def get_missing_sidechains(pdb_dataset, output_scwrl):
"""Get residues that are missing atoms."""
for pdb_filename in db.get_structures_filenames(pdb_dataset):
biopy_structure = db.parse_biopython_structure(pdb_filename)
pdb_name = db.get_pdb_name(pdb_filename)
missing = 0
scwrl_list = []
logging.info("Processing {:}".format(pdb_name))
for model in biopy_structure:
for chain in model:
for i, residue in enumerate(chain):
res_name = residue.resname
if res_name not in expected:
logging.warning("Non-standard residue found: {:}. "
"Skipping.".format(res_name))
continue
res_code = poly.three_to_one(res_name)
res_id = residue.id[1]
curr_count = len(
Bio.PDB.Selection.unfold_entities(residue, 'A'))
if curr_count != expected[res_name]:
logging.debug(
"Missing residue {:} at position {:} (with id {:})"
" which has {:} instead of the expected {:} atoms."
.format(res_name, i, res_id, curr_count,
expected[res_name]))
missing += 1
scwrl_list.append(res_code.upper())
else:
scwrl_list.append(res_code.lower())
logging.debug("Missing {:} residue total".format(missing))
with open(output_scwrl, 'w') as f:
f.write("".join(scwrl_list))
def _generate_reference(pdb_filename, s2r_chain, s2r_res, output_filename,
style):
"""Transform PDB structure to a reference structure."""
biopy_structure = db.parse_biopython_structure(pdb_filename)
pdb_name = db.get_pdb_name(pdb_filename)
new_model = Bio.PDB.Model.Model('0')
new_structure = Bio.PDB.Structure.Structure('')
for (chain, residues) in \
struct.get_chain_to_valid_residues(biopy_structure, pdb_name):
if style == 'dockground' and chain not in s2r_chain:
# If we are in dockground, we allow ourselves to remove unmapped
# chains.
continue
ref_chain = s2r_chain[chain]
if chain in s2r_res:
# If we have an alignment for this chain.
new_chain = Bio.PDB.Chain.Chain(ref_chain)
for i, residue in enumerate(residues):
if residue.id[0] != ' ':
continue
residue.segid = ""
residue.id = (' ', s2r_res[chain][i], residue.id[2])
new_chain.add(residue)
else:
# Else, just remove segment ID.
new_chain = Bio.PDB.Chain.Chain(ref_chain)
for i, residue in enumerate(residues):
residue.segid = ""
new_model.add(new_chain)
new_structure.add(new_model)
w = Bio.PDB.PDBIO()
w.set_structure(new_structure)
w.save(output_filename)
def parse_structure(structure_filename, concoord=False, one_model=False):
"""Parse a file into chain,model-to-residue mapping."""
_, ext = os.path.splitext(structure_filename)
detailed = ext == '.pkl'
if detailed:
# If detailed we are reading pandas pickle file outputted by
# protprep.
df = pd.read_pickle(structure_filename)
# Set model to 0, because a multi-model file was either already split
# into separate files (using the split command) or was pared down to a
# single model by the autodock portion of the protprep pipeline.
# This might need to be revisited if/when autodock is removed from
# pipeline or we decide to actually keep track of correct model.
df['model'] = get_model(structure_filename)
# Remove hydrogens, for now, to maintain compatability.
df = df[df['maestro_atom_name'].apply(lambda x: x.strip()[0]) != 'H']
else:
# BioPython.PDB Structure extracted from PDB file.
biopy_structure = db.parse_biopython_structure(structure_filename)
pdb_name = db.get_pdb_name(structure_filename)
if concoord:
# need to set model number to be correct (drawn from filename)
# TODO: I (Raphael) moved this out of core Structure code, need to
# make sure it is correct still for CONCOORD.
biopy_structure = db.parse_biopython_structure(structure_filename)
biopy_structure = \
Bio.PDB.Structure.Structure(biopy_structure.id)
chainmodel = pdb_name.split('_')[1]
model_id = str(int(re.split('(\d+)', chainmodel)[1]) + 1)
for model_obj in biopy_structure:
new_model = Bio.PDB.Model.Model(model_id)
for chain in model_obj:
new_model.add(chain)
biopy_structure.add(new_model)
if one_model:
new_structure = Bio.PDB.Structure.Structure(biopy_structure.id)
new_structure.add(biopy_structure[0])
biopy_structure = new_structure
atoms = []
for residue in Bio.PDB.Selection.unfold_entities(biopy_structure, 'R'):
# Prune out things that aren't actually residue atoms.
if 'CA' in residue and residue.get_id()[0] == ' ':
for atom in residue:
atoms.append(atom)
df = pd.DataFrame(
[(pdb_name,
str(atom.get_parent().get_parent().get_parent().serial_num),
atom.get_parent().get_full_id()[2],
str(atom.get_parent().get_id()[1]) +
atom.get_parent().get_id()[2], atom.get_parent().get_resname(),
atom.get_coord()[0], atom.get_coord()[1], atom.get_coord()[2],
atom.get_id()[0], atom.get_name(), str(atom.serial_number))
for atom in atoms],
columns=[
'pdb_name', 'model', 'chain', 'residue', 'resname', 'x', 'y',
'z', 'element', 'atom_name', 'aid'
])
return df