Udpate to match changes of rdkit

Author: Old-Shatterhand

glyles/glycans/factory/factory_o.py

@@ -4,6 +4,7 @@
 from rdkit.Chem.rdchem import BondType
 
 from glyles.glycans.utils import Config, Enantiomer, Lactole, Tree, find_longest_c_chain
+from glyles.utils import smiles2mol
 
 
 class OpenFactory:
@@ -180,7 +181,7 @@ def c1_finder(structure, base_smiles):
     if end_double_oxy and not start_double_oxy:
         return list(reversed(longest_c_chain))
 
-    base = Chem.MolFromSmiles(base_smiles)
+    base = smiles2mol(base_smiles)
     if not base.GetNumConformers():
         rdDepictor.Compute2DCoords(base)
     if not structure.GetNumConformers():

glyles/glycans/mono/monomer.py

@@ -2,12 +2,13 @@
 from typing import Literal
 
 import numpy as np
-from rdkit.Chem import MolFromSmiles, MolToSmiles, GetAdjacencyMatrix
+from rdkit.Chem import MolToSmiles, GetAdjacencyMatrix
 
 from glyles.glycans.mono.enum_c import enumerate_carbon
 from glyles.glycans.mono.reactor import SMILESReaktor
 from glyles.glycans.utils import Config, find_isomorphism_nx
 from glyles.iupac.IUPACLexer import IUPACLexer
+from glyles.utils import smiles2mol
 
 
 def shift(d, offset):
@@ -403,7 +404,7 @@ def get_structure(self):
         """
         if self.structure is None:
             # read the structure from the SMILES string
-            self.structure = MolFromSmiles(self.smiles)
+            self.structure = smiles2mol(self.smiles)
 
             # extract some further information from the molecule to not operate always on the molecule
             self.adjacency = GetAdjacencyMatrix(self.structure, useBO=True)

glyles/glycans/poly/anltr_error_listener.py

@@ -14,12 +14,3 @@ def syntaxError(self, recognizer, offendingSymbol, line, column, msg, e):
         # Maybe not a good idea for a library to pollute the stderr when the exceptions are handled?
         # print(error_msg, file=sys.stderr)
         raise ParseError(f"Glycan cannot be parsed:\n{error_msg}")
-    
-    def reportAmbiguity(self, recognizer, dfa, startIndex, stopIndex, exact, ambigAlts, configs):
-        print("Ambiguity")
-
-    def reportAttemptingFullContext(self, recognizer, dfa, startIndex, stopIndex, conflictingAlts, configs):
-        print("AttemptingFullContext")
-
-    def reportContextSensitivity(self, recognizer, dfa, startIndex, stopIndex, prediction, configs):
-        print("ContextSensitivity")

glyles/glycans/poly/glycan.py

@@ -19,6 +19,7 @@
 from glyles.glycans.utils import ParseError
 from glyles.gwb.GWBLexer import GWBLexer
 from glyles.iupac.IUPACLexer import IUPACLexer
+from glyles.utils import smiles2mol
 
 if not hasattr(IUPACLexer, "MOD"):
     IUPACLexer.MOD = IUPACLexer.QMARK + 1
@@ -154,7 +155,7 @@ def summary(self):
             raise ValueError("SMILES string for this glycan is empty, check if the IUPAC is convertable.")
 
         # generate molecule with RDKit and check it's not None
-        mol = Chem.MolFromSmiles(smiles)
+        mol = smiles2mol(smiles)
         if mol is None:
             raise ValueError("Generated SMILES is invalid, rdkit couldn't read it in.")
 
@@ -240,7 +241,7 @@ def count_protonation(self, grouping):
             raise ValueError("SMILES string for this glycan is empty, check if the IUPAC is convertable.")
 
         # generate molecule with RDKit and check it's not None
-        mol = Chem.MolFromSmiles(smiles)
+        mol = smiles2mol(smiles)
         if mol is None:
             raise ValueError("Generated SMILES is invalid, rdkit couldn't read it in.")
 
@@ -254,7 +255,7 @@ def count_protonation(self, grouping):
             matched_atoms = set()
             for g, val in group:
                 # compute the matches against this glycan
-                matches = mol.GetSubstructMatches(Chem.MolFromSmiles(g))
+                matches = mol.GetSubstructMatches(smiles2mol(g))
                 for match in matches:
                     for aid in match:
                         # find the core atom of each match, add it to the list of  covered atoms and increase the count
@@ -285,17 +286,17 @@ def count_functional_groups(self, groups):
             raise ValueError("SMILES string for this glycan is empty, check if the IUPAC is convertable.")
 
         # generate molecule with RDKit and check it's not None
-        mol = Chem.MolFromSmiles(smiles)
+        mol = smiles2mol(smiles)
         if mol is None:
             raise ValueError("Generated SMILES is invalid, rdkit couldn't read it in.")
 
         fgs = []
         for group in groups:
             # convert the functional group into a RDKit molecule
             if group in functional_groups:
-                tmp = Chem.MolFromSmiles(functional_groups[group])
+                tmp = smiles2mol(functional_groups[group])
             else:
-                tmp = Chem.MolFromSmiles(group, sanitize=False)
+                tmp = smiles2mol(group, sanitize=False)
 
             # check the functional groups for validity
             if tmp is None:

glyles/glycans/poly/merger.py

@@ -4,13 +4,13 @@
 
 import networkx as nx
 import numpy as np
-from rdkit import Chem
 
 from glyles.glycans.utils import sanitize_smiles
+from glyles.utils import smiles2mol
 
 
 def masked2nx(smiles: str, mask: list[int]) -> nx.Graph:
-    mol = Chem.MolFromSmiles(smiles)
+    mol = smiles2mol(smiles)
     tmp1, i, read_atom, read_atom_index = defaultdict(list), 0, "", -1
     for i in range(len(smiles)):
         # check for uppercase, i.e., atoms

glyles/glycans/utils.py

@@ -5,12 +5,13 @@
 import networkx as nx
 import numpy as np
 from networkx.algorithms import isomorphism
-from rdkit.Chem import MolFromSmiles
 
 from itertools import permutations
 
 from rdkit.Chem.rdchem import ChiralType
 
+from glyles.utils import smiles2mol
+
 
 class Verbosity(Enum):
     """
@@ -386,11 +387,11 @@ def find_isomorphism_nx(mol1, mol2, name, c1_find=None):
     """
     # generate the RDKit molecules from the SMILES strings
     if isinstance(mol1, str):
-        mol1_rd = MolFromSmiles(mol1)
+        mol1_rd = smiles2mol(mol1)
     else:
         mol1_rd = mol1
     if isinstance(mol2, str):
-        mol2_rd = MolFromSmiles(mol2)
+        mol2_rd = smiles2mol(mol2)
     else:
         mol2_rd = mol2