why target_feat is with shape (N,22), not same as alphafold2 paper (N,21)

[Paulie-ai]

In data_transforms.py, the function make_msa_feat make protein's target_feat, and add has_beak is cat to target_feat, why?
if i only want get the (N,21), can i get ride of first columns datas, thanks.

def make_msa_feat(protein):
"""Create and concatenate MSA features."""
# Whether there is a domain break. Always zero for chains, but keeping for
# compatibility with domain datasets.
has_break = torch.clip(
protein["between_segment_residues"].to(torch.float32), 0, 1
)
aatype_1hot = make_one_hot(protein["aatype"], 21)

target_feat = [
    torch.unsqueeze(has_break, dim=-1),
    aatype_1hot,  # Everyone gets the original sequence.
]