#### Corin Wagen and Eugene Kwan, 2019
filenames = sys.argv[1]
info = []
text_width = 70
to_rotate = [[1, 3, 5, 7], [9, 11, 13, 15], [5, 3, 6, 8], [12, 11, 14, 16]]
ensemble = ConformationalEnsemble()
for filename in sorted(glob.glob(filenames, recursive=True)):
if re.search("slurm", filename):
continue
try:
output_file = GaussianFile.read_file(filename)
if len(output_file.energies) > 0:
mol = output_file.get_molecule()
ensemble.add_molecule(mol,
energy=output_file.energies[-1] * 627.509)
except:
print(f"skipping f{filename} due to error...")
print(f"{len(ensemble.molecules)} conformers before elimination of redundant")
ensemble.eliminate_redundant(cutoff=0.6)
print(f"{len(ensemble.molecules)} conformers after elimination of redundant")
best_confs = ensemble.get_within_cutoff(cutoff=10)
for idx, molecule in enumerate(best_confs):
GaussianFile.write_molecule_to_file(
filenames = sys.argv[1]
energies = {}
dipole = {}
nics = {}
C1_charge = {}
O7_charge = {}
C8_charge = {}
C9_charge = {}
C12_charge = {}
for filename in sorted(glob.glob(filenames, recursive=True)):
if re.search("slurm", filename):
continue
(output_file, lines) = GaussianFile.read_file(filename, return_lines=True)
dist = int(round(output_file.get_molecule().get_distance(1, 8) * 1000))
energies[dist] = output_file.energies[-1]
try:
nics[dist] = -1 * parse.find_parameter(lines, "17 Bq Isotropic", 8,
4)[0]
except:
pass
try:
dipole_line = parse.search_for_block(lines, "Dipole", "Quadrupole")
fields = re.split(" +", dipole_line)
fields = list(filter(None, fields))
dipole[dist] = float(fields[-1])
#### Corin Wagen and Eugene Kwan, 2019
filenames = sys.argv[1]
cent = 1
lg = 7
nu = 8
plot = np.zeros(shape=(18, 18))
for filename in sorted(glob.glob(filenames, recursive=True)):
if re.search("slurm", filename):
continue
output_file = GaussianFile.read_file(filename)
energy = float(output_file.energies[-1]) * 627.509
mol = output_file.get_molecule()
lg_dist = mol.get_distance(cent, lg)
nu_dist = mol.get_distance(cent, nu)
idx1 = int(round((lg_dist - 1.5) * 10))
idx2 = int(round((nu_dist - 1.2) * 10))
plot[idx1][idx2] = energy
min_energy = np.min(plot)
plot = plot - min_energy
#### now to generate the graph...
list of cctk.Molecule objects (with len(thetas) * len(structures) elements)
"""
if idx >= len(angles):
return structures
else:
new_structures = [None] * (len(structures) * len(thetas))
current_idx = 0
for structure in structures:
for theta in thetas:
new_structures[current_idx] = copy.deepcopy(
structure.set_dihedral(*angles[idx],
theta,
check_result=False))
current_idx += 1
print(len(structures))
return rotate_angles_one_by_one(idx + 1, angles, thetas, new_structures)
mols = rotate_angles_one_by_one(0, to_rotate, angles, [output_file.molecule])
mols = rotate_angles_one_by_one(0, to_bin_rotate, bin_angles, mols)
for idx, molecule in enumerate(mols):
try:
molecule.check_for_conflicts()
GaussianFile.write_molecule_to_file(f"conformer_{idx:05d}.gjf",
molecule, "#p opt pm7", None)
except:
pass
import sys, argparse, re
from cctk import GaussianFile, XYZFile
#### Usage: python read_from_xyz.py -h "#p opt freq=noraman b3lyp/6-31g(d)" path/to/file.xyz
parser = argparse.ArgumentParser(prog="read_from_xyz.py")
parser.add_argument("--header", "-H", type=str)
parser.add_argument("filename")
args = vars(parser.parse_args(sys.argv[1:]))
assert args["filename"], "Can't read file without a filename!"
assert args["header"], "Can't write file without a header!"
file = XYZFile.read_file(args["filename"])
newfile = args["filename"].rsplit('/',1)[-1]
newfile = re.sub(r"xyz$", "gjf", newfile)
GaussianFile.write_molecule_to_file(
newfile,
file.molecule,
route_card=args["header"],
link0={"nprocshared": 16, "mem": "32GB"},
footer=None,
)
import sys, os, argparse, glob, re, copy
import numpy as np
from cctk import GaussianFile, Molecule, Group, Ensemble
from cctk.load_groups import load_group
parser = argparse.ArgumentParser(prog="hammett_swap.py")
parser.add_argument("filename")
args = vars(parser.parse_args(sys.argv[1:]))
assert args["filename"], "Can't resubmit files without a filename!"
#### read in output file
output_file = GaussianFile.read_file(args["filename"])
#### read in genecp footer
footer = ""
with open('footer', 'r') as file:
footer = file.read()
#### define groups and atoms
groups = ["NMe2", "OMe", "Me", "CF3", "CO2Me", "CN", "NO2", "F", "Cl", "SF5"]
p_atoms = [19, 30, 41]
ensemble = Ensemble()
headers = []
args = []
for group_name in groups:
print(f"adding {group_name}")
mol = copy.deepcopy(output_file.get_molecule().assign_connectivity())
group = load_group(group_name)
import numpy as np
from cctk import ConformationalEnsemble, GaussianFile
path = "starting_structure.gjf"
cent = 1
lg = 7
nu = 8
file = GaussianFile.read_file(path)
mol = file.get_molecule()
mol.assign_connectivity()
footer = f"B {cent} {lg} F\nB {cent} {nu} F\n"
for lg_dist in np.arange(1.5, 3.3, 0.1):
for nu_dist in np.arange(1.2, 3.0, 0.1):
mol.set_distance(cent, lg, lg_dist)
mol.set_distance(cent, nu, nu_dist)
mol.check_for_conflicts()
GaussianFile.write_molecule_to_file(
f"scan_{int(round(lg_dist*100))}_{int(round(nu_dist*100))}.gjf",
mol,
"#p opt=modredundant b3lyp/6-31+g(d) scrf=(smd, solvent=tetrahydrofuran)",
footer=footer)
#### Usage: ``python generate_pop.py "path/to/output/*.out"``
#### NOTE: It's crucial to wrap the wildcard-containing path in quotes!
#### NOTE: This file will reject any file that contains the string "slurm."
#### Corin Wagen and Eugene Kwan, 2019
parser = argparse.ArgumentParser(prog="resubmit.py")
parser.add_argument("filename")
args = vars(parser.parse_args(sys.argv[1:]))
assert args["filename"], "Can't resubmit files without a filename!"
ensembles = []
for filename in glob.iglob(args["filename"], recursive=True):
if re.search("slurm", filename):
continue
output_file = GaussianFile.read_file(filename)
ensembles.append(output_file.molecules)
new_ensemble = ConformationalEnsemble.join_ensembles(ensembles)
for mol in new_ensemble.molecules:
cc_dist = mol.get_distance(1, 8)
newfile = f"pop_{int(round(cc_dist*1000))}.gjf"
GaussianFile.write_molecule_to_file(newfile, mol, "#p pop=hirshfeld m062x/6-31g(d)", None)
print(f"generating {newfile}...")
import glob
import cctk
from cctk import GaussianFile, ConformationalEnsemble
filenames = sorted(list(glob.iglob("path*.gjf")))
ensemble = ConformationalEnsemble()
for filename in filenames:
output_file = GaussianFile.read_file(filename)
molecule = output_file.ensemble.molecules[-1]
ensemble.add_molecule(molecule)
template = ensemble.molecules[0]
atoms = [1, 2, 3, 4, 5, 6]
#ensemble = ensemble.align(to_geometry=0, comparison_atoms="heavy", compute_RMSD=False)
ensemble = ensemble.align(to_geometry=0,
comparison_atoms=atoms,
compute_RMSD=False)
template = ensemble.molecules[0]
for i, molecule in enumerate(ensemble.molecules):
filename = f"aligned_path_{i+1:03d}.gjf"
header = "#p"
footer = "\n"
GaussianFile.write_molecule_to_file(filename, molecule, header, footer)
ensemble = ConformationalEnsemble()
angles = [0, 60, 120, 180, 240, 241, 300]
for x in angles:
for y in angles:
mol.set_dihedral(1, 7, 6, 8, x)
mol.set_dihedral(23, 24, 25, 1, y)
ensemble.add_molecule(mol, copy=True)
old_num = len(ensemble)
ensemble = ensemble.eliminate_redundant()
new_num = len(ensemble)
print(
f"originally {old_num} conformers, but after eliminating redundant there are {new_num}!"
)
count = 0
for molecule in ensemble.molecules:
x = int(round(molecule.get_dihedral(1, 7, 6, 8)))
y = int(round(molecule.get_dihedral(23, 24, 25, 1)))
if molecule.check_for_conflicts():
GaussianFile.write_molecule_to_file(f"CpG_{x}_{y}.gjf",
molecule,
route_card="#p opt b3lyp/6-31g(d)")
count += 1
else:
print(f"x={x} y={y} no good - error")
print(f"wrote {count} molecules to files")