SEQ2DOMML BINARY AMINO ACID IDENTITY FEATURE MANIFEST

This file documents the 20 binary amino acid identity features generated during Seq2DomML feature extraction.

The features use one-hot encoding to represent the identity of each residue. For each residue, exactly one binary feature is assigned a value of 1, and the remaining 19 binary features are assigned a value of 0.

All binary amino acid identity features are stored as 32-bit floating point values.

Accepted amino acids:

A  Alanine

C  Cysteine

D  Aspartic acid

E  Glutamic acid

F  Phenylalanine

G  Glycine

H  Histidine

I  Isoleucine

K  Lysine

L  Leucine

M  Methionine

N  Asparagine

P  Proline

Q  Glutamine

R  Arginine

S  Serine

T  Threonine

V  Valine

W  Tryptophan

Y  Tyrosine

Feature order:

bin_A

bin_C

bin_D

bin_E

bin_F

bin_G

bin_H

bin_I

bin_K

bin_L

bin_M

bin_N

bin_P

bin_Q

bin_R

bin_S

bin_T

bin_V

bin_W

bin_Y

Encoding rule:

For a residue with amino acid identity X:

bin_X = 1

all other bin features = 0

Sequences containing residue symbols outside the 20 accepted amino acids are excluded before feature extraction.

Storage:

For a sequence of length L, the binary amino acid identity feature block has dimensions L x 20.

The binary feature block is concatenated into the final residue feature matrix after the three positional features.