def update_pdbs_json():
'''This function was used to update the pdbs.json file to include chain sequences and types.'''
pdb_data = {}
pdb_data_ = json.loads(read_file(os.path.join('..', 'json', 'pdbs.json')))
for k, v in pdb_data_.items():
assert(len(k) == 4)
newk = k.upper()
pdb = PDB(read_file(os.path.join('..', 'pdbs', newk + '.pdb')))
chain_ids = set(pdb.chain_types.keys()).union(set(pdb.seqres_chain_order)).union(set(pdb.atom_sequences.keys()))
v['Chains'] = dict.fromkeys(chain_ids)
for chain_id in chain_ids:
v['Chains'][chain_id] = dict(
Sequence = str(pdb.atom_sequences.get(chain_id)),
Type = pdb.chain_types.get(chain_id),
)
pdb_data[newk] = v
write_file(os.path.join('..', 'json', 'pdbs.json.new'), json.dumps(pdb_data, indent = 4, sort_keys=True))
def update_pdbs_json():
'''This function was used to update the pdbs.json file to include chain sequences and types.'''
pdb_data = {}
pdb_data_ = json.loads(read_file(os.path.join('..', 'json', 'pdbs.json')))
for k, v in pdb_data_.iteritems():
assert(len(k) == 4)
newk = k.upper()
pdb = PDB(read_file(os.path.join('..', 'pdbs', newk + '.pdb')))
chain_ids = set(pdb.chain_types.keys()).union(set(pdb.seqres_chain_order)).union(set(pdb.atom_sequences.keys()))
v['Chains'] = dict.fromkeys(chain_ids)
for chain_id in chain_ids:
v['Chains'][chain_id] = dict(
Sequence = str(pdb.atom_sequences.get(chain_id)),
Type = pdb.chain_types.get(chain_id),
)
pdb_data[newk] = v
write_file(os.path.join('..', 'json', 'pdbs.json.new'), json.dumps(pdb_data, indent = 4, sort_keys=True))
def create_constraints_file(preminimization_log, outfile_path):
'''This does the work of the convert_to_cst_file.sh script in the Rosetta repository.'''
constraints = []
contents = read_file(preminimization_log)
for line in contents.split('\n'):
if line.startswith("c-alpha"):
line = line.split()
constraints.append("AtomPair CA %s CA %s HARMONIC %s %s" % (line[5], line[7], line[9], line[12]))
write_file(outfile_path, '\n'.join(constraints))
return outfile_path
def create_constraints_file(preminimization_log, outfile_path):
'''This does the work of the convert_to_cst_file.sh script in the Rosetta repository.'''
constraints = []
contents = read_file(preminimization_log)
for line in contents.split('\n'):
if line.startswith("c-alpha"):
line = line.split()
constraints.append("AtomPair CA %s CA %s HARMONIC %s %s" %
(line[5], line[7], line[9], line[12]))
write_file(outfile_path, '\n'.join(constraints))
return outfile_path
if arguments.get('--parallel'):
valid_options = [int(x) for x in arguments['--parallel'] if x.isdigit()]
if not valid_options:
raise Exception('None of the arguments to --parallel are valid. The argument must be an integer between 1 and the number of processors (%d).' % num_system_processors)
else:
num_processors = max(valid_options)
else:
# If the user has not specified the number of processors, only one is selected, and more exist then let them know that this process may run faster
if num_processors == 1 and num_system_processors > 1:
print('The setup is configured to use one processor but this machine has %d processors. The --parallel or --maxp options may make this setup run faster.' % num_system_processors)
if 1 > num_processors or num_processors > num_system_processors:
raise Exception('The number of processors must be an integer between 1 and %d.' % num_system_processors)
# Read the dataset from disk
try:
dataset = json.loads(read_file(dataset_filepath))
dataset_cases = dataset['data']
except Exception, e:
raise Exception('An error occurred parsing the JSON file: %s..' % str(e))
# Set the job directory name
job_name = '%s_%s_ddg_monomer_16' % (time.strftime("%y-%m-%d-%H-%M"), getpass.getuser())
if arguments.get('--run_identifier'):
job_name += '_' + arguments['--run_identifier'][0]
# Set the root output directory
root_output_directory = 'job_output'
if arguments.get('--output_directory'):
root_output_directory = arguments['--output_directory'][0]
if not os.path.exists(root_output_directory):
print('Creating directory %s:' % root_output_directory)
if arguments.get('--parallel'):
valid_options = [int(x) for x in arguments['--parallel'] if x.isdigit()]
if not valid_options:
raise Exception('None of the arguments to --parallel are valid. The argument must be an integer between 1 and the number of processors (%d).' % num_system_processors)
else:
num_processors = max(valid_options)
else:
# If the user has not specified the number of processors, only one is selected, and more exist then let them know that this process may run faster
if num_processors == 1 and num_system_processors > 1:
print('The setup is configured to use one processor but this machine has %d processors. The --parallel or --maxp options may make this setup run faster.' % num_system_processors)
if 1 > num_processors or num_processors > num_system_processors:
raise Exception('The number of processors must be an integer between 1 and %d.' % num_system_processors)
# Read the dataset from disk
try:
dataset = json.loads(read_file(dataset_filepath))
dataset_cases = dataset['data']
except Exception, e:
raise Exception('An error occurred parsing the JSON file: %s..' % str(e))
# Set the job directory name
job_name = '%s_%s_ddg_monomer_16' % (time.strftime("%y-%m-%d-%H-%M"), getpass.getuser())
if arguments.get('--run_identifier'):
job_name += '_' + arguments['--run_identifier'][0]
# Set the root output directory
root_output_directory = 'job_output'
if arguments.get('--output_directory'):
root_output_directory = arguments['--output_directory'][0]
if not os.path.exists(root_output_directory):
print('Creating directory %s:' % root_output_directory)