def analyze_construct(self, filenames=None):
self.logger.info("ANALYZING CONSTRUCT STRUCTURES")
# read source files
if not filenames:
filenames = os.listdir(self.construct_data_dir)
for filename in filenames:
if filename[-3:] != 'pdb' and filename[-3:] != 'ent':
continue
root, ext = os.path.splitext(os.path.basename(filename))
print(filename)
print(root)
filepath = os.sep.join([self.construct_data_dir, filename])
self.logger.info("Working on a file: {}".format(filename))
header = parse_pdb_header(filepath)
parser = SequenceParser(filepath)
json_data = OrderedDict()
json_data["header"] = header
json_data.update(parser.get_fusions())
json_data.update(parser.get_mutations())
json_data.update(parser.get_deletions())
json.dump(json_data,
open(
os.sep.join(
[settings.DATA_DIR,
"{}_auto.json".format(root)]), 'w'),
indent=4,
separators=(',', ': '))
def handle(self, *args, **options):
print("Working on file {}".format(options['pdb_file']))
header = parse_pdb_header(options['pdb_file'])
print(header['compound'])
sp = SequenceParser(options['pdb_file'])
c = list(sp.mapping.keys())[0]
poly = sp.get_chain_peptides(c)
for peptide in poly:
print("Start: {} Stop: {} Len: {}".format(peptide[0].id[1], peptide[-1].id[1], len(peptide)))
sp.map_to_wt_blast(c, peptide, None, int(peptide[0].id[1]))
sp.map_seqres()
sp.save_excel_report("test.xlsx")
#sp.get_report()
def post(self, request):
# root, ext = os.path.splitext(request._request.FILES['pdb_file'].name)
pdb_file = StringIO(
request._request.FILES['pdb_file'].file.read().decode(
'UTF-8', "ignore"))
header = parse_pdb_header(pdb_file)
parser = SequenceParser(pdb_file)
json_data = OrderedDict()
json_data["header"] = header
json_data.update(parser.get_fusions())
json_data.update(parser.get_mutations())
json_data.update(parser.get_deletions())
return Response(json_data)
def handle(self, *args, **options):
q = QueryPDB()
q.list_xtals(verbose=False)
for record in q.new_structures:
pdb_code = record[0]
wt_id = Protein.objects.get(entry_name=record[1]).id
if not os.path.exists(
os.sep.join([self.pdb_data_dir, "{}.pdb".format(pdb_code)
])):
self.download_pdb(pdb_code)
self.parser = SequenceParser(os.sep.join(
[self.pdb_data_dir, "{}.pdb".format(pdb_code)]),
wt_protein_id=wt_id)
header = parse_pdb_header(
os.sep.join([self.pdb_data_dir, "{}.pdb".format(pdb_code)]))
self.create_yaml(pdb_code, record[1], header)
def handle(self, *args, **options):
root, ext = os.path.splitext(os.path.basename(options['pdb_file']))
print("Working on file {}".format(options['pdb_file']))
header = parse_pdb_header(options['pdb_file'])
sp = SequenceParser(options['pdb_file'])
print(sp.get_fusions())
print(sp.get_mutations())
print(sp.get_deletions())
json_data = {}
json_data["header"] = header
json_data.update(sp.get_fusions())
json_data.update(sp.get_mutations())
json_data.update(sp.get_deletions())
json.dump(
json_data,
open(os.sep.join([settings.DATA_DIR, "{}_auto.json".format(root)]),
'w'),
indent=4,
separators=(',', ': '))
