def test7Fragment(self):
fragremover = rdMolStandardize.FragmentRemover()
mol = Chem.MolFromSmiles("CN(C)C.Cl.Cl.Br")
nm = fragremover.remove(mol)
self.assertEqual(Chem.MolToSmiles(nm), "CN(C)C")
lfragchooser = rdMolStandardize.LargestFragmentChooser()
mol2 = Chem.MolFromSmiles("[N+](=O)([O-])[O-].[CH3+]")
nm2 = lfragchooser.choose(mol2)
self.assertEqual(Chem.MolToSmiles(nm2), "O=[N+]([O-])[O-]")
lfragchooser2 = rdMolStandardize.LargestFragmentChooser(
preferOrganic=True)
nm3 = lfragchooser2.choose(mol2)
self.assertEqual(Chem.MolToSmiles(nm3), "[CH3+]")
def main( ):
args = UserInput()
if args.id is None:
args.id = 'ID'
if args.start is None:
args.start = 0
if args.end is None:
args.end = -1
df = RDkitRead(args.infile, args.id, removeHs=True, add_Hs=False)[int(args.start):int(args.end)].dropna()
remover = SaltRemover.SaltRemover()
normzer = rdMolStandardize.Normalizer()
chooser = rdMolStandardize.LargestFragmentChooser(preferOrganic=True)
## remove salts
print('\033[34m## Desalting moleucles...\033[0m\n')
df['mol'] = df.MOL.apply(remover.StripMol)
## choose largest fragment (most Hs)
print('\033[34m## Choosing moleucles...\033[0m\n')
df['mol2'] = df.mol.apply(chooser.choose)
## clean molecule (not really relevant?)
print('\033[34m## Cleaning moleucles...\033[0m\n')
df['mol3'] = df.mol2.apply(normzer.normalize)
## rewrite SMILES with newest mol3
print('\033[34m## Converting moleucles...\033[0m\n')
df['smiles'] = df.mol3.apply(Chem.MolToSmiles)
if args.format == 'sdf':
rdpd.WriteSDF(df, args.outpref+'.'+args.format, molColName='mol3', idName=args.id, properties=['smiles'])
elif args.format == 'smi':
df.to_csv(args.outpref+'.'+args.format, index=False, sep=' ', columns=['smiles',args.id], header=True)
def graph_corpus(input, output, suffix='sdf'):
metals = {'Na', 'Zn', 'Li', 'K', 'Ca', 'Mg', 'Ag', 'Cs', 'Ra', 'Rb', 'Al', 'Sr', 'Ba', 'Bi'}
voc = utils.VocGraph('data/voc_atom.txt')
inf = gzip.open(input)
if suffix == 'sdf':
mols = Chem.ForwardSDMolSupplier(inf)
total = 2e6
else:
mols = pd.read_table(input).drop_duplicates(subset=['Smiles']).dropna(subset=['Smiles'])
total = len(mols)
mols = mols.iterrows()
vals = {}
exps = {}
codes, ids = [], []
chooser = rdMolStandardize.LargestFragmentChooser()
disconnector = rdMolStandardize.MetalDisconnector()
normalizer = rdMolStandardize.Normalizer()
for i, mol in enumerate(tqdm(mols, total=total)):
if mol is None: continue
if suffix != 'sdf':
idx = mol[1]['Molecule ChEMBL ID']
mol = Chem.MolFromSmiles(mol[1].Smiles)
else:
idx = mol.GetPropsAsDict()
idx = idx['chembl_id']
try:
mol = disconnector.Disconnect(mol)
mol = normalizer.normalize(mol)
mol = chooser.choose(mol)
mol = disconnector.Disconnect(mol)
mol = normalizer.normalize(mol)
except:
print(idx)
symb = [a.GetSymbol() for a in mol.GetAtoms()]
# Nr. of the atoms
bonds = mol.GetBonds()
if len(bonds) < 4 or len(bonds) >= 63: continue
if {'C'}.isdisjoint(symb): continue
if not metals.isdisjoint(symb): continue
smile = Chem.MolToSmiles(mol)
try:
s0 = smile.replace('[O]', 'O').replace('[C]', 'C') \
.replace('[N]', 'N').replace('[B]', 'B') \
.replace('[2H]', '[H]').replace('[3H]', '[H]')
s0 = Chem.CanonSmiles(s0, 0)
code = voc.encode([smile])
s1 = voc.decode(code)[0]
assert s0 == s1
codes.append(code[0].reshape(-1).tolist())
ids.append(idx)
except Exception as ex:
print(ex)
print('Parse Error:', idx)
df = pd.DataFrame(codes, index=ids, columns=['C%d' % i for i in range(64*4)])
df.to_csv(output, sep='\t', index=True)
print(vals)
print(exps)
def corpus(input, output, suffix='sdf'):
if suffix =='sdf':
inf = gzip.open(input)
mols = Chem.ForwardSDMolSupplier(inf)
# mols = [mol for mol in suppl]
else:
df = pd.read_table(input).Smiles.dropna()
mols = [Chem.MolFromSmiles(s) for s in df]
voc = Voc('data/voc_smiles.txt')
charger = rdMolStandardize.Uncharger()
chooser = rdMolStandardize.LargestFragmentChooser()
disconnector = rdMolStandardize.MetalDisconnector()
normalizer = rdMolStandardize.Normalizer()
words = set()
canons = []
tokens = []
smiles = set()
for mol in tqdm(mols):
try:
mol = disconnector.Disconnect(mol)
mol = normalizer.normalize(mol)
mol = chooser.choose(mol)
mol = charger.uncharge(mol)
mol = disconnector.Disconnect(mol)
mol = normalizer.normalize(mol)
smileR = Chem.MolToSmiles(mol, 0)
smiles.add(Chem.CanonSmiles(smileR))
except:
print('Parsing Error:') #, Chem.MolToSmiles(mol))
for smile in tqdm(smiles):
token = voc.split(smile) + ['EOS']
if {'C', 'c'}.isdisjoint(token):
print('Warning:', smile)
continue
if not {'[Na]', '[Zn]'}.isdisjoint(token):
print('Redudent', smile)
continue
if 10 < len(token) <= 100:
words.update(token)
canons.append(smile)
tokens.append(' '.join(token))
log = open(output + '_voc.txt', 'w')
log.write('\n'.join(sorted(words)))
log.close()
log = pd.DataFrame()
log['Smiles'] = canons
log['Token'] = tokens
log.drop_duplicates(subset='Smiles')
log.to_csv(output + '_corpus.txt', sep='\t', index=False)
def choose_largest_fragment(mol):
"""Gets the largest fragment.
Parameters
----------
mol: rdkit.Chem.Mol
A molecule with various fragments in various sizes.
Returns
-------
mol: rdkit.Chem.Mol
Returns a molecule containing the largest fragment.
"""
return rdMolStandardize.LargestFragmentChooser().choose(mol)
def salt_remover(self, smiles: str) -> str:
"""
Removes salts and counterions. Non sanitizable molecules can't be processed
:param smiles: smiles string
:return cleaned_smiles:
"""
rmv = rdMolStandardize.LargestFragmentChooser()
if "." in smiles and Chem.MolFromSmiles(smiles):
cleaned_smiles = Chem.MolToSmiles(rmv.choose(self.smiles_mol))
else:
cleaned_smiles = smiles
return cleaned_smiles
def test7Fragment(self):
fragremover = rdMolStandardize.FragmentRemover()
mol = Chem.MolFromSmiles("CN(C)C.Cl.Cl.Br")
nm = fragremover.remove(mol)
self.assertEqual(Chem.MolToSmiles(nm), "CN(C)C")
lfragchooser = rdMolStandardize.LargestFragmentChooser()
mol2 = Chem.MolFromSmiles("[N+](=O)([O-])[O-].[CH3+]")
nm2 = lfragchooser.choose(mol2)
self.assertEqual(Chem.MolToSmiles(nm2), "O=[N+]([O-])[O-]")
lfragchooser2 = rdMolStandardize.LargestFragmentChooser(
preferOrganic=True)
nm3 = lfragchooser2.choose(mol2)
self.assertEqual(Chem.MolToSmiles(nm3), "[CH3+]")
fragremover = rdMolStandardize.FragmentRemover(skip_if_all_match=True)
mol = Chem.MolFromSmiles("[Na+].Cl.Cl.Br")
nm = fragremover.remove(mol)
self.assertEqual(nm.GetNumAtoms(), mol.GetNumAtoms())
smi3 = "CNC[C@@H]([C@H]([C@@H]([C@@H](CO)O)O)O)O.c1cc2c(cc1C(=O)O)oc(n2)c3cc(cc(c3)Cl)Cl"
lfParams = rdMolStandardize.CleanupParameters()
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol3 = Chem.MolFromSmiles(smi3)
lfrag3 = lfrag_params.choose(mol3)
self.assertEqual(Chem.MolToSmiles(lfrag3),
"CNC[C@H](O)[C@@H](O)[C@H](O)[C@H](O)CO")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserCountHeavyAtomsOnly = True
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol3 = Chem.MolFromSmiles(smi3)
lfrag3 = lfrag_params.choose(mol3)
self.assertEqual(Chem.MolToSmiles(lfrag3),
"O=C(O)c1ccc2nc(-c3cc(Cl)cc(Cl)c3)oc2c1")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserUseAtomCount = False
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol3 = Chem.MolFromSmiles(smi3)
lfrag3 = lfrag_params.choose(mol3)
self.assertEqual(Chem.MolToSmiles(lfrag3),
"O=C(O)c1ccc2nc(-c3cc(Cl)cc(Cl)c3)oc2c1")
smi4 = "CC.O=[Pb]=O"
lfParams = rdMolStandardize.CleanupParameters()
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol4 = Chem.MolFromSmiles(smi4)
lfrag4 = lfrag_params.choose(mol4)
self.assertEqual(Chem.MolToSmiles(lfrag4), "CC")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserCountHeavyAtomsOnly = True
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol4 = Chem.MolFromSmiles(smi4)
lfrag4 = lfrag_params.choose(mol4)
self.assertEqual(Chem.MolToSmiles(lfrag4), "O=[Pb]=O")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserUseAtomCount = False
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol4 = Chem.MolFromSmiles(smi4)
lfrag4 = lfrag_params.choose(mol4)
self.assertEqual(Chem.MolToSmiles(lfrag4), "O=[Pb]=O")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserCountHeavyAtomsOnly = True
lfParams.preferOrganic = True
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol4 = Chem.MolFromSmiles(smi4)
lfrag4 = lfrag_params.choose(mol4)
self.assertEqual(Chem.MolToSmiles(lfrag4), "CC")
lfParams = rdMolStandardize.CleanupParameters()
lfParams.largestFragmentChooserUseAtomCount = False
lfParams.preferOrganic = True
lfrag_params = rdMolStandardize.LargestFragmentChooser(lfParams)
mol4 = Chem.MolFromSmiles(smi4)
lfrag4 = lfrag_params.choose(mol4)
self.assertEqual(Chem.MolToSmiles(lfrag4), "CC")
def main(prm_file):
pref = prm_file.split('.sdf')[0]
print('## Reading file...')
prm_df = PandasTools.LoadSDF(prm_file,
smilesName='SMILES',
molColName='MOL',
includeFingerprints=False)
print(prm_df[:10])
## remove salts and rename the smiles
print('## Cleaning moleucles...')
remover = SaltRemover.SaltRemover()
chooser = rdMolStandardize.LargestFragmentChooser(preferOrganic=True)
prm_df['molx'] = prm_df.MOL.apply(remover.StripMol)
prm_df['mol'] = prm_df.molx.apply(chooser.choose)
prm_df['smiles'] = prm_df.mol.apply(Chem.MolToSmiles)
def add_cb(inp):
return 'CB_' + str(inp)
prm_df['ID'] = prm_df.CB_ID.apply(add_cb)
# prm_df['ID'] = prm_df.CB_ID
## shuffle
print('## Shuffling molecules...')
df = prm_df.sample(frac=1).reset_index(drop=True)
print(prm_df[:10])
## recalculate molecular properties
print('## Calculating properties...')
prm_df['qed'] = prm_df.mol.apply(QED.properties)
prm_df['MW'] = prm_df.qed.apply(lambda x: x.MW)
# prm_df['logP'] = prm_df.qed.apply(lambda x: x.ALOGP)
# prm_df['HBA'] = prm_df.qed.apply(lambda x: x.HBA)
# prm_df['HBD'] = prm_df.qed.apply(lambda x: x.HBD)
# prm_df['PSA'] = prm_df.qed.apply(lambda x: x.PSA)
# prm_df['ROTB'] = prm_df.qed.apply(lambda x: x.ROTB)
# prm_df['AROM'] = prm_df.qed.apply(lambda x: x.AROM)
# prm_df['HA'] = prm_df.mol.apply(rdchem.Mol.GetNumHeavyAtoms)
print(prm_df[:10])
print(' > number of molecules... ', len(prm_df))
## print out molecule properties and smiles (shuffled)
print('## Writing results...')
Cols_csv = [
'ID', 'MW', 'HA', 'logP', 'LogS', 'HBA', 'HBD', 'PSA', 'ROTB', 'AROM',
'SaltType', 'smiles'
]
Cols_smi = ['smiles', 'ID']
prm_df.loc[(prm_df.MW > 150.) & (prm_df.MW <= 300.)].to_csv(
pref + '.frag.csv.bz2',
sep=',',
float_format='%.2f',
columns=Cols_csv,
index=False)
prm_df.loc[(prm_df.MW > 150.) & (prm_df.MW <= 300.)].to_csv(
pref + '.frag.smi', sep='\t', columns=Cols_smi, index=False)
prm_df.loc[(prm_df.MW > 300.) & (prm_df.MW <= 400.)].to_csv(
pref + '.lead.csv.bz2',
sep=',',
float_format='%.2f',
columns=Cols_csv,
index=False)
prm_df.loc[(prm_df.MW > 300.) & (prm_df.MW <= 400.)].to_csv(
pref + '.lead.smi', sep='\t', columns=Cols_smi, index=False)
prm_df.loc[prm_df.MW > 400.].to_csv(pref + '.drug.csv.bz2',
sep=',',
float_format='%.2f',
columns=Cols_csv,
index=False)
prm_df.loc[prm_df.MW > 400.].to_csv(pref + '.drug.smi',
sep='\t',
columns=Cols_smi,
index=False)
prm_df.loc[prm_df.MW <= 150.].to_csv(pref + '.small.csv.bz2',
sep=',',
float_format='%.2f',
columns=Cols_csv,
index=False)
prm_df.loc[prm_df.MW <= 150.].to_csv(pref + '.small.smi',
sep='\t',
columns=Cols_smi,
index=False)