get_cath_domains.py

import urllib
import os, os.path
from optparse import OptionParser

def main(superfamily):
    #fetch the list of domains in the superfamily from the CathDomainList
    dom_lst = get_domain_list(superfamily)
    #for each domain, retrieve the PDB file from CATH
    get_domain_structures(dom_lst, superfamily)

def get_domain_list(superfamily):
    count = 0
    domain_list = []
    sf_tokens = superfamily.split('.')
    fh = open(os.path.join("data", "cath", "CathDomainList"), 'r')
    for line in fh.readlines():
        if not line.startswith('#'):   #exclude comment lines
            tokens = line.rstrip().split()
            #if C, A, T and H match, the domain is a member of the right superfamily
            if int(tokens[1]) == int(sf_tokens[0]) \
              and int(tokens[2]) == int(sf_tokens[1]) \
              and int(tokens[3]) == int(sf_tokens[2]) \
              and int(tokens[4]) == int(sf_tokens[3]):
                domain_list.append(tokens[0])
                count += 1
    print("There are "+str(count)+" domains in superfamily "+superfamily)
    return domain_list

def get_domain_structures(domain_list, superfamily):
    for domain in domain_list:
        #can also get chain and full pdb entries by modifying the URL
        url = 'http://www.cathdb.info/api/data/pdb/'+domain
        pdb = urllib.urlopen(url).read()
        if not os.path.exists(os.path.join('data', 'pdb', superfamily)):
            os.mkdir(os.path.join('data', 'pdb', superfamily))
        out = open(os.path.join('data', 'pdb', superfamily, domain+'.pdb'), 'w')
        out.write(pdb)
    return url

if __name__ == '__main__':
    parser = OptionParser(usage="Usage: %prog [options]", version="%prog 0.1")
    parser.add_option("-c", dest="c", help="Class", metavar="CLASS")
    parser.add_option("-a", dest="a", help="Architecture", metavar="ARCHITECTURE")
    parser.add_option("-t", dest="t", help="Topology", metavar="TOPOLOGY")
    parser.add_option("-s", dest="s", help="Homologous Superfamily", metavar="SUPERFAMILY")  #would have used -h, but it's reserved for help
    (options, args) = parser.parse_args()
    sf = options.c+'.'+options.a+'.'+options.t+'.'+options.s
    main(sf)