Fixes for Issue #936

CONECT records to unknown entries (hopefully TER) are now ignored

package/CHANGELOG

@@ -44,6 +44,8 @@ Fixes
     defaults (#914)
   * Fixed same interRDF can be run twice (Issue #924)
   * Support for TPR files produced by Gromacs-2016 (Issue #932)
+  * Fixed parsing PDB files with CONECT records to TER entries (Issue #936)
+
 Changes
   * Added protected variable _frame_index to to keep track of frame iteration
     number in AnalysisBase

package/MDAnalysis/topology/PDBParser.py

@@ -180,8 +180,14 @@ def _parsebonds(self, atoms):
             for line in lines:
                 atom, atoms = _parse_conect(line.strip())
                 for a in atoms:
-                    bond = tuple([mapping[atom], mapping[a]])
-                    bonds.add(bond)
+                    try:
+                        bond = tuple([mapping[atom], mapping[a]])
+                    except KeyError:
+                        # Bonds to TER records have no mapping
+                        # Ignore these as they are not real atoms
+                        pass
+                    else:
+                        bonds.add(bond)
 
         bonds = tuple(bonds)
 

testsuite/MDAnalysisTests/data/CONECT2TER.pdb

@@ -0,0 +1,12 @@
+HEADER    ISSUE936 Test File
+REMARK    Contains a CONECT record to a TER entry
+MODEL 1
+CRYST1  216.489  216.489  216.489  90.00  90.00  90.00 P 1           1
+ATOM      1 CA   ABC A   1     111.252  98.373  98.187
+ATOM      2 CA   ABC A   1     111.203 101.742  96.430
+ATOM      3 CA   ABC A   1     107.607 102.968  96.316
+TER       4      ABC A   1
+CONECT    1    2
+CONECT    2    1    3
+CONECT    3    2    4
+ENDMDL

testsuite/MDAnalysisTests/datafiles.py

@@ -43,6 +43,7 @@
     "PDB_multiframe",
     "PDB_helix",
     "PDB_conect",
+    "PDB_conect2TER",  # Conect record to a TER entry (Issue 936)
     "XPDB_small",
     "PDB_full",   # PDB 4E43 (full HEADER, TITLE, COMPND, REMARK, altloc)
     "ALIGN",  # Various way to align atom names in PDB files
@@ -172,6 +173,7 @@
 PDB_multiframe = resource_filename(__name__, 'data/nmr_neopetrosiamide.pdb')
 PDB_helix = resource_filename(__name__, 'data/A6PA6_alpha.pdb')
 PDB_conect = resource_filename(__name__, 'data/conect_parsing.pdb')
+PDB_conect2TER = resource_filename(__name__, 'data/CONECT2TER.pdb')
 
 GRO = resource_filename(__name__, 'data/adk_oplsaa.gro')
 GRO_velocity = resource_filename(__name__, 'data/sample_velocity_file.gro')

testsuite/MDAnalysisTests/topology/test_pdb.py

@@ -0,0 +1,30 @@
+# -*- Mode: python; tab-width: 4; indent-tabs-mode:nil; coding:utf-8 -*-
+# vim: tabstop=4 expandtab shiftwidth=4 softtabstop=4 fileencoding=utf-8
+#
+# MDAnalysis --- http://www.MDAnalysis.org
+# Copyright (c) 2006-2015 Naveen Michaud-Agrawal, Elizabeth J. Denning, Oliver Beckstein
+# and contributors (see AUTHORS for the full list)
+#
+# Released under the GNU Public Licence, v2 or any higher version
+#
+# Please cite your use of MDAnalysis in published work:
+# N. Michaud-Agrawal, E. J. Denning, T. B. Woolf, and O. Beckstein.
+# MDAnalysis: A Toolkit for the Analysis of Molecular Dynamics Simulations.
+# J. Comput. Chem. 32 (2011), 2319--2327, doi:10.1002/jcc.21787
+#
+
+from numpy.testing import assert_
+from MDAnalysisTests.datafiles import (
+    PDB_conect2TER,
+)
+
+import MDAnalysis as mda
+from MDAnalysis.topology.PDBParser import PDBParser
+
+
+def test_conect2ter():
+    with PDBParser(PDB_conect2TER) as p:
+        struc = p.parse()
+
+    assert_('bonds' in struc)
+    assert_(len(struc['bonds']) == 4)