2MDA

0.9567 ± 0.0039

0.9380 ± 0.0098

0.9934

0.7091

LAGCN

0.8533 ± 0.0070

0.3571 ± 0.0051

0.9413

0.0423

NTSHMDA

0.8483 ± 0.0020

0.1892 ± 0.0056

0.9896

0.1838

GACNNMDA

0.9777 ± 0.0109

0.7015 ± 0.0366

0.9945

0.7091

  1. Bold values indicate the best results achieved by all these competitive methods
Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us