File size: 1,755 Bytes
e1a6cd9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
import argparse

def main(args):
    import glob
    import random
    import numpy as np
    import json
    import itertools
    
    with open(args.input_path, 'r') as json_file:
        json_list = list(json_file)
    
    fixed_list = [[int(item) for item in one.split()] for one in args.position_list.split(",")]
    global_designed_chain_list = [str(item) for item in args.chain_list.split()]    
    my_dict = {}
    for json_str in json_list:
        result = json.loads(json_str)
        all_chain_list = [item[-1:] for item in list(result) if item[:9]=='seq_chain']
        fixed_position_dict = {}
        for i, chain in enumerate(global_designed_chain_list):
            fixed_position_dict[chain] = fixed_list[i]
        for chain in all_chain_list:
            if chain not in global_designed_chain_list:       
                fixed_position_dict[chain] = []
        my_dict[result['name']] = fixed_position_dict
    
    with open(args.output_path, 'w') as f:
        f.write(json.dumps(my_dict) + '\n')
    
    #e.g. output
    #{"5TTA": {"A": [1, 2, 3, 7, 8, 9, 22, 25, 33], "B": []}, "3LIS": {"A": [], "B": []}}

if __name__ == "__main__":
    argparser = argparse.ArgumentParser(formatter_class=argparse.ArgumentDefaultsHelpFormatter)
    argparser.add_argument("--input_path", type=str, help="Path to the parsed PDBs")
    argparser.add_argument("--output_path", type=str, help="Path to the output dictionary")
    argparser.add_argument("--chain_list", type=str, default='', help="List of the chains that need to be fixed")
    argparser.add_argument("--position_list", type=str, default='', help="Position lists, e.g. 11 12 14 18, 1 2 3 4 for first chain and the second chain")

    args = argparser.parse_args()
    main(args)