def inchi_to_graph(inchi, max_atomic_number=118, device=torch.device('cpu')):
"""
Converts an inchi string to a DGL Graph object and associate the one hot encoding features for each node.
:param inchi: An inchi string
:param max_atomic_number: The max_atomic_number determines the final size of the nodes feature matrix
:return: DGL.Graph
"""
mol = MolFromInchi(inchi)
num_atoms = mol.GetNumAtoms()
# DGLGraph creation from rdkit mol object
graph = dgl.DGLGraph()
graph.add_nodes(num_atoms)
for bond in mol.GetBonds():
src = bond.GetBeginAtomIdx()
dest = bond.GetEndAtomIdx()
graph.add_edge(src, dest)
# Edges in DGL are directional, to ensure bidirectionality, add reverse edge
graph.add_edge(dest, src)
# One hot encoding for nodes features
one_hot_indexes = []
for atom_index in range(num_atoms):
one_hot_indexes.append([mol.GetAtomWithIdx(atom_index).GetAtomicNum()])
graph.ndata['x'] = torch.zeros(num_atoms, max_atomic_number) \
.scatter_(1, torch.tensor(one_hot_indexes), 1).to(device)
return graph
def test_sequence_minimal():
# Violacein
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer().compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
assert MolToSmiles(ans) == 'OC1=NC(c2c[nH]c3ccc(O)cc23)=C/C1=C1\\C(O)=Nc2ccccc21'
# L-Lactate
mol = MolFromInchi('')
def test_keep_biggest():
mol = Filters.keep_biggest(MolFromSmiles('CCCC.CC'))
assert MolToSmiles(mol) == 'CCCC'
mol = Filters.keep_biggest(MolFromSmiles('CCCCC.CC.[H].CCC'))
assert MolToSmiles(mol) == 'CCCCC'
mol = Filters.keep_biggest(MolFromInchi(
'InChI=1S/C5H12N2O2.C4H7NO4/c6-3-1-2-4(7)5(8)9;5-2(4(8)9)1-3(6)7/h4H,1-3,6-7H2,(H,8,9);2H,1,5H2,(H,6,7)(H,8,9)/t4-;2-/m00/s1'))
assert MolToInchi(mol) == 'InChI=1S/C4H7NO4/c5-2(4(8)9)1-3(6)7/h2H,1,5H2,(H,6,7)(H,8,9)/t2-/m0/s1'
mol = Filters.keep_biggest(MolFromInchi('InChI=1S/Mo.4O/q;;;2*-1'))
assert MolToInchi(mol) == 'InChI=1S/Mo'
def annotate_chemical_svg(network):
"""Annotate chemical nodes with SVGs depiction.
:param network: dict, network of elements as outputted by the sbml_to_json method
:return: dict, network annotated
"""
from rdkit.Chem import MolFromInchi
from rdkit.Chem.Draw import rdMolDraw2D
from rdkit.Chem.AllChem import Compute2DCoords
from urllib import parse
for node in network['elements']['nodes']:
if node['data']['type'] == 'chemical' and node['data'][
'inchi'] is not None:
inchi = node['data']['inchi']
try:
mol = MolFromInchi(inchi)
# if mol is None:
# raise BaseException('Mol is None')
Compute2DCoords(mol)
drawer = rdMolDraw2D.MolDraw2DSVG(200, 200)
drawer.DrawMolecule(mol)
drawer.FinishDrawing()
svg_draft = drawer.GetDrawingText().replace("svg:", "")
svg = 'data:image/svg+xml;charset=utf-8,' + parse.quote(
svg_draft)
node['data']['svg'] = svg
except BaseException as e:
msg = 'SVG depiction failed from inchi: "{}"'.format(inchi)
logging.warning(msg)
logging.warning("Below the RDKit backtrace...")
logging.warning(e)
node['data']['svg'] = None
return network
def drawChemicalList(self, id_inchi, subplot_size=[200, 200]):
from rdkit.Chem import MolFromInchi
from rdkit.Chem import Draw
toRet = {}
inchi_list = list(set([id_inchi[i] for i in id_inchi]))
list_mol = [MolFromInchi(inchi) for inchi in inchi_list]
for i in range(len(list_mol)):
cp_list_mol = copy.deepcopy(list_mol)
cp_list_mol.pop(i)
tmp_list_mol = [list_mol[i]]+cp_list_mol
img = Draw.MolsToGridImage(tmp_list_mol, molsPerRow=1, subImgSize=(subplot_size[0], subplot_size[1]), useSVG=True)
#add the groups tag with the id's of the reactions -- should have be size width=subplot_size[0] height=subplot_size[1]*len(list_mol)
bond_0_count = 0
svg_str = ''
for line in img.splitlines():
add_line = True
m0 = re.findall("(\d+\.\d+)", line)
if m0:
for y in m0:
if float(y)>subplot_size[1]:
add_line = False
m1 = re.findall("height=\'\d+", line)
if m1:
line = re.sub(r"height=\'\d+", "height=\'"+str(subplot_size[1]), line)
#line.replace(str(subplot_size[i]*len(list_mol)), str(subplot_size[1]))
if add_line:
svg_str += line+'\n'
for y in id_inchi:
if id_inchi[y]==inchi_list[i]:
toRet[y] = svg_str
return toRet
def _convert_depiction(self, idepic, itype='smiles', otype={'inchikey'}):
# Import (if needed)
if itype == 'smiles':
rdmol = MolFromSmiles(idepic, sanitize=True)
elif itype == 'inchi':
rdmol = MolFromInchi(idepic, sanitize=True)
else:
raise NotImplementedError(
'"{}" is not a valid input type'.format(itype))
if rdmol is None: # Check imprt
raise self.DepictionError(
'Import error from depiction "{}" of type "{}"'.format(
idepic, itype))
# Export
odepic = dict()
for item in otype:
if item == 'smiles':
odepic[item] = MolToSmiles(
rdmol
) # MolToSmiles is tricky, one mays want to check the possible options..
elif item == 'inchi':
odepic[item] = MolToInchi(rdmol)
elif item == 'inchikey':
odepic[item] = MolToInchiKey(rdmol)
else:
raise NotImplementedError(
'"{}" is not a valid output type'.format(otype))
return odepic
def convert_depiction(idepic, itype='smiles', otype={'inchikey'}):
"""Convert chemical depiction to others type of depictions
:param idepic: string depiction to be converted, str
:param itype: type of depiction provided as input, str
:param otype: types of depiction to be generated, {"", "", ..}
:return odepic: generated depictions, {"otype1": "odepic1", ..}
Usage example:
- convert_depiction(idepic='CCO', otype={'inchi', 'smiles', 'inchikey'})
- convert_depiction(idepic='InChI=1S/C2H6O/c1-2-3/h3H,2H2,1H3', itype='inchi', otype={'inchi', 'smiles', 'inchikey'})
"""
# Import (if needed)
if itype == 'smiles':
rdmol = MolFromSmiles(idepic, sanitize=True)
elif itype == 'inchi':
rdmol = MolFromInchi(idepic, sanitize=True)
else:
raise NotImplementedError('"{}" is not a valid input type'.format(itype))
if rdmol is None: # Check imprt
raise Exception('Import error from depiction "{}" of type "{}"'.format(idepic, itype))
# Export
odepic = dict()
for item in otype:
if item == 'smiles':
odepic[item] = MolToSmiles(rdmol) # MolToSmiles is tricky, one mays want to check the possible options..
elif item == 'inchi':
odepic[item] = MolToInchi(rdmol)
elif item == 'inchikey':
odepic[item] = MolToInchiKey(rdmol)
else:
raise NotImplementedError('"{}" is not a valid output type'.format(otype))
return odepic
def _transform(self, x):
try:
mol = MolFromInchi(x['standard_inchi'])
except:
mol = MolFromSmiles(x['Compound_SMILES'])
info = {}
AllChem.GetMorganFingerprintAsBitVect(mol, self.radius, self.dim, bitInfo=info)
return list(info.keys())
def test_remove_stereo():
mol = Filters.remove_stereo(MolFromSmiles('C[C@@H](C(=O)[O-])O'))
assert MolToSmiles(mol) == 'CC(O)C(=O)[O-]'
mol = Filters.remove_stereo(MolFromInchi(
'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'))
assert MolToSmiles(mol) == 'OC1=NC(c2c[nH]c3ccc(O)cc23)=CC1=C1C(O)=Nc2ccccc21'
mol = Filters.commute_inchi(mol) # Expected to change tautomerism
assert MolToSmiles(mol) == 'O=C1NC(C2=CNC3=C2C=C(O)C=C3)=CC1=C1C(=O)NC2=CC=CC=C21'
def add_exact_mass(specs):
for s in specs:
mol = MolFromSmiles(s.get('smiles'))
if mol is None:
mol = MolFromInchi(s.get('inchi'))
exact_mass_smi = CalcExactMolWt(mol)
if abs(exact_mass_smi - s.get('parent_mass', 0.0) > 1):
print(exact_mass_smi, s.get('parent_mass'))
s.set('exact_mass', exact_mass_smi)
def standarize_mol_by_inchi(mol, neutralize=True):
newmol = AddHs(mol)
sinchi, code, msg = generate_inchi(newmol, FixedH=False, RecMet=False)
if neutralize:
nsinchi = neutralize_inchi(sinchi)
else:
nsinchi = sinchi
newmol = MolFromInchi(nsinchi, removeHs=False)
newmol = AddHs(newmol, explicitOnly=True)
return newmol
def test_sequence_rr_legacy():
# Violacein
mol = MolFromInchi(
'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
)
ans = Standardizer(sequence_fun='sequence_rr_legacy').compute(mol)
assert MolToInchi(
ans
) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
assert MolToSmiles(
ans
) == '[H]OC1=NC(C2=C([H])N([H])C3=C2C([H])=C(O[H])C([H])=C3[H])=C([H])/C1=C1\\C(O[H])=NC2=C([H])C([H])=C([H])C([H])=C21'
def commute_inchi(cls, mol_in):
"""Convert RDKit compound back and forth to InChi.
Returns a new compound after the initial one has been converted
back and forth to InChi.
:param mol_in: RDKit Mol
:return mol_out: RDKit Mol
"""
inchi = MolToInchi(mol_in, logLevel=None) # this is talkative...
mol_out = MolFromInchi(inchi,
sanitize=False,
removeHs=False,
logLevel=None,
treatWarningAsError=False)
if not mol_out:
raise ValueError("Failed InChi validity filter.")
# Copy the properties
cls._copy_properties(mol_in, mol_out)
return mol_out
def _convert_depiction(self, idepic, itype='smiles', otype={'inchikey'}):
"""Convert chemical depiction to others type of depictions
Usage example:
- convert_depiction(idepic='CCO', otype={'inchi', 'smiles', 'inchikey'})
- convert_depiction(idepic='InChI=1S/C2H6O/c1-2-3/h3H,2H2,1H3', itype='inchi', otype={'inchi', 'smiles', 'inchikey'})
:param idepic: Input string
:param itype: The type of input
:param otype: Type of output. Valid options: inchi, smiles, inchikey
:type idepic: str
:type itype: str
:type otype: dict
:rtype: dict
:return: Dictionnary of results
"""
# Import (if needed)
if itype == 'smiles':
rdmol = MolFromSmiles(idepic, sanitize=True)
elif itype == 'inchi':
rdmol = MolFromInchi(idepic, sanitize=True)
else:
raise NotImplementedError('"{}" is not a valid input type'.format(itype))
if rdmol is None: # Check imprt
raise self.DepictionError('Import error from depiction "{}" of type "{}"'.format(idepic, itype))
# Export
odepic = dict()
for item in otype:
if item == 'smiles':
odepic[item] = MolToSmiles(rdmol) # MolToSmiles is tricky, one mays want to check the possible options..
elif item == 'inchi':
odepic[item] = MolToInchi(rdmol)
elif item == 'inchikey':
odepic[item] = MolToInchiKey(rdmol)
else:
raise NotImplementedError('"{}" is not a valid output type'.format(otype))
return odepic
def rdmols_from_document(document, build_from="inchi", add_hs=True):
"""
Convert back a document to a set of rdmols. This method is a companion of "as_document".
:param document: a document produced by the "as_mongo_document" method, dict
:param build_from: the type of depiction to be used to build back the rdmols, str in ["inchi", "smiles"]
:param add_hs: add Hs to RDKit mol object, default is True
:returns list_list_rdmols: list of list of rdmols
"""
assert build_from in ["inchi", "smiles"]
assert add_hs in [True, False]
list_list_rdmols = list()
list_stoechiometry = document['list_stoechiometry']
if build_from == 'inchi':
for list_inchis in document['list_list_inchis']:
list_rdmols = list()
for inchi in list_inchis:
rd_mol = MolFromInchi(inchi, sanitize=True)
if add_hs:
rd_mol = AddHs(rd_mol)
list_rdmols.append(rd_mol)
list_list_rdmols.append(list_rdmols)
elif build_from == 'smiles':
for list_smiles in document['list_list_smiles']:
list_rdmols = list()
for smiles in list_smiles:
rd_mol = MolFromSmiles(smiles, sanitize=True)
if add_hs:
rd_mol = AddHs(rd_mol)
list_rdmols.append(rd_mol)
list_list_rdmols.append(list_rdmols)
else:
raise NotImplementedError()
return list_list_rdmols, list_stoechiometry
def generate_structure_and_dictionary(batch):
"""
Adding the structure data to a compound batch object
"""
chirality = "1"
if batch.id:
print "not updating"
# currently we dont update existing compound records
else:
if not batch.ctab:
#blinded compound
uox_id = generate_uox_id()
batch.blinded_batch_id = uox_id
batch.save(validate=False)
else:
if not batch.canonical_smiles or not batch.related_molregno_id:
try:
pybelmol = readstring("mol",
str(batch.ctab).encode("ascii"))
batch.canonical_smiles = pybelmol.write("can").split(
"\t")[0]
batch.properties["cdxml"] = pybelmol.write("cdxml")
except:
pass
try:
mol = MolFromInchi(
batch.standard_inchi.encode('ascii', 'ignore'))
if mol:
batch.std_ctab = MolToMolBlock(mol, includeStereo=True)
except:
pass
inchi_key = batch.standard_inchi_key
inchi = batch.standard_inchi
if not batch.related_molregno_id:
try:
moldict = MoleculeDictionary.objects.get(
project=batch.project,
structure_type="MOL",
# chirality=chirality,
structure_key=batch.standard_inchi_key)
except ObjectDoesNotExist:
uox_id = None
forced_uox_id = batch.warnings.get(
"original_uox_id", None)
if forced_uox_id:
count_existing_objects = CBHCompoundBatch.objects.filter(
related_molregno__chembl__chembl_id=
forced_uox_id).count()
count_existing_objects += CBHCompoundBatch.objects.filter(
blinded_batch_id=forced_uox_id).count()
if count_existing_objects == 0:
uox_id = forced_uox_id
#Now check if there is a chembl and remove if so
ChemblIdLookup.objects.filter(
chembl_id=uox_id).delete()
else:
print(
"Had to generate a new compound ID for %s"
% forced_uox_id)
if not uox_id:
uox_id = generate_uox_id()
rnd = random.randint(-1000000000, -2)
uox_id_lookup = ChemblIdLookup.objects.create(
chembl_id=uox_id,
entity_type="COMPOUND",
entity_id=rnd)
moldict = MoleculeDictionary.objects.get_or_create(
chembl=uox_id_lookup,
project=batch.project,
structure_type="MOL",
structure_key=batch.standard_inchi_key)[0]
uox_id_lookup.entity_id = moldict.molregno
uox_id_lookup.save()
structure = CompoundStructures(
molecule=moldict,
molfile=batch.std_ctab,
standard_inchi_key=inchi_key,
standard_inchi=inchi)
structure.save()
if structure.molecule_id:
generateCompoundPropertiesTask(structure)
batch.related_molregno = moldict
batch.save(validate=False)
return batch
def test_commute_inchi():
inchi = 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)/p-1'
mol = Filters.commute_inchi(MolFromInchi(inchi))
assert MolToInchi(mol) == inchi
def test1InchiReadPubChem(self):
for f in self.dataset.values():
same, diff, reasonable = 0, 0, 0
for m in f:
if m is None: # pragma: nocover
continue
x = MolToInchi(m)
y = None
RDLogger.DisableLog('rdApp.error')
mol = MolFromInchi(x)
RDLogger.EnableLog('rdApp.error')
if mol is not None:
y = MolToInchi(
MolFromSmiles(MolToSmiles(mol, isomericSmiles=True)))
if y is None:
# metal involved?
try:
MolToInchi(m, treatWarningAsError=True)
except InchiReadWriteError as inst:
_, error = inst.args
if 'Metal' in error or \
'Charges were rearranged' in error:
reasonable += 1
continue
# THERE ARE NO EXAMPLES FOR THE FOLLOWING (no coverage)
# RDKit does not like the SMILES? use MolBlock instead
inchiMol = MolFromInchi(x)
if inchiMol:
rdDepictor.Compute2DCoords(inchiMol)
z = MolToInchi(MolFromMolBlock(
MolToMolBlock(inchiMol)))
if x == z:
reasonable += 1
continue
# InChI messed up the radical?
unsanitizedInchiMol = MolFromInchi(x, sanitize=False)
if sum([
a.GetNumRadicalElectrons() * a.GetAtomicNum()
for a in m.GetAtoms()
if a.GetNumRadicalElectrons() != 0
]) != sum([
a.GetNumRadicalElectrons() * a.GetAtomicNum()
for a in unsanitizedInchiMol.GetAtoms()
if a.GetNumRadicalElectrons() != 0
]):
reasonable += 1
continue
diff += 1
cid = m.GetProp('PUBCHEM_COMPOUND_CID')
print(COLOR_GREEN + 'Empty mol for PubChem Compound ' +
cid + '\n' + COLOR_RESET)
continue
if x != y:
# if there was warning in the first place, then this is
# tolerable
try:
MolToInchi(m, treatWarningAsError=True)
MolFromInchi(x, treatWarningAsError=True)
except InchiReadWriteError as inst:
reasonable += 1
continue
# or if there are big rings
SanitizeMol(m)
if filter(lambda i: i >= 8,
[len(r) for r in m.GetRingInfo().AtomRings()]):
reasonable += 1
continue
# THERE ARE NO EXAMPLES FOR THE FOLLOWING (no coverage)
# or if RDKit loses bond stereo
s = MolToSmiles(m, True)
if MolToSmiles(MolFromSmiles(s), True) != s:
reasonable += 1
continue
# or if it is RDKit SMILES writer unhappy about the mol
inchiMol = MolFromInchi(x)
rdDepictor.Compute2DCoords(inchiMol)
z = MolToInchi(MolFromMolBlock(MolToMolBlock(inchiMol)))
if x == z:
reasonable += 1
continue
diff += 1
print(COLOR_GREEN +
'Molecule mismatch for PubChem Compound ' + cid +
COLOR_RESET)
print(inchiDiff(x, y))
print()
else:
same += 1
fmt = "\n{0}InChI read Summary: {1} identical, {2} variance, {3} reasonable variance{4}"
print(fmt.format(COLOR_GREEN, same, diff, reasonable, COLOR_RESET))
self.assertEqual(same, 621)
self.assertEqual(diff, 0)
self.assertEqual(reasonable, 560)
def save(self, force_insert=False, force_update=False, *args, **kwargs):
changed = False
new = not bool(CompoundStructures.objects.filter(pk=self.pk).count())
if settings.OPEN_SOURCE:
if self.molfile:
if not new: # The structure already exists and we only want to modify it
super(CompoundStructures, self).save(force_insert, force_update, *args, **kwargs) # this should trigger CMPD_STR_UPDATE_TRIG, which deletes compound images and properties and nulls standard inchi, key, smiles, and molformula
changed = True
# newInchi = inchiFromPipe(self.molfile, settings.INCHI_BINARIES_LOCATION['1.02'])
#if newInchi != self.standard_inchi:
# self.standard_inchi = newInchi
# changed = True
mol = MolFromInchi(self.standard_inchi.encode("ascii"))
if mol:
# self.canonical_smiles = MolToSmiles(mol)
if not self.standard_inchi:
raise NoStandardInchi("for CompundStructure, pk = " + str(self.pk))
newInchiKey = InchiToInchiKey(self.standard_inchi.encode("ascii"))
if self.standard_inchi_key != newInchiKey:
self.standard_inchi_key = newInchiKey
mol = MolFromInchi(self.standard_inchi.encode("ascii"))
# self.canonical_smiles = MolToSmiles(mol)
changed = True
self.molfile = MolToMolBlock(MolFromMolBlock(str(self.molfile))) # This is how we do kekulisation in RDKit...
self.clean_fields()
self.validate_unique()
super(CompoundStructures, self).save(force_insert, force_update, *args, **kwargs)
else:
if self.molfile:
if not new: # The structure already exists and we only want to modify it
super(CompoundStructures, self).save(force_insert, force_update, *args, **kwargs) # this should trigger CMPD_STR_UPDATE_TRIG, which deletes compound images and properties and nulls standard inchi, key, smiles, and molformula
changed = True
data = getStructure(self.molfile)
newInchi = data['InChI']
if newInchi != self.standard_inchi:
self.standard_inchi = newInchi
self.standard_inchi_key = data['InChIKey']
#self.molformula = data['Molecular_Formula']
self.canonical_smiles = data['Canonical_Smiles']
changed = True
if not self.standard_inchi:
raise NoStandardInchi("for CompundStructure, pk = " + str(self.pk))
if not self.standard_inchi_key:
self.standard_inchi_key = InchiToInchiKey(self.standard_inchi.encode("ascii"))
self.clean_fields()
self.validate_unique()
super(CompoundStructures, self).save(force_insert, force_update, *args, **kwargs)
if changed:
self.molecule.structure_key = self.standard_inchi_key
self.molecule.structure_type = "MOL"
self.molecule.molfile_update = datetime.now()
self.molecule.save()
structureChanged.send(sender=self.__class__, instance=self)
from rdkit.Chem import MolFromInchi inchi = 'InChI=1S/C6H6O4/c7-5(8)3-1-2-4-6(9)10/h1-4H,(H,7,8)(H,9,10)/b3-1+,4-2+' mol = MolFromInchi(inchi) assert mol
def get_charge_from_inchi(inchi, removeHs=False):
mol = MolFromInchi(inchi, removeHs=removeHs)
netc = GetFormalCharge(mol)
del mol
return netc
# Using production model
print("Production model running...")
w_path = os.path.join(MODELS_PATH, f"{data}_noHs.pt")
model = MPNNPredictor(
node_in_feats=49,
edge_in_feats=10,
global_feats=4,
n_tasks=1,
output_f=output_f,
).to(DEVICE)
model.load_state_dict(torch.load(w_path, map_location=DEVICE))
gis = [
molecule_importance(MolFromInchi(inchi), model)[4]
for inchi in tqdm(inchis)
]
global_importances = np.vstack(gis)
np.save(os.path.join(DATA_PATH, f"importances{data}.npy"),
arr=global_importances)
# Using oof models
global_importances_oof = []
kf = KFold(n_splits=N_FOLDS, shuffle=True, random_state=SEED)
for idx_split, (_, idx_test) in enumerate(kf.split(inchis)):
print("Split {}/{} running...".format(idx_split + 1, N_FOLDS))
inchis_test, values_test = (
inchis[idx_test].tolist(),
def test_sequence_tunable():
# Check default arguments
args, varargs, varkw, defaults, kwonlyargs, kwonlydefaults, annotations = inspect.getfullargspec(sequence_tunable)
default_params = dict(zip(args[-len(defaults):], defaults))
assert default_params == {
'OP_REMOVE_ISOTOPE':True,
'OP_NEUTRALISE_CHARGE': True,
'OP_REMOVE_STEREO': False,
'OP_COMMUTE_INCHI': False,
'OP_KEEP_BIGGEST': True,
'OP_ADD_HYDROGEN': True,
'OP_KEKULIZE': True,
'OP_NEUTRALISE_CHARGE_LATE': True
}
# Violacein, default parameter
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer(sequence_fun='sequence_tunable').compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
assert MolToSmiles(ans) == '[H]OC1=NC(C2=C([H])N([H])C3=C2C([H])=C(O[H])C([H])=C3[H])=C([H])/C1=C1\\C(O[H])=NC2=C([H])C([H])=C([H])C([H])=C21'
# Violacein, strip stereo
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_REMOVE_STEREO': True}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)'
assert MolToSmiles(ans) == '[H]OC1=C([H])C2=C(C([H])=C1[H])N([H])C([H])=C2C1=C([H])C(=C2C(=O)N([H])C3=C([H])C([H])=C([H])C([H])=C23)C(=O)N1[H]'
# Violacien, implicit Hs
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_ADD_HYDROGEN': False}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
assert MolToSmiles(ans) == 'OC1=CC2=C(C=C1)NC=C2C1=C/C(=C2/C3=CC=CC=C3N=C2O)C(O)=N1'
# Violacien, no kekulerization
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_KEKULIZE': False}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+'
assert MolToSmiles(ans) == '[H]OC1=NC(c2c([H])n([H])c3c([H])c([H])c(O[H])c([H])c23)=C([H])/C1=C1\\C(O[H])=Nc2c([H])c([H])c([H])c([H])c21'
# Violacien, strip stereo & implicit Hs & no kekulerization
mol = MolFromInchi('InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)/b18-13+')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_REMOVE_STEREO': True, 'OP_ADD_HYDROGEN': False, 'OP_KEKULIZE': False}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C20H13N3O3/c24-10-5-6-15-12(7-10)14(9-21-15)17-8-13(19(25)23-17)18-11-3-1-2-4-16(11)22-20(18)26/h1-9,21,24H,(H,22,26)(H,23,25)'
assert MolToSmiles(ans) == 'O=C1NC(c2c[nH]c3ccc(O)cc23)=CC1=C1C(=O)Nc2ccccc21'
# Lactate, default parameter
mol = MolFromSmiles('C[C@@H](C(=O)[O-])O')
ans = Standardizer(sequence_fun='sequence_tunable').compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)/t2-/m0/s1'
assert MolToSmiles(ans) == '[H]OC(=O)[C@@]([H])(O[H])C([H])([H])[H]'
# L-lactate, implicit Hs
mol = MolFromSmiles('C[C@@H](C(=O)[O-])O')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_ADD_HYDROGEN': False}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)/t2-/m0/s1'
assert MolToSmiles(ans) == 'C[C@H](O)C(=O)O'
# L-lactate, no stereo
mol = MolFromSmiles('C[C@@H](C(=O)[O-])O')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_REMOVE_STEREO': True}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)'
assert MolToSmiles(ans) == '[H]OC(=O)C([H])(O[H])C([H])([H])[H]'
# L-lactate, no charge neutralisation
mol = MolFromSmiles('C[C@@H](C(=O)[O-])O')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_NEUTRALISE_CHARGE': False, 'OP_NEUTRALISE_CHARGE_LATE': False}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)/p-1/t2-/m0/s1'
assert MolToSmiles(ans) == '[H]O[C@]([H])(C(=O)[O-])C([H])([H])[H]'
# L-lactate, implicit Hs & no stereo
mol = MolFromSmiles('C[C@@H](C(=O)[O-])O')
ans = Standardizer(sequence_fun='sequence_tunable', params={'OP_ADD_HYDROGEN': False, 'OP_REMOVE_STEREO': True}).compute(mol)
assert MolToInchi(ans) == 'InChI=1S/C3H6O3/c1-2(4)3(5)6/h2,4H,1H3,(H,5,6)'
assert MolToSmiles(ans) == 'CC(O)C(=O)O'
def process(self,
input: Union[str, list] = "",
input_file: str = "",
output_file: str = "",
output_file_sdf: str = "",
output_file_cml: str = "",
sdf_append: bool = False,
format_output: bool = True,
opsin_output_format: str = "",
output_formats: list = None,
write_header: bool = True,
dry_run: bool = False,
csv_delimiter: str = ";",
standardize_mols: bool = True,
normalize_plurals: bool = True,
continue_on_failure: bool = False) -> OrderedDict:
r"""
Process the input file with OPSIN.
Parameters
----------
input : str or list
| str: String with IUPAC names, one per line.
| list: List of IUPAC names.
input_file : str
Path to file to be processed by OPSIN. One IUPAC name per line.
output_file : str
File to write output in.
output_file_sdf : str
File to write SDF output in.
output_file_cml : str
| File to write CML (Chemical Markup Language) output in. `opsin_output_format` must be "cml".
| Not supported by RDKit so standardization and conversion to other formats cannot be done.
sdf_append : bool
If True, append new molecules to existing SDF file or create new one if doesn't exist.
format_output : bool
| If True, the value of "content" key of returned dict will be list of OrderedDicts with keys:
| "iupac", <output formats>, ..., "error"
| If True and `output_file` is set it will be created as CSV file with columns: "iupac", <output formats>, ..., "error"
| If False, the value of "content" key of returned dict will be None.
opsin_output_format : str
| Output format from OPSIN. Temporarily overrides the option `output_format` set during instantiation (in __init__).
| Choices: "cml", "smi", "extendedsmi", "inchi", "stdinchi", "stdinchikey"
output_formats : list
| If True and `format_output` is also True, this specifies which molecule formats will be output.
| You can specify more than one format, but only one format from OPSIN. This format must be also set with `output_format` in __init__
or with `osra_output_format` here.
| Default value: ["smiles"]
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| Value | Source | Note |
+=======================+=======================+============================================================================================+
| smiles | RDKit | canonical |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| smiles_opsin | OPSIN ("smi") | SMILES |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| smiles_extended_opsin | OPSIN ("extendedsmi") | Extended SMILES. Not supported by RDKit. |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| inchi | RDKit | Not every molecule can be converted to InChI (it doesn`t support wildcard characters etc.) |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| inchi_opsin | OPSIN ("inchi") | InChI |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| stdinchi_opsin | OPSIN ("stdinchi") | standard InChI |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| inchikey | RDKit | The same applies as for "inchi". Also molecule cannot be created from InChI-key. |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| stdinchikey_opsin | OPSIN ("stdinchikey") | Standard InChI-key. Cannot be used by RDKit to create molecule. |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
| sdf | RDKit | If present, an additional SDF file will be created. |
+-----------------------+-----------------------+--------------------------------------------------------------------------------------------+
write_header : bool
If True and if `output_file` is set and `output_format` is True, write a CSV write_header.
dry_run : bool
If True, only return list of commands to be called by subprocess.
csv_delimiter : str
Delimiter for output CSV file.
standardize_mols : bool
If True and `format_output` is also True, use molvs (https://github.com/mcs07/MolVS) to standardize molecules.
normalize_plurals : bool
| If True, normalize plurals ("nitrates" -> "nitrate"). See OPSIN.PLURAL_PATTERNS for relating plurals. You can
set your own regex pattern with `plural_patterns` in __init__.
continue_on_failure : bool
| If True, continue running even if OPSIN returns non-zero exit code.
| If False and error occurs, print it and return.
Returns
-------
dict
Keys:
- stdout: str ... standard output from OPSIN
- stderr: str ... standard error output from OPSIN
- exit_code: int ... exit code from OPSIN
- content:
- list of OrderedDicts ... when format_output is True. Fields: "iupac", <output formats>, ..., "error"
- None ... when format_output is False
"""
options_internal = self.options_internal.copy()
opsin_nonreadable_formats = ["cml", "stdinchikey"]
if input and input_file:
input_file = ""
self.logger.warning(
"Both 'input' and 'input_file' are set, but 'input' will be prefered."
)
elif not input and not input_file:
raise ValueError("One of 'input' or 'input_file' must be set.")
# OSRA output format check
if opsin_output_format:
options_internal["output_format"] = opsin_output_format
else:
opsin_output_format = options_internal["output_format"]
opsin_valid_output_formats = {
"cml": "cml_opsin",
"smi": "smiles_opsin",
"extendedsmi": "smiles_extended_opsin",
"inchi": "inchi_opsin",
"stdinchi": "stdinchi_opsin",
"stdinchikey": "stdinchikey_opsin"
}
if opsin_output_format not in opsin_valid_output_formats:
raise ValueError(
"Unknown OPSIN output format. Possible values: {}".format(
list(opsin_valid_output_formats.keys())))
if standardize_mols and opsin_output_format in opsin_nonreadable_formats:
self.logger.warning(
"OPSIN output format is \"{}\", which cannot be used by RDKit."
.format(opsin_output_format))
# output formats check
if not output_formats:
output_formats = ["smiles"]
else:
if opsin_output_format == "stdinchikey":
output_formats = ["stdinchikey_opsin"]
elif opsin_output_format == "extendedsmi":
output_formats = ["smiles_extended_opsin"]
else:
output_formats = sorted(list(set(output_formats)))
possible_output_formats = [
"smiles", "inchi", "inchikey", "sdf"
]
output_formats = [
x for x in output_formats if x in possible_output_formats
or x == opsin_valid_output_formats[opsin_output_format]
]
if normalize_plurals:
if input_file:
with open(input_file, mode="r", encoding="utf-8") as f:
input = "\n".join([x.strip() for x in f.readlines()])
input_file = ""
input = self.normalize_iupac(input)
commands, _, _ = self.build_commands(options_internal,
self._OPTIONS_REAL,
self.path_to_binary)
if input_file:
commands.append(input)
stdout, stderr, exit_code = common_subprocess(commands)
elif input:
if isinstance(input, list):
input = "\n".join([x.strip() for x in input])
stdout, stderr, exit_code = common_subprocess(commands,
stdin=input)
else:
raise UserWarning("Input is empty.")
if dry_run:
return " ".join(commands)
to_return = {
"stdout": stdout,
"stderr": stderr,
"exit_code": exit_code,
"content": None
}
if not continue_on_failure and exit_code > 0:
self.logger.warning("OPSIN error:")
eprint("\n\t".join("\n{}".format(stderr).splitlines()))
return to_return
if output_file_cml and opsin_output_format == "cml":
with open(output_file_cml, mode="w", encoding="utf-8") as f:
f.write(stdout)
return to_return
elif output_file_cml and opsin_output_format != "cml":
self.logger.warning(
"Output file for CML is requested, but OPSIN output format is '{}'"
.format(opsin_output_format))
if not format_output:
if output_file:
with open(output_file, mode="w", encoding="utf-8") as f:
f.write(stdout)
return to_return
compounds = []
standardizer = Standardizer()
empty_cols = OrderedDict([(x, "") for x in output_formats])
if output_file_sdf:
if sdf_append:
if not os.path.isfile(output_file_sdf):
open(output_file_sdf, mode="w", encoding="utf-8").close()
writer = SDWriter(
open(output_file_sdf, mode="a", encoding="utf-8"))
else:
writer = SDWriter(output_file_sdf)
stdout = stdout.split("\n")
del stdout[-1]
stderr = [
x.strip() for x in stderr.split("\n")[1:] if x
] # remove first line of stderr because there is OPSIN message (y u du dis...)
if input_file:
with open(input_file, mode="r", encoding="utf-8") as f:
lines = iter(f.readlines())
else:
lines = iter(input.split("\n"))
mol_output_template = OrderedDict.fromkeys(["iupac"] + output_formats +
["error"])
e = 0
for i, line in enumerate(lines):
line = line.strip()
converted = stdout[i].strip()
mol_output = mol_output_template.copy()
if converted:
if opsin_output_format == "stdinchikey":
compounds.append(
OrderedDict([("iupac", line),
("stdinchikey_opsin", converted),
("error", "")]))
continue
elif opsin_output_format == "extendedsmi":
compounds.append(
OrderedDict([("iupac", line),
("smiles_extended_opsin", converted),
("error", "")]))
continue
if opsin_output_format == "smi":
mol = MolFromSmiles(
converted,
sanitize=False if standardize_mols else True)
elif opsin_output_format in ["inchi", "stdinchi"]:
mol = MolFromInchi(
converted,
sanitize=False if standardize_mols else True,
removeHs=False if standardize_mols else True)
if mol:
if standardize_mols:
try:
mol = standardizer.standardize(mol)
except ValueError as e:
self.logger.warning(
"Cannot standardize '{}': {}".format(
MolToSmiles(mol), str(e)))
for f in output_formats:
if f == "smiles":
mol_output["smiles"] = MolToSmiles(
mol, isomericSmiles=True)
elif f == "smiles_opsin" and opsin_output_format == "smi":
mol_output["smiles_opsin"] = converted
elif f == "inchi":
inchi = MolToInchi(mol)
if inchi:
mol_output["inchi"] = inchi
else:
mol_output["inchi"] = ""
self.logger.warning(
"Cannot convert to InChI: {}".format(
converted))
elif f == "inchi_opsin" and opsin_output_format == "inchi":
mol_output["inchi_opsin"] = converted
elif f == "stdinchi_opsin" and opsin_output_format == "stdinchi":
mol_output["stdinchi_opsin"] = converted
elif f == "inchikey":
inchi = MolToInchi(mol)
if inchi:
mol_output["inchikey"] = InchiToInchiKey(inchi)
else:
mol_output["inchikey"] = ""
self.logger.warning(
"Cannot create InChI-key from InChI: {}".
format(converted))
elif f == "stdinchikey_opsin" and opsin_output_format == "stdinchikey":
mol_output["stdinchikey_opsin"] = converted
elif f == "sdf":
mol_output["sdf"] = MolToMolBlock(
mol, includeStereo=True)
if output_file_sdf:
writer.write(mol)
mol_output.update(
OrderedDict([("iupac", line), ("error", "")]))
else:
mol_output.update([
("iupac", line),
("error",
"Cannot convert to RDKit mol: {}".format(converted))
])
mol_output.update(empty_cols)
self.logger.warning(compounds[-1].error)
else:
try:
error = stderr[e].strip()
except IndexError:
error = ""
mol_output.update([("iupac", line), ("error", error)])
mol_output.update(empty_cols)
e += 1
compounds.append(mol_output)
to_return["content"] = compounds
if output_file and compounds:
dict_to_csv(to_return["content"],
output_file=output_file,
csv_delimiter=csv_delimiter,
write_header=write_header)
elif output_file and not compounds:
write_empty_file(output_file,
csv_delimiter=csv_delimiter,
header=list(mol_output_template.keys()),
write_header=write_header)
return to_return
