def molobjfilter(molobj):
# GetRingInfo
info = molobj.GetRingInfo()
n_rings = info.NumRings()
# if n_rings == 0:
# return False
# if n_rings > 2:
# return False
# really_small_space = [1, 5, 6, 7, 8]
really_small_space = [1, 6]
atoms = cheminfo.molobj_to_atoms(molobj)
if not is_allowed_atoms(atoms, allowed_atoms=really_small_space):
return False
# n_atoms = len(atoms)
# n_heavy_atoms, = np.where(atoms > 1)
# n_heavy_atoms = len(n_heavy_atoms)
#
# # no long chains
# aromatic_atoms = molobj.GetAromaticAtoms()
# aromatic_atoms = [atom for atom in aromatic_atoms]
# aromatic_atoms = [atom.GetAtomicNum() for atom in aromatic_atoms]
# n_atomatic_atoms = len(aromatic_atoms)
#
# n_non_aromatic_atoms = n_heavy_atoms - n_atomatic_atoms
#
# if n_non_aromatic_atoms > 7:
# return False
return True
def prepare_sdf_and_csv(smi, values, debug=True, **kwargs):
kelvin = np.array(values)
#
standard_deviation = np.std(kelvin)
mean = np.mean(kelvin)
# Load molecule information
molobj = Chem.MolFromSmiles(smi)
atoms = cheminfo.molobj_to_atoms(molobj)
n_atoms = len(atoms)
# NOTE This is a choice
# NOTE Filter organic chemistry
if n_atoms > 50: return None
if n_atoms < 4: return None
if not is_allowed_atoms(atoms): return None
molobj = Chem.AddHs(molobj)
if molobj is None: return None
molobj = cheminfo.conformationalsearch(smi)
if molobj is None: return None
# sdfstr = cheminfo.molobj_to_sdfstr(molobj)
if debug:
print("{:4.1f}".format(mean), "{:1.2f}".format(standard_deviation))
# return molobj, mean, standard_deviation, values
return molobj, values
def main():
import argparse
parser = argparse.ArgumentParser()
parser.add_argument('--scratch',
action='store',
help='',
metavar="DIR",
default="_tmp_")
parser.add_argument('--json', action='store', help='', metavar="FILE")
parser.add_argument('-j',
'--procs',
action='store',
help='pararallize',
metavar="int",
default=0,
type=int)
args = parser.parse_args()
if args.scratch[-1] != "/":
args.scratch += "/"
data = misc.load_json(args.json)
keys = data.keys()
keys = list(keys)
canonical_data = {}
for key in keys:
molobj, status = cheminfo.smiles_to_molobj(key)
if molobj is None:
print("error none mol:", key)
continue
smiles = cheminfo.molobj_to_smiles(molobj, remove_hs=True)
if "." in smiles:
print("error multi mol:", smiles)
continue
atoms = cheminfo.molobj_to_atoms(molobj)
if not is_mol_allowed(atoms):
print("error heavy mol:", smiles)
continue
canonical_data[smiles] = data[key]
misc.save_json(args.scratch + "molecule_data", canonical_data)
misc.save_obj(args.scratch + "molecule_data", canonical_data)
return
def merge_individual_mp(molobjs, filenames, procs=1, debug=True):
print("starting {:} procs".format(procs))
atoms_list = [cheminfo.molobj_to_atoms(molobj) for molobj in molobjs]
easyusage.parallel(filenames,
merge_results_filename, [atoms_list], {},
procs=procs)
return
def merge_results_cumulative(sdffile, filenames, debug=True, molid=0):
# init
energies = []
coordinates = []
representations = []
atoms = []
n_total = 0
molobjs = cheminfo.read_sdffile(sdffile[0])
molobjs = [molobj for molobj in molobjs]
atoms_list = [cheminfo.molobj_to_atoms(molobj) for molobj in molobjs]
for filename in filenames:
energies_next, coordinates_next, atoms = read_resulttxt(
atoms_list, filename)
representations_next = [
sim.get_representation(atoms, coord) for coord in coordinates_next
]
if len(energies) == 0:
energies += energies_next
coordinates += coordinates_next
representations += representations_next
n_total += len(energies_next)
continue
idxs = merge_asymmetric(atoms, energies_next, energies,
representations_next, representations)
n_new = 0
for i, idxl in enumerate(idxs):
N = len(idxl)
if N > 0: continue
energies.append(energies_next[i])
coordinates.append(coordinates_next[i])
representations.append(representations_next[i])
n_new += 1
if debug:
n_total += n_new
print(" - new", n_new)
print("total", n_total)
return
def merge_results_filenames(molobjs, filenames):
print("filenames")
# init
energies = []
coordinates = []
representations = []
atoms = []
n_total = 0
atoms_list = [cheminfo.molobj_to_atoms(molobj) for molobj in molobjs]
for filename in filenames:
merge_results_filename(filename, atoms_list)
return
def clean_data(listdata):
data = {}
atom_types = []
for row in listdata:
idx = row[0]
smi = row[1]
value = row[3]
value = float(value)
molobj, status = cheminfo.smiles_to_molobj(smi)
if molobj is None:
print("error:", smi)
continue
smi = cheminfo.molobj_to_smiles(molobj, remove_hs=True)
atoms = cheminfo.molobj_to_atoms(molobj)
# filter for organic chemistry
if not is_mol_allowed(atoms):
continue
atom_types += list(atoms)
if smi not in data:
data[smi] = []
data[smi].append(value)
atom_types, counts = np.unique(atom_types, return_counts=True)
for atom, count in zip(atom_types, counts):
print(atom, count)
keys = data.keys()
print("Total molecules", len(keys))
return data
def filter_molobj(molobj):
# GetRingInfo
info = molobj.GetRingInfo()
n_rings = info.NumRings()
# if n_rings == 0:
# return False
# if n_rings > 2:
# return False
atoms = cheminfo.molobj_to_atoms(molobj)
if not is_allowed_atoms(atoms):
return False
n_atoms = len(atoms)
n_heavy_atoms, = np.where(atoms > 1)
n_heavy_atoms = len(n_heavy_atoms)
# # no long chains
# aromatic_atoms = molobj.GetAromaticAtoms()
# aromatic_atoms = [atom for atom in aromatic_atoms]
# aromatic_atoms = [atom.GetAtomicNum() for atom in aromatic_atoms]
# n_atomatic_atoms = len(aromatic_atoms)
#
# n_non_aromatic_atoms = n_heavy_atoms - n_atomatic_atoms
#
# if n_non_aromatic_atoms > 7:
# return False
if n_heavy_atoms < 10:
return False
if n_heavy_atoms > 20:
return False
if n_atoms > 40:
return False
return True
def filter_dict(molecules):
keys = molecules.keys()
keys = list(keys)
max_atoms = 0
for key in keys:
molobj, status = cheminfo.smiles_to_molobj(key)
if molobj is None:
continue
status = filter_molobj(molobj)
if not status:
del molecules[key]
print(key, status)
continue
status = filter_value(molecules[key])
if not status:
print(status, key, molecules[key])
del molecules[key]
continue
# Report
atoms = cheminfo.molobj_to_atoms(molobj)
n_atoms = len(atoms)
if n_atoms > max_atoms:
max_atoms = n_atoms
continue
print("max atoms: ", max_atoms)
return molecules
def clean_data(df, scratch):
smiles = df.iloc[1]
data = {}
atom_types = []
for index, row in df.iterrows():
smi = row.smiles
value = row.mpC + 273.15
molobj, status = cheminfo.smiles_to_molobj(smi)
if molobj is None:
print("error:", smi)
continue
smi = cheminfo.molobj_to_smiles(molobj, remove_hs=True)
# Atoms
atoms = cheminfo.molobj_to_atoms(molobj)
atom_types += list(atoms)
if smi not in data:
data[smi] = []
data[smi].append(value)
atom_types, counts = np.unique(atom_types, return_counts=True)
for atom, count in zip(atom_types, counts):
print(atom, count)
misc.save_obj(scratch + "molecule_data", data)
misc.save_json(scratch + "molecule_data", data)
return
def ajax_submitquantum(request):
"""
Setup quantum calculation
"""
if not request.POST:
return {
'error': 'Error 128 - empty post',
'message': "Error. Empty post."
}
if not request.POST["sdf"]:
return {
'error': 'Error 132 - sdf key error',
'message': "Error. Missing information."
}
# Get coordinates from request
sdfstr = request.POST["sdf"].encode('utf-8')
# Get rdkit
molobj, status = cheminfo.sdfstr_to_molobj(sdfstr)
if molobj is None:
status = status.split("]")
status = status[-1]
return {'error': 'Error 141 - rdkit error', 'message': status}
try:
conf = molobj.GetConformer()
except ValueError:
# Error
return {
'error':
'Error 141 - rdkit error',
'message':
"Error. Server was unable to generate conformations for this molecule"
}
# If hydrogens not added, assume graph and optimize with forcefield
atoms = cheminfo.molobj_to_atoms(molobj)
if 1 not in atoms:
molobj = cheminfo.molobj_add_hydrogens(molobj)
cheminfo.molobj_optimize(molobj)
# TODO Check lengths of atoms
# TODO Define max in settings
# Fix sdfstr
sdfstr = sdfstr.decode('utf8')
for _ in range(3):
i = sdfstr.index('\n')
sdfstr = sdfstr[i + 1:]
sdfstr = "\n" * 3 + sdfstr
# hash on sdf (conformer)
hshobj = hashlib.md5(sdfstr.encode())
hashkey = hshobj.hexdigest()
calculation = request.dbsession.query(models.GamessCalculation) \
.filter_by(hashkey=hashkey).first()
if calculation is not None:
msg = {'hashkey': hashkey}
calculation.created = datetime.datetime.now()
return msg
print("new:", hashkey)
molecule_info = {"sdfstr": sdfstr, "molobj": molobj, "hashkey": hashkey}
msg = pipelines.gamess_quantum_pipeline(request, molecule_info)
return msg
#
#
#
calculation = request.dbsession.query(models.GamessCalculation) \
.filter_by(hashkey=hashkey).first()
if calculation is not None:
calculation.created = datetime.datetime.now()
return msg
else:
pass
# check if folder exists
here = os.path.abspath(os.path.dirname(__file__)) + "/"
datahere = here + "data/"
if os.path.isdir(datahere + hashkey):
# return msg
pass
else:
os.mkdir(datahere + hashkey)
os.chdir(datahere + hashkey)
# Minimize with forcefield first
molobj = cheminfo.molobj_add_hydrogens(molobj)
cheminfo.molobj_optimize(molobj)
header = """ $basis gbasis=pm3 $end
$contrl runtyp=optimize icharg=0 $end
$statpt opttol=0.0005 nstep=200 projct=.F. $end
"""
# Prepare gamess input
# inpstr = gamess.molobj_to_gmsinp(molobj, header)
# Save and run file
# with open("optimize.inp", "w") as f:
# f.write(inpstr)
#
# stdout, stderr = gamess.calculate(hashkey+".inp", store_output=False)
# with open("start.sdf", 'w') as f:
# f.write(cheminfo.molobj_to_sdfstr(molobj))
# Check output
# status, message = gamess.check_output(stdout)
os.chdir(here)
# if not status:
# msg["error"] = "error 192: QM Calculation fail"
# msg["message"] = message
# return msg
# Saveable sdf and reset title
sdfstr = cheminfo.molobj_to_sdfstr(molobj)
sdfstr = str(sdfstr)
for _ in range(2):
i = sdfstr.index('\n')
sdfstr = sdfstr[i + 1:]
sdfstr = "\n\n" + sdfstr
# Get a 2D Picture
# TODO Compute 2D coordinates
svgstr = cheminfo.molobj_to_svgstr(molobj, removeHs=True)
# Success, setup database
calculation = models.GamessCalculation()
calculation.smiles = smiles
calculation.hashkey = hashkey
calculation.sdf = sdfstr
calculation.svg = svgstr
calculation.created = datetime.datetime.now()
# Add calculation to the database
request.dbsession.add(calculation)
# Add smiles to counter
countobj = request.dbsession.query(models.Counter) \
.filter_by(smiles=smiles).first()
if countobj is None:
counter = models.Counter()
counter.smiles = smiles
counter.count = 1
request.dbsession.add(counter)
print(counter)
else:
countobj.count += 1
return msg
def get_conformations(molobj, torsions, resolutions, method="sqm", debug=False):
molobj = copy.deepcopy(molobj)
n_torsions = len(torsions)
# init energy
energies = []
states = []
coordinates = []
# no constraints
ffprop, forcefield = get_forcefield(molobj)
# Forcefield generation failed
if forcefield is None:
return [], [], []
# Get conformer and origin
conformer = molobj.GetConformer()
origin = conformer.GetPositions()
# Origin angle
origin_angles = []
# HACK rdkit requires int type for index
torsions = [[int(y) for y in x] for x in torsions]
for idxs in torsions:
angle = Chem.rdMolTransforms.GetDihedralDeg(conformer, *idxs)
origin_angles.append(angle)
# Get resolution angles
angle_iterator = clockwork.generate_angles(resolutions, n_torsions)
# set calculate func
if method == "ff":
# rdkit mmff
calculate_method = calculate_forcefield
cal_kwargs = {
"ffprop": ffprop,
"ff": forcefield
}
else:
atoms = cheminfo.molobj_to_atoms(molobj)
atoms_str = [cheminfo.convert_atom(atom) for atom in atoms]
smiles = quantum.get_smiles(atoms, origin)
calculate_method = calculate_mopac
cal_kwargs = {
"ffprop": ffprop,
"atoms": atoms,
"reference_smiles": smiles
}
for angle in angle_iterator:
# reset coordinates
set_coordinates(conformer, origin)
# Minimze with torsion angle constraint
# energy, pos, status = calculate_forcefield(molobj, conformer, torsions, origin_angles, angle,
# ffprop=ffprop,
# ff=forcefield)
if debug:
start = time.time()
energy, pos, status = calculate_method(molobj, conformer, torsions, origin_angles, angle, **cal_kwargs)
if debug:
end = time.time()
print("{:6.5f}s".format(end-start), "{:6.2f}".format(energy), status)
# collect
energies += [energy]
coordinates += [pos]
states += [status]
return np.asarray(energies), np.asarray(coordinates), np.asarray(states)
def parse_results(molidx,
readtemplate,
molobjs,
dump_results=None,
debug=True,
**kwargs):
"""
"""
if debug:
filename = dump_results.format(molidx)
if os.path.exists(filename):
print("exists", molidx)
return
print("parsing", molidx)
filename = readtemplate.format(molidx)
molobj = molobjs[molidx]
reference_smiles = cheminfo.molobj_to_smiles(molobj, remove_hs=True)
atoms = cheminfo.molobj_to_atoms(molobj)
n_atoms = len(atoms)
energies, coordinates, costs = merge.read_txt(filename, n_atoms)
oenergies = []
ocoordinates = []
ocosts = []
for i, energy, coord, cost in zip(range(len(energies)), energies,
coordinates, costs):
filename = "_tmp_mopac_/_" + str(molidx) + "-" + str(i) + "_"
try:
oenergy, ocoord = optmize_conformation(atoms,
coord,
filename=filename)
except:
print("unconverged", filename)
continue
m = get_molobj(atoms, ocoord)
smiles = cheminfo.molobj_to_smiles(m)
same_graph = (smiles == reference_smiles)
if same_graph:
oenergies.append(oenergy)
ocoordinates.append(ocoord)
ocosts.append(cost)
# print(smiles == reference_smiles, "{:5.2f}".format(energy), "{:5.2f}".format(oenergy), cost)
idxs = merge.merge_cost(atoms, oenergies, ocoordinates, ocosts)
renergies = []
rcoords = []
rcosts = []
for idx in idxs:
energy = oenergies[idx]
coord = ocoordinates[idx]
cost = ocosts[idx]
renergies.append(energy)
rcoords.append(coord)
rcosts.append(cost)
if dump_results is not None:
out = merge.dump_txt(renergies, rcoords, rcosts)
filename = dump_results.format(molidx)
f = open(filename, 'w')
f.write(out)
f.close()
return renergies, rcoords, rcosts
def merge_results_cumulative_prime(molid,
molobj,
filenametemplate,
debug=True,
dump_results=None,
iolock=None):
# the G list
combos = clockwork.generate_linear_costlist()
# init
energies = []
coordinates = []
representations = []
atoms = []
costs = []
n_total = 0
atoms = cheminfo.molobj_to_atoms(molobj)
n_atoms = len(atoms)
for combo in combos:
filename = filenametemplate.format(molid, *combo)
stdprint(filename, std="err", iolock=iolock)
energies_next, coordinates_next = read_txt(filename, n_atoms)
# file did not exists
if energies_next is None:
continue
representations_next = [
sim.get_representation(atoms, coord) for coord in coordinates_next
]
if len(energies) == 0:
n_new = len(energies_next)
energies += energies_next
coordinates += coordinates_next
representations += representations_next
costs += [combo] * n_new
n_total += n_new
continue
idxs = merge_asymmetric(atoms, energies_next, energies,
representations_next, representations)
n_new = 0
for i, idxl in enumerate(idxs):
N = len(idxl)
if N > 0: continue
energies.append(energies_next[i])
coordinates.append(coordinates_next[i])
representations.append(representations_next[i])
costs.append(combo)
n_new += 1
if debug:
n_total += n_new
print(" - new", n_new, file=sys.stderr)
print("total", n_total, file=sys.stderr)
if dump_results:
out = dump_txt(energies, coordinates, costs)
filename = dump_results.format(molid)
f = open(filename, 'w')
f.write(out)
f.close()
return energies, coordinates, costs
def parse_molandprop(*args, debug=False, **kwargs):
if len(args) > 1:
molobj = args[0]
props = args[1]
else:
molobj, props = args[0]
if molobj is None:
return None, None
keys = props.keys()
if "SMILES" not in keys:
return None, None
prop_smiles = props["SMILES"]
# Ignore multi molecules
if "." in prop_smiles:
if debug:
print(f"ignore: {prop_smiles}")
return None, None
# Count
atoms = cheminfo.molobj_to_atoms(molobj)
# if len(atoms) < 3:
# if debug:
# print("ignore small", props)
# return None, None
# if len(atoms) > 40:
# if debug:
# print("ignore large", props)
# return None, None
# atoms_carbons, = np.where(atoms == 6)
# if len(atoms_carbons) < 1:
# if debug:
# print("ignore non-org", props)
# return None, None
# Add hydrogens and optimize structure
molobj = cheminfo.molobj_add_hydrogens(molobj)
status = cheminfo.molobj_optimize(molobj)
# if unconverged
if status == 5:
# try the smiles
molobj, status = cheminfo.smiles_to_molobj(prop_smiles)
if molobj is None:
print("error", props)
return None, None
molobj = cheminfo.molobj_add_hydrogens(molobj)
status = cheminfo.molobj_optimize(molobj)
if status == 5:
print("error", props)
return None, None
idx_ref = [key for key in keys if "{measured}" in key]
idx_ref = idx_ref[0]
value = str(props[idx_ref])
if "<" in value:
return None, None
if ">" in value:
return None, None
idx_value = [key for key in keys if "measured, converted" in key]
idx_value = idx_value[0]
idx_unit = [key for key in keys if "UNIT" in key]
idx_unit = [key for key in idx_unit if "Point" in key]
idx_unit = idx_unit[0]
prop_unit = props[idx_unit]
prop_value = props[idx_value]
if prop_unit == "Celsius":
prop_value += 273.15
elif prop_unit == "K":
pass
else:
print("error unknown unit", prop_unit, props)
return None, None
return molobj, prop_value
