Table 3 The evaluation indicators of MHXGMDA with different classifiers on VG-DATA.

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

Classifier

AUC

PRC

F1-Score

Accuracy

Recall

Specificity

Precision

XGBoost

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

SVM

0.9550±0.0023

0.9495±0.0028

0.8901±0.0043

0.8829±0.0051

0.9434±0.0206

0.8322±0.0230

0.8521±0.0178

RF

0.9540±0.0042

0.9479±0.0064

0.8873±0.0076

0.8814±0.0107

0.9116±0.0172

0.8456±0.0331

0.8568±0.0246

KNN

0.9533±0.0049

0.9459±0.0083

0.8877±0.0059

0.8838±0.0069

0.9219±0.0091

0.8418±0.0195

0.8549±0.0140

LR

0.9445±0.0041

0.9380±0.0073

0.8789±0.0046

0.8753±0.0060

0.9107±0.0131

0.8378±0.0206

0.8475±0.0162

DT

0.9425±0.0061

0.8931±0.0534

0.8724±0.0133

0.8677±0.0149

0.9048±0.0262

0.8250±0.0351

0.8409±0.0202

NB

0.8251±0.0510

0.8648±0.0249

0.8310±0.0219

0.8110±0.0390

0.9221±0.0412

0.6997±0.1202

0.7621±0.0646

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