ETGPDA: identification of piRNA-disease associations based on embedding transformation graph convolutional network

Table 2 Performance comparison between ETGPDA and removing activation function \(ReLU\)

Testing set	AUC↑	Accuracy↑	Recall↑	Specificity↑
With Activation Function	0.9603	0.9551	0.8636	0.9565
Without Activation Function	0.9066	0.9397	0.8434	0.9309

ISSN: 1471-2164