def getChemicalDescriptors(
self, data_file, destpath, filename
): # datafile(csv file) destpath(where to save) # filename (name of file to save)
test1 = pd.read_csv(data_file)
for i in range(len(test1)):
try:
temp = test1["Smiles"][i]
descriptors = from_smiles(temp)
except RuntimeError:
temp = test1["Smiles"][i]
descriptors = from_smiles(temp, timeout=30)
if i == 0:
df = pd.DataFrame(descriptors,
columns=descriptors.keys(),
index=[0])
else:
df1 = pd.DataFrame(descriptors,
columns=descriptors.keys(),
index=[i])
if i is 1:
ff = pd.concat([df, df1], axis=0)
if i > 1:
ff = pd.concat([ff, df1], axis=0)
ff = pd.concat([test1['Activation Status'], ff, test1['Ligand']],
axis=1)
ff.to_csv(destpath + filename + ".csv", index=False)
def use(self, smiles: list, backend: str = 'padel'):
''' use: uses the trained project to predict values for supplied
molecules
Args:
smiles (list): list of SMILES strings to predict for
backend (str): backend software to use for QSPR generation; `padel`
or `alvadesc`; default = `padel`; alvadesc requries valid
license
Returns:
numpy.array: predicted values
'''
if backend == 'alvadesc':
mols = [smiles_to_descriptors(s) for s in smiles]
for mol in mols:
for key in list(mol.keys()):
if mol[key] == 'na':
mol[key] = 0
elif backend == 'padel':
mols = [from_smiles(s) for s in smiles]
else:
raise ValueError('Unknown backend software: {}'.format(backend))
return mean([
model.use(
asarray([[float(mol[name]) for name in self._df._input_names]
for mol in mols])) for model in self._models
],
axis=0)
def Pubchem_FP(smi,**kwargs):
if type(smi) != str:
smi = MolToSmiles(smi)
fp = from_smiles(smi,**kwargs)
lst_as_vect = []
for key,val in fp.items():
lst_as_vect.append(val)
assert len(lst_as_vect)==881
return lst_as_vect
def generate_padel_features_serially(self, java_path):
self.jlogger.info("Inside generate_padel_features_serial")
test1 = self.ml_pipeline.data
for i in range(len(test1)):
self.jlogger.debug(
"Generating Padel Features for datapoint {}".format(i))
try:
temp = test1["SMILES"][i]
descriptors = from_smiles(temp,
timeout=60,
java_path=java_path)
except RuntimeError:
self.jlogger.error(
"Padel feature generation failed with timeout of 60 secs, datapoint {}"
.format(i))
continue
# try:
# temp = test1["SMILES"][i]
# descriptors = from_smiles(temp, timeout=60)
# except RuntimeError:
# self.jlogger.exception(
# "Padel feature generation failed on 2nd retry of 60secs, ignoring this datapoint {}".format(
# i))
# continue
if i == 0:
df = pd.DataFrame(descriptors,
columns=descriptors.keys(),
index=[0])
else:
df1 = pd.DataFrame(descriptors,
columns=descriptors.keys(),
index=[i])
if i is 1:
ff = pd.concat([df, df1], axis=0)
if i > 1:
ff = pd.concat([ff, df1], axis=0)
ff = pd.concat([ff, test1[['CNAME', 'Activation Status']]], axis=1)
self.ml_pipeline.data = ff
return ff
def lower_heating_value(smiles: list) -> tuple:
desc = from_smiles(smiles)
masses = [[
int(d['nC']) * 12.011,
int(d['nH']) * 1.008,
int(d['nO']) * 15.999,
int(d['nS']) * 32.06
] for d in desc]
totals = [sum(m) for m in masses]
mass_fracs = [[
m[0] / totals[i], m[1] / totals[i], m[2] / totals[i], m[3] / totals[i]
] for i, m in enumerate(masses)]
lhv = []
for m in mass_fracs:
lhv.append(_dulong(m[0], m[1], m[2], m[3]))
errors = []
for l in lhv:
# error assumed at 3.8%
errors.append(0.038 * l)
return (lhv, errors)
def _qspr_from_padel(smiles: List[str], timeout: int = None) -> Tuple[List[List[float]], List[str]]:
"""
Args:
smiles (list[str]): list of SMILES strings
timeout (int, optional): timeout for PaDEL-Descriptor process call; if None, uses
max(15, len(smiles)) seconds; default = None
Returns:
Tuple[List[List[float]], List[str]]: (descriptors w/ shape (n_compounds, n_desc),
descriptor names)
"""
if timeout is None:
timeout = len(smiles)
desc = from_smiles(smiles, timeout=max(15, len(smiles)))
keys = list(desc[0].keys())
for idx, d in enumerate(desc):
for k in keys:
if d[k] == '':
desc[idx][k] = 0.0
desc = [[float(d[k]) for k in keys] for d in desc]
return (desc, keys)
def test_from_smiles(self):
descriptors = from_smiles('CCC')
self.assertEqual(len(descriptors), 1875)
self.assertAlmostEqual(float(descriptors['MW']), 44.0626, 4)
self.assertEqual(int(descriptors['nC']), 3)
def test_multiple_smiles(self):
smiles = ['CCC', 'CCCC']
descriptors = from_smiles(smiles)
self.assertEqual(len(descriptors), 2)
self.assertEqual(len(descriptors[0]), 1875)
nms = [x[0] for x in Descriptors._descList]
print('\n')
calc = MoleculeDescriptors.MolecularDescriptorCalculator(nms)
f = open('/scratch/woon/b3lyp_2017/datasmile2.txt')
for i, line in enumerate(f):
mydes = []
mylist = []
line = line.split(',')
number = str(line[0])
print(number)
line = line[1]
m = Chem.MolFromSmiles(line)
try:
time.sleep(1)
des = from_smiles(line, fingerprints=True, timeout=180)
des = str(des).split(',')
for ii in range(len(des)):
b = des[ii].split(',')
b = des[ii].strip('[').strip(']')
b = re.sub('[^.,a-zA-Z0-9 \n\.]', '', b)
b = b.replace('[', ' ')
b = b.replace(']', ' ')
b = b.strip()
b = b.split(' ')
mylist.append(b[0])
try:
b = b[1]
except:
b = ''
if bool(b) == True:
def create_db(smiles: list,
db_name: str,
targets: list = None,
id_prefix: str = '',
extra_strings: dict = {},
backend: str = 'padel',
convert_mdl: bool = False):
''' create_db: creates an ECNet-formatted database from SMILES strings
using either PaDEL-Descriptor or alvaDesc software; using alvaDesc
requires a valid installation/license of alvaDesc
Args:
smiles (list): list of SMILES strings
db_name (str): name/path of database being created
targets (list): target (experimental) values, align with SMILES
strings; if None, all TARGETs set to 0
id_prefix (str): prefix of molecule DATAID, if desired
extra_strings (dict): extra STRING columns, label = name, value = list
with length equal to number of SMILES strings
backend (str): software used to calculate QSPR descriptors, 'padel' or
'alvadesc'
convert_mdl (bool): if `True`, converts SMILES strings to MDL 3D
format before calculating descriptors (PaDEL only)
'''
if targets is not None:
if len(targets) != len(smiles):
raise ValueError('Must supply same number of targets as SMILES '
'strings: {}, {}'.format(len(targets),
len(smiles)))
for string in list(extra_strings.keys()):
if len(extra_strings[string]) != len(smiles):
raise ValueError('Extra string values for {} not equal in length '
'to supplied SMILES: {}, {}'.format(
len(extra_strings[string]), len(smiles)))
mols = []
if backend == 'alvadesc':
for mol in smiles:
mols.append(smiles_to_descriptors(mol))
elif backend == 'padel':
for idx, mol in enumerate(smiles):
if convert_mdl is True:
if pybel is None:
raise ImportError(
'pybel (Python Open Babel wrapper) not installed, '
'cannot convert SMILES to MDL')
mdl = pybel.readstring('smi', mol)
mdl.make3D()
curr_time = datetime.now().strftime('%Y%m%d%H%M%S%f')[:-3]
mdl.write('mdl', '{}.mdl'.format(curr_time))
try:
mols.append(from_mdl('{}.mdl'.format(curr_time))[0])
except RuntimeError:
warn(
'Could not calculate descriptors for {}, omitting'.
format(mol), RuntimeWarning)
del smiles[idx]
if targets is not None:
del targets[idx]
for string in list(extra_strings.keys()):
del extra_strings[string][idx]
remove('{}.mdl'.format(curr_time))
else:
try:
mols.append(from_smiles(mol))
except RuntimeError:
warn(
'Could not calculate descriptors for {}, omitting'.
format(mol), RuntimeWarning)
del smiles[idx]
if targets is not None:
del targets[idx]
for string in list(extra_strings.keys()):
del extra_strings[string][idx]
else:
raise ValueError('Unknown backend software: {}'.format(backend))
rows = []
type_row = ['DATAID', 'ASSIGNMENT', 'STRING', 'STRING']
title_row = ['DATAID', 'ASSIGNMENT', 'Compound Name', 'SMILES']
strings = list(extra_strings.keys())
for string in strings:
if string != 'Compound Name':
type_row.append('STRING')
title_row.append(string)
type_row.append('TARGET')
title_row.append('TARGET')
descriptor_keys = list(mols[0].keys())
for key in descriptor_keys:
type_row.append('INPUT')
title_row.append(key)
mol_rows = []
for idx, desc in enumerate(mols):
for key in descriptor_keys:
if desc[key] == 'na' or desc[key] == '':
desc[key] = 0
mol = _Molecule('{}'.format(id_prefix) + '%04d' % (idx + 1))
for string in strings:
mol.strings[string] = extra_strings[string][idx]
if targets is not None:
mol.target = targets[idx]
mol.inputs = desc
mol_rows.append(mol)
with open(db_name, 'w', encoding='utf-8') as db_file:
wr = writer(db_file, delimiter=',', lineterminator='\n')
wr.writerow(type_row)
wr.writerow(title_row)
for idx, mol in enumerate(mol_rows):
row = [
mol.id, mol.assignment, mol.strings['Compound Name'],
smiles[idx]
]
for string in strings:
if string != 'Compound Name':
row.append(mol.strings[string])
row.append(mol.target)
for key in descriptor_keys:
row.append(mol.inputs[key])
wr.writerow(row)
db_file.close()
#from zinc_id.get_zincid import get_zincid_from_smile
#zinc_id = get_zincid_from_smile("FC(F)(F)C1=CC=C(NC(=O)CSC2=NC(=CC=N2)C2=CC(=NO2)C2=CC=C(Cl)C=C2Cl)C=C1")
#print(zinc_id)
from padelpy import from_smiles
#calculate molecular descriptors for propane
descriptors = from_smiles(
'FC(F)(F)C1=CC=C(NC(=O)CSC2=NC(=CC=N2)C2=CC(=NO2)C2=CC=C(Cl)C=C2Cl)C=C1')
#print(type(descriptors))
#print(len(descriptors))
# in addition to descriptors, calculate PubChem fingerprints
#desc_fp = from_smiles('CCC', fingerprints=True)
# only calculate fingerprints
#fingerprints = from_smiles('CCC', fingerprints=True, descriptors=False)
# save descriptors to a CSV file
#_ = from_smiles('FC(F)(F)C1=CC=C(NC(=O)CSC2=NC(=CC=N2)C2=CC(=NO2)C2=CC=C(Cl)C=C2Cl)C=C1', output_csv='descriptors.csv')
from tabula import read_pdf, convert_into
#convert_into("./data/smiles_pdf.pdf", "smiles.csv", output_format="csv", pages='all')
#zinc_id = get_zincid_from_smile("ClC1=CC(NC(=O)CSC2=NC=CC(=N2)C2=CSC(=N2)C2=CC=CC=C2)=CC(Cl)=C1")
#print(zinc_id)
#print("arun")
import sys
from padelpy import from_smiles
i = sys.argv[1]
smi = i
descriptors = from_smiles(smi, timeout=30)
vol = descriptors['McGowan_Volume']
with open("volume_out.txt", "w") as f:
f.write(str(float(vol) * 100))
