def standardize_smiles(smiles,
min_heavy_atoms=2,
max_heavy_atoms=70,
element_list=None,
remove_long_side_chains=True,
neutralise_charges=True):
if element_list is None:
element_list = [6, 7, 8, 9, 16, 17, 35]
mol = rkc.MolFromSmiles(smiles)
if mol:
mol = _get_largest_fragment(mol)
if mol:
mol = rdmolops.RemoveHs(mol,
implicitOnly=False,
updateExplicitCount=False,
sanitize=True)
if mol:
mol = _remove_salts(mol)
if mol and neutralise_charges:
mol, _ = _neutralise_charges(mol)
if mol:
rdmolops.Cleanup(mol)
rdmolops.SanitizeMol(mol)
mol = rdmolops.RemoveHs(mol,
implicitOnly=False,
updateExplicitCount=False,
sanitize=True)
if mol and _valid_size(mol, min_heavy_atoms, max_heavy_atoms, element_list,
remove_long_side_chains):
return rkc.MolToSmiles(mol, isomericSmiles=False)
return None
def standardize_smiles(smiles, min_heavy_atoms=10, max_heavy_atoms=50, element_list=[6, 7, 8, 9, 16, 17, 35],
remove_long_side_chains=True, neutralise_charges=True):
mol = Chem.MolFromSmiles(smiles)
if mol:
mol = _getlargestFragment(mol)
if mol:
mol = rdmolops.RemoveHs(mol, implicitOnly=False, updateExplicitCount=False, sanitize=True)
if mol:
mol = _saltremover.StripMol(mol, dontRemoveEverything=True)
if mol and neutralise_charges:
mol, _ = _neutraliseCharges(mol)
if mol:
rdmolops.Cleanup(mol)
rdmolops.SanitizeMol(mol)
mol = rdmolops.RemoveHs(mol, implicitOnly=False, updateExplicitCount=False, sanitize=True)
if mol and valid_size(mol, min_heavy_atoms, max_heavy_atoms, element_list, remove_long_side_chains):
return Chem.MolToSmiles(mol, isomericSmiles=False)
return None
def test_mols():
mols = []
all_smiles = [
'CN=C=O', 'Cc1ccccc1', 'CC1=CC2CC(CC1)O2', 'CCCCCCCCCCCCCCCC'
]
for smiles in all_smiles:
mol = rdmolfiles.MolFromSmiles(smiles)
mol = rdmolops.AddHs(mol, addCoords=True)
rdDistGeom.EmbedMolecule(mol, rdDistGeom.ETKDG())
mol = rdmolops.RemoveHs(mol)
mol.SetProp('Fitness', str(np.random.rand(1)[0]))
mols.append(mol)
return mols
def apply_retrorules(self, smile, rxns, explicit_hydrogens=False):
'''Function takes a smile and dictionary of reactions, applys the reactions and
returns a dictionary of rxn_names : products '''
try:
substrate_molecule = AllChem.MolFromSmiles(smile)
except:
return {}
if explicit_hydrogens == True:
substrate_molecule = rdmolops.AddHs(substrate_molecule)
rxn_product_dict = {}
for rxn_name, rxn in rxns.items():
try:
products = rxn.RunReactants((substrate_molecule, ))
except:
products = []
print('Error running reactants for: ' + str(smile))
smiles_products = []
for product in products:
sub_list = []
for mol in product:
mols = [mol]
if explicit_hydrogens == True:
mol = rdmolops.RemoveHs(mol)
try:
mols = rdmolops.GetMolFrags(mol, asMols=True)
except:
pass
for mol in mols:
try:
p_smile = AllChem.MolToSmiles(mol)
p_smile = rdkit_smile(p_smile)
if self._check_valid_smile(
p_smile, rxn_name=rxn_name) == True:
sub_list.append(p_smile)
except:
pass
if (sub_list not in smiles_products) and (len(sub_list) != 0):
smiles_products.append(sub_list)
if len(smiles_products) != 0:
rxn_product_dict[rxn_name] = smiles_products
return rxn_product_dict
def prepare_mol(mol,
do_geometry=True,
do_charge=True,
property_name='_GasteigerCharge',
max_iter=1000,
mmffvariant='MMFF94',
seed=26,
max_attempts=5):
# 'mmffVariant : “MMFF94” or “MMFF94s”'
# seeded coordinate generation, if = -1, no random seed provided
# removes starting coordinates to ensure reproducibility
# max attempts, to increase if issues are encountered during optimization
if do_charge is True:
property_name = '_GasteigerCharge'
# options for sanitization
san_opt = Chem.SanitizeFlags.SANITIZE_ALL ^ Chem.SanitizeFlags.SANITIZE_KEKULIZE
# sanitization
if mol is None:
err = 1
else:
# sanitize
sanitize_fail = Chem.SanitizeMol(mol,
catchErrors=True,
sanitizeOps=san_opt)
if sanitize_fail:
raise ValueError(sanitize_fail)
err = 1
if do_geometry is True:
mol, err = opt_geometry(mol, max_iter, mmffvariant, seed,
max_attempts)
# calculates or assigns atom charges based on what annotated in do_charge
mol = rdmolops.RemoveHs(mol)
if do_charge is True:
mol, name, err = get_charge(mol, property_name, do_charge)
if err == 1:
print('Error in molecule pre-treatment')
return mol, err
def prepare_mol(mol,
do_geometry=True,
do_charge=True,
property_name='_GasteigerCharge',
max_iter=1000,
mmffvariant='MMFF94',
seed=26,
max_attempts=5):
if do_charge is True:
property_name = '_GasteigerCharge'
# options for sanitization
san_opt = Chem.SanitizeFlags.SANITIZE_ALL ^ Chem.SanitizeFlags.SANITIZE_KEKULIZE
# sanitization
if mol is None:
err = 1
else:
# sanitize
sanitize_fail = Chem.SanitizeMol(mol,
catchErrors=True,
sanitizeOps=san_opt)
if sanitize_fail:
raise ValueError(sanitize_fail)
err = 1
if do_geometry is True:
mol, err = opt_geometry(mol, max_iter, mmffvariant, seed,
max_attempts)
# calculates or assigns atom charges based on what annotated in do_charge
mol = rdmolops.RemoveHs(mol)
if do_charge is True:
mol, name, err = get_charge(mol, property_name, do_charge)
if err == 1:
print('Error in molecule pre-treatment')
return mol, err
def construct_pos_matrix(mol: rdchem.Mol,
out_size: Optional[int] = -1) -> np.ndarray:
"""Construct relative positions from each atom within the molecule.
Params:
-------
mol: rdkit.Chem.rdchem.Mol
Molecule of interest.
out_size: int, optional, default=-1
The size of the returned array. If this option is negative, it
does not take any effect. Otherwise, it must be larger than or
equal to the number of atoms in the input molecule. If so, the
end of the array is padded with zeros.
Returns:
--------
pos_matrix: np.ndarray, shape=(n,n,3)
Relative position (XYZ) coordinates from one atom the others in
the mol.
Examples:
---------
```python
>>> from rdkit import Chem
>>> from rdkit.Chem import AllChem
>>> smiles = 'N[C@@]([H])([C@]([H])(O2)C)C(=O)N[C@@]([H])(CC(=O)N)C(=O)N[C@@]([H])([C@]([H])' \
'(O)C)C(=O)N[C@@]([H])(Cc1ccc(O)cc1)C(=O)2'
>>> mol = Chem.MolFromSmiles(smiles)
>>> mol = Chem.AddHs(mol, addCoords=True)
>>> AllChem.EmbedMolecule(mol, AllChem.ETKDG())
>>> mol = Chem.RemoveHs(mol)
>>> pos_matrix = construct_pos_matrix(mol, out_size=-1)
>>> pos_matrix.shape
(34,34,3)
>>> pos_matrix = construct_pos_matrix(mol, out_size=49)
>>> pos_matrix.shape
(49,49,3)
```
"""
# Obtain initial distance geometry between atoms, if unavilable
if mol.GetNumConformers() == 0:
mol = rdmolops.AddHs(mol, addCoords=True)
rdDistGeom.EmbedMolecule(mol, rdDistGeom.ETKDG())
mol = rdmolops.RemoveHs(mol)
coords = mol.GetConformer().GetPositions() # shape=(N,3)
N = mol.GetNumAtoms()
# Determine appropiate output size to generate feature matrix of same size for all mols.
if out_size < 0:
size = N
elif out_size >= N:
size = out_size
else:
raise ValueError(
'`out_size` (N={}) is smaller than number of atoms in mol (N={})'.
format(out_size, N))
pos_matrix = np.zeros(shape=(size, size, 3), dtype=np.float)
for atom_idx in range(N):
atom_pos = coords[atom_idx] # central atom of interest
for neighbor_idx in range(N):
neigh_pos = coords[neighbor_idx] # neighboring atom
pos_matrix[
atom_idx,
neighbor_idx] = atom_pos - neigh_pos # dist between neighbor -> center
return pos_matrix
def sample_mol():
mol = rdmolfiles.MolFromSmiles('CN=C=O')
mol = rdmolops.AddHs(mol, addCoords=True)
rdDistGeom.EmbedMolecule(mol, rdDistGeom.ETKDG())
return rdmolops.RemoveHs(mol)
def ChopWithRDKit(outputDir,inputPath):
#read input from terminal and get file name
lig=os.path.basename(inputPath) #file name, no path
#output folder
output=outputDir+'output-chop/'
outputFolderPath_log=outputDir+'output-log/'
outputFolderPath_sdf=outputDir+'output-sdf/'
outputFolderPath_chop_comb=outputDir+'output-chop-comb/'
suppl=Chem.MolFromMol2File(inputPath,sanitize=False)
tempSDFPath=outputDir+'output-sdf/'+lig+'.sdf'
w=Chem.SDWriter(tempSDFPath)
w.SetKekulize(False)
w.write(suppl)
w.close()
suppl2 = rdmolops.RemoveHs(suppl)
newmol=Chem.FragmentOnBRICSBonds(suppl2)
mfl=Chem.GetMolFrags(newmol,asMols=True,sanitizeFrags=False)
# Reconnect some double bonds broken by BRICS - L7
mfl2 = ReconnectDoubleBond(suppl2, mfl)
#generate fragments with rdkit
fileList=[]
f=0
l=0
r=0
for m in mfl2:
carbonC=0
nitrogC=0
oxygenC=0
rmAtomCount=0
for i in range(m.GetNumAtoms()):
#record dummy atom and hydrogen number
if m.GetAtomWithIdx(i).GetSymbol() == '*':
rmAtomCount=rmAtomCount+1
if m.GetAtomWithIdx(i).GetSymbol() == 'H':
rmAtomCount=rmAtomCount+1
if m.GetAtomWithIdx(i).GetSymbol() == 'C':
carbonC=carbonC+1
if m.GetAtomWithIdx(i).GetSymbol() == 'N':
nitrogC=nitrogC+1
if m.GetAtomWithIdx(i).GetSymbol() == 'O':
oxygenC=oxygenC+1
#create file
totalAtomNum=m.GetNumAtoms()-rmAtomCount
if m.GetNumAtoms()-rmAtomCount >=4 :
tempFileName=output+'b-'+lig+'-'+str(r).zfill(3)+'.sdf'
r=r+1
if m.GetNumAtoms()-rmAtomCount <4 :
tempFileName=output+'l-'+lig+'-'+str(l).zfill(3)+'.sdf'
l=l+1
w=Chem.SDWriter(tempFileName)
w.SetKekulize(False)
f=f+1
w.write(m)
w.close()
fileList.append(tempFileName)
#create file list with atom numbers
with open(outputFolderPath_log+'ListAll','at') as outlist:
outlist.write(tempFileName+' T '+str(totalAtomNum)+' C '+str(carbonC)+' N '+str(nitrogC)+' O '+str(oxygenC)+' \n')
#with open(outputFolderPath_log+'Process.log','at') as outf:
# outf.write('Files are created.\n')
#read atom coordinates and atom type from mol2 file
mol2AllList=[]
with open(inputPath,'r') as inf:
mol2AllList=inf.readlines()
mol2AtomInfo=[]
molHead=mol2AllList.index('@<TRIPOS>ATOM\n')
molEnd=mol2AllList.index('@<TRIPOS>BOND\n')
mol2AtomInfo=mol2AllList[molHead+1:molEnd]
mol2X=[]
mol2Y=[]
mol2Z=[]
mol2A=[]
for i in range(len(mol2AtomInfo)):
mol2Line=mol2AtomInfo[i].split()
mol2X.append(float(mol2Line[2]))
mol2Y.append(float(mol2Line[3]))
mol2Z.append(float(mol2Line[4]))
mol2A.append(mol2Line[5])
for filePath in fileList:
fileName=os.path.basename(filePath)
if len(fileName) >0:
#processing brick fragments
if fileName[0] == 'b':
brickInfoList=[]
with open(filePath,'r') as inf:
brickInfoList=inf.readlines()
#print(brickInfoList)
brickMolEndList=[i for i, x in enumerate(brickInfoList) if x == '$$$$\n']
#print(brickInfoList[:brickMolEndList[0]])
fileHead=list(filter(lambda x: 'V2000' in x, brickInfoList))
fileHeadLineNum=brickInfoList.index(fileHead[0])
#print(fileHeadLineNum)
fileHeadList=fileHead[0].split()
atomNum=int(fileHead[0][0:3])
bondNum=int(fileHead[0][3:6])
atomList=brickInfoList[fileHeadLineNum+1:fileHeadLineNum+atomNum+1]
bondList=brickInfoList[fileHeadLineNum+atomNum+1:fileHeadLineNum+atomNum+bondNum+1]
#Search for atom type
atomTypeList=[]
dummyAtomList=[]
dummyAtomLineList=[]
hydrAtomList=[]
hydrAtomLineList=[]
for atomLine in atomList:
atomLineInfoList=atomLine.split()
#atom in brick.sdf, xyz coordinates of one line
atomX=float(atomLineInfoList[0])
atomY=float(atomLineInfoList[1])
atomZ=float(atomLineInfoList[2])
#calculate norm
normList=[]
for i in range(len(mol2AtomInfo)):
norm=(atomX-mol2X[i])*(atomX-mol2X[i])+(atomY-mol2Y[i])*(atomY-mol2Y[i])+(atomZ-mol2Z[i])*(atomZ-mol2Z[i])
normList.append(norm)
minInd=normList.index(min(normList))
atomTypeList.append(mol2A[minInd]+'\n')
#dummy atom List
if atomLineInfoList[3] == "R":
dummyAtomList.append(atomList.index(atomLine))
dummyAtomLineList.append(atomLine)
#hydrogen atom list
if atomLineInfoList[3] == "H":
hydrAtomList.append(atomList.index(atomLine))
hydrAtomLineList.append(atomLine)
newBrickInfoList=brickInfoList[:brickMolEndList[0]]
#Branch, eligible to connect
bondInfoList=[]
for bondLine in bondList:
#bondLineInfoList=bondLine.split()
bondLineInfoList=[bondLine[0:3],bondLine[3:6]]+bondLine[6:].split()
bondInfoList.append([int(bondLineInfoList[0]),int(bondLineInfoList[1])])
dummyConnection=[] #dummyConnection is a list of connections of the original file, eg. ['8 14 1 0\n',''], which will be used to remove not using connections in the last step
allConnection=[] #all connection is a list of connection pairs, eg. [[8,14],[6,15]], which will be used to generate appendix II
for dummyIdx in dummyAtomList:
connectionList=list(filter(lambda x: dummyIdx+1 in x, bondInfoList))
for tempCon in connectionList:
conIndex=bondInfoList.index(tempCon)
dummyConnection.append(bondList[conIndex])
#remove the case both dummy atoms are in the bond
rmBond=[]
for connect in connectionList:
if connect[0]-1 in dummyAtomList:
if connect[1]-1 in dummyAtomList:
rmBond.append(connect)
for tempBond in rmBond:
connectionList.remove(tempBond)
allConnection=allConnection+connectionList
tempDummyCon=[]
for dummyCon in dummyConnection:
if dummyCon not in tempDummyCon:
tempDummyCon.append(dummyCon)
dummyConnection=tempDummyCon
branchCon=[]
for connect in allConnection:
if connect[0]-1 in dummyAtomList:
branchCon.append(str(connect[1])+' '+atomTypeList[connect[0]-1])
if connect[1]-1 in dummyAtomList:
branchCon.append(str(connect[0])+' '+atomTypeList[connect[1]-1])
#sort branch by atom index
branchConAtomList=[]
branchConAtomListBefore=[]
branchConAtomIndexList=[]
newBranchCon=[] #newBranchCon is the list of appendix II
for branchLine in branchCon:
branchLineList=branchLine.split()
branchConAtomListBefore.append(branchLineList[0])
branchConAtomList=sorted(branchConAtomListBefore)
branchConAtomIndexList=sorted(range(len(branchConAtomListBefore)),key=lambda k:branchConAtomListBefore[k])
for ind in range(len(branchConAtomList)):
newBranchCon.append(branchCon[branchConAtomIndexList[ind]])
#hydrogen
hydrConnection=[]
for hydrIdx in hydrAtomList:
connectionList=filter(lambda x: hydrIdx+1 in x, bondInfoList)
for tempCon in connectionList:
conIndex=bondInfoList.index(tempCon)
hydrConnection.append(bondList[conIndex])
#edit head line
newAtomNum=atomNum-len(dummyAtomLineList)-len(hydrAtomLineList)
newBondNum=bondNum-len(dummyConnection)-len(hydrConnection)
newHead=str(newAtomNum).rjust(3)+str(newBondNum).rjust(3)+fileHead[0][6:]
newBrickInfoList[fileHeadLineNum]=newHead
newBrickInfoList[0]=fileName+'\n'
#edit output list
#edit appendix I - ATOM TYPES
newBrickInfoList.append('\n')
newBrickInfoList.append('> <ATOMTYPES> \n')
newBrickInfoList=newBrickInfoList+atomTypeList[:newAtomNum]
#edit appendix II - BRANCH ATOM NUMBER AND ELIGIBLE ATMTYPE TO CONNECT
newBrickInfoList.append('\n')
newBrickInfoList.append('> <BRANCH @atom-number eligible-atmtype-to-connect> \n')
newBrickInfoList=newBrickInfoList+newBranchCon
newBrickInfoList.append('\n')
newBrickInfoList.append('$$$$\n')
#remove dummy atoms
for dummyLine in dummyAtomLineList:
newBrickInfoList.remove(dummyLine)
#remove dummy bonds
for dummyCon in dummyConnection:
newBrickInfoList.remove(dummyCon)
#remove hydrogen atoms
for hydrLine in hydrAtomLineList:
newBrickInfoList.remove(hydrLine)
#remove hydrogen bonds
for hydrCon in hydrConnection:
newBrickInfoList.remove(hydrCon)
#remove M ISO line
fileMISO=list(filter(lambda x: 'M ISO' in x, newBrickInfoList))
#print(fileMISO)
if len(fileMISO)>0:
for ISO in fileMISO:
newBrickInfoList.remove(ISO)
#remove M CHG line
fileMCHG=list(filter(lambda x: 'M CHG' in x, newBrickInfoList))
if len(fileMCHG)>0:
for CHG in fileMCHG:
newBrickInfoList.remove(CHG)
#write brick info to file
with open(filePath,'w') as outf:
outf.writelines(newBrickInfoList)
#Processing linker fragments
if fileName[0] == 'l':
linkerInfoList=[]
with open(filePath,'r+') as inf:
linkerInfoList=inf.readlines()
#find the end of molcules
linkerMolEndList=[i for i, x in enumerate(linkerInfoList) if x == '$$$$\n']
#find the start of molecules
fileHead=list(filter(lambda x: 'V2000' in x, linkerInfoList))
#indicate the line num of the head line
fileHeadLineNum=linkerInfoList.index(fileHead[0])
#separate atom num and bond num, then separate atom and bond info
fileHeadList=fileHead[0].split()
atomNum=int(fileHead[0][0:3])
bondNum=int(fileHead[0][3:6])
atomList=linkerInfoList[fileHeadLineNum+1:fileHeadLineNum+atomNum+1]
bondList=linkerInfoList[fileHeadLineNum+atomNum+1:fileHeadLineNum+atomNum+bondNum+1]
#Search for atom type
atomTypeList=[]
dummyAtomList=[]
dummyAtomLineList=[]
hydrAtomList=[]
hydrAtomLineList=[]
for atomLine in atomList:
atomLineInfoList=atomLine.split()
#atom in brick.sdf, xyz coordinates of one line
atomX=float(atomLineInfoList[0])
atomY=float(atomLineInfoList[1])
atomZ=float(atomLineInfoList[2])
#calculate norm
normList=[]
for i in range(len(mol2AtomInfo)):
norm=(atomX-mol2X[i])*(atomX-mol2X[i])+(atomY-mol2Y[i])*(atomY-mol2Y[i])+(atomZ-mol2Z[i])*(atomZ-mol2Z[i])
normList.append(norm)
minInd=normList.index(min(normList))
atomTypeList.append(mol2A[minInd]+'\n')
#dummy atom List
if atomLineInfoList[3] == "R":
dummyAtomList.append(atomList.index(atomLine))
dummyAtomLineList.append(atomLine)
#hydrogen atom list
if atomLineInfoList[3] == "H":
hydrAtomList.append(atomList.index(atomLine))
hydrAtomLineList.append(atomLine)
newLinkerInfoList=linkerInfoList[:linkerMolEndList[0]]
#Branch, eligible to connect
bondInfoList=[]
for bondLine in bondList:
#bondLineInfoList=bondLine.split()
bondLineInfoList=[bondLine[0:3],bondLine[3:6]]+bondLine[6:].split()
bondInfoList.append([int(bondLineInfoList[0]),int(bondLineInfoList[1])])
dummyConnection=[]
allConnection=[]
for dummyIdx in dummyAtomList:
connectionList=list(filter(lambda x: dummyIdx+1 in x, bondInfoList))
for tempCon in connectionList:
conIndex=bondInfoList.index(tempCon)
dummyConnection.append(bondList[conIndex])
#remove the case both dummy atom are in the bond
rmBond=[]
for connect in connectionList:
if connect[0]-1 in dummyAtomList:
if connect[1]-1 in dummyAtomList:
rmBond.append(connect)
for tempBond in rmBond:
connectionList.remove(tempBond)
allConnection=allConnection+connectionList
#remove connection duplicates
tempDummyCon=[]
for dummyCon in dummyConnection:
if dummyCon not in tempDummyCon:
tempDummyCon.append(dummyCon)
dummyConnection=tempDummyCon
contactCount=[]
for connect in allConnection:
if connect[0]-1 in dummyAtomList:
contactCount.append(connect[1])
if connect[1]-1 in dummyAtomList:
contactCount.append(connect[0])
#hydrogen
hydrConnection=[]
for hydrIdx in hydrAtomList:
connectionList=list(filter(lambda x: hydrIdx+1 in x, bondInfoList))
for tempCon in connectionList:
conIndex=bondInfoList.index(tempCon)
hydrConnection.append(bondList[conIndex])
#edit output list
#edit head line
newAtomNum=atomNum-len(dummyAtomLineList)-len(hydrAtomLineList)
newBondNum=bondNum-len(dummyConnection)-len(hydrConnection)
newHead=str(newAtomNum).rjust(3)+str(newBondNum).rjust(3)+fileHead[0][6:]
newLinkerInfoList[fileHeadLineNum]=newHead
newLinkerInfoList[0]=fileName+'\n'
#edit appendix I - MAX NUMBER OF CONTACTS AND ATOMTYPES
contactAppend=[]
for i in range(atomNum):
contactAppend.append(str(contactCount.count(i+1))+' '+atomTypeList[i])
newLinkerInfoList.append('\n')
newLinkerInfoList.append('> <MAX-NUMBER-Of-CONTACTS ATOMTYPES> \n')
newLinkerInfoList=newLinkerInfoList+contactAppend[:newAtomNum]
newLinkerInfoList.append('\n')
newLinkerInfoList.append('$$$$\n')
#remove dummy atoms
for dummyLine in dummyAtomLineList:
newLinkerInfoList.remove(dummyLine)
#remove dummy bonds
for dummyCon in dummyConnection:
newLinkerInfoList.remove(dummyCon)
#remove hydrogen atoms
for hydrLine in hydrAtomLineList:
newLinkerInfoList.remove(hydrLine)
#remove hydrogen bonds
for hydrCon in hydrConnection:
newLinkerInfoList.remove(hydrCon)
#remove M ISO line
fileMISO=list(filter(lambda x: 'M ISO' in x, newLinkerInfoList))
if len(fileMISO)>0:
for ISO in fileMISO:
newLinkerInfoList.remove(ISO)
#remove M CHG line
fileMCHG=list(filter(lambda x: 'M CHG' in x, newLinkerInfoList))
if len(fileMCHG)>0:
for CHG in fileMCHG:
newLinkerInfoList.remove(CHG)
#write linker info to file
with open(filePath,'w') as outf:
outf.writelines(newLinkerInfoList)
with open(outputFolderPath_log+'Process.log','at') as outLog:
outLog.write(time.asctime( time.localtime(time.time()) ))
outLog.write(' CHOP-MOL ')
outLog.write(inputPath)
outLog.write('\n')
tempCombineList=[]
tempCombineList.append(inputPath)
tempCombineList=tempCombineList+fileList
combineLinkers(outputDir,tempCombineList)
tempValue = FindDoubleBonds(inputFrags[i])
if tempValue >= 0:
# Find C.2 = C.2 bond
dbFragList.append(fragmentMolblocks[i])
else:
newFragmentMolBlocks.append(fragmentMolblocks[i])
reconnectedDBFrags = ProcessDoubleBonds(parentMolblock, dbFragList)
newFragmentMolBlocks = newFragmentMolBlocks + reconnectedDBFrags
newFragmentMol = []
for i in range(len(newFragmentMolBlocks)):
tempFragMol = Chem.MolFromMolBlock(newFragmentMolBlocks[i],sanitize=False)
newFragmentMol.append(tempFragMol)
# return tuple mol-objects
return tuple(newFragmentMol)
suppl2 = rdmolops.RemoveHs(suppl)
new2 = BRICS.BreakBRICSBonds(suppl2)
mfl2 = Chem.GetMolFrags(new2, asMols=True, sanitizeFrags=False)
mfl3 = ReconnectDoubleBond(suppl2,mfl2)
for i in range(len(mfl3)):
print(Chem.MolToMolBlock(mfl3[i]))
pass
#FindDoubleBonds(mfl2[i])