def test_clean_pdb_and_get_chain(self):
files = [('1kf6.pdb', '1kf6_clean_chainA_tester.pdb')]
outdir = op.join('test_files', 'out')
working_dir = 'test_structures'
out_suffix = '_clean_chainA'
custom_clean = CleanPDB(keep_chains='A')
for infile, outfile in files:
outfile_new = '{}{}.pdb'.format(op.splitext(infile)[0], out_suffix)
infile_path = op.join(working_dir, infile)
my_pdb = StructureIO(infile_path)
default_cleaned_pdb = my_pdb.write_pdb(
custom_selection=custom_clean,
out_suffix=out_suffix,
out_dir=outdir,
force_rerun=True)
default_cleaned_pdb_basename = op.basename(default_cleaned_pdb)
# test if the filename is correct
# print(default_cleaned_pdb_basename, outfile_new)
self.assertEqual(default_cleaned_pdb_basename, outfile_new)
# test if the file contents are equal
self.assertEqual(
open(default_cleaned_pdb, 'r').read(),
open(op.join(working_dir, outfile), 'r').read())
# test that the file does not equal the original file
self.assertNotEqual(
open(default_cleaned_pdb, 'r').read(),
open(infile_path, 'r').read())
def clean_pdb(pdb_file,
out_suffix='_clean',
outdir=None,
force_rerun=False,
remove_atom_alt=True,
keep_atom_alt_id='A',
remove_atom_hydrogen=True,
add_atom_occ=True,
remove_res_hetero=True,
keep_chemicals=None,
keep_res_only=None,
add_chain_id_if_empty='X',
keep_chains=None):
"""Clean a PDB file.
Args:
pdb_file (str): Path to input PDB file
out_suffix (str): Suffix to append to original filename
outdir (str): Path to output directory
force_rerun (bool): If structure should be re-cleaned if a clean file exists already
remove_atom_alt (bool): Remove alternate positions
keep_atom_alt_id (str): If removing alternate positions, which alternate ID to keep
remove_atom_hydrogen (bool): Remove hydrogen atoms
add_atom_occ (bool): Add atom occupancy fields if not present
remove_res_hetero (bool): Remove all HETATMs
keep_chemicals (str, list): If removing HETATMs, keep specified chemical names
keep_res_only (str, list): Keep ONLY specified resnames, deletes everything else!
add_chain_id_if_empty (str): Add a chain ID if not present
keep_chains (str, list): Keep only these chains
Returns:
str: Path to cleaned PDB file
"""
outfile = ssbio.utils.outfile_maker(inname=pdb_file,
append_to_name=out_suffix,
outdir=outdir,
outext='.pdb')
if ssbio.utils.force_rerun(flag=force_rerun, outfile=outfile):
my_pdb = StructureIO(pdb_file)
my_cleaner = CleanPDB(remove_atom_alt=remove_atom_alt,
remove_atom_hydrogen=remove_atom_hydrogen,
keep_atom_alt_id=keep_atom_alt_id,
add_atom_occ=add_atom_occ,
remove_res_hetero=remove_res_hetero,
keep_res_only=keep_res_only,
add_chain_id_if_empty=add_chain_id_if_empty,
keep_chains=keep_chains,
keep_chemicals=keep_chemicals)
my_clean_pdb = my_pdb.write_pdb(out_suffix=out_suffix,
out_dir=outdir,
custom_selection=my_cleaner,
force_rerun=force_rerun)
return my_clean_pdb
else:
return outfile
def copy_results(self,
copy_to_dir,
rename_model_to=None,
force_rerun=False):
"""Copy the raw information from I-TASSER modeling to a new folder.
Copies all files in the list _attrs_to_copy.
Args:
copy_to_dir (str): Directory to copy the minimal set of results per sequence.
rename_model_to (str): New file name (without extension)
force_rerun (bool): If existing models and results should be overwritten.
"""
# Save path to the structure and copy it if specified
if not rename_model_to:
rename_model_to = self.model_to_use
new_model_path = op.join(copy_to_dir, '{}.pdb'.format(rename_model_to))
if self.structure_path:
if ssbio.utils.force_rerun(flag=force_rerun,
outfile=new_model_path):
# Clean and save it
custom_clean = CleanPDB()
my_pdb = StructureIO(self.structure_path)
new_model_path = my_pdb.write_pdb(
custom_selection=custom_clean,
custom_name=rename_model_to,
out_dir=copy_to_dir,
force_rerun=force_rerun)
# Update the structure_path to be the new clean file
self.load_structure_path(structure_path=new_model_path,
file_type='pdb')
# Other modeling results - store in a new folder
dest_itasser_dir = op.join(copy_to_dir,
'{}_itasser'.format(rename_model_to))
if not op.exists(dest_itasser_dir):
os.mkdir(dest_itasser_dir)
for attr in self._attrs_to_copy:
old_file_path = getattr(self, attr)
new_file_path = op.join(dest_itasser_dir,
op.basename(old_file_path))
if ssbio.utils.force_rerun(flag=force_rerun,
outfile=new_file_path):
shutil.copy2(old_file_path, new_file_path)
log.debug('{}: copied from {}'.format(
new_file_path, old_file_path))
else:
log.debug('{}: file already exists'.format(new_file_path))
setattr(self, attr, new_file_path)
p.add_argument(
'mutations',
help=
'Mutations in the form of Chain1.ResNum1.Mutation1,Chain2.ResNum2.Mutation2. Example: A.4.TYR,B.4.TYR'
)
p.add_argument('--outsuffix',
'-o',
default='_mutated',
help='Suffix appended to PDB file')
p.add_argument('--clean',
'-c',
action='store_true',
help='Clean PDB and keep only chain with mutation')
args = p.parse_args()
mutations = parse_mutation_input(args.mutations)
my_pdb = StructureIO(args.infile)
if args.clean:
my_cleaner = CleanPDB(keep_chains=[x[0] for x in mutations])
my_clean_pdb = my_pdb.write_pdb(out_suffix='_clean',
out_dir=tempfile.gettempdir(),
custom_selection=my_cleaner)
my_pdb = StructureIO(my_clean_pdb)
my_mutation = MutatePDB(mutations)
my_mutated_pdb = my_pdb.write_pdb(out_suffix=args.outsuffix,
out_dir='mutated_pdbs',
custom_selection=my_mutation)
print('Mutated PDB at: {}'.format(my_mutated_pdb))
if not op.isdir(args.outdir):
os.mkdir(args.outdir)
infiles = ssbio.utils.input_list_parser(args.infile)
for pdb in tqdm(infiles):
outfile = ssbio.utils.outfile_maker(inname=pdb,
append_to_name=args.outsuffix,
outdir=args.outdir,
outext='.pdb')
if ssbio.utils.force_rerun(flag=args.force, outfile=outfile):
my_pdb = StructureIO(pdb)
my_cleaner = CleanPDB(remove_atom_alt=args.keepalt,
remove_atom_hydrogen=args.keephydro,
keep_atom_alt_id='A',
add_atom_occ=True,
remove_res_hetero=args.keephetero,
add_chain_id_if_empty='X',
keep_chains=args.chain)
my_clean_pdb = my_pdb.write_pdb(out_suffix=args.outsuffix,
out_dir=args.outdir,
custom_selection=my_cleaner,
force_rerun=args.force)
print('Clean PDBs at: {}'.format(args.outdir))