def _calculateDescriptors(mol):
df = pd.DataFrame(index=[0])
df["SlogP"] = rdMolDescriptors.CalcCrippenDescriptors(mol)[0]
df["SMR"] = rdMolDescriptors.CalcCrippenDescriptors(mol)[1]
df["LabuteASA"] = rdMolDescriptors.CalcLabuteASA(mol)
df["TPSA"] = Descriptors.TPSA(mol)
df["AMW"] = Descriptors.MolWt(mol)
df["ExactMW"] = rdMolDescriptors.CalcExactMolWt(mol)
df["NumLipinskiHBA"] = rdMolDescriptors.CalcNumLipinskiHBA(mol)
df["NumLipinskiHBD"] = rdMolDescriptors.CalcNumLipinskiHBD(mol)
df["NumRotatableBonds"] = rdMolDescriptors.CalcNumRotatableBonds(mol)
df["NumHBD"] = rdMolDescriptors.CalcNumHBD(mol)
df["NumHBA"] = rdMolDescriptors.CalcNumHBA(mol)
df["NumAmideBonds"] = rdMolDescriptors.CalcNumAmideBonds(mol)
df["NumHeteroAtoms"] = rdMolDescriptors.CalcNumHeteroatoms(mol)
df["NumHeavyAtoms"] = Chem.rdchem.Mol.GetNumHeavyAtoms(mol)
df["NumAtoms"] = Chem.rdchem.Mol.GetNumAtoms(mol)
df["NumRings"] = rdMolDescriptors.CalcNumRings(mol)
df["NumAromaticRings"] = rdMolDescriptors.CalcNumAromaticRings(mol)
df["NumSaturatedRings"] = rdMolDescriptors.CalcNumSaturatedRings(mol)
df["NumAliphaticRings"] = rdMolDescriptors.CalcNumAliphaticRings(mol)
df["NumAromaticHeterocycles"] = \
rdMolDescriptors.CalcNumAromaticHeterocycles(mol)
df["NumSaturatedHeterocycles"] = \
rdMolDescriptors.CalcNumSaturatedHeterocycles(mol)
df["NumAliphaticHeterocycles"] = \
rdMolDescriptors.CalcNumAliphaticHeterocycles(mol)
df["NumAromaticCarbocycles"] = \
rdMolDescriptors.CalcNumAromaticCarbocycles(mol)
df["NumSaturatedCarbocycles"] = \
rdMolDescriptors.CalcNumSaturatedCarbocycles(mol)
df["NumAliphaticCarbocycles"] = \
rdMolDescriptors.CalcNumAliphaticCarbocycles(mol)
df["FractionCSP3"] = rdMolDescriptors.CalcFractionCSP3(mol)
df["Chi0v"] = rdMolDescriptors.CalcChi0v(mol)
df["Chi1v"] = rdMolDescriptors.CalcChi1v(mol)
df["Chi2v"] = rdMolDescriptors.CalcChi2v(mol)
df["Chi3v"] = rdMolDescriptors.CalcChi3v(mol)
df["Chi4v"] = rdMolDescriptors.CalcChi4v(mol)
df["Chi1n"] = rdMolDescriptors.CalcChi1n(mol)
df["Chi2n"] = rdMolDescriptors.CalcChi2n(mol)
df["Chi3n"] = rdMolDescriptors.CalcChi3n(mol)
df["Chi4n"] = rdMolDescriptors.CalcChi4n(mol)
df["HallKierAlpha"] = rdMolDescriptors.CalcHallKierAlpha(mol)
df["kappa1"] = rdMolDescriptors.CalcKappa1(mol)
df["kappa2"] = rdMolDescriptors.CalcKappa2(mol)
df["kappa3"] = rdMolDescriptors.CalcKappa3(mol)
slogp_VSA = list(map(lambda i: "slogp_VSA" + str(i), list(range(1, 13))))
df = df.assign(**dict(zip(slogp_VSA, rdMolDescriptors.SlogP_VSA_(mol))))
smr_VSA = list(map(lambda i: "smr_VSA" + str(i), list(range(1, 11))))
df = df.assign(**dict(zip(smr_VSA, rdMolDescriptors.SMR_VSA_(mol))))
peoe_VSA = list(map(lambda i: "peoe_VSA" + str(i), list(range(1, 15))))
df = df.assign(**dict(zip(peoe_VSA, rdMolDescriptors.PEOE_VSA_(mol))))
MQNs = list(map(lambda i: "MQN" + str(i), list(range(1, 43))))
df = df.assign(**dict(zip(MQNs, rdMolDescriptors.MQNs_(mol))))
return df
def main(in_file, output):
Cmpds = {}
InMols = rdkit_open([in_file])
print('\n # Number of input molecule: {0}'.format(len(InMols)))
for mol in InMols:
m = {}
name = mol.GetProp('_Name').split()[0]
m['Name'] = name
m['Formula'] = rd.CalcMolFormula(mol)
m['SMILES'] = Chem.MolToSmiles(mol)
m['MW'] = rd._CalcMolWt(mol) # Molecular Weight
m['logP'] = rd.CalcCrippenDescriptors(mol)[0] # Partition coefficient
m['HDon'] = rd.CalcNumLipinskiHBD(mol) # Lipinski Hbond donor
m['HAcc'] = rd.CalcNumLipinskiHBA(mol) # Lipinski Hbond acceptor
m['TPSA'] = rd.CalcTPSA(mol) # Topological polar surface area
m['Rotat'] = rd.CalcNumRotatableBonds(mol, strict=True) # Rotatable bond
m['MolRef'] = rd.CalcCrippenDescriptors(mol)[1] # Molar refractivity
m['AliRing'] = rd.CalcNumAliphaticRings(mol) # Aliphatic ring number
m['AroRing'] = rd.CalcNumAromaticRings(mol) # Aromatic ring number
# m['Stereo'] = rd.CalcNumAtomStereoCenters(mol) # Stereo center number
# m['UnspStereo'] = rd.CalcNumUnspecifiedAtomStereoCenters(mol) # unspecified stereo
m['SMILES'] = Chem.MolToSmiles(mol,
isomericSmiles=True, allHsExplicit=False)
Cmpds[name] = m
####################################
df = pd.DataFrame.from_dict(Cmpds, orient='index')
df.index.name = 'Name'
# Columns of data to print out
Columns = [ 'Formula',
'MW', 'logP', 'HDon', 'HAcc', 'TPSA',
'Rotat', 'MolRef', 'AliRing', 'AroRing',
#'Stereo', 'UnspStereo',
'SMILES', ]
reorder = df[Columns]
# Output to CSV
reorder.to_csv( output+'.csv', sep=',', na_rep='NA', encoding='utf-8',
float_format='%.5f', header=True )
# Output to Excel
reorder.to_excel( output+'.xlsx', header=True, na_rep='NA' )
def main():
sub_df = pd.read_csv("submissions_final_result.csv")
cmp_ds = []
for _, row in sub_df.iterrows():
cmp_dict = {}
mol = Chem.MolFromSmiles(row['smiles_string'])
cmp_dict['submission_id'] = row['submission_id']
cmp_dict['smiles_string'] = row['smiles_string']
# Lipinski's rule
cmp_dict['h_bond_donor'] = rd.CalcNumLipinskiHBD(
mol) # Lipinski Hbond donor
cmp_dict['h_bond_acceptor'] = rd.CalcNumLipinskiHBA(
mol) # Lipinski Hbond acceptor
cmp_dict['moluclar_mass'] = rd._CalcMolWt(mol) # Molecular Weight
cmp_dict['log_p'] = rd.CalcCrippenDescriptors(mol)[
0] # Partition coefficient
# Topological polar surface area
cmp_dict['topological_polar_surface_area'] = rd.CalcTPSA(mol)
cmp_ds.append(cmp_dict)
result = pd.merge(sub_df,
pd.DataFrame(cmp_ds),
on=['submission_id', 'smiles_string'])
result.to_csv("lipinski_psa_result.csv", index=False, encoding='utf-8')
def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
try:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
hac = m.GetNumHeavyAtoms()
if hac == 0:
fmf = 0
else:
fmf = GetScaffoldForMol(m).GetNumHeavyAtoms() / hac
qed = QED.qed(m)
nrings_fused = fused_ring_count(m)
n_unique_hba_hbd_atoms = count_hbd_hba_atoms(m)
max_ring_size = len(max(m.GetRingInfo().AtomRings(), key=len, default=()))
n_chiral_centers = len(FindMolChiralCenters(m, includeUnassigned=True))
fcsp3_bm = rdMolDescriptors.CalcFractionCSP3(GetScaffoldForMol(m))
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3), round(qed, 3), hac, nrings_fused, n_unique_hba_hbd_atoms, \
max_ring_size, n_chiral_centers, round(fcsp3_bm, 3)
except:
sys.stderr.write(f'molecule {name} was omitted due to an error in calculation of some descriptors\n')
return None
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
try:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
hac = m.GetNumHeavyAtoms()
if hac == 0:
fmf = 0
else:
fmf = GetScaffoldForMol(m).GetNumHeavyAtoms() / hac
qed = QED.qed(m)
nrings_fused = fused_ring_count(m)
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3), round(qed, 3), hac, nrings_fused
except:
sys.stderr.write(
f'molecule {name} was omitted due to an error in calculation of some descriptors\n'
)
return None
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def calculate_crippen_logp(self):
'''
Calcules the Crippen LogP
:return: ClogP
'''
clogp = rdMolDescriptors.CalcCrippenDescriptors(self.mol)
return clogp[0]
def calculate_properties(self, mol):
"""this method calculates basic properties for the smiles
returns : list of int or float (properties)"""
properties = []
properties.append(mol.GetNumAtoms())
properties.append(desc.CalcCrippenDescriptors(mol)[0])
properties.append(desc.CalcTPSA(mol))
properties.append(desc.CalcNumRotatableBonds(mol))
properties.append(desc.CalcFractionCSP3(mol))
return properties
def __init__(self):
self.temp_dir = tempfile.TemporaryDirectory()
self.temp_sdf = tempfile.NamedTemporaryFile(delete=False,
suffix='.sdf',
dir=self.temp_dir.name)
self.api_cache = {}
self.esol = ESOLCalculator()
self._properties = [
('MW', 'Molecular Weight', '%.3f', Desc.MolWt),
('logP', 'Lipophilicity (logP)', '%.3f',
lambda mol: mDesc.CalcCrippenDescriptors(mol)[0]),
('TPSA', 'Total Polar Surface Area', '%.3f', mDesc.CalcTPSA),
('ESOL', 'Estimated Solubility', '%.3f', self.esol.calc_esol),
('HBA', '# H-Bond Acceptors', '%d', mDesc.CalcNumHBA),
('HBD', '# H-Bond Donors', '%d', mDesc.CalcNumHBD),
('RB', '# Rotatable Bonds', '%d', mDesc.CalcNumRotatableBonds),
('AR', '# Aromatic Rings', '%d', mDesc.CalcNumAromaticRings)
]
if not os.path.exists(API_SETTINGS):
return
with open(API_SETTINGS, 'r') as f:
self.api = json.load(f)
if self.api.get('overwrite'):
self._properties = []
# validate config
try:
required_endpoint_keys = ['url', 'method', 'data']
required_property_keys = ['description', 'format', 'path']
for endpoint in self.api.get('endpoints'):
if not endpoint.get('name'):
raise Exception('Invalid config: missing endpoint name')
test = [endpoint[k] for k in required_endpoint_keys]
for prop, info in endpoint.get('properties').items():
test = [info[k] for k in required_property_keys]
except KeyError as key:
raise Exception(
f'Invalid config: missing {key} on {endpoint["name"]}')
except TypeError:
raise Exception(f'Invalid config: array where object should be')
# register properties
for endpoint in self.api.get('endpoints'):
for prop, info in endpoint['properties'].items():
fn = partial(self.fetch_property, endpoint, prop)
p = (prop, info['description'], info['format'], fn)
self._properties.append(p)
def get_lipinksi_test(mol, rule_test):
mol.UpdatePropertyCache(strict=False)
MW = rdMolDescriptors.CalcExactMolWt(mol)
# Calculate mol features. NB CalcCrippenDescriptors returns tuple logP & mr_values
feature_values = [rdMolDescriptors.CalcCrippenDescriptors(mol)[0],
rdMolDescriptors.CalcNumLipinskiHBD(mol),
rdMolDescriptors.CalcNumLipinskiHBA(mol)]
test_rule = all(value <= rule_test for value in feature_values)
if MW < 500 and MW > 300 and test_rule == True:
return True
else:
return False
def calc(smi, name):
m = Chem.MolFromSmiles(smi)
if m is not None:
hba = rdMolDescriptors.CalcNumHBA(m)
hbd = rdMolDescriptors.CalcNumHBD(m)
nrings = rdMolDescriptors.CalcNumRings(m)
rtb = rdMolDescriptors.CalcNumRotatableBonds(m)
psa = rdMolDescriptors.CalcTPSA(m)
logp, mr = rdMolDescriptors.CalcCrippenDescriptors(m)
mw = rdMolDescriptors._CalcMolWt(m)
csp3 = rdMolDescriptors.CalcFractionCSP3(m)
fmf = GetScaffoldForMol(m).GetNumAtoms(onlyHeavy=True) / m.GetNumAtoms(onlyHeavy=True)
return name, hba, hbd, hba + hbd, nrings, rtb, round(psa, 2), round(logp, 2), round(mr, 2), round(mw, 2), \
round(csp3, 3), round(fmf, 3)
else:
sys.stderr.write('smiles %s cannot be parsed (%s)' % (smi, name))
return None
def __init__(self):
self.temp_dir = tempfile.TemporaryDirectory()
self.temp_sdf = tempfile.NamedTemporaryFile(delete=False,
suffix='.sdf',
dir=self.temp_dir.name)
self.esol = ESOLCalculator()
self._properties = [
('MW', 'Molecular Weight', '%.3f', Desc.MolWt),
('logP', 'Lipophilicity (logP)', '%.3f',
lambda mol: mDesc.CalcCrippenDescriptors(mol)[0]),
('TPSA', 'Total Polar Surface Area', '%.3f', mDesc.CalcTPSA),
('ESOL', 'Estimated Solubility', '%.3f', self.esol.calc_esol),
('HBA', '# H-Bond Acceptors', '%d', mDesc.CalcNumHBA),
('HBD', '# H-Bond Donors', '%d', mDesc.CalcNumHBD),
('RB', '# Rotatable Bonds', '%d', mDesc.CalcNumRotatableBonds),
('AR', '# Aromatic Rings', '%d', mDesc.CalcNumAromaticRings)
]
def calculate_properties(self, smiles=None, mol=None, props=[]):
"""this method calculates basic properties for the mol
returns : error (bool)"""
if len(props) == 0:
return True
if mol is None:
mol = Chem.MolFromSmiles(smiles)
if mol is None:
return True
if 'py_formula' in props:
self.data['py_formula'] = desc.CalcMolFormula(mol)
if 'py_em' in props:
self.data['py_em'] = round(desc.CalcExactMolWt(mol), 5)
if 'py_n_Cl_Br' in props:
all_atoms = []
for atom in mol.GetAtoms():
all_atoms.append(atom.GetSymbol())
n_Cl = all_atoms.count('Cl')
n_Br = all_atoms.count('Br')
self.data['py_n_Cl_Br'] = n_Cl + n_Br
if 'py_na' in props:
self.data['py_na'] = mol.GetNumAtoms()
if 'py_mw' in props:
self.data['py_mw'] = desc._CalcMolWt(mol)
if 'py_fsp3' in props:
self.data['py_fsp3'] = desc.CalcFractionCSP3(mol)
if 'py_rb' in props:
self.data['py_rb'] = desc.CalcNumRotatableBonds(mol)
if 'py_tpsa' in props:
self.data['py_tpsa'] = desc.CalcTPSA(mol)
if 'py_clogp' in props:
self.data['py_clogp'] = desc.CalcCrippenDescriptors(mol)[0]
if 'py_nar' in props:
self.data['py_nar'] = desc.CalcNumAromaticRings(mol)
if 'py_nhba' in props:
self.data['py_nhba'] = desc.CalcNumHBA(mol)
if 'py_nhbd' in props:
self.data['py_nhbd'] = desc.CalcNumHBD(mol)
return False
def calculate_scalar_descriptors(molecule, symbols):
features = list()
features.append(rdMD.CalcAsphericity(molecule))
features += list(rdMD.CalcCrippenDescriptors(molecule))
features.append(rdMD.CalcExactMolWt(molecule))
features.append(rdMD.CalcEccentricity(molecule))
features.append(rdMD.CalcFractionCSP3(molecule))
features.append(rdMD.CalcLabuteASA(molecule))
features.append(rdMD.CalcNPR1(molecule))
features.append(rdMD.CalcNPR2(molecule))
features.append(rdMD.CalcHallKierAlpha(molecule))
# elemental distribution
symbols = np.array(symbols)
features.append(np.sum(symbols == 'H'))
features.append(np.sum(symbols == 'C'))
features.append(np.sum(symbols == 'N'))
features.append(np.sum(symbols == 'O'))
features.append(np.sum(symbols == 'F'))
# ring features
features.append(rdMD.CalcNumAliphaticCarbocycles(molecule))
features.append(rdMD.CalcNumAliphaticHeterocycles(molecule))
features.append(rdMD.CalcNumAromaticCarbocycles(molecule))
features.append(rdMD.CalcNumAromaticHeterocycles(molecule))
features.append(rdMD.CalcNumSaturatedCarbocycles(molecule))
features.append(rdMD.CalcNumSaturatedHeterocycles(molecule))
features.append(rdMD.CalcNumSpiroAtoms(
molecule)) # atom shared between rings with one bond
features.append(rdMD.CalcNumBridgeheadAtoms(
molecule)) # atom shared between rings with at least two bonds
# other counts
features.append(rdMD.CalcNumAmideBonds(molecule))
features.append(rdMD.CalcNumHBA(molecule)) # number of hydrogen acceptors
features.append(rdMD.CalcNumHBD(molecule)) # number of hydrogen donors
return np.array(features)
def get_fingerprint(SMILES=None, E_BIND=None):
"""
PRE: Takes in a MOLECULE as a SMILES
POST: Prints its finger prints as two list, the first contains the names, the second contains the fingerprints
"""
def get_atoms_coords(RDKIT_BLOCK):
"""Takes as input an RDKIT BLOCK and returns a list of atoms with a numpy array containing the coordinates"""
RDKIT_BLOCK = RDKIT_BLOCK.split('\n')
atm_number = int(RDKIT_BLOCK[3][:3])
RDKIT_BLOCK = [x.split() for x in RDKIT_BLOCK]
atm_list = []
coords_array = np.zeros([atm_number, 3], dtype=float)
for i, line in enumerate(RDKIT_BLOCK[4:4 + atm_number]):
coords_atm = line
atm_list.append(coords_atm[3])
coords_array[i, :] = coords_atm[:3]
return atm_list, coords_array
def get_atom_types(mol):
"""
PRE: Takes in the mol
POST: Returns a dictionary with the atom types and numbers
"""
atom_types = {}
for atom in mol.GetAtoms():
symbol = atom.GetSymbol()
if symbol in atom_types:
atom_types[symbol] += 1
else:
atom_types[symbol] = 1
return atom_types
def AreRingFused(mol):
"""
PRE : Takes in a mol rdkit
POST : Returns the max number of fused rings. That is the maximum number of rings any atom belongs to
"""
rings = Chem.GetSymmSSSR(mol)
ring_dic = {}
for ring in rings:
for atom in list(ring):
if atom in ring_dic:
ring_dic[atom] += 1
else:
ring_dic[atom] = 1
if ring_dic.values() == []:
return 0
else:
return max(ring_dic.values())
def getVolume(mol, atom_types):
"""
PRE: Takes in a mol with HYDROGENS ADDED
POST: Returns its volume computed as a linear combination of the contribution of the vdW volumes
"""
index_of_vols = {'H': 7.24, 'C': 20.58, 'N': 15.60, 'O': 14.71, 'F': 13.31, 'Cl': 22.45, 'Br': 26.52,
'I': 32.52, 'P': 24.43, 'S': 24.43, 'As': 26.52, 'B': 40.48, 'Si': 38.79, 'Se': 28.73,
'Te': 36.62}
gross_volume = 0
# for sym in atom_types:
# gross_volume += atom_types[sym] * index_of_vols[sym]
bonds = mol.GetNumBonds()
rings = Chem.GetSymmSSSR(mol)
# print 'aromatic ring count is ',descriptors.CalcNumAromaticRings(mol)
# print 'aliphatic ring count is ',descriptors.CalcNumAliphaticRings(mol)
ra = 0
largest_ra = 0
rna = 0
largest_rna = 0
for ringId in range(len(rings)):
if isRingAromatic(mol, tuple(rings[ringId])):
ra += 1
if largest_ra < len(rings[ringId]):
largest_ra = len(rings[ringId])
else:
rna += 1
if largest_rna < len(rings[ringId]):
largest_rna = len(rings[ringId])
# volume = gross_volume - 5.92 * bonds - 14.7 * ra - 3.8 * rna
try:
AllChem.EmbedMolecule(mol)
AllChem.MMFFOptimizeMolecule(mol)
volume = AllChem.ComputeMolVolume(mol)
except:
raise ValueError("Can't build the molecule")
return volume, ra, rna, largest_ra, largest_rna
def isRingAromatic(mol, ring):
"""
PRE: Takes in a mol and a ring given as a tuple of atom id
POST: Returns TRUE is all the atoms inside the ring are aromatic and FALSE otherwise
"""
aromatic = True
for ids in ring:
if mol.GetAtomWithIdx(ids).GetIsAromatic():
# print ids
pass
else:
aromatic = False
break
return aromatic
mol = SMILES
features = [
'atomNbr',
'Volume',
'NAtom',
'OAtom',
'SAtom',
'PAtom',
'ClAtom',
'BrAtom',
'FAtom',
'IAtom',
'AromaticRingNumber',
'LargestAromaticRingAtomNbr',
'NonAromaticRingNumber',
'LargestNonAromaticRingAtomNbr',
'MaxNbrFusedRings',
'SurfaceArea',
'Charge',
# 'MinRadiusOfCylinder',
# 'RadiusOfCylinderBestConf',
'NitroNbr',
'AlcoholNbr',
'KetoneNbr',
'NitrileNbr',
'ThiolNbr',
'Phenol_likeNbr',
'EsterNbr',
'SulfideNbr',
'CarboxilicAcidNbr',
'EtherNbr',
'AmideNbr',
'AnilineNbr',
'PrimaryAmineNbr',
'SecondaryAmineNbr',
'RotableBondNum',
'HBondDonor',
'HBondAcceptor',
'MolLogP',
'MolMR'
]
for i in range(6):
features.append('Chi{}v'.format(i + 1))
features.append('Chi{}n'.format(i + 1))
if i < 3:
features.append('Kappa{}'.format(i + 1))
feature_dic = dict.fromkeys(features)
if mol == None:
return sorted(feature_dic.keys())
mol = Chem.MolFromSmiles(SMILES)
mol = Chem.AddHs(mol)
feature_dic['RotableBondNum'] = descriptors.CalcNumRotatableBonds(mol)
for i in range(6):
feature_dic['Chi{}v'.format(i + 1)] = descriptors.CalcChiNv(mol, i + 1)
feature_dic['Chi{}n'.format(i + 1)] = descriptors.CalcChiNn(mol, i + 1)
feature_dic['Kappa1'] = descriptors.CalcKappa1(mol)
feature_dic['Kappa2'] = descriptors.CalcKappa2(mol)
feature_dic['Kappa3'] = descriptors.CalcKappa3(mol)
feature_dic['HBondAcceptor'] = descriptors.CalcNumHBA(mol)
feature_dic['HBondDonor'] = descriptors.CalcNumHBD(mol)
CrippenDescriptors = descriptors.CalcCrippenDescriptors(mol)
feature_dic['MolLogP'] = CrippenDescriptors[0]
feature_dic['MolMR'] = CrippenDescriptors[1]
atom_types = get_atom_types(mol)
for feat, symbol in zip(['NAtom', 'OAtom', 'SAtom', 'PAtom', 'ClAtom', 'BrAtom', 'FAtom', 'IAtom'],
['N', 'O', 'S', 'P', 'Cl', 'Br', 'F', 'I']):
if symbol in atom_types:
feature_dic[feat] = atom_types[symbol]
else:
feature_dic[feat] = 0
feature_dic['atomNbr'] = mol.GetNumHeavyAtoms()
feature_dic['Volume'], feature_dic['AromaticRingNumber'], feature_dic['NonAromaticRingNumber'], feature_dic[
'LargestAromaticRingAtomNbr'], feature_dic['LargestNonAromaticRingAtomNbr'] = getVolume(mol, atom_types)
feature_dic['MaxNbrFusedRings'] = AreRingFused(mol)
feature_dic['SurfaceArea'] = descriptors.CalcTPSA(mol)
feature_dic['Charge'] = Chem.GetFormalCharge(mol)
funct_dic = {
'[$([NX3](=O)=O),$([NX3+](=O)[O-])][!#8]': 'NitroNbr',
'[#6][OX2H]': 'AlcoholNbr',
'[NX1]#[CX2]': 'NitrileNbr',
'[#6][CX3](=O)[#6]': 'KetoneNbr',
'[#16X2H]': 'ThiolNbr',
"[OX2H][cX3][c]": 'Phenol_likeNbr',
'[#6][CX3](=O)[OX2H0][#6]': 'EsterNbr',
'[#16X2H0]': 'SulfideNbr',
'[CX3](=O)[OX2H1]': 'CarboxilicAcidNbr',
'[OD2]([#6])[#6]': 'EtherNbr',
# '[NX3][CX3](=[OX1])[#6]':'AmideNbr',
'[#7X3][#6X3](=[OX1])[#6]': 'AmideNbr',
'[NX3][cc]': 'AnilineNbr',
'[NX3H2;!$(NC=O)]': 'PrimaryAmineNbr',
'[NX3H1;!$(NC=O)]': 'SecondaryAmineNbr'}
for funct in funct_dic:
patt = Chem.MolFromSmarts(funct)
feature_dic[funct_dic[funct]] = len(mol.GetSubstructMatches(patt))
# names, coords = get_atoms_coords(Chem.MolToMolBlock(mol))
# feature_dic['MinRadiusOfCylinder'] = returnCircleAsTuple(coords[:,1:])[2]
# feature_dic['MinRadiusOfCylinder'] = RADIUS[0]
# feature_dic['RadiusOfCylinderBestConf'] = RADIUS[1]
values = []
for key in sorted(feature_dic.keys()):
values.append(feature_dic[key])
# print key, feature_dic[key]
return values
mol = inMol
if patts is None:
global _smartsPatterns, _patternOrder
if _smartsPatterns == {}:
_patternOrder, _smartsPatterns = _ReadPatts(defaultPatternFileName)
patts = _smartsPatterns
order = _patternOrder
atomContribs = _pyGetAtomContribs(mol, patts, order, verbose=verbose)
return numpy.sum(atomContribs, 0)[1]
_pyMolMR.version = "1.1.0"
MolLogP = lambda *x, **y: rdMolDescriptors.CalcCrippenDescriptors(*x, **y)[0]
MolLogP.version = rdMolDescriptors._CalcCrippenDescriptors_version
MolLogP.__doc__ = """ Wildman-Crippen LogP value
Uses an atom-based scheme based on the values in the paper:
S. A. Wildman and G. M. Crippen JCICS 39 868-873 (1999)
**Arguments**
- inMol: a molecule
- addHs: (optional) toggles adding of Hs to the molecule for the calculation.
If true, hydrogens will be added to the molecule and used in the calculation.
"""
def logp(molecule):
"""
Calculate the logP of the selfies string
"""
m = MolFromSmiles(sf.decoder(molecule))
return rdMolDescriptors.CalcCrippenDescriptors(m)[0]
def compute_logP(self, mol_input):
logP, mr = rdMolDescriptors.CalcCrippenDescriptors(mol_input)
return logP
