Table 5 Performance of MHXGMDA with other seven models on VG-DATA.

From: A method for miRNA-disease association prediction using machine learning decoding of multi-layer heterogeneous graph Transformer encoded representations

Model

AUC

PRC

F1-Score

Accuracy

Recall

Specificity

Precision

Time (s)

CGHCN

0.8980±0.0055

0.8953±0.0032

0.8311±0.0060

0.8228±0.0097

0.8718±0.0144

0.7746±0.0193

0.7950±0.0185

0.0074

VGAMF

0.9283±0.0024

0.9294±0.0019

0.8586±0.0026

0.8678±0.0254

0.8881±0.0289

0.8075±0.0517

0.8390±0.0330

0.0428

HFHLMDA

0.9346±0.0056

0.9339±0.0095

0.8660±0.0082

0.8620±0.0110

0.8933±0.0167

0.8310±0.0125

0.8407±0.0116

104.8440

MINIMDA

0.9371±0.0090

0.8680±0.0125

0.8656±0.0152

0.8835±0.0090

0.8477±0.0189

0.8530±0.0110

0.8455±0.0244

0.1937

AMHMDA

0.9375±0.0071

0.9349±0.0068

0.8675±0.0045

0.8610±0.0127

0.9086±0.0097

0.8131±0.0101

0.8305±0.0107

0.2231

GATECDA

0.9411±0.0075

0.9413±0.0082

0.8716±0.0074

0.8694±0.0087

0.8873±0.0131

0.8510±0.0096

0.8569±0.0236

1.6756

MGADAE

0.9456±0.0032

0.9459±0.0061

0.8772±0.0080

0.8743±0.0091

0.8978±0.0113

0.8509±0.0101

0.8582±0.0198

0.1084

MHXGMDA

0.9594±0.0034

0.9539±0.0040

0.8938±0.0056

0.8899±0.0064

0.9256±0.0106

0.8520±0.0200

0.8613±0.0166

0.1530

  1. The optimal values of evaluation indicators are in bold.
Back to article page