AntAngioCOOL: computational detection of anti-angiogenic peptides

Table 1 Distribution of the features used to encode each peptide

Feature type	No. of features
PseAAC (λ = 6)	28
k-mer composition
k = 2	400
k = 3	8000
k = 4	160,000
k-mer composition (reduced alphabet^a)
k = 2	64
k = 3	512
k = 4	4096
Physico-chemical profile	1910
Atomic profile	80
Total	175,062

^aTo compute k-mer composition features, the reduced amino acid alphabet proposed by Zahiri et al. was applied: the 20 alphabet of amino acids was reduced to a new alphabet with size 8 according to 544 physicochemical and biochemical indices that extracted from AAIndex database (C₁ = {A, E}, C₂ = {I, L, F, M, V}, C₃ = {N, D, T, S}, C₄ = {G}, C₅ = {P}, C₆ = {R, K, Q, H}, C₇ = {Y, W}, C₈ = {C}). We computed k-mer composition for k = 2, 3, 4 for each peptide

ISSN: 1479-5876