ALPHABET "Protein" PROTEIN-LIKE

# Core symbols
A "Alanine" 0000CC
R "Arginine" CC0000
N "Asparagine" 008000
D "Aspartic acid" FF00FF
C "Cysteine" 0000CC
E "Glutamic acid" FF00FF
Q "Glutamine" 008000
G "Glycine" FFB300
H "Histidine" FFCCCC
I "Isoleucine" 0000CC
L "Leucine" 0000CC
K "Lysine" CC0000
M "Methionine" 0000CC
F "Phenylalanine" 0000CC
P "Proline" FFFF00
S "Serine" 008000
T "Threonine" 008000
W "Tryptophan" 0000CC
Y "Tyrosine" 33E6CC
V "Valine" 0000CC
# These are commented-out because they are not in the default MEME Suite Protein alphabet
U "Selenocysteine" 0000CC
O "Pyrrolysine" 0000CC

# Ambiguous symbols
B = ND
Z = QE
J = LI
X = ARNDCEQGHILKMFPSTWYVUO # wildcard symbol including U and O
#X = ARNDCEQGHILKMFPSTWYV # wildcard symbol omitting U and O