def count_struct_isomers(smiles_list):
"""
Counts the number of molecules with the same molecular formula
Keyword arguments:
smiles_list -- a list of smiles strings of the set/subset of molecules to look at
Returns:
"""
# formula: isomer count
dict_isomers = {}
# formula : smiles list
dict_smiles = {}
# weight : isomer count
dict_exactwt = {}
for mol_smiles in smiles_list:
mol = MolFromSmiles(mol_smiles)
formula = CalcMolFormula(mol)
weight = ExactMolWt(mol)
if formula in dict_isomers.keys():
dict_isomers[formula] += 1 # increase the isomer count by 1
dict_smiles[formula].append(
mol_smiles) # These are MOD's smiles, not RDKit's
dict_exactwt[
weight] += 1 # Weight calculated by RDKit, not MOD's in-built
else:
dict_isomers[formula] = 1
dict_smiles[formula] = [mol_smiles]
dict_exactwt[weight] = 1
return dict_exactwt # modify this as per your needs
def ghose_filter(self, filepath, exclude_salt=False):
r""" Filter the given file with ghose filter. If exclude_salt is true,
the molecule with atoms not in the no_salt_atoms list will also be
filtered out.
file_path (str): path to the .mol2 file or .gz file.
exclude_salt(bool): if filter out the molecule containg salt atoms.
=======================================================================
return (str): filtered string in Mol2 file format.
"""
reader = Mol2Reader(filepath)
blocks = reader.get_blocks()
filtered = list()
for block in tqdm(blocks):
mol = Chem.rdmolfiles.MolFromMol2Block(block, sanitize=False)
if mol is None:
continue
n_atoms = mol.GetNumAtoms()
if n_atoms < 20 or n_atoms > 70:
continue
mw = ExactMolWt(mol)
if mw < 180 or mw > 480:
continue
if exclude_salt:
atoms = mol.GetAtoms()
flag = 0
for atom in atoms:
if atom.GetSymbol() not in self.no_salt_atoms:
flag = 1
break
if flag == 1:
continue
filtered.append(block)
return "\n\n".join(filtered)
def calc_properties(smi):
# returns logP, TPSA, MW, MR
m = Chem.MolFromSmiles(smi.numpy())
logP = MolLogP(m)
tpsa = CalcTPSA(m)
# sas = calculateScore(m)
mw = ExactMolWt(m)
mr = MolMR(m)
return np.asarray(logP), np.asarray(tpsa), np.asarray(mw), np.asarray(mr)
def fill_calculated_fields(comp: metob.Compound, mol: Chem.rdchem.Mol) -> None:
assert mol is not None
comp.inchi_key = comp.inchi_key or Chem.inchi.InchiToInchiKey(comp.inchi)
comp.formula = comp.formula or Chem.rdMolDescriptors.CalcMolFormula(mol)
comp.mono_isotopic_molecular_weight = comp.mono_isotopic_molecular_weight or ExactMolWt(
mol)
comp.permanent_charge = comp.permanent_charge or Chem.GetFormalCharge(mol)
comp.number_components = comp.number_components or 1 # type: ignore
comp.num_free_radicals = comp.num_free_radicals or Chem.Descriptors.NumRadicalElectrons(
mol)
fill_neutralized_fields(comp, mol)
def _printinfo(mol):
mol2 = Chem.AddHs(mol)
AllChem.EmbedMolecule(mol2)
OUTPUT_FILENAME = "output.mol"
output_path = os.path.join(output_dir, OUTPUT_FILENAME)
with open(output_path, "w") as fp:
print(Chem.MolToMolBlock(mol2), file=fp)
print(CONFORMATION_KEY, output_path)
print(MOLW_KEY, ExactMolWt(mol2))
print(ATOMCOUNT_KEY, mol2.GetNumAtoms())
print(BONDCOUNT_KEY, mol2.GetNumBonds())
def sdf_text_worker(merged_results, vendors, num_mols, start_time, mol_counter,
fragment_counter, drug_like_counter, big_counter,
parent_fragment_collector, parent_drug_like_collector,
parent_big_collector, failures, addhs, embed, verbose):
if not verbose:
RDLogger.DisableLog('rdApp.*')
fragment_collector, drug_like_collector, big_collector = [], [], []
for index, row in merged_results.iterrows():
try:
mol = Chem.MolFromSmiles(row['smiles'])
if addhs:
mol = Chem.AddHs(mol)
if embed:
AllChem.EmbedMolecule(mol)
properties = {vendor: row[vendor] for vendor in vendors}
mol_name = ','.join([
identifier for identifier in properties.values()
if len(identifier) > 0
])
if len(mol_name) > 20:
mol_name = mol_name[:17] + '...'
mol.SetProp('_Name', mol_name)
properties['smiles'] = row['smiles']
molecular_weight = ExactMolWt(mol)
except:
failures.append(' '.join(['write_error', row['smiles']]))
molecular_weight = 10000
if molecular_weight < 1200:
if molecular_weight < 300:
with fragment_counter.get_lock():
fragment_counter.value += 1
fragment_collector.append(sdf_text(mol, properties))
elif 300 <= molecular_weight < 700:
with drug_like_counter.get_lock():
drug_like_counter.value += 1
drug_like_collector.append(sdf_text(mol, properties))
else:
with big_counter.get_lock():
big_counter.value += 1
big_collector.append(sdf_text(mol, properties))
with mol_counter.get_lock():
mol_counter.value += 1
update_progress(mol_counter.value / num_mols,
'Progress of writing',
((time.time() - start_time) / mol_counter.value) *
(num_mols - mol_counter.value))
parent_fragment_collector.extend(fragment_collector)
parent_drug_like_collector.extend(drug_like_collector)
parent_big_collector.extend(big_collector)
return
def mol_remover(smile, mol):
remove = False
reason = 0
if len(smile) == 0:
reason = "No smile this line, removed"
remove = True
#mol = MolFromSmiles(smile)
if ExactMolWt(mol) > 700:
reason = "Molecule too heavy, removed"
remove = True
"""
remover = SaltRemover(defnData = "[Cl]")
res = remover(mol)
if res is not None:
reason = "Include salt"
remove = True
"""
return remove, reason
def calc_properties(smi):
"""
:param smi:
:return: logP, TPSA, MR, MW
"""
m = Chem.MolFromSmiles(smi.numpy())
logP = np.asarray(MolLogP(m))
logP = (logP - LOGP_MEAN) / LOGP_STD
tpsa = np.asarray(CalcTPSA(m))
tpsa = np.log10(tpsa + 1)
tpsa = (tpsa - TPSA_MEAN) / TPSA_STD
# sas = calculateScore(m)
mw = np.asarray(ExactMolWt(m))
mw = np.log10(mw + 1)
mw = (mw - MW_MEAN) / MW_STD
mr = np.asarray(MolMR(m))
mr = np.log10(mr + 1)
mr = (mr - MR_MEAN) / MR_STD
return logP, tpsa, mr, mw