Table 1. Summary of the considered features, where x, x′ = {A, R, N, D, C, Q, E, G, H, I, L, K, M, F, P, S, T, W, Y, V} denotes the 20 AA types, y =  {C, H, E} denotes the three secondary structure states, h = {0.1, 0.2, 0.3, 0.4, 0.5} denotes the cutoff used to categorize the buried/exposed residues based on their relative solvent accessibility, t = {0, 25, 50, 75, 100} denotes the ratio for computing the percentile values, and m = {1, 2, 3, 4, 5, 6, 7, 8, 9, 10} denotes the lag for calculating the auto-correlation coefficients.

Category	Feature description	Abbreviation	No. of features
SS based	Content of the residues with secondary structure type y	Con_SSy	3
Average RSA based	Average RSA of the residues with AA type x	AveRSA_Resx	20
	Average RSA of the residues with secondary structure type y	AveRSA_SSy	3
	Average RSA of the residues with AA type x and secondary structure type y	AveRSA_Resx_SSy	60
Amino acid composition based	Composition of the residues with AA type x	AAC_Resx	20
	Composition of the residues with AA type x and secondary structure type y	AAC_Resx_SSy	60
	Composition of the residues with AA type x and RSA value≥h (i.e., the residueis assumed exposed)	AAC_Resx_Exh	100
	Composition of the residues with AA type x and RSA value<h (i.e., the residueis assumed buried)	AAC_Resx_Buh	100
	Composition of dipeptide with the left AA type x and right AA type x′	DIC_Resxx ′	400
PSSM score based	Average PSSM score of the residues along with the column of amino acid type x	AvePscore_AAx	20
	Average PSSM score of the residues with AA type x′ along with the column ofamino acid x in the PSSM matrix	AvePscore_AAx_Resx ′	400
	Percentile of the PSSM scores according to the percent threshold t along withthe column of amino acid x	Pscore_AAx_Pt	100
	Auto-correlation coefficient of scores with lag m along with the column ofamino acid x	AutoCC_AAx_Lagm	200