trim_fastas.py

from util import *

data_source_file = f'./csp_stats.csv'
parsed_data = parse_csv(data_source_file)

bounds = [data['holo_pdb'] for data in parsed_data]
res_ranges = [ data['Well_Defined_Residues'] for data in parsed_data ]

for i, bound in enumerate(bounds):
    fasta_file = './input_fastas/'+bound.lower()+'.fasta'
    res_range = res_ranges[i]

    print(bound)
    print(res_range)

    start_index = int(res_range.split(':')[1].split('..')[0])-1
    end_index = int(res_range.split(':')[1].split('..')[1])
    original_text = ""
    str_o = ""
    next_l = False
    with open(fasta_file, 'r') as in_f:
        for l in in_f:
            original_text += l
            if next_l:
                str_o += l[start_index:end_index] + '\n'
                next_l = False
                continue
            if l.endswith(res_range[0]+'\n'):
                next_l = True
                str_o += l
                continue
            str_o += l

    print("original = " + original_text)
    print("trimmed = " + str_o)
    output_file = './input_fastas_trimmed/'+bound.lower()+'.fasta'

    with open(output_file, 'w') as out_f:
        out_f.write(str_o)