def read_input_structure(pdb_file_name, ignore_oxt=True):
"""Reads the input structure.
The arguments pdb_file_name can be a PDB file or a file
containing a list of PDB files.
ignore_oxt flag avoids saving OXT atoms.
"""
atoms_to_ignore = []
if ignore_oxt:
atoms_to_ignore.append('OXT')
structures = []
file_names = []
file_name, file_extension = os.path.splitext(pdb_file_name)
if file_extension == DEFAULT_LIST_EXTENSION:
file_names.extend(get_pdb_files(pdb_file_name))
else:
file_names.append(pdb_file_name)
for file_name in file_names:
log.info("Reading structure from %s PDB file..." % file_name)
atoms, residues, chains = parse_complex_from_file(file_name, atoms_to_ignore)
structures.append({'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': file_name})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
# Representatives are now the first structure, but this could change in the future
structure = Complex.from_structures(structures)
return structure
def read_input_structure(pdb_file_name,
ignore_oxt=True,
ignore_hydrogens=False,
verbose_parser=False):
"""Reads the input structure.
The arguments pdb_file_name can be a PDB file or a file
containing a list of PDB files.
ignore_oxt flag avoids saving OXT atoms.
"""
atoms_to_ignore = []
if ignore_oxt:
atoms_to_ignore.append('OXT')
log.info('Ignoring OXT atoms')
if ignore_hydrogens:
atoms_to_ignore.append('H')
log.info('Ignoring Hydrogen atoms')
structures = []
file_names = []
file_name, file_extension = os.path.splitext(pdb_file_name)
if file_extension == DEFAULT_LIST_EXTENSION:
file_names.extend(get_pdb_files(pdb_file_name))
else:
file_names.append(pdb_file_name)
for file_name in file_names:
log.info("Reading structure from %s PDB file..." % file_name)
atoms, residues, chains = parse_complex_from_file(
file_name, atoms_to_ignore, verbose_parser)
structures.append({
'atoms': atoms,
'residues': residues,
'chains': chains,
'file_name': file_name
})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
# Representatives are now the first structure, but this could change in the future
structure = Complex.from_structures(structures)
return structure
else:
file_names.append(args.structure)
for file_name in file_names:
log.info("Reading %s PDB file..." % file_name)
atoms, residues, chains = parse_complex_from_file(
file_name, atoms_to_ignore)
structures.append({
'atoms': atoms,
'residues': residues,
'chains': chains,
'file_name': file_name
})
log.info("%s atoms, %s residues read." %
(len(atoms), len(residues)))
molecule = Complex.from_structures(structures)
try:
ellipsoid = MinimumVolumeEllipsoid(
molecule.atom_coordinates[0].coordinates)
except MinimumVolumeEllipsoidError as e:
log.error(
"Impossible to calculate minimum volume ellipsoid. Reason: %s"
% str(e))
raise SystemExit("%s finished with error" % script_name)
output_file_name = molecule.structure_file_names[
0] + DEFAULT_REFERENCE_POINTS_EXTENSION
with open(output_file_name, 'w') as output:
for point in ellipsoid.poles:
output.write(get_point_respresentation(point) + os.linesep)
output.write(
n_modes = int(sys.argv[2])
factor = float(sys.argv[3])
except:
usage()
raise SystemExit("Wrong command line")
protein = parsePDB(pdb_structure)
ca_atoms = protein.select('name CA')
protein_anm = ANM('protein ca')
protein_anm.buildHessian(ca_atoms)
protein_anm.calcModes(n_modes=n_modes)
print('Normal modes calculated')
atoms, residues, chains = parse_complex_from_file(pdb_structure)
lightdock_structures = [{'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': pdb_structure}]
lightdock_structure = Complex.from_structures(lightdock_structures)
print('Structure read by lightdock')
num_atoms_prody = len(protein.protein)
num_atoms_lightdock = len(atoms)
if num_atoms_prody != num_atoms_lightdock:
raise SystemExit("Number of atoms is different")
protein_anm_ext, protein_all = extendModel(protein_anm, ca_atoms, protein, norm=True)
modes = []
for i in range(n_modes):
nm = protein_anm_ext.getEigvecs()[:, i].reshape((num_atoms_lightdock, 3))
modes.append(nm)
n_modes = int(sys.argv[2])
factor = float(sys.argv[3])
except:
usage()
raise SystemExit("Wrong command line")
protein = parsePDB(pdb_structure)
ca_atoms = protein.select('name CA')
protein_anm = ANM('protein ca')
protein_anm.buildHessian(ca_atoms)
protein_anm.calcModes(n_modes=n_modes)
print 'Normal modes calculated'
atoms, residues, chains = parse_complex_from_file(pdb_structure)
lightdock_structures = [{'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': pdb_structure}]
lightdock_structure = Complex.from_structures(lightdock_structures)
print 'Structure read by lightdock'
num_atoms_prody = len(protein.protein)
num_atoms_lightdock = len(atoms)
if num_atoms_prody != num_atoms_lightdock:
raise SystemExit("Number of atoms is different")
protein_anm_ext, protein_all = extendModel(protein_anm, ca_atoms, protein, norm=True)
modes = []
for i in range(n_modes):
nm = protein_anm_ext.getEigvecs()[:, i].reshape((num_atoms_lightdock, 3))
modes.append(nm)
num_anm_rec = setup['anm_rec']
num_anm_lig = setup['anm_lig']
# Receptor
structures = []
for structure in get_lightdock_structures(args.receptor_structures):
log.info("Reading %s receptor PDB file..." % structure)
atoms, residues, chains = parse_complex_from_file(structure)
structures.append({
'atoms': atoms,
'residues': residues,
'chains': chains,
'file_name': structure
})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
receptor = Complex.from_structures(structures)
# Ligand
structures = []
for structure in get_lightdock_structures(args.ligand_structures):
log.info("Reading %s ligand PDB file..." % structure)
atoms, residues, chains = parse_complex_from_file(structure)
structures.append({
'atoms': atoms,
'residues': residues,
'chains': chains,
'file_name': structure
})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
ligand = Complex.from_structures(structures)
atoms_to_ignore.append('OXT')
structures = []
file_names = []
file_name, file_extension = os.path.splitext(args.structure)
if file_extension == DEFAULT_LIST_EXTENSION:
file_names.extend(get_pdb_files(args.structure))
else:
file_names.append(args.structure)
for file_name in file_names:
log.info("Reading %s PDB file..." % file_name)
atoms, residues, chains = parse_complex_from_file(file_name, atoms_to_ignore)
structures.append({'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': file_name})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
molecule = Complex.from_structures(structures)
try:
ellipsoid = MinimumVolumeEllipsoid(molecule.atom_coordinates[0].coordinates)
except MinimumVolumeEllipsoidError, e:
log.error("Impossible to calculate minimum volume ellipsoid. Reason: %s" % str(e))
raise SystemExit("%s finished with error" % script_name)
output_file_name = molecule.structure_file_names[0] + DEFAULT_REFERENCE_POINTS_EXTENSION
with open(output_file_name, 'w') as output:
for point in ellipsoid.poles:
output.write(get_point_respresentation(point) + os.linesep)
output.write(get_point_respresentation(ellipsoid.center) + os.linesep)
log.info('Points written to %s' % output_file_name)
points = [point for point in ellipsoid.poles]
points.append(ellipsoid.center)
setup = get_setup_from_file(args.setup_file) if args.setup_file else None
num_anm_rec = DEFAULT_NMODES_REC
num_anm_lig = DEFAULT_NMODES_LIG
if setup and setup['use_anm']:
num_anm_rec = setup['anm_rec']
num_anm_lig = setup['anm_lig']
# Receptor
structures = []
for structure in get_lightdock_structures(args.receptor_structures):
log.info("Reading %s receptor PDB file..." % structure)
atoms, residues, chains = parse_complex_from_file(structure)
structures.append({'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': structure})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
receptor = Complex.from_structures(structures)
# Ligand
structures = []
for structure in get_lightdock_structures(args.ligand_structures):
log.info("Reading %s ligand PDB file..." % structure)
atoms, residues, chains = parse_complex_from_file(structure)
structures.append({'atoms': atoms, 'residues': residues, 'chains': chains, 'file_name': structure})
log.info("%s atoms, %s residues read." % (len(atoms), len(residues)))
ligand = Complex.from_structures(structures)
# Output file
translations, rotations, receptor_ids, ligand_ids, \
rec_extents, lig_extents = parse_output_file(args.lightdock_output, num_anm_rec, num_anm_lig)
found_conformations = len(translations)
