70 lines
2.4 KiB
Python
Executable file
70 lines
2.4 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
|
|
# Copyright 2020, Tanushree Tunstall
|
|
# This program is distributed under General Public License v. 3. See the file
|
|
# COPYING for a copy of the license.
|
|
|
|
__description__ = \
|
|
"""
|
|
chain_extract.py
|
|
|
|
extract chain/s from pdb and saves each chain as a separate file
|
|
"""
|
|
__author__ = "Tanushree Tunstall"
|
|
__date__ = ""
|
|
#=======================================================================
|
|
import os, shutil, sys
|
|
#from pdbtools.helper import cmdline
|
|
from chain_extract import ChainExtract
|
|
from Bio.PDB import PDBParser, PDBIO, Select
|
|
#from Bio.PDB.PDBParser import PDBParser
|
|
|
|
#io = PDBIO()
|
|
import argparse
|
|
#=======================================================================
|
|
|
|
def main():
|
|
"""
|
|
Function to call if run from command line.
|
|
|
|
Example use:
|
|
pdb_chain_extract.py -f <your_pdb_file> -c <chainid1><chainid2> -p <outpath> -o <outfile>
|
|
Extracts chain 'A' by default.
|
|
"""
|
|
arg_parser = argparse.ArgumentParser()
|
|
arg_parser.add_argument('-i', '--pdb_file', help='provide pdb file', default = 'None')
|
|
arg_parser.add_argument('-c', '--chain', help='chain/s to extract without spaces.', nargs = '+', default = 'A', type = list)
|
|
arg_parser.add_argument('-p', '--out_path', help='specify output path', default = '.', type = str)
|
|
arg_parser.add_argument('-o', '--out_file', help='specify output filename. Will be used as a prefix to append chain id and pdb file extension', default = 'pdbfile', type = str)
|
|
args = arg_parser.parse_args()
|
|
|
|
# Extract chains and write each chain as a separate file
|
|
pdb_file = args.pdb_file
|
|
print('input pdb file:', pdb_file)
|
|
|
|
# type = list, makes it a list of lists. Hence extracting the list of chains.
|
|
chains = args.chain[0]
|
|
#chains = ['A','B','C']
|
|
print ('user supplied chain:', chains)
|
|
|
|
# output filename and path
|
|
outpath = args.out_path
|
|
outfile = args.out_file
|
|
|
|
# get structure
|
|
p = PDBParser(PERMISSIVE=1)
|
|
structure = p.get_structure(pdb_file, pdb_file)
|
|
print('input pdb filename:', structure.get_id())
|
|
|
|
my_chains = chains
|
|
#my_chains = ['G', 'H']
|
|
c_names = ''.join(my_chains)
|
|
print('Extracting chains:', my_chains)
|
|
pdb_chains_file = outpath + '/' + outfile + '_' + c_names + '.pdb'
|
|
io = PDBIO()
|
|
io.set_structure(structure)
|
|
io.save(pdb_chains_file, ChainExtract(my_chains))
|
|
|
|
if __name__ == "__main__":
|
|
main()
|
|
|