Merge pull request #38 from datamol-io/fix/fused-ring

Fix Error in Digit Counting That mess up Fused Rings

safe/converter.py

@@ -288,6 +288,7 @@ def encoder(
                 continue
             obond = mol.GetBondBetweenAtoms(i_a, i_b)
             bonds.append(obond.GetIdx())
+
         if len(bonds) > 0:
             mol = Chem.FragmentOnBonds(
                 mol,
@@ -297,7 +298,6 @@ def encoder(
         # here we need to be clever and disable rooted atom as the atom with mapping
 
         frags = list(Chem.GetMolFrags(mol, asMols=True))
-
         if randomize:
             frags = rng.permutation(frags).tolist()
         elif canonical:
@@ -322,18 +322,23 @@ def encoder(
             )
 
         scaffold_str = ".".join(frags_str)
+        # EN: fix for https://github.com/datamol-io/safe/issues/37
+        # we were using the wrong branch number count which did not take into account
+        # possible change in digit utilization after bond slicing
+        scf_branch_num = self._find_branch_number(scaffold_str) + branch_numbers
+
         # don't capture atom mapping in the scaffold
         attach_pos = set(re.findall(r"(\[\d+\*\]|!\[[^:]*:\d+\])", scaffold_str))
-
         if canonical:
             attach_pos = sorted(attach_pos)
-        starting_num = 1 if len(branch_numbers) == 0 else max(branch_numbers) + 1
+        starting_num = 1 if len(scf_branch_num) == 0 else max(scf_branch_num) + 1
         for attach in attach_pos:
             val = str(starting_num) if starting_num < 10 else f"%{starting_num}"
             # we cannot have anything of the form "\([@=-#-$/\]*\d+\)"
             attach_regexp = re.compile(r"(" + re.escape(attach) + r")")
             scaffold_str = attach_regexp.sub(val, scaffold_str)
             starting_num += 1
+
         # now we need to remove all the parenthesis around digit only number
         wrong_attach = re.compile(r"\(([\%\d]*)\)")
         scaffold_str = wrong_attach.sub(r"\g<1>", scaffold_str)

tests/test_safe.py

@@ -110,3 +110,14 @@ def test_bracket_smiles_issues(input_sm):
     assert safe.decode(safe_str) is not None
     assert dm.same_mol(dm.to_mol(safe_str), input_mol)
     assert None not in fragments
+
+
+def test_fused_ring_issue():
+    FUSED_RING_LIST = [
+        "[H][C@@]12CC[C@@]3(CCC(=O)O3)[C@@]1(C)CC[C@@]1([H])[C@@]2([H])[C@@]([H])(CC2=CC(=O)CC[C@]12C)SC(C)=O",
+        "[H][C@@]12C[C@H](C)[C@](OC(=O)CC)(C(=O)COC(=O)CC)[C@@]1(C)C[C@H](O)[C@@]1(Cl)[C@@]2([H])CCC2=CC(=O)C=C[C@]12C",
+        "[H][C@@]12CC[C@@](O)(C#C)[C@@]1(CC)CC[C@]1([H])[C@@]3([H])CCC(=O)C=C3CC[C@@]21[H]",
+    ]
+    for fused_ring in FUSED_RING_LIST:
+        output_string = safe.decode(safe.encode(fused_ring))
+        assert dm.same_mol(fused_ring, output_string)