Prediction of pandemic risk for animal-origin coronavirus using a deep learning method

Table 2 Prediction performance of CCSI-DL-specific model for pandemic risk

Train\Test	MERS-CoV		HCoV-OC43		HCoV-NL63		HCoV-229E		HCoV-HKU1		SARS-CoV
Train\Test	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR	AUROC	AUPR
MERS-CoV	1	1	0.566	0.474	0.335	0.375	0.503	0.441	0.03	0.333	0.984	0.942
HCoV-OC43	0.066	0.328	1	1	1	1	0.528	0.454	0.943	0.896	0.331	0.396
HCoV-NL63	0.262	0.375	1	1	1	1	0.644	0.523	0.895	0.815	0.549	0.488
HCoV-229E	0.516	0.471	0.917	0.808	0.995	0.995	1	1	0.173	0.366	0.79	0.645
HCoV-HKU1	0.432	0.436	0.914	0.924	1	1	0.66	0.534	1	1	0.621	0.536
SARS-CoV	1	1	0.946	0.887	0.96	0.881	0.863	0.734	1	1	1	1

AUROC area under the receiver operating characteristic curve, AUPR area under precision–recall curve, CCSI-DL coronavirus cross-species infection with deep learning