get_lig.py

#!/usr/bin/env python3

# extract ligand lines from given PDB_CHAIN_LIG triplet
# e.g. 1yom_A_P01

import os, sys

#"HETATM 4172 CL1  P01 A   1       8.995 -11.569  -2.901  1.00 52.76"
# 0                17  21

pdb_chain_lig = sys.argv[1]

tokens = pdb_chain_lig.split('_')
pdb_base_fn = tokens[0]
pdb_fn = pdb_base_fn + ".pdb"
chain_letter = tokens[1]
lig_res = tokens[2]

# debug
print(pdb_base_fn)
print(chain_letter)
print(lig_res)

# D/L the PDB file
os.system('wget https://files.rcsb.org/download/%s.pdb' % pdb_base_fn)
with open(pdb_fn, 'r') as input:
    lig_fn = pdb_base_fn + "_lig.pdb"
    with open(lig_fn, 'w') as output:
        for line in input.readlines():
            if (line[0:6] == "HETATM" and line[21:22] == chain_letter and
                line[17:20] == lig_res):
                print("%s" % line, file=output, end='')