url = "http://www.rcsb.org/pdb/download/downloadFile.do?fileFormat=pdb&compression=NO&structureId="
not_available_list = []
for pdb in pdb_list:
pdb_name = "{0}.pdb".format(pdb)
if not os.path.exists(pdb_name):
pdbid = url+str(pdb)
content = urllib.urlopen(pdbid).read()
if '404 Not Found' in content: not_available_list.append(pdb)
else:
open(pdb_name, "w" ).write(content)
print pdb_name
return not_available_list
def check(not_available_list):
new_list = not_available_list[:]
for pdb in not_available_list:
if os.path.exists('{0}-pdb-bundle.tar.gz'.format(pdb)) or os.path.exists('{0}-pdb-bundle.tar'.format(pdb)):
new_list.remove(pdb)
if new_list:
print "copy and paste the {0} structures below in the rcsb.org download feature (could not be downloaded programatically)".format(len(new_list)) #obtain bundle case
print ",".join(new_list)
if __name__ == "__main__":
help_message(help_msg)
d = read_in('pdb', 'uniprot', 'pre_seq2struc')
pdb_list = [x[:4] for x in d]
not_available_list = save_pdb_file(set(pdb_list))
check(not_available_list)
print_next_step()
'PPI_degree', 'dosage_tolerance'
]
log_zero_list = [
-1, -1, -4, 1, -1
] #make into dict #dont log dosage tolerance, already logged for yeast, ecoli is discrete
for organism in organism_list:
pre_d_i = read_in('pdb', 'uniprot', organism=organism)
pre_d_i = collections.OrderedDict(sorted(pre_d_i.items()))
d_index[organism] = {i: pdb for i, pdb in enumerate(pre_d_i)}
d_ref = read_in('oln', 'pdb', organism=organism)
for protein_property in protein_property_list:
x_input = database(organism, protein_property)
d = read_in(*x_input)
d_subset = {
pdb: d[oln]
for oln, pdb in d_ref.iteritems() if oln in d
}
d_val[organism].append(d_subset)
line_list = prepare_sql(d_org, d_index, d_val, protein_property_list,
log_zero_list)
columns = ['chain_id', 'species', 'pdb']
columns.extend(protein_property_list)
write_sqlite = SQLite3('proteomevis_chain', columns, line_list)
write_sqlite.run()
print_next_step('../')