Table 3 Open in new tab Comparison... | Oxford Academic

Table 3

Open in new tab

Comparison results of the proposed GAE-LGA and other deep learning methods on datasets NPInter, LncTarD and LncRNA2Targe under the same experimental setup

Method	NPInter				LncTarD				LncRNA2Targe
	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC
GAE-LGA	0.9743	0.6730	0.8468	0.7262	0.9308	0.6345	0.8831	0.6123	0.8956	0.5295	0.7787	0.7871
DeepLGP	0.9218	0.6013	0.7526	0.7216	0.9196	0.6501	0.7508	0.6102	0.8657	0.5058	0.7582	0.7815
CNN	0.9102	0.5961	0.8197	0.7135	0.9103	0.6254	0.8003	0.6025	0.8802	0.5062	0.7713	0.7658
Autoencoder	0.9013	0.5936	0.7761	0.6897	0.9042	0.6188	0.7952	0.5901	0.8752	0.5108	0.7652	0.7726
Autoencoder+CNN	0.9205	0.6009	0.8453	0.7258	0.9158	0.6291	0.8527	0.6136	0.8865	0.5163	0.7738	0.7829

Method	NPInter				LncTarD				LncRNA2Targe
	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC
GAE-LGA	0.9743	0.6730	0.8468	0.7262	0.9308	0.6345	0.8831	0.6123	0.8956	0.5295	0.7787	0.7871
DeepLGP	0.9218	0.6013	0.7526	0.7216	0.9196	0.6501	0.7508	0.6102	0.8657	0.5058	0.7582	0.7815
CNN	0.9102	0.5961	0.8197	0.7135	0.9103	0.6254	0.8003	0.6025	0.8802	0.5062	0.7713	0.7658
Autoencoder	0.9013	0.5936	0.7761	0.6897	0.9042	0.6188	0.7952	0.5901	0.8752	0.5108	0.7652	0.7726
Autoencoder+CNN	0.9205	0.6009	0.8453	0.7258	0.9158	0.6291	0.8527	0.6136	0.8865	0.5163	0.7738	0.7829

Note: The bold value corresponds to the best performance method for each metric.

Table 3

Open in new tab

Comparison results of the proposed GAE-LGA and other deep learning methods on datasets NPInter, LncTarD and LncRNA2Targe under the same experimental setup

Method	NPInter				LncTarD				LncRNA2Targe
	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC
GAE-LGA	0.9743	0.6730	0.8468	0.7262	0.9308	0.6345	0.8831	0.6123	0.8956	0.5295	0.7787	0.7871
DeepLGP	0.9218	0.6013	0.7526	0.7216	0.9196	0.6501	0.7508	0.6102	0.8657	0.5058	0.7582	0.7815
CNN	0.9102	0.5961	0.8197	0.7135	0.9103	0.6254	0.8003	0.6025	0.8802	0.5062	0.7713	0.7658
Autoencoder	0.9013	0.5936	0.7761	0.6897	0.9042	0.6188	0.7952	0.5901	0.8752	0.5108	0.7652	0.7726
Autoencoder+CNN	0.9205	0.6009	0.8453	0.7258	0.9158	0.6291	0.8527	0.6136	0.8865	0.5163	0.7738	0.7829

Method	NPInter				LncTarD				LncRNA2Targe
	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC	AUC	AUPR	F1-score	MCC
GAE-LGA	0.9743	0.6730	0.8468	0.7262	0.9308	0.6345	0.8831	0.6123	0.8956	0.5295	0.7787	0.7871
DeepLGP	0.9218	0.6013	0.7526	0.7216	0.9196	0.6501	0.7508	0.6102	0.8657	0.5058	0.7582	0.7815
CNN	0.9102	0.5961	0.8197	0.7135	0.9103	0.6254	0.8003	0.6025	0.8802	0.5062	0.7713	0.7658
Autoencoder	0.9013	0.5936	0.7761	0.6897	0.9042	0.6188	0.7952	0.5901	0.8752	0.5108	0.7652	0.7726
Autoencoder+CNN	0.9205	0.6009	0.8453	0.7258	0.9158	0.6291	0.8527	0.6136	0.8865	0.5163	0.7738	0.7829

Note: The bold value corresponds to the best performance method for each metric.