Merge pull request #181 from Autodesk/cif-singleton-fix

Handle mmCIF fields with single entries
Autodesk · Oct 12, 2017 · 6900a9c · 6900a9c
2 parents 5cbeab2 + 27b2856
commit 6900a9c
Show file tree

Hide file tree

Showing 3 changed files with 26 additions and 10 deletions.
diff --git a/moldesign/_tests/data/2p8w.cif.bz2 b/moldesign/_tests/data/2p8w.cif.bz2
diff --git a/moldesign/_tests/test_pdb_processing.py b/moldesign/_tests/test_pdb_processing.py
@@ -123,6 +123,13 @@ 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

diff --git a/moldesign/interfaces/parmed_interface.py b/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]