Script to use the UniChem REST API to get the PDB ligand identifier for a particular ChEMBL identifier

unichem_rest_example_get_pdbligandids_for_chemblid.py

#!/usr/bin/env python
# script to find out the PDB three-letter ligand id. for a ChEMBL id., using UniChem

import argparse
import sys
import requests # this is used to access json files

PY3 = sys.version > '3'

if PY3:
    import urllib.request as urllib2
else:
    import urllib2

SERVER_URL = "https://www.ebi.ac.uk/unichem/rest"

UNICHEM = "/src_compound_id"

#====================================================================#

def get_request(url, arg, pretty=False):

    full_url = "%s/%s/%s/1/3" % (SERVER_URL, url, arg)

    # e.g. for ChEMBL id. CHEMBL14249 we get:
    # full_url = https://www.ebi.ac.uk/unichem/rest//src_compound_id/CHEMBL14249/1/3
    print("This is the url string:\n{}".format(full_url))

    json_results = requests.get( full_url ).json() #This calls the information back from the API using the 'requests' module, and converts it to json format
    # e.g. [{'src_compound_id': 'ATP'}]
    # This seems to have been changed from json format to Python format by the 'requests' module.

    # Pull out the dictionary:
    json_results2 = json_results[0] # e.g. a dictionary like {'src_compound_id': 'ATP'}

    # pull out the PDB ligand id. for this ChEMBL id.:
    ligand_id = json_results2['src_compound_id']
    print("Ligand id. in PDB:",ligand_id)

    return(json_results)

#====================================================================#

if __name__ == '__main__':
    parser = argparse.ArgumentParser(formatter_class=argparse.RawTextHelpFormatter)
    parser.add_argument('-e', type=str, default=None, action='store', help='the chemblID')
    args = parser.parse_args()

    # If you type:
    #  % python3 unichem_rest_example_get_pdbligandids_for_chemblid.py
    #  usage: unichem_rest_example_get_pdbligandids_for_chemblid.py [-h] [-e E]
    #  optional arguments:
    # -h, --help  show this help message and exit
    # -e E        the chemblID

    # Note we defined at the top of the script that:
    # UNICHEM = "/rest/src_compound_id"

    if args.e:
        response = get_request(UNICHEM, args.e, True)
    else:
        parser.print_help()
        sys.exit(1)

    print("FINISHED\n")

#====================================================================#