c_help = 'Atom ids to use for alignment (default = all heavy atoms)'
parser = argparse.ArgumentParser(description=description,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i', '--allow_inversion', help=i_help, action='store_true')
parser.add_argument('-f', '--output_format', help=f_help, default='cml')
parser.add_argument('-c', '--center_id', help=c_help, action='append', type=int)
parser.add_argument('ref_file', help='cml file containing the reference conformer that all others will be aligned to')
parser.add_argument('input_files', help='cml files containing the other conformers to be algigned',
nargs='+')
args = parser.parse_args()
input_names = args.input_files
if len(input_names) == 1 and '*' in input_names[0]:
# If the shell is dumb (powershell/cmd.exe), glob input files ourselves
from glob import glob
input_names = glob(input_names[0])
mols = [molecule.from_cml(i) for i in input_names]
ref_mol = molecule.from_cml(args.ref_file)
ref_num_atoms = len(ref_mol.atoms)
if args.center_id:
center_ids = [i - 1 for i in args.center_id]
else:
center_ids = [i.get_id() for i in ref_mol.atoms if i.num > 1]
for each_id in center_ids:
if not (0 <= each_id < ref_num_atoms):
raise ValueError, 'The atom id to align molecules at must be a valid atom id for the molecule, i.e. an integer between between 1 and %d inclusive.' %ref_num_atoms
for each_mol in mols:
if len(each_mol.atoms) != ref_num_atoms:
raise ValueError, 'Not all molecules to be aligned have the same number of atoms. Please retry with conformers of only one molecule'
ref_center = numpy.array([i.coords for i in ref_mol.atoms if i.get_id() in center_ids])
ref_mol.translate(-1*ref_center.mean(axis=0))
input_names = [path.split(i) for i in input_names]
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-s', '--scaling', help=scaling_help, type=float,
default=None)
parser.add_argument('-d', '--delta', help=delta_help, type=int, default=30)
parser.add_argument('-i', '--allow_inversion', help=i_help, action='store_true')
parser.add_argument('-o', '--output_name', help=o_help)
parser.add_argument('-f', '--output_format', help=f_help, default='cml')
parser.add_argument('-r', '--ring_generation', help=r_help, default=-1, type=int)
parser.add_argument('-a', '--avoid_division', help=a_help, action='store_true')
parser.add_argument('-b', '--break_at', help=b_help, action='append', type=int, nargs=2)
parser.add_argument('file_name', help='cml file containing the molecule')
args = parser.parse_args()
vary_rings = args.ring_generation
fix_or_split = []
try:
mol = molecule.from_cml(args.file_name)
except:
msg = 'Reading molecule failed. Please check that the file a) exists and b) is a .cml molecule file'
raise RuntimeError(msg)
if args.output_name is None:
in_name = os.path.normpath(args.file_name)
in_path_name, in_file_name = os.path.split(in_name)
base_file_name = os.path.join(in_path_name, 'Conformer_{0}_' + in_file_name)
# Make sure that the file extension is appropriate to the contents of the file
if args.output_format == 'xyz':
base_file_name = os.path.splitext(base_file_name)[0] + '.xyz'
elif args.output_format == 'gauss':
base_file_name = os.path.splitext(base_file_name)[0] + '.gjf'
elif args.output_format != 'cml':
base_file_name = os.path.splitext(base_file_name)[0] + '.inp'
else:
parser = argparse.ArgumentParser(description=description,
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-i', '--allow_inversion', help=i_help, action='store_true')
parser.add_argument('-f', '--output_format', help=f_help, default='cml')
parser.add_argument('-c', '--center_id', help=c_help, action='append', type=int)
parser.add_argument('ref_file', help='cml file containing the reference ' +
'conformer that all others will be aligned to')
parser.add_argument('input_files', help='cml files containing the other ' +
'conformers to be algigned', nargs='+')
args = parser.parse_args()
input_names = args.input_files
if len(input_names) == 1 and '*' in input_names[0]:
# If the shell is dumb (powershell/cmd.exe), glob input files ourselves
from glob import glob
input_names = glob(input_names[0])
mols = [molecule.from_cml(i) for i in input_names]
ref_mol = molecule.from_cml(args.ref_file)
ref_num_atoms = len(ref_mol.atoms)
if args.center_id:
center_ids = [i - 1 for i in args.center_id]
else:
center_ids = [i.get_id() for i in ref_mol.atoms if i.num > 1]
for each_id in center_ids:
if not (0 <= each_id < ref_num_atoms):
raise ValueError('The atom id to align molecules at must be a valid ' +
'atom id for the molecule, i.e. an integer between ' +
'between 1 and %d inclusive.' % ref_num_atoms)
for each_mol in mols:
if len(each_mol.atoms) != ref_num_atoms:
raise ValueError('Not all molecules to be aligned have the same ' +
'number of atoms. Please retry with conformers ' +
parser.add_argument('-n', '--no_rmsd', help=n_help, action='store_true')
parser.add_argument('-a', '--automatic', help=a_help, action='store_true')
parser.add_argument('-i', '--allow_inversion', help=i_help, action='store_true')
parser.add_argument('-u', '--uniqueness_cutoff', type=float, help=u_help, default=1.0)
parser.add_argument('-H', '--use_hierachical_clustering', help=c_help, action='store_true')
parser.add_argument('input_files', help='cml files containing the conformers to be analysed',
nargs='+')
# Prepare input
args = parser.parse_args()
input_names = args.input_files
for idx, i in enumerate(input_names):
if '*' in i:
# If the shell is dumb (powershell/cmd.exe), glob input files ourselves
input_names[idx:idx + 1] = glob(i)
mols = [molecule.from_cml(i) for i in input_names]
for i in mols:
canonicalise(i)
# Clean up the molecule names for pretty-printing
mol_names = [path.splitext(path.split(i)[1])[0] for i in input_names]
writer = csv.writer(args.output_name)
if args.use_hierachical_clustering:
cluster = cluster_hierarchy
else:
cluster = cluster_kmeans
# Validate input
if len(set([len(i.atoms) for i in mols])) != 1:
raise ValueError, 'Not all molecules to be analysed have the same number of atoms. Please retry with conformers of only one molecule'
if args.rmsd_arrange not in ['t', 'b', 'i']:
raise ValueError, 'RMSD arrangement must be by [t]orsion clustering, [b]ounding box clustering, or conformer [i]d'
formatter_class=argparse.RawDescriptionHelpFormatter)
parser.add_argument('-s', '--scaling', help=scaling_help, type=float,
default=None)
parser.add_argument('-d', '--delta', help=delta_help, type=int, default=30)
parser.add_argument('-i', '--allow_inversion', help=i_help, action='store_true')
parser.add_argument('-o', '--output_name', help=o_help)
parser.add_argument('-f', '--output_format', help=f_help, default='cml')
parser.add_argument('-r', '--ring_generation', help=r_help, default=-1, type=int)
parser.add_argument('-a', '--avoid_division', help=a_help, action='store_true')
parser.add_argument('-b', '--break_at', help=b_help, action='append', type=int, nargs=2)
parser.add_argument('file_name', help='cml file containing the molecule')
args = parser.parse_args()
vary_rings = args.ring_generation
fix_or_split = []
try:
mol = molecule.from_cml(args.file_name)
except:
msg = 'Reading molecule failed. Please check that the file a) exists and b) is a .cml molecule file'
raise RuntimeError(msg)
if args.output_name is None:
in_name = os.path.normpath(args.file_name)
in_path_name, in_file_name = os.path.split(in_name)
base_file_name = os.path.join(in_path_name, 'Conformer_{0}_' + in_file_name)
# Make sure that the file extension is appropriate to the contents of the file
if args.output_format == 'xyz':
base_file_name = os.path.splitext(base_file_name)[0] + '.xyz'
elif args.output_format == 'gauss':
base_file_name = os.path.splitext(base_file_name)[0] + '.gjf'
elif args.output_format != 'cml':
base_file_name= os.path.splitext(base_file_name)[0] + '.inp'
else:
parser.add_argument('-H',
'--use_hierachical_clustering',
help=c_help,
action='store_true')
parser.add_argument('input_files',
help='cml files containing the conformers' +
' to be analysed',
nargs='+')
# Prepare input
args = parser.parse_args()
input_names = args.input_files
for idx, i in enumerate(input_names):
if '*' in i:
# If the shell is dumb (powershell/cmd.exe), glob input files ourselves
input_names[idx:idx + 1] = glob(i)
mols = [molecule.from_cml(i) for i in input_names]
for i in mols:
canonicalise(i)
# Clean up the molecule names for pretty-printing
mol_names = [path.splitext(path.split(i)[1])[0] for i in input_names]
writer = csv.writer(args.output_name)
if args.use_hierachical_clustering:
cluster = cluster_hierarchy
else:
cluster = cluster_kmeans
# Validate input
if len(set([len(i.atoms) for i in mols])) != 1:
raise ValueError(
'Not all molecules to be analysed have the same number ' +
'of atoms. Please retry with conformers of only one molecule')