Table 7. The training performance of CNN_4 on the GWH dataset with different window sizes.

The training performance on the GWH dataset with different window sizes were collected from 5-fold cross-validation. The average values of each evaluation matrix are shown.

Site	Window size (nt)	Model
		CNN_4
		AUPRC	Precision	Recall	MCC
Donor	40	0.924	0.848	0.890	0.849
	80	0.933	0.871	0.894	0.866
	160	0.948	0.886	0.908	0.882
	240	0.951	0.888	0.916	0.888
	398	0.951	0.888	0.918	0.889
Acceptor	40	0.846	0.774	0.788	0.749
	80	0.890	0.818	0.834	0.801
	160	0.922	0.856	0.860	0.838
	240	0.933	0.880	0.870	0.857
	398	0.938	0.886	0.880	0.867

Notes.

Bold styling emphasizes the highest values regarding the evaluation metrics used in the study.