Skip to main content

Table 1 Protein descriptors commonly used for predicting protein functional families.

From: Efficacy of different protein descriptors in predicting protein functional families

Sets

Descriptor-sets

No. of descriptors (properties)

No. of components

Type

Physicochemical properties

Refs

D1

Amino acid composition

1

20

Sequence composition

 

[23]

D2

Dipeptide composition

1

400

Sequence composition

 

[24]

D3

Normalized Moreau – Broto autocorrelation

8

240

Correlation of physicochemical properties

Hydrophobicity scale, average flexibility index, polarizability parameter, free energy of amino acid solution in water, residue accessible surface area, amino acid residue volume, steric parameters, relative mutability

[25, 26]

D4

Moran autocorrelation

8

240

Correlation of physicochemical properties

Hydrophobicity scale, average flexibility index, polarizability parameter, free energy of amino acid solution in water, residue accessible surface area, amino acid residue volume, steric parameters, relative mutability

[27]

D5

Geary autocorrelation

8

240

Square correlation of physicochemical properties

Hydrophobicity scale, average flexibility index, polarizability parameter, free energy of amino acid solution in water, residue accessible surface area, amino acid residue volume, steric parameters, relative mutability

[28]

D6

Descriptors of composition, transition and distribution

21

147

Distribution and variation of physicochemical properties

Hydrophobicity, Van der Waals volume, polarity, polarizability, charge, secondary structures, solvent accessibility

[2-6, 8, 17, 29, 30]

D7

Quasi sequence order

4

160

Combination of sequence composition and correlation of physicochemical

Hydrophobicity, hydrophilicity, polarity, side-chain volume

[10, 11, 18, 31]

D8

Pseudo amino acid composition

3

298

Combination of sequence composition and square correlation of physicochemical

Hydrophobicity, hydrophilicity, side chain mass

[23, 32]

D9

Combination of amino acid and dipeptide composition

2

420

Combination of sequence compositions

  

D10

Combination of all eight sets of descriptors

54

1745

Combination of all sets

 Â