def write_fb_target_abinitio(self, records):
""" Write a list of {'energy': xxx, 'molecule': xxx, 'name': xxx} records into a new target folder """
# prepare folder for writing
target_name = 'abinitio_bond_angles'
target_folder = os.path.join(self.out_folder, target_name)
os.mkdir(target_folder)
os.chdir(target_folder)
# load data into a fb Molecule
out_m = Molecule()
out_m.elem = self.m.elem.copy()
out_m.xyzs = []
out_m.qm_energies = []
out_m.comms = []
for record in records:
qcmol = record['molecule']
energy = record['energy']
name = record.get('name', 'created by FBTargetBuilder')
m = self.qc_molecule_to_fb_molecule(qcmol)
assert m.elem == out_m.elem, 'Elements list of resulting qcmol is not consistent with self.m'
# append geometry
out_m.xyzs.append(m.xyzs[0])
# append energy
out_m.qm_energies.append(energy)
# append name
out_m.comms.append(name)
# write output
print(
f"Writing {len(records)} frames into targets/abinitio_bond_angles/traj.xyz"
)
out_m.write('traj.xyz')
print(
f"Writing {len(records)} frames into targets/abinitio_bond_angles/qdata.txt"
)
out_m.write('qdata.txt')
def qc_molecule_to_fb_molecule(self, qc_molecule):
""" Convert an qcportal.Molecule object to a forcebalance.molecule.Molecule object"""
m = Molecule()
m.elem = [Elements[i] for i in qc_molecule.atomic_numbers]
m.xyzs = [qc_molecule.geometry * bohr2ang]
m.molecular_charge = qc_molecule.molecular_charge
m.mult = qc_molecule.molecular_multiplicity
return m
def __init__(self, molecule=None):
# molecule.py can not parse psi4 input yet, so we use self.load_psi4_input() as a walk around
if molecule is None:
# create a fake molecule
molecule = Molecule()
molecule.elem = ['H']
molecule.xyzs = [[[0, 0, 0]]]
super(Psi4, self).__init__(molecule)
self.threads = None
def write_molecule_files(molecule_data_list):
molecule, e0 = molecule_data_list[0]
qcjson_mol = molecule.dict(encoding='json')
oemol = cmiles.utils.load_molecule(qcjson_mol)
# write the mol2 file using oechem
ofs.open(f'input.mol2')
oechem.OEWriteMolecule(ofs, oemol)
ofs.close()
# write the pdb file using ForceBalance Molecule
fbmol = Molecule(f'input.mol2')
fbmol.write(f'conf.pdb')
# write xyz file using a new ForceBalance Molecule object
m = Molecule()
m.elem = [Elements[i] for i in molecule.atomic_numbers]
m.xyzs = []
m.qm_energies = []
for mol, e in molecule_data_list:
m.xyzs.append(mol.geometry * bohr2ang)
m.qm_energies.append(e)
m.write("coords.xyz")
# write qdata.txt file with coords and energies
m.write('qdata.txt')
def read_sdf_to_fb_mol(filename):
""" read sdf file and return ForceBalance.molecule.Molecule object """
from forcebalance.molecule import Molecule, Elements
import numpy as np
mol_list = read_split_mols(filename)
assert len(mol_list) == 1, 'file contains multiple molecules'
oe_mol = mol_list[0]
# create a new molecule
fb_mol = Molecule()
# load elems
fb_mol.elem = [Elements[a.GetAtomicNum()] for a in oe_mol.GetAtoms()]
noa = len(fb_mol.elem)
# load coordinates
coords_dict = oe_mol.GetCoords()
fb_mol.xyzs = [np.array([coords_dict[i] for i in range(noa)])]
# load bonds
bonds, bond_orders = [], []
for oe_bond in oe_mol.GetBonds():
idx_a = oe_bond.GetBgnIdx()
idx_b = oe_bond.GetEndIdx()
bond = (idx_a, idx_b) if idx_a <= idx_b else (idx_b, idx_a)
bonds.append(bond)
bond_orders.append(oe_bond.GetOrder())
fb_mol.bonds = bonds
fb_mol.bond_orders = bond_orders
# load atomic formal charges
atomic_formal_charges = [a.GetFormalCharge() for a in oe_mol.GetAtoms()]
molecular_charge = sum(atomic_formal_charges)
fb_mol.Data['molecular_charge'] = molecular_charge
fb_mol.Data['atomic_formal_charges'] = atomic_formal_charges
# set the oe_mol as one attribute
fb_mol.oe_mol = oe_mol
# set the cmiles id
mapped_smiles = cmiles.utils.mol_to_smiles(oe_mol)
fb_mol.Data['cmiles_id'] = cmiles.generator.get_molecule_ids(mapped_smiles)
return fb_mol
from forcebalance.molecule import Molecule
from forcebalance.readfrq import read_frq_gen
# Frequency output file.
fout = sys.argv[1]
# Mode number, starting from 1.
modenum = int(sys.argv[2])
if modenum == 0:
raise RuntimeError("Start mode number from one, please")
frqs, modes, intens, elem, xyz = read_frq_gen(fout)
M = Molecule()
M.elem = elem[:]
M.xyzs = []
xmode = modes[modenum - 1]
xmode /= (np.linalg.norm(xmode)/np.sqrt(M.na))
xmode *= 0.3 # Reasonable vibrational amplitude
spac = np.linspace(0, 1, 101)
disp = np.concatenate((spac, spac[::-1][1:], -1*spac[1:], -1*spac[::-1][1:-1]))
for i in disp:
M.xyzs.append(xyz+i*xmode.reshape(-1,3))
M.comms = ['Vibrational Mode %i Frequency %.3f Displacement %.3f' % (modenum, frqs[modenum-1], disp[i]*(np.linalg.norm(xmode)/np.sqrt(M.na))) for i in range(len(M))]
M.write(os.path.splitext(fout)[0]+'.mode%03i.xyz' % modenum)
def gen_tid_calculated_molecules_list(torsiondrive_data,
forcefield,
verbose=False):
# gen dictionary with keys, including all tids in the input forcefield
ff_torsion_param_list = forcefield.get_parameter_handler(
'ProperTorsions').parameters
tid_calculated_molecules_list = {}
molecules_list_dict_from_td = defaultdict = {}
for torsion_param in ff_torsion_param_list:
tid_calculated_molecules_list[torsion_param.id] = []
if os.path.exists('tmp'):
shutil.rmtree('tmp')
os.mkdir('tmp')
os.chdir('tmp')
for entry_index, td_data in torsiondrive_data.items():
# pick a single initial molecule
qcmol = td_data['initial_molecules'][0]
# write input.mol2 file
qcjson_mol = qcmol.dict(encoding='json')
oemol = cmiles.utils.load_molecule(qcjson_mol)
ofs.open(f'input.mol2')
oechem.OEWriteMolecule(ofs, oemol)
ofs.close()
# test mol2 file
success, msg, molecule_labels = test_ff_mol2(forcefield, 'input.mol2')
if not success:
if verbose == True:
print(
'Error occured while testing input.mol2. Excluded in tid_calculated_molecules_list. '
)
continue
# check if the torsion scan contains one or more conformers forming strong internal H bonds
if success:
# write conf.pdb file
fbmol = FBMolecule(f'input.mol2')
# list of grid ids sorted
sorted_grid_ids = sorted(td_data['final_molecules'].keys())
# write scan.xyz
target_mol = FBMolecule()
target_mol.elem = fbmol.elem
target_mol.xyzs = []
target_mol.qm_energies = []
target_mol.qm_grads = []
for grid_id in sorted_grid_ids:
grid_qc_mol = td_data['final_molecules'][grid_id]
# convert geometry unit Bohr -> Angstrom
geo = grid_qc_mol.geometry * 0.529177
target_mol.xyzs.append(geo)
# add energy and gradient
target_mol.qm_energies.append(
td_data['final_energies'][grid_id])
target_mol.qm_grads.append(td_data['final_gradients'][grid_id])
target_mol.write('scan.xyz')
no_hbonds = check_Hbond(scan_fnm='scan.xyz', top_fnm='input.mol2')
if not no_hbonds:
if verbose == True:
print(
'Internal hydrogen bond detacted. Excluded in tid_calculated_molecules_list. '
)
success = False
if success:
mol_index = td_data['attributes']["canonical_isomeric_smiles"]
indices = td_data['keywords']['dihedrals'][0]
tid = molecule_labels['ProperTorsions'][tuple(indices)].id
# qcschema_molecules = [qcmol.dict(encoding='json') for qcmol in td_data['initial_molecules']]
tid_calculated_molecules_list[tid].append({
'mol_index': mol_index,
'indices': indices
})
qcschema_molecules = []
for qcmol in td_data['initial_molecules']:
j_dict = qcmol.dict(encoding='json')
qcschema_molecule = {
'symbols': j_dict['symbols'],
'geometry': j_dict['geometry'],
'connectivity': j_dict['connectivity'],
'molecular_charge': j_dict['molecular_charge'],
'molecular_multiplicity': j_dict['molecular_multiplicity']
}
qcschema_molecules.append(qcschema_molecule)
molecules_list_dict_from_td[mol_index] = qcschema_molecules
print("\n## Available torsion scans from QCArchive ##\n" + '-' * 90)
print(f"{'idx':<7} {'tid':7s} {'Number of torsion scans'}")
for idx, (tid, molecules_list) in enumerate(
tid_calculated_molecules_list.items()):
if len(molecules_list) > 0:
print(f'{idx:<7} {tid:7s} {len(molecules_list)}')
print('-' * 90)
os.chdir('..')
shutil.rmtree('tmp')
return tid_calculated_molecules_list, molecules_list_dict_from_td
def make_fb_targets():
result_mol_folders = [
os.path.join(results_folder, f) for f in os.listdir(results_folder)
if os.path.isdir(os.path.join(results_folder, f))
]
result_mol_folders.sort()
print(
f"\nLoading data from {len(result_mol_folders)} result folders under {results_folder}"
)
# output folder
if os.path.exists(out_folder):
shutil.rmtree(out_folder)
os.mkdir(out_folder)
target_names = []
for mol_folder in result_mol_folders:
mol_name = os.path.basename(mol_folder)
# the name of the molecules should be consistent with the mol_folder
mol_file = os.path.join(molecules_folder, mol_name + '.mol2')
molecule = Molecule(mol_file)
# find all torsion data
finished_scans = []
for f in os.listdir(mol_folder):
name, ext = os.path.splitext(f)
if ext == '.xyz':
finished_scans.append(name)
if len(finished_scans) == 0:
print(f'No finished scans found in {mol_folder}')
continue
# output target name
target_name = 'td_' + mol_name
target_names.append(target_name)
# make target folder
this_target_folder = os.path.join(out_folder, target_name)
os.mkdir(this_target_folder)
# read data from each finished scans
target_mol = Molecule()
target_mol.elem = molecule.elem
target_mol.xyzs = []
target_mol.qm_energies = []
target_mol.qm_grads = []
for f in finished_scans:
xyz_file = os.path.join(mol_folder, f + '.xyz')
m = Molecule(xyz_file)
target_mol.xyzs += m.xyzs
# read energy from comment line
energies = [float(comm.split()[-1]) for comm in m.comms]
target_mol.qm_energies += energies
# read gradient
grad_file = os.path.join(mol_folder, f + '.gradxyz')
grads = read_gradxyz(grad_file)
target_mol.qm_grads += grads
# write qdata.txt
target_mol.write(os.path.join(this_target_folder, 'qdata.txt'))
# write scan.xyz
target_mol.write(os.path.join(this_target_folder, 'scan.xyz'))
# write pdb
molecule.write(os.path.join(this_target_folder, 'conf.pdb'))
# copy mol2 file
shutil.copyfile(mol_file, os.path.join(this_target_folder,
'input.mol2'))
# write a note
with open(os.path.join(this_target_folder, 'notes.txt'), 'w') as fnote:
fnote.write(
"Notes: This target is made by make_fb_targets.py, using data from\n"
)
fnote.write(mol_file + '\n')
for f in finished_scans:
xyz_file = os.path.join(mol_folder, f + '.xyz')
grad_file = os.path.join(mol_folder, f + '.gradxyz')
fnote.write(xyz_file + '\n')
fnote.write(grad_file + '\n')
# write a target.in file for use in ForceBalance input
with open(os.path.join(out_folder, 'targets.in'), 'w') as fout:
for tname in target_names:
fout.write(target_str.format(name=tname) + '\n')
print(f"Targets generation finished!")
print(
f"You can copy contents in {os.path.join(out_folder, 'targets.in')} to your ForceBalance input file."
)
def make_torsiondrive_target(dataset_name, torsiondrive_data, test_ff=None):
"""
Make a folder of ForceBalance targets from the torsiondrive data
"""
target_name_prefix = 'td_' + dataset_name.replace(' ', '_')
# create new targets folder
if os.path.exists('targets'):
shutil.rmtree('targets')
os.mkdir('targets')
os.chdir('targets')
# write each entry as an individual target
target_idx = 0
n_targets = len(torsiondrive_data)
idx_fmt_string = get_int_fmt_string(n_targets)
target_names = []
print(f"Generating {n_targets} targets")
for entry_index, td_data in torsiondrive_data.items():
# pick a single initial molecule
qcmol = td_data['initial_molecules'][0]
# get mol_formula
mol_formula = qcmol.get_molecular_formula()
# create target folder
target_idx_str = idx_fmt_string.format(target_idx)
target_name = f"{target_name_prefix}_{target_idx_str}_{mol_formula}"
print(f"{target_idx}: {target_name}")
os.mkdir(target_name)
os.chdir(target_name)
# write a note
with open('note.txt', 'w') as notefile:
notefile.write(
f'Target generated from dataset {dataset_name}, entry {entry_index}'
)
# write input.mol2 file
qcjson_mol = qcmol.dict(encoding='json')
oemol = cmiles.utils.load_molecule(qcjson_mol)
ofs.open(f'input.mol2')
oechem.OEWriteMolecule(ofs, oemol)
ofs.close()
# test mol2 file
success = True
if test_ff != None:
success, msg, molecule_labels = test_ff_mol2(test_ff, 'input.mol2')
if not success:
if not os.path.exists('../error_mol2s'):
os.mkdir('../error_mol2s')
shutil.move(f'input.mol2', f'../error_mol2s/{target_name}.mol2')
with open(f'../error_mol2s/{target_name}_error.txt',
'w') as notefile:
notefile.write(f'{dataset_name}\ntarget_name {target_name}\n')
notefile.write(
f'entry {entry_index}\ntd_keywords {td_data["keywords"]}\n'
)
notefile.write(f'error message:\n{msg}')
# remove this folder
os.chdir('..')
shutil.rmtree(target_name)
else:
# write conf.pdb file
fbmol = Molecule(f'input.mol2')
fbmol.write(f'conf.pdb')
# list of grid ids sorted
sorted_grid_ids = sorted(td_data['final_molecules'].keys())
# write scan.xyz and qdata.txt files
target_mol = Molecule()
target_mol.elem = fbmol.elem
target_mol.xyzs = []
target_mol.qm_energies = []
target_mol.qm_grads = []
for grid_id in sorted_grid_ids:
grid_qc_mol = td_data['final_molecules'][grid_id]
# convert geometry unit Bohr -> Angstrom
geo = grid_qc_mol.geometry * 0.529177
target_mol.xyzs.append(geo)
# add energy and gradient
target_mol.qm_energies.append(
td_data['final_energies'][grid_id])
target_mol.qm_grads.append(td_data['final_gradients'][grid_id])
target_mol.write('scan.xyz')
target_mol.write('qdata.txt')
# check if the torsion scan contains one or more conformers forming strong internal H bonds
no_hbonds, hbonds = screening_Hbond(mol2_fnm='input.mol2',
scan_fnm='scan.xyz')
if no_hbonds != True:
msg = 'One or more internal H bonds exist.'
if not os.path.exists('../error_mol2s'):
os.mkdir('../error_mol2s')
shutil.move(f'input.mol2',
f'../error_mol2s/{target_name}.mol2')
with open(f'../error_mol2s/{target_name}_error.txt',
'w') as notefile:
notefile.write(
f'{dataset_name}\ntarget_name {target_name}\n')
notefile.write(
f'entry {entry_index}\ntd_keywords {td_data["keywords"]}\n'
)
notefile.write(f'error message:\n{msg}')
# remove this folder
os.chdir('..')
shutil.rmtree(target_name)
else:
# pick metadata to write into the metadata.json file
metadata = copy.deepcopy(td_data['keywords'])
metadata['dataset_name'] = dataset_name
metadata['entry_label'] = entry_index
metadata['canonical_smiles'] = td_data['attributes'].get(
'canonical_smiles', 'unknown')
metadata['torsion_grid_ids'] = sorted_grid_ids
# find SMIRKs for torsion being scaned if test_ff is provided
if test_ff:
metadata['smirks'] = []
metadata['smirks_ids'] = []
for torsion_indices in td_data['keywords']['dihedrals']:
param = molecule_labels['ProperTorsions'][tuple(
torsion_indices)]
metadata['smirks'].append(param.smirks)
metadata['smirks_ids'].append(param.id)
with open('metadata.json', 'w') as jsonfile:
json.dump(metadata, jsonfile, indent=2)
# finish this target
target_names.append(target_name)
os.chdir('..')
target_idx += 1
# write targets.{dataset_name}.in file
target_in_fnm = f"targets.{dataset_name.replace(' ', '_')}.in"
with open(target_in_fnm, 'w') as outfile:
for target_name in target_names:
outfile.write(target_in_str.format(name=target_name))
print(f"Successfull generated {len(target_names)} targets.")
print(
f"You can copy contents in {target_in_fnm} to your ForceBalance input file."
)
os.chdir('..')
espval.append(float(s[3]))
elif len(espxyz) > 0:
# After reading in a block of ESPs, don't read any more.
ESPMode = -1
if line.strip().startswith("Geometry (in Angstrom)"):
XMode = 1
EMode = len(elem) == 0
if 'Electrostatic Potential' in line.strip() and ESPMode == 0:
ESPMode = 1
if len(xyzs) == 0:
raise Exception('%s has length zero' % psiout)
return xyzs, elem, espxyz, espval
xyzs, elem, espxyz, espval = read_psi_xyzesp(sys.argv[1])
M = Molecule()
M.xyzs = xyzs
M.elem = elem
M.write('%s.xyz' % os.path.splitext(sys.argv[1])[0])
EM = Molecule()
EM.xyzs = [np.array(espxyz) * 0.52917721092]
EM.elem = ['H' for i in range(len(espxyz))]
EM.write('%s.espx' % os.path.splitext(sys.argv[1])[0], ftype="xyz")
M.qm_espxyzs = EM.xyzs
M.qm_espvals = [np.array(espval)]
M.write("qdata.txt")
np.savetxt('%s.esp' % os.path.splitext(sys.argv[1])[0], espval)
elif len(espxyz) > 0:
# After reading in a block of ESPs, don't read any more.
ESPMode = -1
if line.strip().startswith("Geometry (in Angstrom)"):
XMode = 1
EMode = len(elem) == 0
if 'Electrostatic Potential' in line.strip() and ESPMode == 0:
ESPMode = 1
if len(xyzs) == 0:
raise Exception('%s has length zero' % psiout)
return xyzs, elem, espxyz, espval
xyzs, elem, espxyz, espval = read_psi_xyzesp(sys.argv[1])
M = Molecule()
M.xyzs = xyzs
M.elem = elem
M.write('%s.xyz' % os.path.splitext(sys.argv[1])[0])
EM = Molecule()
EM.xyzs = [np.array(espxyz) * 0.52917721092]
EM.elem = ['H' for i in range(len(espxyz))]
EM.write('%s.espx' % os.path.splitext(sys.argv[1])[0], ftype="xyz")
M.qm_espxyzs = EM.xyzs
M.qm_espvals = [np.array(espval)]
M.write("qdata.txt")
np.savetxt('%s.esp' % os.path.splitext(sys.argv[1])[0], espval)
import os, sys, re
import numpy as np
from forcebalance.molecule import Molecule
from forcebalance.readfrq import read_frq_psi
# Psi4 output file.
psiout = sys.argv[1]
# Mode number, starting from 1.
modenum = int(sys.argv[2])
frqs, modes, elem, xyz = read_frq_psi(psiout)
M = Molecule()
M.elem = elem[:]
M.xyzs = []
xmode = modes[modenum - 1]
xmode /= (np.linalg.norm(xmode)/np.sqrt(M.na))
xmode *= 0.3 # Reasonable vibrational amplitude
spac = np.linspace(0, 1, 101)
disp = np.concatenate((spac, spac[::-1][1:], -1*spac[1:], -1*spac[::-1][1:-1]))
for i in disp:
M.xyzs.append(xyz+i*xmode)
M.comms = ['Vibrational Mode %i Frequency %.3f Displacement %.3f' % (modenum, frqs[modenum-1], disp[i]*(np.linalg.norm(xmode)/np.sqrt(M.na))) for i in range(len(M))]
M.write(os.path.splitext(psiout)[0]+'.mode%03i.xyz' % modenum)