Table 8 Ablation experiment results on different network architectures of MHXGMDA on DA-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

MHXGMDA-w/o Linear

0.9591±0.0046

0.9527±0.0053

0.8968±0.0047

0.8912±0.0041

0.9356±0.0165

0.8340±0.0167

0.8483±0.0117

MHXGMDA-w/o Last

0.9601±0.0033

0.9541±0.0058

0.8964±0.0051

0.8906±0.0045

0.9437±0.0176

0.8384±0.0253

0.8506±0.0190

MHXGMDA-used HAN

0.9601±0.0041

0.9536±0.0052

0.8981±0.0079

0.8929±0.0076

0.9395±0.0083

0.8568±0.0100

0.8625±0.0149

MHXGMDA

0.9601±0.0040

0.9545±0.0058

0.8988±0.0058

0.8937±0.0058

0.9489±0.0148

0.8381±0.0168

0.8574±0.0116

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