Fix failure to parse large molecules

Increased maxMatches in rdkit GetSubstructMatches to allow for larger molecules (maxMatches increased from 1000 to 10000.)

Author: wittregr

pgradd/RDkitWrapper/MolQuery.py

@@ -612,7 +612,14 @@ def GetQueryMatches(self, mol, debug=0):
             except Exception:
                 return tuple()
         # Match mol substructure matches
-        rdkit_matches = mol.GetSubstructMatches(self.mol, uniquify=False)
+        maxMatches = 10000
+        rdkit_matches = mol.GetSubstructMatches(self.mol, uniquify=False,
+                                                maxMatches=maxMatches)
+        lenMatches = len(rdkit_matches)
+        if lenMatches == maxMatches:
+            print('\nMax RDKit substructure matches exceeded. All groups in',
+                  'molecule may not have been determined.')
+            print(Chem.MolToSmiles(Chem.RemoveHs(mol)))
         if debug:
             print('structure matches:' + str(rdkit_matches))
         # if no rdkit match

pgradd/__init__.py

@@ -8,6 +8,6 @@
 # present, too:
 #
 name = 'pgradd'
-__version__ = '1.0.0'
+__version__ = '2.9'
 #
 ####

setup.py

@@ -16,7 +16,7 @@
 
 setuptools_info = {
 	'name': 'pgradd',
-	'version': '2.8',
+	'version': '2.9',
 	'author': 'Vlachos Research Group',
 	'author_email': '[email protected]',
 	'description': 'Python package implements the Group Additivity (GA) method for estimating thermodynamic properties',