seq_cutting.py

ALPHABET_UNMOD = {
    "A": 1,
    "C": 2,
    "D": 3,
    "E": 4,
    "F": 5,
    "G": 6,
    "H": 7,
    "I": 8,
    "K": 9,
    "L": 10,
    "M": 11,
    "N": 12,
    "P": 13,
    "Q": 14,
    "R": 15,
    "S": 16,
    "T": 17,
    "V": 18,
    "W": 19,
    "Y": 20,
}


# trypsin cut after A or L (if not followed by P)

def cut(seq, format):
    cuts = []
    l = len(seq)
    if format == 'alphabetical':
        for i in range(l):
            if seq[i] == 'R' or seq[i] == 'K':
                if i < l - 1 and seq[i + 1] != 'P':
                    cuts.append(i + 1)

    if format == 'numerical':
        for i in range(l):
            if seq[i] == 15 or seq[i] == 9:
                if i < l - 1 and seq[i + 1] != 13:
                    cuts.append(i + 1)
    return cuts


def cut_with_ind(seq, ind_list):
    l = []
    size = len(seq)
    ind_list.append(size)

    for i in range(len(ind_list) - 1):
        if i == 0:
            l.append(seq[:ind_list[i]])
        l.append(seq[ind_list[i]:ind_list[i + 1]])

    return l