def get_ro3_from_mol(mol):
"""
Get rule of three criteria for a fragment, i.e. molecular weight, logP, number of hydrogen bond acceptors/donors, number of rotatable bonds, and PSA.
Parameters
----------
mol : rdkit.Chem.rdchem.Mol
Fragment.
Returns
-------
pd.Series
Rule of three criteria for input fragment.
Notes
-----
Taken from: https://europepmc.org/article/med/14554012
"""
properties = QED.properties(mol)
mw = 1 if properties.MW < 300 else 0
logp = 1 if properties.ALOGP <= 3 else 0
hbd = 1 if properties.HBD <= 3 else 0
hba = 1 if properties.HBA <= 3 else 0
nrot = 1 if properties.ROTB <= 3 else 0
psa = 1 if properties.PSA <= 60 else 0
return pd.Series([mw, logp, hbd, hba, nrot, psa],
index="mw logp hbd hba nrot psa".split())
def compute_druglikeness(mol: Chem.rdchem.Mol):
"""Call RDKit to compute the drug likeness properties."""
try:
data = QED.properties(mol)
results = [getattr(data, key) for key in KEYS_DRUGS_LIKENESS]
except RuntimeError:
results = [None] * len(KEYS_DRUGS_LIKENESS)
return results
def getMoleculeProperties(m: Chem.rdchem.Mol, index: int):
qed = QED.properties(m)
return [
#index,
Descriptors.ExactMolWt(m),
qed[1],
qed[4],
qed[3]
]
def test_properties(self):
m = Chem.MolFromSmiles('N=C(CCSCc1csc(N=C(N)N)n1)NS(N)(=O)=O')
p = QED.properties(m)
self.assertAlmostEqual(p.MW, 337.456)
self.assertAlmostEqual(p.ALOGP, -0.55833)
self.assertAlmostEqual(p.HBA, 6)
self.assertAlmostEqual(p.HBD, 5)
self.assertAlmostEqual(p.PSA, 173.33)
self.assertAlmostEqual(p.ROTB, 7)
self.assertAlmostEqual(p.AROM, 1)
self.assertAlmostEqual(p.ALERTS, 3)
p = QED.properties(Chem.AddHs(m))
self.assertAlmostEqual(p.MW, 337.456)
self.assertAlmostEqual(p.ALOGP, -0.55833)
self.assertAlmostEqual(p.HBA, 6)
self.assertAlmostEqual(p.HBD, 5)
self.assertAlmostEqual(p.PSA, 173.33)
self.assertAlmostEqual(p.ROTB, 7)
self.assertAlmostEqual(p.AROM, 1)
self.assertAlmostEqual(p.ALERTS, 3)
def test_properties(self):
m = Chem.MolFromSmiles('N=C(CCSCc1csc(N=C(N)N)n1)NS(N)(=O)=O')
p = QED.properties(m)
self.assertAlmostEqual(p.MW, 337.456)
self.assertAlmostEqual(p.ALOGP, -0.55833)
self.assertAlmostEqual(p.HBA, 6)
self.assertAlmostEqual(p.HBD, 5)
self.assertAlmostEqual(p.PSA, 173.33)
self.assertAlmostEqual(p.ROTB, 7)
self.assertAlmostEqual(p.AROM, 1)
self.assertAlmostEqual(p.ALERTS, 3)
p = QED.properties(Chem.AddHs(m))
self.assertAlmostEqual(p.MW, 337.456)
self.assertAlmostEqual(p.ALOGP, -0.55833)
self.assertAlmostEqual(p.HBA, 6)
self.assertAlmostEqual(p.HBD, 5)
self.assertAlmostEqual(p.PSA, 173.33)
self.assertAlmostEqual(p.ROTB, 7)
self.assertAlmostEqual(p.AROM, 1)
self.assertAlmostEqual(p.ALERTS, 3)
def QSArproperties_test(array,forest, num, namefile):
##Bickerton, G.R.; Paolini, G.V.; Besnard, J.; Muresan, S.; Hopkins, A.L. (2012)
##Quantifying the chemical beauty of drugs,
##Nature Chemistry, 4, 90-98
##[https://doi.org/10.1038/nchem.1243]
#
##Wildman, S.A.; Crippen, G.M. (1999)
##Prediction of Physicochemical Parameters by Atomic Contributions,
##Journal of Chemical Information and Computer Sciences, 39, 868-873
##[https://doi.org/10.1021/ci990307l]
#
fw = open( 'QSAR-2D' + str(num) + str(namefile) + '.csv', 'w')
#
for line in array:
parameter= line.split(sep="\t",maxsplit=9)
peptide_seq = parameter[0]
peptide = parameter[1]
#
molpeptideLi = Chem.MolFromSmiles(peptide)
# subprocess
scoreSA_Li = calculateScore(molpeptideLi)
#
# Make Prediction Random-Forest
fp_vect_Li = genFP(molpeptideLi)
# Get probabilities
predictionsLi = forest.predict_proba(fp_vect_Li.reshape(1,-1))
#print ("Probability %s mutagenic %0.6f " % (sequence,predictionsLi[0][1]))
# See http://cdb.ics.uci.edu/cgibin/Smi2DepictWeb.py
propQSAR = QED.properties(molpeptideLi)
MolWeight = propQSAR.MW
MolLogP = propQSAR.ALOGP
HbondA = propQSAR.HBA
HbondD = propQSAR.HBD
PolarSA = propQSAR.PSA
Rbonds = propQSAR.ROTB
Aromatic = propQSAR.AROM
#
MolarRefractivity = Crippen.MolMR(molpeptideLi)
nAtoms = molpeptideLi.GetNumAtoms()
#
SynthAcces = scoreSA_Li
AmesMutagenic = predictionsLi[0][1]
#
result = ( str(MolWeight) + "\t" + str(MolLogP) + "\t" + str(HbondA) + "\t" + str(HbondD) + "\t" + str(PolarSA) + "\t" + str(Rbonds) + "\t" + str(MolarRefractivity) + "\t" + str(nAtoms) + "\t" + str(SynthAcces) + "\t" + str(AmesMutagenic) + "\t" + str (peptide_seq) + "\t" + str(peptide) + "\n")
#print (result)
fw.write(result)
fw.close()
def __init__(self,
mol=None,
mw=None,
logP=None,
hba=None,
hbd=None,
psa=None,
rotb=None,
arom=None):
self.molecule = mol if mol else None
self.molecule_name = mol.GetProp('_Name') if mol else None
self._qed = QED.properties(self.molecule) if mol else None
self.mw = mw if not mol else self._qed.MW
self.logP = logP if not mol else self._qed.ALOGP
self.hba = hba if not mol else self._qed.HBA
self.hbd = hbd if not mol else self._qed.HBD
self.psa = psa if not mol else self._qed.PSA
self.rotb = rotb if not mol else self._qed.ROTB
self.arom = arom if not mol else self._qed.AROM
def QSArproperties(mol, sa, seq, Ames):
propQSAR = QED.properties(mol)
"""Bickerton, G.R.; Paolini, G.V.; Besnard, J.; Muresan, S.; Hopkins, A.L. (2012)
Quantifying the chemical beauty of drugs,
Nature Chemistry, 4, 90-98
[https://doi.org/10.1038/nchem.1243]"""
#
"""Wildman, S.A.; Crippen, G.M. (1999)
Prediction of Physicochemical Parameters by Atomic Contributions,
Journal of Chemical Information and Computer Sciences, 39, 868-873
[https://doi.org/10.1021/ci990307l]"""
#
MolWeight = propQSAR.MW
MolLogP = propQSAR.ALOGP
HbondA = propQSAR.HBA
HbondD = propQSAR.HBD
PolarSA = propQSAR.PSA
Rbonds = propQSAR.ROTB
Aromatic = propQSAR.AROM
MolarRefractivity = Crippen.MolMR(mol)
SynthAcces = sa
nAtoms = mol.GetNumAtoms()
AmesMutagenic = Ames
def filter_mols(mols: List[Chem.Mol],
names: Optional[List[str]] = None,
max_atoms: int = 1000,
max_weight: float = 10000.,
max_logP: float = 10.,
**kwargs) -> Tuple[List[str], Optional[List[str]]]:
"""Filter a list of molecules according to input critera
Parameters
----------
mols : List[Chem.Mol]
the molecules to filter
names : Optional[List[str]] (Default = None)
a parallel list of names corresponding to each molecule
max_atoms : int (Default = 1000)
max_weight : float (Default = 10000)
max_logP : float (Default = 10)
Returns
-------
smis_filtered : List[str]
the SMILES strings corresponding to the filtered molecules
names_filtered : Optional[List[str]]
the names corresponding to the filtered molecules. None, if no names
were originally supplied
"""
names = names or []
smis_filtered = []
names_filtered = []
if names:
for mol, name in tqdm(zip(mols, names),
total=len(mols),
desc='Filtering mols',
unit='mol'):
if mol.GetNumHeavyAtoms() > max_atoms:
continue
props = QED.properties(mol)
if props.MW > max_weight:
continue
if props.ALOGP > max_logP:
continue
smis_filtered.append(mol_to_smi(mol))
names_filtered.append(name)
else:
names_filtered = None
for mol in tqdm(mols,
total=len(mols),
desc='Filtering mols',
unit='mol'):
if mol.GetNumHeavyAtoms() > max_atoms:
continue
props = QED.properties(mol)
if props.MW > max_weight:
continue
if props.ALOGP > max_logP:
continue
smis_filtered.append(mol_to_smi(mol))
return smis_filtered, names_filtered
