Table 4.

Comparison with other feature representation algorithms.

Dataset-S51	Acc	Sn	Sp	MCC	Dataset-H41	Acc	Sn	Sp	MCC
RFH	0.7295	0.7582	0.7008	0.4598	RFH	0.9097	0.8195	1	0.8332
PseDNC	0.64	0.6993	0.5807	0.282	PseDNC	0.6956	0.5973	0.7938	0.3989
PCP	0.627	0.6389	0.6151	0.2541	PCP	0.6447	0.6177	0.6717	0.2898
KNN	0.7131	0.6917	0.7345	0.4266	KNN	0.8235	0.7363	0.9106	0.657
AthMethPre	0.7536	0.7605	0.7467	0.5073	AthMethPre	0.9071	0.8142	1	0.8286
Our features	0.7425	0.7521	0.733	0.4852	Our features	0.9102	0.8204	1	0.8339
Dataset-M41	Acc	Sn	Sp	MCC	Dataset-A101	Acc	Sn	Sp	MCC
RFH	0.8903	0.7848	0.9959	0.7987	RFH	0.7993	0.7705	0.8281	0.5996
PseDNC	0.6228	0.6386	0.6069	0.2456	PseDNC	0.8138	0.8057	0.8219	0.6277
PCP	0.6166	0.5669	0.6662	0.2343	PCP	0.8257	0.8281	0.8233	0.6514
KNN	0.8283	0.7448	0.9117	0.6659	KNN	0.8238	0.8462	0.8014	0.6483
AthMethPre	0.8897	0.7793	1	0.799	AthMethPre	0.85	0.85	0.85	0.7
Our features	0.8924	0.789	0.9959	0.8022	Our features	0.8105	0.8067	0.8143	0.6210