Merge branch 'master' into testsize

moldesign/_tests/test_pdb_processing.py

@@ -123,6 +123,20 @@ def test_numeric_residue_name_1PYN(request, mol):
     assert list(contents.keys())[0] == '941'
 
 
+def test_single_chain_2p8w():
+    mol = mdt.read(get_data_path('2p8w.cif.bz2'))
+    assert mol.num_chains == 3
+    assert mol.chains['C'].num_residues == 1
+    assert mol.chains['C'].residues['GNP843'].num_atoms == 32
+
+
+def test_missing_atoms_3b5x():
+    mol = mdt.read(get_data_path('3b5x.cif.bz2'))
+    assert mol.num_chains == 2
+    assert mol.num_atoms == 1144
+    assert mol.num_residues == 1144
+
+
 MISSINGRES_2JAJ = [('A', 'GLY', -4), ('A', 'PRO', -3), ('A', 'LEU', -2), ('A', 'GLY', -1),
                    ('A', 'MET', 0), ('A', 'ALA', 1), ('A', 'GLY', 2), ('A', 'LEU', 3),
                    ('A', 'GLY', 4), ('A', 'HIS', 5), ('A', 'PRO', 6), ('A', 'ALA', 7),

moldesign/interfaces/parmed_interface.py

@@ -261,23 +261,26 @@ def _reassign_chains(f, mol):
     """
     data = mdt.interfaces.biopython_interface.get_mmcif_data(f)
     f.seek(0)
+
     try:
-        newchain_names = set(data['_pdbx_poly_seq_scheme.asym_id']+
-                             data['_pdbx_nonpoly_scheme.asym_id'])
+        poly_seq_ids = _aslist(data['_pdbx_poly_seq_scheme.asym_id'])
+        nonpoly_ids = _aslist(data['_pdbx_nonpoly_scheme.asym_id'])
     except KeyError:
         return mol.copy(name=mol.name)
+
+    newchain_names = set(poly_seq_ids + nonpoly_ids)
     newchains = {name: mdt.Chain(name) for name in newchain_names}
 
     residue_iterator = itertools.chain(
-            zip(data['_pdbx_poly_seq_scheme.mon_id'],
-                data['_pdbx_poly_seq_scheme.pdb_seq_num'],
-                data['_pdbx_poly_seq_scheme.pdb_strand_id'],
-                data['_pdbx_poly_seq_scheme.asym_id']),
+            zip(_aslist(data['_pdbx_poly_seq_scheme.mon_id']),
+                _aslist(data['_pdbx_poly_seq_scheme.pdb_seq_num']),
+                _aslist(data['_pdbx_poly_seq_scheme.pdb_strand_id']),
+                _aslist(data['_pdbx_poly_seq_scheme.asym_id'])),
 
-            zip(data['_pdbx_nonpoly_scheme.mon_id'],
-                data['_pdbx_nonpoly_scheme.pdb_seq_num'],
-                data['_pdbx_nonpoly_scheme.pdb_strand_id'],
-                data['_pdbx_nonpoly_scheme.asym_id']))
+            zip(_aslist(data['_pdbx_nonpoly_scheme.mon_id']),
+                _aslist(data['_pdbx_nonpoly_scheme.pdb_seq_num']),
+                _aslist(data['_pdbx_nonpoly_scheme.pdb_strand_id']),
+                _aslist(data['_pdbx_nonpoly_scheme.asym_id'])))
 
     reschains = {(rname, ridx, rchain): newchains[chainid]
                  for rname, ridx, rchain, chainid in residue_iterator}
@@ -290,3 +293,9 @@ def _reassign_chains(f, mol):
     return mdt.Molecule(mol.atoms,
                         name=mol.name, metadata=mol.metadata)
 
+
+def _aslist(l):
+    if isinstance(l, list):
+        return l
+    else:
+        return [l]

moldesign/molecules/residue.py

@@ -247,11 +247,10 @@ def _is_ending_residue(self):
         except KeyError:
             # If we're here, the residue is missing some atoms. We'll fall back to checking the
             # next residues in line
-            if self.index == len(self.molecule.residues):
+            if self.index == len(self.molecule.residues) - 1:
                 return True
             else:
-                print('WARNING: %s is missing expected atoms. Attempting to infer chain end' % \
-                    self)
+                print('WARNING: %s is missing expected atoms. Attempting to infer chain end' % self)
                 nextres = self.molecule.residues[self.index + 1]
                 return not self._same_polymer(nextres)