Fragment_Cages-RDKIT

import rdkit
from rdkit.Chem import AllChem
import operator

mol = AllChem.MolFromMolFile('test.mol')
imine = AllChem.MolFromSmiles('CC=NC')
subs = mol.GetSubstructMatches(imine)

bonds = []
for i in subs:
  bonds.append(i[1:3])
bond_ids = [mol.GetBondBetweenAtoms(x,y).GetIdx() for x,y in bonds]
new_mol = AllChem.FragmentOnBonds(mol,bond_ids)

new_smiles = AllChem.MolToSmiles(new_mol, True)
new_split = new_smiles.split('.')

corrected_fragments = []
uncorrected_fragments = []

for i in new_split:
  a = AllChem.ReplaceSubstructs(AllChem.MolFromSmiles(str(i)), AllChem.MolFromSmarts('C=[D1]'), AllChem.MolFromSmarts('C=O'), replaceAll=True)
  b = AllChem.MolToSmiles(a[0])
  c = AllChem.MolFromSmiles(b)

  if '*' not in str(b):
    au = AllChem.ReplaceSubstructs(AllChem.MolFromSmiles(str(i)), AllChem.MolFromSmarts('C=[D1]'), AllChem.MolFromSmarts('C=[D1]'), replaceAll=True)
    corrected_fragments.append(c)
    uncorrected_fragments.append(au[0])

  else:
    d = AllChem.ReplaceSubstructs(c, AllChem.MolFromSmarts('N=[D1]'), AllChem.MolFromSmarts('N'), replaceAll=True)
    au = AllChem.ReplaceSubstructs(c, AllChem.MolFromSmarts('N=[D1]'), AllChem.MolFromSmarts('[D1]'), replaceAll=True)
    corrected_fragments.append(d[0])
    uncorrected_fragments.append(au[0])

smiles_fragments = []
for i in corrected_fragments:
        smiles_fragments.append(AllChem.MolToSmiles(i))

building_blocks_dict = {i:smiles_fragments.count(i) for i in smiles_fragments}
print(building_blocks_dict)

uncorrected_smiles_fragments = []
for i in uncorrected_fragments:
  uncorrected_smiles_fragments.append(AllChem.MolToSmiles(i))

unknown_functional_group = AllChem.MolFromSmiles('*')
number_of_groups = []
for i in uncorrected_smiles_fragments:
  a = AllChem.MolFromSmiles(i)
  b = a.GetSubstructMatches(unknown_functional_group)
  number_of_groups.append(len(b))
  
functional_group_dict = {i:number_of_groups.count(i) for i in number_of_groups}
sorted_fgd = sorted(functional_group_dict.items(), key=operator.itemgetter(0))

if str(sorted_fgd) == '[(2, 3), (3, 2)]':
  topology = 'stk.TwoPlusThree'
elif str(sorted_fgd) == '[(2, 6), (3, 4)]':
  topology = 'stk.FourPlusSix'
elif str(sorted_fgd) == '[(2, 9), (3, 6)]':
  topology = 'stk.SixPlusNine'
elif str(sorted_fgd) == '[(2, 12), (3, 8)]':
  topology = 'stk.EightPlusTwelve'

elif str(sorted_fgd) == '[(3, 4), (4, 2)]':
  topology = 'stk.TwoPlusFour'
elif str(sorted_fgd) == '[(3, 6), (4, 3)]':
  topology = 'stk.ThreePlusSix'
elif str(sorted_fgd) == '[(3, 12), (4, 6)]':
  topology = 'stk.SixPlusTwelve'
else:
  topology = 'unknown'

print(topology)