Bug in ring index bumping fixed

glyles/glycans/mono/monomer.py

@@ -12,6 +12,13 @@
     GlycanLexer.MOD = GlycanLexer.QMARK + 1
 
 
+def shift(d, offset):
+    x = str(int(d) + offset)
+    if len(x) != 1:
+        return "%" + x
+    return x
+
+
 class Monomer:
 
     def __init__(self, origin=None, **kwargs):
@@ -319,9 +326,19 @@ def to_smiles(self, ring_index, root_idx=None, root_id=None):
         root_id = self.__check_root_id(root_id)
 
         smiles = MolToSmiles(self.get_structure(), rootedAtAtom=root_id)
-        for match in reversed(list(re.finditer(r'[a-zA-GI-Z|\]]\d+', smiles))):
-            num = int(smiles[match.start() + 1: match.end()]) + ring_index
-            smiles = smiles[:match.start() + 1] + ("" if num < 10 else "%") + str(num) + smiles[match.end():]
+
+        # bump ring indices to avoid clashes with outer rings
+        # for match in reversed(list(re.finditer(r'[a-zA-GI-Z0-9|\]]\d', smiles))):
+        #     num = int(smiles[match.start() + 1: match.end()]) + ring_index * 10
+        #     smiles = smiles[:match.start() + 1] + "%" + str(num) + smiles[match.end():]
+        for m in reversed(list(iter(re.finditer(r'[A-G|I-Za-z|\]|%]\d+', smiles)))):
+            start, end = m.start(), m.end()
+            match = smiles[start:end]
+            if match[0] == "%":
+                new_str = shift(match[1:], ring_index)
+            else:
+                new_str = match[0] + "".join(shift(d, ring_index) for d in match[1:])
+            smiles = smiles[:start] + new_str + smiles[end:]
         return smiles
 
     def __check_root_id(self, root_id):

glyles/glycans/mono/reactor.py

@@ -63,6 +63,7 @@
     "TIPS": "[Si](C(C)C)(C(C)C)C(C)C",
     "TMS": "[Si](C)(C)C",
     "Thr": "N[C@@H](C(=O)O)[C@@H](O)C",
+    "triN": "N=[N+]=[N-]",
     "Troc": "C(=O)OCC(Cl)(Cl)Cl",
     "Ts": "S(=O)(=O)c2ccc(C)cc2",
     "Ulo": "OC(c2ccccc2)(c2ccccc2(Cl))CCN(C)C",
@@ -135,20 +136,33 @@
     "tdPam": "OC(=O)CCCCCCC/C=C/CCCCCC",
     "tBu": "OC(C)(C)C",
 
-    # Methanol, Ethanol, Propanol, ...
-    "Me": "O" + "C" * 1,
-    "Et": "O" + "C" * 2,
-    "Pr": "O" + "C" * 3,
-    "Prop": "O" + "C" * 3,
-    "Bu": "O" + "C" * 4,
-    "Pe": "O" + "C" * 5,
-    "Hx": "O" + "C" * 6,
-    "Hp": "O" + "C" * 7,
-    "Oc": "O" + "C" * 8,
-    "Nn": "O" + "C" * 9,
-    "Dec": "O" + "C" * 10,
-    "Und": "O" + "C" * 11,
-    "Dod": "O" + "C" * 12,
+    # Methan, Ethan, Propan, ...
+    "Me": "C" * 1,
+    "Et": "C" * 2,
+    "Pr": "C" * 3,
+    "Prop": "C" * 3,
+    "Bu": "C" * 4,
+    "Pe": "C" * 5,
+    "Hx": "C" * 6,
+    "Hp": "C" * 7,
+    "Oc": "C" * 8,
+    "Nn": "C" * 9,
+    "Dec": "C" * 10,
+    "Und": "C" * 11,
+    "Dod": "C" * 12,
+    # "Me": "O" + "C" * 1,
+    # "Et": "O" + "C" * 2,
+    # "Pr": "O" + "C" * 3,
+    # "Prop": "O" + "C" * 3,
+    # "Bu": "O" + "C" * 4,
+    # "Pe": "O" + "C" * 5,
+    # "Hx": "O" + "C" * 6,
+    # "Hp": "O" + "C" * 7,
+    # "Oc": "O" + "C" * 8,
+    # "Nn": "O" + "C" * 9,
+    # "Dec": "O" + "C" * 10,
+    # "Und": "O" + "C" * 11,
+    # "Dod": "O" + "C" * 12,
     # ... and their acids
     "But": "OC(=O)" + "C" * 2,
     "Vl": "OC(=O)" + "C" * 4,

glyles/glycans/poly/glycan.py

@@ -397,6 +397,7 @@ def __parse(self):
             if not self.tree_only and self.tree_full and self.full:
                 self.glycan_smiles = Merger(self.factory).merge(self.parse_tree, self.root_orientation, start=self.start)
                 # catch any exception at glycan level to not destroy the whole pipeline because of one mis-formed glycan
+                print(self.glycan_smiles)
 
         except ParseError as e:
             msg = e.__str__().replace("\n", " ")

glyles/grammar/Glycan.g4

@@ -60,15 +60,15 @@ PHOSPHOR:
     'P';
 FG:
     'Ceroplastic' | 'Lacceroic' | '3oxoMyr' | 'Psyllic' | 'Geddic' | 'Alloc' | 'Allyl' | 'Phthi' | 'TBDPS' | 'aLnn'
-    | 'ClAc' | 'Coum' | 'eSte' | 'Fmoc' | 'gLnn' | 'HSer' | 'Pico' | 'Prop' | 'TIPS' | 'Troc' | 'Ach' | 'Aep' | 'Ala'
-    | 'Ang' | 'Asp' | 'Beh' | 'Boc' | 'But' | 'Cbz' | 'Cct' | 'Cer' | 'Cet' | 'Cho' | 'cHx' | 'Cin' | 'Crt' | 'Cys'
-    | 'DCA' | 'Dce' | 'Dco' | 'Dec' | 'Dhp' | 'DMT' | 'Dod' | 'Etg' | 'Etn' | 'EtN' | 'Fer' | 'Glu' | 'Gly' | 'Gro'
-    | 'Hpo' | 'Hse' | 'Hxo' | 'Lac' | 'Lau' | 'Leu' | 'Lev' | 'Lin' | 'Lys' | 'Mal' | 'Mar' | 'Mel' | 'MMT' | 'MOM'
-    | 'Mon' | 'Myr' | 'NAP' | 'Ner' | 'Nno' | 'Non' | 'Oco' | 'Ole' | 'oNB' | 'Orn' | 'Pam' | 'Pic' | 'Piv' | 'PMB'
-    | 'PMP' | 'Poc' | 'Pro' | 'Pyr' | 'Ser' | 'Sin' | 'Ste' | 'TBS' | 'tBu' | 'TCA' | 'TES' | 'TFA' | 'THP' | 'Thr'
-    | 'Tig' | 'TMS' | 'Udo' | 'Ulo' | 'ulo' | 'Und' | 'Vac' | 'Ac' | 'Al' | 'Am' | 'Bn' | 'Br' | 'Bu' | 'Bz' | 'Cl'
-    | 'Cm' | 'DD' | 'DL' | 'en' | 'Et' | 'Fo' | 'Gc' | 'Hp' | 'Hx' | 'LD' | 'LL' | 'Me' | 'N3' | 'Nn' | 'Ns' | 'Oc'
-    | 'Pe' | 'Ph' | 'Pp' | 'Pr' | 'Tf' | 'Tr' | 'Ts' | 'Vl' | 'A' | 'F' | 'I' | 'S';
+    | 'ClAc' | 'Coum' | 'eSte' | 'Fmoc' | 'gLnn' | 'HSer' | 'Pico' | 'Prop' | 'TIPS' | 'triN' | 'Troc' | 'Ach' | 'Aep'
+    | 'Ala' | 'Ang' | 'Asp' | 'Beh' | 'Boc' | 'But' | 'Cbz' | 'Cct' | 'Cer' | 'Cet' | 'Cho' | 'cHx' | 'Cin' | 'Crt'
+    | 'Cys' | 'DCA' | 'Dce' | 'Dco' | 'Dec' | 'Dhp' | 'DMT' | 'Dod' | 'Etg' | 'Etn' | 'EtN' | 'Fer' | 'Glu' | 'Gly'
+    | 'Gro' | 'Hpo' | 'Hse' | 'Hxo' | 'Lac' | 'Lau' | 'Leu' | 'Lev' | 'Lin' | 'Lys' | 'Mal' | 'Mar' | 'Mel' | 'MMT'
+    | 'MOM' | 'Mon' | 'Myr' | 'NAP' | 'Ner' | 'Nno' | 'Non' | 'Oco' | 'Ole' | 'oNB' | 'Orn' | 'Pam' | 'Pic' | 'Piv'
+    | 'PMB' | 'PMP' | 'Poc' | 'Pro' | 'Pyr' | 'Ser' | 'Sin' | 'Ste' | 'TBS' | 'tBu' | 'TCA' | 'TES' | 'TFA' | 'THP'
+    | 'Thr' | 'Tig' | 'TMS' | 'Udo' | 'Ulo' | 'ulo' | 'Und' | 'Vac' | 'Ac' | 'Al' | 'Am' | 'Bn' | 'Br' | 'Bu' | 'Bz'
+    | 'Cl' | 'Cm' | 'DD' | 'DL' | 'en' | 'Et' | 'Fo' | 'Gc' | 'Hp' | 'Hx' | 'LD' | 'LL' | 'Me' | 'N3' | 'Nn' | 'Ns'
+    | 'Oc' | 'Pe' | 'Ph' | 'Pp' | 'Pr' | 'Tf' | 'Tr' | 'Ts' | 'Vl' | 'A' | 'F' | 'I' | 'S';
 ANHYDRO:
     'Anhydro';
 HEAD: