script to retrieve UniProt ids for an input list of PDB ids.

pdb_rest_example_get_uniprot_for_pdbidlist.py

#!/usr/bin/env python
# example from https://github.com/PDBeurope/PDBe_Programming/blob/master/REST_API/snippets/basic_get_post.py
# edited to use the python 'requests' module, and to get the UniProt id. for particular PDBe entry ids

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/pdbe/api"

UNIPROT = "/mappings/uniprot"

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

def get_request(url, arg, pretty=False):
    full_url = "%s/%s/%s?pretty=%s" % (SERVER_URL, url, arg, str(pretty).lower())
    # e.g. for PDB id. 1ivv we get:
    # full_url = https://www.ebi.ac.uk/pdbe/api//mappings/uniprot/1ivv?pretty=true
    # 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

    # pull out the UniProt id. for this PDB id:
    uniprot_id = json_results[arg] # 'arg' is the input PDB ID e.g. 1ivv
    uniprot_id2 = uniprot_id["UniProt"]
    uniprot_id3 = list(uniprot_id2.keys()) # a list of the UniProt ids. for this input PDB id.
    uniprot_ids_string = ','.join(uniprot_id3) # there can be more than one uniprot id in a pdb entry e.g. https://www.ebi.ac.uk/pdbe/entry/pdb/2zwe
    # print("UniProt_ids=",uniprot_ids_string)

    return uniprot_ids_string

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

def read_pdb_idlist(pdbidlistfile,outputfile):

    inputfileObj = open(pdbidlistfile, "r")
    # 1 CHEMBL1009 DAH 1ivv,1rnr,2vh3,2zwe,2zwf,2zwg,3teg,3teh,4eis,4p6s,5xdh,5z0f,5z0g,5z0h,5z0i,5z0j,5z0k,5z0l,5z0m,6ebp,6ebz,6gp2,6pah
    # 2 CHEMBL101 P1Z 2bxc,2bxp,2bxq,2w98
    # 3 CHEMBL101683 8ST 3hng
    outputfileObj = open(outputfile,"w")

    for line in inputfileObj:
        line = line.rstrip()
        temp = line.split()
        cnt = temp[0]
        chembl_id = temp[1]
        ligand_id = temp[2]
        pdbids = temp[3]
        if ligand_id != 'NA':
            pdbidlist2 = ""
            pdbidlist = pdbids.split(',')
            for pdbid in pdbidlist:  # note that one pdbid can contain more than one ChEMBL compound, e.g. https://www.ebi.ac.uk/pdbe/entry/pdb/2bxp
                # get the uniprot id for this pbbid:
                uniprot_ids_string = get_request(UNIPROT, pdbid, True)
                pdbidlist2 += "%s(%s)," % (pdbid, uniprot_ids_string)
            pdbidlist2 = pdbidlist2[:-1] # remove the last ','
            output_line = "%s %s %s %s\n" % (cnt,chembl_id,ligand_id,pdbidlist2)
            outputfileObj.write(output_line)
            sys.stdout.write(output_line)
    inputfileObj.close()
    outpufileObj.close()

    return

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

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

    # If you type:
    # % python3 pdb_rest_example_get_uniprot_for_pdbidlist.py
    # You will see:
    #  usage: pdb_rest_example_get_uniprot_for_pdbidlist.py [-h] [-e E]
    #
    # optional arguments:
    #       -h, --help  show this help message and exit
    #       -e E        the pdbidlistfile
    #       -o O        the outputfile

    # Note we defined at the top of the script that:
    # UNIPROT = "/mappings/uniprot"

    if args.e:
        # now read in the list of pdb ids, and find their uniprot ids:
        read_pdb_idlist(args.e,args.o)
    else:
        parser.print_help()
        sys.exit(1)

    print("FINISHED\n")

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