Pdbecif correction (#12)

* removed weight

* Use None for empty values

* test writing of fragments

* make empty inchi as None

* bumped version

* removed unnecessary quotes

pdbeccdutils/__init__.py

@@ -1 +1 @@
-__version__ = "0.7.1"
+__version__ = "0.7.2"

pdbeccdutils/core/bm_reader.py

@@ -130,7 +130,7 @@ def infer_multiple_chem_comp(path_to_cif: str, bm: dict, sanitize: bool = True):
             formula=CalcMolFormula(comp.mol),
             modified_date="",
             pdbx_release_status="",
-            weight=round(comp.physchem_properties["exactmw"], 3),
+            weight="",
         )
         comp = Component(mol.GetMol(), cif_block, properties, descriptors)
         reader_result = ccd_reader.CCDReaderResult(

pdbeccdutils/core/ccd_writer.py

@@ -1135,15 +1135,13 @@ def _add_sw_info_cif(cif_block_copy):
     category = "_software."
     sw_fields = ["name", "version", "description"]
     sw_loop = cif_block_copy.init_loop(category, sw_fields)
-    sw_loop.add_row(
-        cif.quote_list(["rdkit", rdkit.__version__, cif.quote("Core functionality.")])
-    )
+    sw_loop.add_row(cif.quote_list(["rdkit", rdkit.__version__, "Core functionality."]))
     sw_loop.add_row(
         cif.quote_list(
             [
                 "pdbeccdutils",
                 pdbeccdutils.__version__,
-                cif.quote("Wrapper to provide 2D templates and molecular fragments."),
+                "Wrapper to provide 2D templates and molecular fragments.",
             ]
         )
     )
@@ -1188,27 +1186,31 @@ def _add_fragments_and_scaffolds_cif(component, cif_block_copy):
 
     for i, scaffold in enumerate(component.scaffolds):
         mol = rdkit.Chem.MolFromSmiles(scaffold.smiles)
+        inchi = rdkit.Chem.MolToInchi(mol)
+        inchikey = rdkit.Chem.MolToInchiKey(mol)
         new_row = [
             component.id,
             scaffold.name,
             f"S{i+1}",
             "scaffold",
             scaffold.smiles,
-            rdkit.Chem.MolToInchi(mol),
-            rdkit.Chem.MolToInchiKey(mol),
+            inchi if inchi else None,
+            inchikey if inchikey else None,
         ]
         substructure_loop.add_row(cif.quote_list(new_row))
 
     for j, fragment in enumerate(component.fragments):
         mol = rdkit.Chem.MolFromSmiles(fragment.smiles)
+        inchi = rdkit.Chem.MolToInchi(mol)
+        inchikey = rdkit.Chem.MolToInchiKey(mol)
         new_row = [
             component.id,
             fragment.name,
             f"F{j+1}",
             "fragment",
             fragment.smiles,
-            rdkit.Chem.MolToInchi(mol),
-            rdkit.Chem.MolToInchiKey(mol),
+            inchi if inchi else None,
+            inchikey if inchikey else None,
         ]
         substructure_loop.add_row(cif.quote_list(new_row))
 

pdbeccdutils/tests/test_file_writing.py

@@ -6,6 +6,8 @@
 from pdbeccdutils.core import ccd_writer
 from pdbeccdutils.core.component import Component
 from pdbeccdutils.core.models import ConformerType
+from pdbeccdutils.core.fragment_library import FragmentLibrary
+from pdbeccdutils.core.exceptions import CCDUtilsError
 from gemmi import cif
 from rdkit import Chem
 
@@ -209,3 +211,43 @@ def test_plain_cif_write(component: Component, tmpdir, rem_hs):
         assert component.id == cif_block.name
         for c in to_check:
             assert c in cif_block.get_mmcif_category_names()
+
+    @staticmethod
+    def test_fragment_writing(component: Component, tmpdir):
+        path = tmpdir.join(f"{component.id}.cif")
+        fragment_library = FragmentLibrary()
+        component.library_search(fragment_library)
+        ccd_writer.write_molecule(str(path), component)
+        cif_block = cif.read(str(path)).sole_block()
+        assert cif_block
+        assert component.id == cif_block.name
+        cif_categories = cif_block.get_mmcif_category_names()
+        if component.fragments:
+            assert "_pdbe_chem_comp_substructure." in cif_categories
+            substructure = cif_block.get_mmcif_category("_pdbe_chem_comp_substructure.")
+            for _, values in substructure.items():
+                for value in values:
+                    if value is not None:
+                        assert len(value) > 0
+
+    @staticmethod
+    def test_scaffold_writing(component: Component, tmpdir):
+        path = tmpdir.join(f"{component.id}.cif")
+        try:
+            component.get_scaffolds()
+            ccd_writer.write_molecule(str(path), component)
+            cif_block = cif.read(str(path)).sole_block()
+            assert cif_block
+            assert component.id == cif_block.name
+            cif_categories = cif_block.get_mmcif_category_names()
+            if component.scaffolds:
+                assert "_pdbe_chem_comp_substructure." in cif_categories
+                substructure = cif_block.get_mmcif_category(
+                    "_pdbe_chem_comp_substructure."
+                )
+                for _, values in substructure.items():
+                    for value in values:
+                        if value is not None:
+                            assert len(value) > 0
+        except CCDUtilsError:
+            assert True