fix parsing entity ID with numeric values (#571)

* fix parsing entity ID with numeric values

* add test to parse problematic structure

molecularnodes/entities/molecule/pdbx.py

@@ -18,7 +18,7 @@ def entity_ids(self):
         return self.file.block.get("entity").get("pdbx_description").as_array().tolist()
 
     def _get_entity_id(self, array, file):
-        chain_ids = file.block["entity_poly"]["pdbx_strand_id"].as_array()
+        chain_ids = file.block["entity_poly"]["pdbx_strand_id"].as_array(str)
 
         # the chain_ids are an array of individual items np.array(['A,B', 'C', 'D,E,F'])
         # which need to be categorised as [1, 1, 2, 3, 3, 3] for their belonging to individual

tests/test_pdbx.py

@@ -12,6 +12,11 @@ def test_ss_label_to_int():
     ]
 
 
+def test_entity_parsing():
+    mn.entities.fetch("6VBU", format="bcif")
+    assert True
+
+
 def test_get_ss_from_mmcif(snapshot_custom: NumpySnapshotExtension):
     mol = mn.entities.load_local(data_dir / "1cd3.cif")