Table 1 A full list of features used in building classification models

Amino acid composition

Amino acid composition (AAC)

–

1

Enhanced amino acid composition (EAAC)

1

10

Composition of k-spaced amino acid pairs (CKSAAP)

8

4

Dipeptide composition (DPC)

3

1

Tripeptide composition (TPC)

41

6

Grouped amino acid composition

Grouped amino acid composition (GAAC)

1

2

Enhanced grouped amino acid composition (EGAAC)

–

10

Composition of k-spaced amino acid group pairs (CKSAAGP)

6

18

Grouped dipeptide composition (GDPC)

2

2

Grouped tripeptide composition (GTPC)

–

1

C/T/D

Composition (CTD-C)

1

11

Distribution (CTD-D)

–

1

Transition (CTD-T)

–

11

Conjoint Triad

Conjoint Triad (C-Triad)

2

2

Conjoint k-spaced Triad (CKS-Triad)

2

2

Quasi-sequence-order

Sequence-order-coupling number (SOC-Number)

–

2

Quasi-sequence-order descriptors (QS-Order)

1

4

Pseudo-amino acid composition

Pseudo-amino acid composition (PAAC)

1

1

Amphiphilic PAAC (APAAC)

1

-

Autocorrelation

Normalized Moreau-Broto (NM-Broto)

–

–

Moran

1

–

Geary

1

–

Binary

Binary

3

5

AA-index

AA-index

64

52

BLOSUM62

BLOSUM62 matrix

–

4

Z-scale

Z-scale

1

–