Table 2.

Comparison among DeepIsoFun, mi-SVM and WLRM on different expression datasets in terms of AUC and AUPRC values

	AUC			AUPRC
Dataset method	DeepIsoFun	mi- SVM	WLRM	DeepIsoFun	mi- SVM	WLRM
Dataset#1	0.735	0.679	0.691	0.292	0.221	0.218
Dataset#2	0.729	0.667	0.658	0.246	0.209	0.182
Dataset#3	0.704	0.643	0.664	0.234	0.198	0.177

Note: The benchmark positive and negative instances of each GO term used in testing were defined by following the procedure in Eksi et al. (2013).