Table 6.

Comparison of the Se, Sp, ACC and MCC between four traditional models and sequence information model on Dataset 2

Membrane protein types	Index	AAC	DipC	TipC	PseAAC	Our model
	Se	0.6571	0.5306	0.3388	0.6898	0.8408
Type I	Sp	0.9384	0.9643	0.9824	0.9440	0.9806
	ACC	0.9193	0.9348	0.9387	0.9267	0.9711
	MCC	0.4951	0.4903	0.4156	0.5341	0.7841
	Se	0.1139	0.0	0.0	0.0633	0.7468
Type II	Sp	0.9901	1.0	1.0	0.9889	0.9739
	ACC	0.9709	0.9781	0.9781	0.9686	0.9689
	MCC	0.1387	0.0	0.0	0.0696	0.5267
	Se	0.0	0.0	0.0	0.0	0.0
Type III	Sp	1.0	1.0	1.0	1.0	1.0
	ACC	0.9975	0.9975	0.9975	0.9975	0.9975
	MCC	0.0	0.0	0.0	0.0	0.0
	Se	0.0	0.0	0.0	0.0	0.7647
Type IV	Sp	1.0	1.0	1.0	1.0	0.9958
	ACC	0.9953	0.9953	0.9953	0.9953	0.9947
	MCC	0.0	0.0	0.0	0.0	0.5935
	Se	0.8721	0.9290	0.9617	0.8709	0.9157
Mutipass	Sp	0.8526	0.7105	0.4885	0.8588	0.9813
	ACC	0.8660	0.8607	0.8138	0.8671	0.9362
	MCC	0.7022	0.6669	0.5442	0.7058	0.8638
	Se	0.0556	0.0	0.0	0.0278	0.0
Lipid-chain-anchored	Sp	1.0	1.0	1.0	1.0	0.9983
	ACC	0.9906	0.9900	0.9900	0.9903	0.9883
	MCC	0.2346	0.0	0.0	0.1659	-0.0041
	Se	0.3659	0.0488	0.0	0.3659	0.9024
GPI-anchored	Sp	0.9986	1.0	1.0	0.9941	0.9938
	ACC	0.9914	0.9892	0.9886	0.9870	0.9928
	MCC	0.5203	0.2197	0.0	0.3839	0.7490
	Se	0.7425	0.6881	0.5451	0.7797	0.9013
Peripheral	Sp	0.8885	0.9164	0.9580	0.8954	0.9418
	ACC	0.8602	0.8721	0.8779	0.8729	0.9340
	MCC	0.5893	0.5965	0.5740	0.6290	0.8025

Note: Best performing method in bold.