def confab_operator(filename, options, logfunction=None):
'''
'''
if logfunction is not None:
logfunction(
f'--> Performing conformational search and optimization on {filename}'
)
data = read_xyz(filename)
if len(data.atomcoords) > 1:
raise InputError(
f'Requested conformational search on file {filename} that already contains more than one structure.'
)
if len(
tuple(
connected_components(graphize(data.atomcoords[0],
data.atomnos)))) > 1:
raise InputError((
f'Requested conformational search on a molecular complex (file {filename}). '
'Confab is not suited for this task, and using TSCoDe\'s csearch> operator '
'is a better idea.'))
if len(set(data.atomnos) - {1, 6, 7, 8, 9, 15, 16, 17, 35, 53}) != 0:
raise InputError((
'Requested conformational search on a molecule that contains atoms different '
'than the ones for which OpenBabel Force Fields are parametrized. Please '
'perform this conformational search through the more sophisticated and better '
'integrated csearch> operator, part of the TSCoDe program.'))
confname = filename[:-4] + '_confab.xyz'
with suppress_stdout_stderr():
check_call(
f'obabel {filename} -O {confname} --confab --rcutoff 0.5 --original'
.split(),
stdout=DEVNULL,
stderr=STDOUT)
# running Confab through Openbabel
data = read_xyz(confname)
conformers = data.atomcoords
if len(conformers) > 10 and not options.let:
conformers = conformers[0:10]
logfunction(
f'Will use only the best 10 conformers for TSCoDe embed.\n')
os.remove(confname)
with open(confname, 'w') as f:
for i, conformer in enumerate(conformers):
write_xyz(conformer,
data.atomnos,
f,
title=f'Generated conformer {i}')
return confname
def _set_reactive_indexes(self, filename):
'''
Manually set the molecule reactive atoms from the ASE GUI, imposing
constraints on the desired atoms.
'''
from ase import Atoms
from ase.gui.gui import GUI
from ase.gui.images import Images
data = read_xyz(filename)
coords = data.atomcoords[0]
labels = ''.join([pt[i].symbol for i in data.atomnos])
atoms = Atoms(labels, positions=coords)
while atoms.constraints == []:
print((
'\nPlease, manually select the reactive atom(s) for molecule %s.'
'\nRotate with right click and select atoms by clicking. Multiple selections can be done by Ctrl+Click.'
'\nWith desired atom(s) selected, go to Tools -> Constraints -> Constrain, then close the GUI.'
) % (filename))
GUI(images=Images([atoms]), show_bonds=True).run()
return list(atoms.constraints[0].get_indices())
def opt_operator(filename, embedder, logfunction=None):
'''
'''
if logfunction is not None:
logfunction(
f'--> Performing {embedder.options.calculator} {embedder.options.theory_level} optimization on {filename}'
)
t_start = time.perf_counter()
data = read_xyz(filename)
conformers = data.atomcoords
energies = []
lowest_calc = _get_lowest_calc(embedder)
conformers, energies = _refine_structures(
conformers,
data.atomnos,
*lowest_calc,
loadstring='Optimizing conformer')
energies, conformers = zip(
*sorted(zip(energies, conformers), key=lambda x: x[0]))
energies = np.array(energies) - np.min(energies)
conformers = np.array(conformers)
# sorting structures based on energy
mask = energies < 10
# getting the structures to reject (Rel Energy > 10 kcal/mol)
if logfunction is not None:
s = 's' if len(conformers) > 1 else ''
s = f'Completed optimization on {len(conformers)} conformer{s}. ({time_to_string(time.perf_counter()-t_start)}).\n'
if max(energies) > 10:
s += f'Discarded {len(conformers)-np.count_nonzero(mask)}/{len(conformers)} unstable conformers (Rel. E. > 10 kcal/mol)\n'
conformers, energies = conformers[mask], energies[mask]
# applying the mask that rejects high energy confs
optname = filename[:-4] + '_opt.xyz'
with open(optname, 'w') as f:
for i, conformer in enumerate(conformers):
write_xyz(
conformer,
data.atomnos,
f,
title=
f'Optimized conformer {i} - Rel. E. = {round(energies[i], 3)} kcal/mol'
)
logfunction(s + '\n')
return optname
def neb_operator(filename, embedder):
'''
'''
embedder.t_start_run = time.perf_counter()
data = read_xyz(filename)
assert len(
data.atomcoords
) == 2, 'NEB calculations need a .xyz input file with two geometries.'
from tscode.ase_manipulations import ase_neb, ase_popt
reagents, products = data.atomcoords
title = filename[:-4] + '_NEB'
embedder.log(
f'--> Performing a NEB TS optimization. Using start and end points from {filename}\n'
f'Theory level is {embedder.options.theory_level} via {embedder.options.calculator}'
)
print('Getting start point energy...', end='\r')
_, reag_energy, _ = ase_popt(embedder, reagents, data.atomnos, steps=0)
print('Getting end point energy...', end='\r')
_, prod_energy, _ = ase_popt(embedder, products, data.atomnos, steps=0)
ts_coords, ts_energy, _ = ase_neb(embedder,
reagents,
products,
data.atomnos,
title=title,
logfunction=embedder.log,
write_plot=True,
verbose_print=True)
e1 = ts_energy - reag_energy
e2 = ts_energy - prod_energy
embedder.log(
f'NEB completed, relative energy from start/end points (not barrier heights):\n'
f' > E(TS)-E(start): {"+" if e1>=0 else "-"}{round(e1, 3)} kcal/mol\n'
f' > E(TS)-E(end) : {"+" if e2>=0 else "-"}{round(e2, 3)} kcal/mol')
if not (e1 > 0 and e2 > 0):
embedder.log(
f'\nNEB failed, TS energy is lower than both the start and end points.\n'
)
with open('Me_CONMe2_Mal_tetr_int_NEB_NEB_TS.xyz', 'w') as f:
write_xyz(ts_coords,
data.atomnos,
f,
title='NEB TS - see log for relative energies')
def run_tests():
import os
import time
from subprocess import CalledProcessError
os.chdir(os.path.dirname(os.path.realpath(__file__)))
from tscode.settings import (CALCULATOR, COMMANDS, DEFAULT_FF_LEVELS,
DEFAULT_LEVELS, FF_CALC, FF_OPT_BOOL, PROCS)
if CALCULATOR not in ('MOPAC','ORCA','GAUSSIAN','XTB'):
raise Exception(f'{CALCULATOR} is not a valid calculator. Use MOPAC, ORCA, GAUSSIAN or XTB.')
import numpy as np
from ase.atoms import Atoms
from ase.optimize import LBFGS
from tscode.ase_manipulations import get_ase_calc
from tscode.optimization_methods import opt_funcs_dict
from tscode.utils import (HiddenPrints, clean_directory, loadbar, read_xyz,
run_command, time_to_string)
os.chdir('tests')
t_start_run = time.perf_counter()
data = read_xyz('C2H4.xyz')
##########################################################################
print('\nRunning tests for TSCoDe. Settings used:')
print(f'{CALCULATOR=}')
if CALCULATOR != 'XTB':
print(f'{CALCULATOR} COMMAND = {COMMANDS[CALCULATOR]}')
print('\nTesting calculator...')
##########################################################################
opt_funcs_dict[CALCULATOR](data.atomcoords[0],
data.atomnos,
method=DEFAULT_LEVELS[CALCULATOR],
procs=PROCS,
read_output=False)
print(f'{CALCULATOR} raw calculator works.')
##########################################################################
atoms = Atoms('HH', positions=np.array([[0, 0, 0], [0, 0, 1]]))
atoms.calc = get_ase_calc((CALCULATOR, DEFAULT_LEVELS[CALCULATOR], PROCS, None))
LBFGS(atoms, logfile=None).run()
clean_directory()
print(f'{CALCULATOR} ASE calculator works.')
##########################################################################
print(f'\n{FF_OPT_BOOL=}')
ff = f'on. Calculator is {FF_CALC}. Checking its status.' if FF_OPT_BOOL else 'off.'
print(f'Force Field optimization is turned {ff}')
if FF_OPT_BOOL:
if FF_CALC == 'OB':
try:
print('Trying to import the OpenBabel Python Module...')
from openbabel import openbabel
print('Module imported successfully.')
except ImportError:
raise Exception(f'Could not import OpenBabel Python module. Is standalone openbabel correctly installed?')
else: # == 'XTB', 'GAUSSIAN'
opt_funcs_dict[FF_CALC](data.atomcoords[0],
data.atomnos,
method=DEFAULT_FF_LEVELS[FF_CALC],
procs=PROCS,
read_output=False)
print(f'{FF_CALC} FF raw calculator works.')
##########################################################################
atoms.calc = get_ase_calc((FF_CALC, DEFAULT_FF_LEVELS[FF_CALC], PROCS, None))
LBFGS(atoms, logfile=None).run()
clean_directory()
print(f'{FF_CALC} ASE calculator works.')
print('\nNo installation faults detected with the current settings. Running tests.')
##########################################################################
tests = []
for f in os.listdir():
if f.endswith('.txt'):
tests.append(os.path.realpath(f))
# os.chdir(os.path.dirname(os.getcwd()))
# os.chdir('tscode')
# # Back to ./tscode
times = []
for i, f in enumerate(tests):
name = f.split('\\')[-1].split('/')[-1][:-4] # trying to make it work for either Win, Linux (and Mac?)
loadbar(i, len(tests), f'Running TSCoDe tests ({name}): ')
t_start = time.perf_counter()
try:
with HiddenPrints():
run_command(f'python -m tscode {f} -n {name}')
except CalledProcessError as error:
print('\n\n--> An error occurred:\n')
print(error.stderr.decode("utf-8"))
quit()
t_end = time.perf_counter()
times.append(t_end-t_start)
loadbar(len(tests), len(tests), f'Running TSCoDe tests ({name}): ')
print()
for i, f in enumerate(tests):
print(' {:25s}{} s'.format(f.split('\\')[-1].split('/')[-1][:-4], round(times[i], 3)))
print(f'\nTSCoDe tests completed with no errors. ({time_to_string(time.perf_counter() - t_start_run)})\n')
def __init__(self, filename, reactive_indexes=None, debug=False):
'''
Initializing class properties: reading conformational ensemble file, aligning
conformers to first and centering them in origin.
:params filename: Input file name. Can be anything, .xyz preferred
:params reactive_indexes: Index of atoms that will link during the desired reaction.
May be either int or list of int.
:params hyper: bool, whether to calculate orbitals positions
'''
if not os.path.isfile(filename):
if '.' in filename:
raise SyntaxError((
f'Molecule {filename} cannot be read. Please check your syntax.'
))
raise SyntaxError((
f'The program is trying to read something that is not a valid molecule input ({filename}). '
+
'If this looks like a keyword, it is probably faulted by a syntax error.'
))
self.rootname = filename.split('.')[0]
self.name = filename
self.debug = debug
if isinstance(reactive_indexes, np.ndarray):
self.reactive_indexes = reactive_indexes
else:
self.reactive_indexes = np.array(reactive_indexes) if isinstance(
reactive_indexes, (tuple, list)) else ()
ccread_object = read_xyz(filename)
if ccread_object is None:
raise CCReadError(f'Cannot read file {filename}')
coordinates = np.array(ccread_object.atomcoords)
# if coordinates.shape[0] > 5:
# coordinates = coordinates[0:5]
# # Do not keep more than 5 conformations
self.atomnos = ccread_object.atomnos
self.position = np.array([0, 0, 0],
dtype=float) # used in Embedder class
self.rotation = np.identity(
3) # used in Embedder class - rotation matrix
assert all([
len(coordinates[i]) == len(coordinates[0])
for i in range(1, len(coordinates))
]), 'Ensembles must have constant atom number.'
# Checking that ensemble has constant length
if self.debug:
print(
f'DEBUG--> Initializing object {filename}\nDEBUG--> Found {len(coordinates)} structures with {len(coordinates[0])} atoms'
)
self.centroid = np.sum(np.sum(coordinates, axis=0), axis=0) / (
len(coordinates) * len(coordinates[0]))
if self.debug:
print('DEBUG--> Centroid was', self.centroid)
self.atomcoords = coordinates - self.centroid
self.graph = graphize(self.atomcoords[0], self.atomnos)
# show_graph(self)
self.atoms = np.array([
atom for structure in self.atomcoords for atom in structure
]) # single list with all atomic positions
if self.debug:
print(f'DEBUG--> Total of {len(self.atoms)} atoms')
def xtb_opt(coords,
atomnos,
constrained_indexes=None,
method='GFN2-xTB',
solvent=None,
title='temp',
read_output=True,
**kwargs):
'''
This function writes an XTB .inp file, runs it with the subprocess
module and reads its output.
:params coords: array of shape (n,3) with cartesian coordinates for atoms.
:params atomnos: array of atomic numbers for atoms.
:params constrained_indexes: array of shape (n,2), with the indexes
of atomic pairs to be constrained.
:params method: string, specifiyng the theory level to be used.
:params title: string, used as a file name and job title for the mopac input file.
:params read_output: Whether to read the output file and return anything.
'''
with open(f'{title}.xyz', 'w') as f:
write_xyz(coords, atomnos, f, title=title)
s = f'$opt\n logfile={title}_opt.log\n$end'
if constrained_indexes is not None:
s += '\n$constrain\n'
for a, b in constrained_indexes:
s += ' distance: %s, %s, %s\n' % (
a + 1, b + 1, round(norm_of(coords[a] - coords[b]), 5))
if method.upper() in ('GFN-XTB', 'GFNXTB'):
s += '\n$gfn\n method=1\n'
elif method.upper() in ('GFN2-XTB', 'GFN2XTB'):
s += '\n$gfn\n method=2\n'
s += '\n$end'
s = ''.join(s)
with open(f'{title}.inp', 'w') as f:
f.write(s)
flags = '--opt'
if method in ('GFN-FF', 'GFNFF'):
flags += ' tight'
# tighter convergence for GFN-FF works better
flags += ' --gfnff'
# declaring the use of FF instead of semiempirical
if solvent is not None:
if solvent == 'methanol':
flags += f' --gbsa methanol'
else:
flags += f' --alpb {solvent}'
elif method.upper() in ('GFN-FF', 'GFNFF'):
flags += f' --alpb thf'
try:
check_call(
f'xtb --input {title}.inp {title}.xyz {flags} > temp.log 2>&1'.
split(),
stdout=DEVNULL,
stderr=STDOUT)
except KeyboardInterrupt:
print('KeyboardInterrupt requested by user. Quitting.')
quit()
if read_output:
try:
outname = 'xtbopt.xyz'
opt_coords = read_xyz(outname).atomcoords[0]
energy = read_xtb_energy(outname)
clean_directory()
os.remove(outname)
for filename in ('gfnff_topo', 'charges', 'wbo', 'xtbrestart',
'xtbtopo.mol', '.xtboptok'):
try:
os.remove(filename)
except FileNotFoundError:
pass
return opt_coords, energy, True
except FileNotFoundError:
return None, None, False
def csearch_operator(filename, embedder):
'''
'''
embedder.log(f'--> Performing conformational search on {filename}')
t_start = time.perf_counter()
data = read_xyz(filename)
if len(data.atomcoords) > 1:
embedder.log(
f'Requested conformational search on multimolecular file - will do\n'
+
'an individual search from each conformer (might be time-consuming).'
)
calc, method, procs = _get_lowest_calc(embedder)
conformers = []
for i, coords in enumerate(data.atomcoords):
opt_coords = optimize(
coords, data.atomnos, calculator=calc, method=method,
procs=procs)[0] if embedder.options.optimization else coords
# optimize starting structure before running csearch
conf_batch = clustered_csearch(opt_coords,
data.atomnos,
title=f'{filename}, conformer {i+1}',
logfunction=embedder.log)
# generate the most diverse conformers starting from optimized geometry
conformers.append(conf_batch)
conformers = np.array(conformers)
batch_size = conformers.shape[1]
conformers = conformers.reshape(-1, data.atomnos.shape[0], 3)
# merging structures from each run in a single array
if embedder.embed is not None:
embedder.log(
f'\nSelected the most diverse {batch_size} out of {conformers.shape[0]} conformers for {filename} ({time_to_string(time.perf_counter()-t_start)})'
)
conformers = most_diverse_conformers(batch_size, conformers,
data.atomnos)
confname = filename[:-4] + '_confs.xyz'
with open(confname, 'w') as f:
for i, conformer in enumerate(conformers):
write_xyz(conformer,
data.atomnos,
f,
title=f'Generated conformer {i}')
# if len(conformers) > 10 and not embedder.options.let:
# s += f' Will use only the best 10 conformers for TSCoDe embed.'
# embedder.log(s)
embedder.log('\n')
return confname
def orca_opt(coords,
atomnos,
constrained_indexes=None,
method='PM3',
procs=1,
solvent=None,
title='temp',
read_output=True):
'''
This function writes an ORCA .inp file, runs it with the subprocess
module and reads its output.
:params coords: array of shape (n,3) with cartesian coordinates for atoms.
:params atomnos: array of atomic numbers for atoms.
:params constrained_indexes: array of shape (n,2), with the indexes
of atomic pairs to be constrained.
:params method: string, specifiyng the first line of keywords for the MOPAC input file.
:params title: string, used as a file name and job title for the mopac input file.
:params read_output: Whether to read the output file and return anything.
'''
s = '! %s Opt\n\n# ORCA input generated by TSCoDe\n\n' % (method)
if solvent is not None:
s += '\n' + get_solvent_line(solvent, 'ORCA', method) + '\n'
if procs > 1:
s += f'%pal nprocs {procs} end\n'
if constrained_indexes is not None:
s += f'%{""}geom\nConstraints\n'
# weird f-string to prevent python misinterpreting %
for a, b in constrained_indexes:
s += '{B %s %s C}\n' % (a, b)
s += 'end\nend\n\n'
s += '*xyz 0 1\n'
for i, atom in enumerate(coords):
s += '%s % .6f % .6f % .6f\n' % (pt[atomnos[i]].symbol, atom[0],
atom[1], atom[2])
s += '*\n'
s = ''.join(s)
with open(f'{title}.inp', 'w') as f:
f.write(s)
try:
check_call(f'{COMMANDS["ORCA"]} {title}.inp'.split(),
stdout=DEVNULL,
stderr=STDOUT)
except KeyboardInterrupt:
print('KeyboardInterrupt requested by user. Quitting.')
quit()
if read_output:
try:
opt_coords = read_xyz(f'{title}.xyz').atomcoords[0]
energy = read_orca_property(f'{title}_property.txt')
clean_directory()
return opt_coords, energy, True
except FileNotFoundError:
return None, None, False