def get_formula(smiles, inchi):
formula_from_smiles = ""
formula_from_inchi = ""
try:
if len(smiles) > 5:
formula_from_smiles = str(
CalcMolFormula(Chem.MolFromSmiles(smiles)))
else:
formula_from_smiles = ""
except:
formula_from_smiles = ""
try:
if len(inchi) > 5:
formula_from_inchi = str(CalcMolFormula(Chem.MolFromInchi(inchi)))
else:
formula_from_inchi = ""
except:
formula_from_inchi = ""
if len(formula_from_smiles) > 2 and len(formula_from_inchi) > 2:
return formula_from_smiles, formula_from_inchi
if len(formula_from_smiles) > 2:
return formula_from_smiles, ""
if len(formula_from_inchi) > 2:
return formula_from_inchi, ""
return "", ""
def syncProperties(smiles):
try:
mol = Chem.MolFromSmiles(smiles)
formula = CalcMolFormula(mol)
charge = GetFormalCharge(mol)
formula = formula.replace(str(charge), '')
return formula, charge, 'calculated properties from structure'
except:
return False, False, 'property calculation error'
def filter_pubchem(ms):
ms_filtered = []
elements = set(['C', 'H', 'O', 'N', 'S', 'P', 'Cl', 'B', 'Br', 'Se'])
for m in ms:
mw = CalcExactMolWt(m)
if mw < 100 or mw > 1500:
continue
if GetFormalCharge(m) != 0:
continue
atoms = [a.GetSymbol() for a in m.GetAtoms()]
c = Counter(atoms)
if 'C' in c and 'H' in c:
if 'S' in c and c['S'] > 5:
continue
if 'Cl' in c and c['Cl'] > 5:
continue
if 'Br' in c and c['Br'] > 5:
continue
if 'B' in c and c['B'] > 5:
continue
if set(c.keys()).issubset(elements):
ms_filtered.append(CalcMolFormula(m))
return ms_filtered
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 smi_to_formula(smi_str):
"""
Given a smiles string in arbitrary format, return the smiles string as produced by RDKit,
the molecular formula, and the molecular weight using only the most abundant isotopes
:param smi_str: str, standard SMILES format
:return: str, the molecular formula in standard chemistry notation
"""
# Use RDKit to make a SMILES from a SMILES so that we get a unique string for any given SMILES entry
mol = Chem.MolFromSmiles(smi_str)
if mol is None:
raise InvalidDataError(
f"The input SMILES string '{smi_str}' could not be recognized by RDKit"
)
Chem.Kekulize(mol)
rd_smi = Chem.MolToSmiles(mol, kekuleSmiles=True)
mol_formula = CalcMolFormula(mol)
stoich_dict = parse_stoich(mol_formula)
dbe = calc_dbe(stoich_dict)
mol_mass = 0
for atom_type, num_atoms in stoich_dict.items():
mass_most_abundant_isotope = LIGNIN_ISOTOPE_DICT[atom_type][MASS][0]
mol_mass += mass_most_abundant_isotope * num_atoms
mw_deprot = round(mol_mass - LIGNIN_ISOTOPE_DICT[HYDROG][MASS][0],
MAX_SIG_FIGS)
mw_prot = round(mol_mass + LIGNIN_ISOTOPE_DICT[HYDROG][MASS][0],
MAX_SIG_FIGS)
return rd_smi, mol_formula, round(mol_mass,
MAX_SIG_FIGS), mw_deprot, mw_prot, dbe
def _desc_list(mol, names):
descriptors = dict()
for name, fn in Descriptors.descList:
if not names or name in names:
descriptors[name] = fn(mol)
if 'MolecularFormula' not in descriptors:
descriptors['MolecularFormula'] = CalcMolFormula(mol)
return descriptors
def get_molecular_formula(self, smi):
try:
m = Chem.MolFromSmiles(smi)
return CalcMolFormula(m)
except:
'-'
def annotate_ms(ms_pred, smi, ion_mode='+', treeDepth=2):
mzs = np.array(ms_pred['mz'])
intensities = np.array(ms_pred['intensity'])
mol = Chem.MolFromSmiles(smi)
# only M+H and M-H is considered now.
if ion_mode=='+':
precursor = CalcExactMolWt(mol) + 1.0032
else:
precursor = CalcExactMolWt(mol) - 1.0032
formula = CalcMolFormula(mol)
frags = np.unique(generateFragments(smi, treeDepth=2))
frags_new = np.array([Chem.MolFromSmiles(s) for s in frags])
frags_formula = np.unique([CalcMolFormula(f) for f in frags_new])
loss_formula = []
for f in frags_formula:
l = subtract_formula(formula, f)
if l == '':
continue
if check_formula(l):
loss_formula.append(l)
add_H = add_formula(l, 'H')
de_H = subtract_formula(l, 'H')
if check_formula(add_H):
loss_formula.append(add_H)
if check_formula(de_H):
loss_formula.append(de_H)
loss_formula = np.unique(loss_formula)
loss_mass = np.array([getFormulaExactMass(f) for f in loss_formula])
ms_new = pd.DataFrame(columns=['mz', 'intensity', 'annotate_loss', 'exact_mass'])
for i, mz in enumerate(mzs):
intensity = intensities[i]
diff = precursor - mz
if abs(diff) < 0.5:
annotate_loss = ['precursor']
accurate_mass = [precursor]
if min(np.abs(loss_mass - diff)) < 0.5:
match = np.where(np.abs(loss_mass - diff) < 0.5)[0]
annotate_loss = loss_formula[match]
accurate_mass = precursor - loss_mass[match]
else:
annotate_loss = ''
accurate_mass = ''
ms_new.loc[len(ms_new)] = [mz, intensity, annotate_loss, accurate_mass]
return ms_new
def to_formula(self):
""" str: the chemical formula of the molecule.
Raises:
RuntimeError"""
# formula may be undefined if atoms are uncertainly typed
# e.g. if the molecule was initialize through SMARTS
try:
with Suppressor():
return CalcMolFormula(self)
except RuntimeError:
raise ValueError('Formula is undefined for {}'.format(self))
def process(fname):
results = []
label = int(os.path.basename(fname).replace('.json', ''))
with open(fname, 'r') as f:
data = json.load(f)
ok = []
for d in data:
smi = d['smiles']
if smi is None: continue
# Validate SMILES
errs = molvs.validate_smiles(smi)
if errs:
# print('Validation error(s):', errs)
continue
# Standardize SMILES
smi = molvs.standardize_smiles(smi)
# Check if exists already
if smi in pubchem:
# print('Exists in PubChem')
continue
ok.append(smi)
#print('Kept:', len(ok))
atc_codes = [atc_lookup[i] for i in atc_model.predict(ok)]
for smi, atc_code in zip(ok, atc_codes):
mol = Chem.MolFromSmiles(smi)
formula = CalcMolFormula(mol)
h = md5(smi.encode('utf8')).hexdigest()
im = Draw.MolToImage(mol)
im_path = os.path.join(images_dir, '{}.png'.format(h))
im.save(im_path)
results.append({
'label': label,
'smiles': smi,
'formula': formula,
'image': im_path,
'atc_code': atc_code,
'created_at': datetime.utcnow().isoformat()
})
# Save generated compounds
with open(fname, 'w') as f:
json.dump(results, f)
def make_image(smi, base=False):
mol = Chem.MolFromSmiles(smi)
formula = CalcMolFormula(mol)
if base: formula = '{} (base)'.format(formula)
mol_im = Draw.MolToImage(mol, size=(w, h_))
im = Image.new('RGB', (w, h), color='white')
im.paste(mol_im)
draw = ImageDraw.Draw(im)
tw, th = draw.textsize(formula)
draw.text((w / 2 - tw / 2, h - th - vpadding),
formula,
font=font,
fill='black')
return im
def canon(df, idx):
print('trying to canonize smile for idx: {}'.format(idx))
try:
smile = df.loc[idx]['smiles']
m = Chem.MolFromSmiles(smile)
m = Chem.AddHs(m)
c_smile = Chem.MolToSmiles(m)
df.loc[idx, 'c_smiles'] = c_smile
df.loc[idx, 'status'] = 0
formula = CalcMolFormula(m)
if 'Cl' in formula:
formula = formula.replace('Cl', '')
formula = formula + 'Cl'
df.loc[idx, 'Formula'] = formula
except Exception as e:
df.loc[idx, 'status'] = -2
print("could not convert smile {} of molecule {} : {}".format(
smile, idx, df.loc[idx]['Name']))
print('Exception: {}'.format(e))
return df
def _chembl_desc_list(mol):
mol = _neutralise_sulphoxide(mol)
descriptors = dict()
for name, fn in Descriptors.descList:
if name in CBL_DESC_LIST:
if name == 'ExactMolWt':
mol = _remove_isotope_info(deepcopy(mol))
descriptors[name] = fn(mol)
if 'MolecularFormula' not in descriptors:
descriptors['MolecularFormula'] = CalcMolFormula(mol)
descriptors['Ro3Pass'] = _ro3_pass(descriptors['MolWt'],
descriptors['NumHAcceptors'],
descriptors['NumHDonors'],
descriptors['MolLogP'],
descriptors['NumRotatableBonds'],
descriptors['TPSA'])
descriptors['NumRo5'] = _num_ro5_violations(descriptors['MolLogP'],
descriptors['MolWt'],
descriptors['NumHAcceptors'],
descriptors['NumHDonors'])
descriptors['MonoisotopicMolWt'] = descriptors.pop('ExactMolWt')
return descriptors
def process_compound(line):
id, smi, label = line.split('\t')
atc = atcs.get(id, set())
label = labels[int(label)].replace('/', '_')
name = names.get(id)
mol = Chem.MolFromSmiles(smi)
formula = CalcMolFormula(mol)
# Just generate all images
# so we don't have to worry about them later
im_fname = 'img/{}.png'.format(id)
if not os.path.exists(im_fname):
im = Draw.MolToImage(mol)
im.save(im_fname)
return label, {
'id': id,
'name': name,
'formula': formula,
'atc_codes': list([atc[:5] for atc in atc])
}
summary = pd.DataFrame({'smiles': smiles, 'ion_mode': modes, 'energy': energies})
# example 1
idx = 551
smi = smiles[idx]
mol = Chem.MolFromSmiles(smi)
ms_pred = model_predict(smi, model)
ms_real = ms[idx]
# annotation
mzs = np.array(ms_pred['mz'])
intensities = np.array(ms_pred['intensity'])
mol = Chem.MolFromSmiles(smi)
precursor = CalcExactMolWt(mol) - 1.0032
formula = CalcMolFormula(mol)
frags = np.unique(generateFragments(smi, treeDepth=2))
frags_new = [Chem.MolFromSmiles(s) for s in frags]
frags_formula = np.unique([CalcMolFormula(f) for f in frags_new])
loss_formula = []
for f in frags_formula:
l = subtract_formula(formula, f)
if l == '':
continue
if check_formula(l):
loss_formula.append(l)
add_H = add_formula(l, 'H')
de_H = subtract_formula(l, 'H')
if check_formula(add_H):
loss_formula.append(add_H)
if check_formula(de_H):
def getMoleculeFeatures(self):
"""Get the essential features of the constructed rdMol for the input component."""
mD = self.__rdMol.GetPropsAsDict()
logger.debug("mol props %r", mD.items())
#
formula = CalcMolFormula(self.__rdMol)
ccId = self.__ccId
ifCharge = Chem.rdmolops.GetFormalCharge(self.__rdMol)
#
inchiKey = Chem.inchi.MolToInchiKey(self.__rdMol)
inchi = Chem.inchi.MolToInchi(self.__rdMol)
smiles = Chem.rdmolfiles.MolToSmiles(self.__rdMol,
isomericSmiles=False,
canonical=True)
isoSmiles = Chem.rdmolfiles.MolToSmiles(self.__rdMol,
isomericSmiles=True,
canonical=True)
logger.debug("%s formula %s", ccId, formula)
details = ComponentDetails(ccId=ccId,
formula=formula,
ifCharge=ifCharge)
descriptors = ComponentDescriptors(smiles=smiles,
isoSmiles=isoSmiles,
inchi=inchi,
inchiKey=inchiKey)
#
typeCounts = defaultdict(int)
ccAtomD = {}
ccAtomIdD = {}
for ii, at in enumerate(self.__rdMol.GetAtoms(), 1):
atIdx = at.GetIdx()
aType = at.GetSymbol()
typeCounts[aType] += 1
atName = self.__atomIdxD[
ii] if ii in self.__atomIdxD else aType + str(
typeCounts[aType])
# atNo = at.GetAtomicNum()
isAromatic = at.GetIsAromatic()
isChiral = at.GetChiralTag() > 0
iCharge = at.GetFormalCharge()
# cipStereo = at.GetProp("_CIPCode")
atD = at.GetPropsAsDict(includePrivate=True, includeComputed=True)
cipStereo = None
if "_CIPCode" in atD:
cipStereo = atD["_CIPCode"]
if cipStereo and cipStereo not in ["S", "R"]:
logger.error("%s (%s): Unexpected atom CIP stereo setting %r",
ccId, atName, cipStereo)
#
ccAtomD[atName] = ComponentAtom(name=atName,
aType=aType,
isAromatic=isAromatic,
isChiral=isChiral,
CIP=cipStereo,
fCharge=iCharge)
ccAtomIdD[atIdx] = atName
# nL = at.GetProp(includePrivate=True, includeComputed=True)
atD = at.GetPropsAsDict(includePrivate=True, includeComputed=True)
logger.debug("%s Atom %s %s %r %r %s", ccId, atName, aType,
isAromatic, isChiral, cipStereo)
#
ccBondD = {}
for bnd in self.__rdMol.GetBonds():
atI = bnd.GetBeginAtomIdx()
atJ = bnd.GetEndAtomIdx()
atNameI = ccAtomIdD[atI]
atNameJ = ccAtomIdD[atJ]
isAromatic = bnd.GetIsAromatic()
#
# bType = bnd.GetBondType()
# iType = 0
cipStereo = None
tS = bnd.GetStereo()
if tS == Chem.rdchem.BondStereo.STEREOE:
cipStereo = "E"
elif tS == Chem.rdchem.BondStereo.STEREOZ:
cipStereo = "Z"
# bL = bnd.GetPropNames(includePrivate=True, includeComputed=True)
bD = bnd.GetPropsAsDict(includePrivate=True, includeComputed=True)
iType = bD["_MolFileBondType"]
logger.debug("Bond %s %s iType %r cipStereo %r aromatic %r",
atNameI, atNameJ, iType, cipStereo, isAromatic)
#
if cipStereo and cipStereo not in ["E", "Z"]:
logger.error(
"%s (%s %s): Unexpected bond CIP stereo setting %r", ccId,
atNameI, atNameJ, cipStereo)
#
ccBondD[(atNameI, atNameJ)] = ComponentBond(iType=iType,
isAromatic=isAromatic,
CIP=cipStereo)
#
ccD = {
"details": details,
"descriptors": descriptors,
"atoms": ccAtomD,
"bonds": ccBondD
}
return ccD
from rdkit import Chem import sys import re from rdkit.Chem.rdMolDescriptors import CalcMolFormula formula = CalcMolFormula(Chem.MolFromSmiles(sys.argv[1])) print re.sub(r'([a-z]*)([A-Z])', r'\1 \2', formula).lstrip()
def parse_f(f):
names = ['']
cid = -1
CAS = f.split('/')[1] if '/' in f else f
CAS = CAS.split('.')[0]
if CAS in ignored_CASs:
return None
failed_mol = False
try:
if CAS in syn_data:
d = syn_data[CAS]
if 'pubchem' in d:
raise Exception(
'Pubchem specified, not trying to use the mol file')
elif 'formula' in d:
raise Exception(
'Formula specified, not trying to use the mol file')
try:
mol = Chem.MolFromMolFile(f)
assert mol is not None
except:
print('Cannot read %s' % f)
1 / 0
try:
inchi_val = inchi.MolToInchi(mol)
except:
print('BAILING ON %s' % f)
1 / 0
mol = inchi.MolFromInchi(inchi_val) # Works better for ions
if mol is None:
print('BAILING ON reconversion to mol %s' % f)
1 / 0
except:
failed_mol = True
if CAS in syn_data:
d = syn_data[CAS]
if 'pubchem' in d:
if str(d['pubchem']) in mycache:
cid, iupac_name, names, mw, smi, inchi_val, inchikey, formula = mycache[
str(d['pubchem'])]
else:
pc = Compound.from_cid(d['pubchem'])
cid = pc.cid
iupac_name = pc.iupac_name
names = pc.synonyms
mw = pc.molecular_weight
smi = pc.canonical_smiles
inchi_val = pc.inchi
inchikey = pc.inchikey
formula = pc.molecular_formula
mycache[str(d['pubchem'])] = (cid, iupac_name, names, mw,
smi, inchi_val, inchikey,
formula)
else:
cid = -1
names = d['synonyms'] if 'synonyms' in d else ['']
mw = float(d['MW'])
smi = d['smiles'] if 'smiles' in d else ''
formula = d['formula'] if 'formula' in d else ''
inchi_val = d['inchi'] if 'inchi' in d else ''
inchikey = d['inchikey'] if 'inchikey' in d else ''
iupac_name = ''
else:
print('FAILED on %s and no custom data was available either' % CAS)
return None
if not failed_mol:
smi = Chem.MolToSmiles(mol, True)
inchi_val = inchi.MolToInchi(mol)
inchikey = inchi.InchiToInchiKey(inchi_val)
mw = Descriptors.MolWt(mol)
# for i in mol.GetAtoms():
# if i.GetIsotope():
# mw = Descriptors.ExactMolWt(mol)
# break
formula = CalcMolFormula(mol, True, True)
iupac_name = ''
try:
if not failed_mol:
if str(inchikey) in mycache:
cid, iupac_name, names = mycache[str(inchikey)]
else:
try:
pc = get_compounds(inchikey, 'inchikey')[0]
cid = pc.cid
iupac_name = pc.iupac_name
names = pc.synonyms
mycache[str(inchikey)] = (cid, iupac_name, names)
except:
mycache[str(inchikey)] = (-1, '', [''])
except:
cid = -1
iupac_name = ''
names = ['']
other_CAS = []
if CAS in pdf_data:
d = pdf_data[CAS]
name = d['Name']
if 'Other Names' in d:
syns = d['Other Names']
else:
syns = []
if not iupac_name:
iupac_name = name
else:
syns.insert(0, name)
if 'Deleted CAS' in d:
other_CAS.extend(d['Deleted CAS'])
if 'Alternate CAS' in d:
other_CAS.extend(d['Alternate CAS'])
syns = [i for i in syns if i not in dup_names]
names = syns + [i for i in names if i not in all_names] + other_CAS
actual_names = []
for name in names:
if name in all_user_names:
# If the name is in the user db, only add it if it corresponds to this CAS number
if CAS in syn_data and 'synonyms' in syn_data[
CAS] and name in syn_data[CAS]['synonyms']:
actual_names.append(name)
else:
# Discard it otherwise
pass
else:
# If the name is not in the user db we're all good
actual_names.append(name)
if CAS in syn_data and 'synonyms' in syn_data[CAS]:
# If the user has any syns for this cas number, add those names if the name hasn't already been aded
for n in syn_data[CAS]['synonyms']:
if n not in actual_names:
actual_names.append(n)
actual_names = [i for i in actual_names if i]
if inchi_val is not None:
inchi_val = inchi_val.replace('InChI=1S/', '')
formula = serialize_formula(formula)
s = '%d\t%s\t%s\t%g\t%s\t%s\t%s\t%s\t' % (cid, CAS, formula, mw, smi,
inchi_val, inchikey, iupac_name)
s += '\t'.join(actual_names)
print(s)
return None
def process(init_data, use_cache=True):
'''
Examples
--------
>>> res = process({'CAS': '10170-69-1', 'synonyms': ['14267-36-8', 'NSC 22319'], 'name': 'Manganese, decacarbonyldi-, (Mn-Mn)'})
>>> res['inchi'], res['smiles'], res['cid'], res['CAS']
('InChI=1S/10CO.2Mn/c10*1-2;;', '[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[C-]#[O+].[Mn].[Mn]', 517769, '10170-69-1')
'''
# print(locals())
init_data = init_data.copy()
cc = cc_CAS = cc_name = cc_inchi = cc_inchikey = cc_smiles = cc_synonyms = cc_deprecated_CASs = None
if 'CAS' in init_data:
try:
cc = common_chemistry_data(init_data['CAS'])
cc_CAS, cc_name, cc_inchi, cc_inchikey, cc_smiles, cc_synonyms, cc_deprecated_CASs = cc
except ValueError:
# Compund is not in common chemistry; this is OK
pass
cid = iupac_name = p_MW = p_inchi = p_inchikey = p_smiles = p_formula = p_synonyms = None
if init_data.get('mol', None) is not None:
# If not in common chemistry or no InChi there, but if we have a mol file, get the inchi and inchikey for the
# pubchem lookup
mol = Chem.MolFromMolFile(init_data['mol'])
if mol is not None:
init_data['inchi'] = MolToInchi(mol)
init_data['inchikey'] = InchiToInchiKey(init_data['inchi'])
can_search_pubchem = (init_data.get('pubchem') is not None
or init_data.get('CASRN', cc_CAS) is not None
or init_data.get('inchi', cc_inchi) is not None
or init_data.get('inchikey', cc_inchikey) is not None
or init_data.get('smiles', cc_smiles) is not None)
if can_search_pubchem:
try:
p = find_pubchem_from_ids(
pubchem=init_data.get('pubchem'),
CASRN=init_data.get('CASRN', cc_CAS),
inchi=init_data.get('inchi', cc_inchi),
inchikey=init_data.get('inchikey', cc_inchikey),
smiles=init_data.get('smiles', cc_smiles),
use_cache=use_cache)
except Exception as e:
p = None
print(e, 'exception')
if p is not None:
cid, iupac_name, p_MW, p_inchi, p_inchikey, p_smiles, p_formula, p_synonyms = p
# print(locals())
mol = None
# Be aware some smiles descriptions are wrong
# Start with user overridding
if 'mol' in init_data:
mol = Chem.MolFromMolFile(init_data['mol'])
if mol is None and 'smiles' in init_data:
mol = Chem.MolFromSmiles(init_data['smiles'])
if mol is None and 'inchi' in init_data:
mol = MolFromInchi(
init_data['inchi']) if init_data['inchi'].startswith(
"InChI=1S/") else MolFromInchi("InChI=1S/" +
init_data['inchi'])
# Trust common chemistry next
if mol is None and cc_smiles is not None:
mol = Chem.MolFromSmiles(cc_smiles)
if mol is None and cc_inchi is not None:
mol = MolFromInchi(cc_inchi) if cc_inchi.startswith(
"InChI=1S/") else MolFromInchi("InChI=1S/" + cc_inchi)
# Did we pull up the structure from pubchem??
if mol is None and p_smiles is not None:
mol = Chem.MolFromSmiles(p_smiles)
if mol is None and p_inchi is not None:
mol = MolFromInchi(p_inchi) if p_inchi.startswith(
"InChI=1S/") else MolFromInchi("InChI=1S/" + p_inchi)
if mol is None:
raise ValueError("No structure found")
smiles = Chem.MolToSmiles(mol, True)
inchi = MolToInchi(mol)
inchikey = InchiToInchiKey(inchi)
#MW = Descriptors.ExactMolWt(mol)
formula = CalcMolFormula(mol, True, True)
formula = serialize_formula(formula)
MW = molecular_weight(nested_formula_parser(formula))
# print(inchi, cc_inchi, p_inchi)
# print(inchikey, cc_inchikey, p_inchikey)
# print(smiles, cc_smiles, p_smiles)
# output values
if 'pubchem' in init_data:
cid = init_data['pubchem']
elif cid is None:
cid = -1
if cc_CAS is not None:
CAS = cc_CAS
elif 'CAS' in init_data:
CAS = init_data['CAS']
else:
raise ValueError("CAS culd not be found")
if 'formula' in init_data:
# Override rdkit
formula = init_data['formula']
if 'MW' in init_data:
# Override rdkit
MW = init_data['MW']
if 'smiles' in init_data:
smiles = init_data['smiles']
if 'inchi' in init_data:
inchi = init_data['inchi']
if 'inchikey' in init_data:
inchikey = init_data['inchikey']
if inchikey == '*' or smiles == '*' or inchi == '*':
raise ValueError("Failure in rdkit")
# Do we have a name specified in the settings?
if 'name' in init_data:
name = init_data['name']
elif cc_name is not None:
name = cc_name
elif iupac_name is not None:
name = iupac_name
else:
raise ValueError("There is no name for this compound")
synonyms = []
if cc_synonyms is not None:
synonyms += cc_synonyms
if cc_deprecated_CASs is not None:
synonyms += cc_deprecated_CASs
if p_synonyms is not None:
synonyms += p_synonyms
if 'synonyms' in init_data:
synonyms += init_data['synonyms']
synonyms = list(set(synonyms))
if name in synonyms:
synonyms.remove(name)
if synonyms:
def key_sort_str(s):
return len(s), s.lower()
synonyms = sorted(synonyms, key=key_sort_str)
# synonyms = natsorted(synonyms)
# synonyms = []
return {
'cid': cid,
'CAS': CAS,
'formula': formula,
'MW': MW,
'smiles': smiles,
'inchi': inchi,
'inchikey': inchikey,
'name': name,
'synonyms': synonyms
}
def get_chemicalFormula(mol):
''' Chemical Formula '''
return CalcMolFormula(mol)
if val.isalpha():
break
else:
checkIsItFirst = True
num += str(val)
secondPart = secondPart[1:]
if not checkIsItFirst:
num = 1
return num
for index, row in df.iterrows():
smiles = row['smiles']
readedFormula = row['stoichiometry']
molObj = Chem.MolFromSmiles(smiles)
formula = CalcMolFormula(molObj)
atoms = rdkit.Chem.rdchem.Mol.GetAtoms(molObj)
if isnan(formula) or isnan(readedFormula):
print("*************** NAN VALUE : " + str(readedFormula) + " - " +
str(formula))
else:
if readedFormula != formula:
for atom in atoms:
atomSymbol = rdkit.Chem.rdchem.Atom.GetSymbol(atom)
atomSymbolSTR = str(atomSymbol)
readedNumber = GetNumber(str(readedFormula), atomSymbolSTR)
createdNumber = GetNumber(str(formula), atomSymbolSTR)
if readedNumber != createdNumber:
print(readedFormula)
print(formula)
print(count)
df = pd.DataFrame(all_dicts)
return df
print('doing biocyc')
molecules = []
for path in biocyc_paths:
mol_files = glob.glob(os.path.join(path, 'MetaCyc-MOLfiles/*.mol'))
for f in mol_files:
cpd_id = os.path.basename(f).replace('.mol', '')
with open(f, 'r', encoding='utf-8', errors='ignore') as fid:
t = fid.read()
name = t.split('\n')[0].strip().strip('"')
mol = Chem.MolFromMolFile(f, sanitize=True)
if mol is not None:
formula = CalcMolFormula(mol)
try:
Chem.rdmolops.Kekulize(mol, clearAromaticFlags=True)
smiles = Chem.MolToSmiles(mol, isomericSmiles=True)
original_smiles = smiles
except:
original_smiles = None
molecules.append({
'original_id': str(cpd_id),
'name': str(name),
'source': str('BioCyc'),
'formula': str(formula),
'original_smiles': str(original_smiles),
'unique_id': str(uuid.uuid4())
})
else:
mol, status = neutralise_charges(mol)
mol, status = desalt(mol)
SanitizeMol(mol)
mol, status = neutralise_charges(mol)
SanitizeMol(mol)
Kekulize(mol, clearAromaticFlags=True)
new_smiles = MolToSmiles(mol, isomericSmiles=True)
new_inchikey = MolToInchiKey(mol)
new_inchi = MolToInchi(mol)
mw = ExactMolWt(mol)
sdf.loc[i, 'smiles'] = new_smiles
sdf.loc[i, 'inchi_key'] = new_inchikey
sdf.loc[i, 'inchi'] = new_inchi
sdf.loc[i, 'neutral_mass'] = mw
sdf.loc[i, 'formula'] = CalcMolFormula(mol)
setup_cols = {
'inchi_key': 'metatlas_inchikey',
'inchi': 'metatlas_inchi',
'formula': 'metatlas_formula',
'neutral_mass': 'metatlas_mw',
'code': 'original_id',
'library': 'source'
}
sdf.rename(columns=setup_cols).to_csv(
'/Users/bpb/Downloads/Tim-Tec-Compounds.tab', sep='\t', index=None)
df = pd.merge(sdf[[
'code', 'inchi_key', 'inchi', 'name', 'neutral_mass', 'original_smiles'
]],