Merge pull request #37 from ipqa-research/pubchempy_error

Pubchempy error

Author: SalvadorBrandolin

.github/workflows/ci.yml

@@ -1,10 +1,12 @@
 name: Tox
 
 on:
-  - push
-  - pull_request
-  - release
-  - workflow_dispatch
+  push:
+  pull_request:
+  release:
+  workflow_dispatch:
+  schedule:
+    - cron: '0 12 * * *'  # Every day at 09:00 ART (12:00 UTC)
 
 jobs:
   test-linux:

pyproject.toml

@@ -35,7 +35,7 @@ markers = [
 
 [project]
 name = "ugropy"
-version = "3.1.5"
+version = "3.1.6"
 authors = [{name = "Brandolín, Salvador Eduardo", email = "[email protected]"}]
 license = {text = "The MIT License"}
 readme = "README.md"

ugropy/core/frag_classes/gibbs_model/gibbs_result.py

@@ -22,6 +22,10 @@ class GibbsFragmentationResult(FragmentationResult):
         Dictionary of subgroups atoms indexes.
     subgroups_info : pd.DataFrame
         DataFrame with subgroups information.
+    calculate_r_q : bool
+        If True, calculate R and Q values for the molecule.
+    calculate_num_dict : bool, optional
+        If True, calculate the subgroup numbers dictionary. Default is True.
 
     Attributes
     ----------
@@ -37,6 +41,9 @@ class GibbsFragmentationResult(FragmentationResult):
         Gibss excess model R value estimation of the molecule.
     q : float
         Gibss excess model Q value estimation of the molecule.
+    subgroups_num : dict
+        Dictionary with the subgroup numbers and the number of times they
+        appear in the molecule.
     """
 
     def __init__(
@@ -46,12 +53,14 @@ def __init__(
         subgroups_atoms_indexes: dict,
         subgroups_info: pd.DataFrame,
         calculate_r_q: bool,
+        calculate_num_dict: bool = True,
     ):
         super().__init__(molecule, subgroups, subgroups_atoms_indexes)
 
         r = 0.0
         q = 0.0
 
+        # R and Q
         if self.subgroups != {}:
             if calculate_r_q:
                 for group, n in self.subgroups.items():
@@ -66,3 +75,16 @@ def __init__(
         else:
             self.r = None
             self.q = None
+
+        # Subgroups numbers dictionary
+        if self.subgroups != {}:
+            if calculate_num_dict:
+                self.subgroups_num = {}
+
+                for group, occ in self.subgroups.items():
+                    snum = int(subgroups_info.loc[group, "subgroup_number"])
+
+                    self.subgroups_num[snum] = occ
+
+            else:
+                self.subgroups_num = None

ugropy/core/get_rdkit_object.py

@@ -74,8 +74,16 @@ def instantiate_mol_from_name(name: str) -> Chem.rdchem.Mol:
     """
     try:
         pcp_object = pcp.get_compounds(name, "name")[0]
-        smiles = pcp_object.canonical_smiles
-        chem_object = Chem.MolFromSmiles(smiles)
+
+        if pcp_object.canonical_smiles:
+            chem_object = Chem.MolFromSmiles(pcp_object.canonical_smiles)
+        elif pcp_object.inchi:
+            chem_object = Chem.MolFromInchi(pcp_object.inchi)
+        else:
+            raise IndexError(
+                f"Could not find a SMILES or InChI for the molecule '{name}' "
+                "on PubChem."
+            )
     except IndexError:
         raise ValueError(
             f"Could not find a molecule with the name '{name}' on " "PubChem"