Fix #1579 (#1589)

* fix #1579 and add test

* [pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

* update file names and release history

---------

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

docs/releasehistory.md

@@ -15,6 +15,9 @@ Releases follow the `major.minor.micro` scheme recommended by [PEP440](https://w
 ### Behavior changes
 - [PR #1569](https://github.com/openforcefield/openff-toolkit/pull/1569): Several instances of `Exception` being raised are now replaced with other exceptions being raised.
 
+### Bugfixes
+- [PR #1589](https://github.com/openforcefield/openff-toolkit/pull/1589): Fixes [Issue #1579](https://github.com/openforcefield/openff-toolkit/issues/1579), where Molecule.from_polymer_pdb could not handle NH2 caps at C termini.  
+
 ### Improved documentation and warnings
 
 - [PR #1564](https://github.com/openforcefield/openff-toolkit/pull1564) Improve documentation of conformer selection in `Molecule.assign_partial_charges()`

openff/toolkit/data/proteins/aa_residues_substructures_explicit_bond_orders_with_caps.json

@@ -6345,11 +6345,10 @@
         ]
     },
     "PEPTIDE_BOND": {
-        "[C:1](=[O:2])[N:3]([C:4])": [
+        "[C:1](=[O:2])[N:3]": [
             "C",
             "O",
-            "N",
-            "CA"
+            "N"
         ]
     },
     "DISULFIDE": {

openff/toolkit/data/proteins/ace-ala-nh2.pdb

@@ -0,0 +1,21 @@
+ATOM      1 HH33 ACE A   0      -5.284  -2.981   5.320  1.00  0.00
+ATOM      2  CH3 ACE A   0      -4.851  -3.877   5.426  1.00  0.00
+ATOM      3 HH31 ACE A   0      -5.412  -4.481   6.144  1.00  0.00
+ATOM      4 HH32 ACE A   0      -4.840  -4.406   4.474  1.00  0.00
+ATOM      5  C   ACE A   0      -3.431  -3.679   5.966  1.00  0.00
+ATOM      6  O   ACE A   0      -2.705  -2.809   5.481  1.00  0.00
+ATOM      7  N   ALA A   1      -2.983  -4.446   6.956  1.00  0.00
+ATOM      8  CA  ALA A   1      -1.682  -4.415   7.599  1.00  0.00
+ATOM      9  CB  ALA A   1      -1.818  -3.599   8.890  1.00  0.00
+ATOM     10  C   ALA A   1      -1.154  -5.834   7.868  1.00  0.00
+ATOM     11  O   ALA A   1      -1.891  -6.699   8.345  1.00  0.00
+ATOM     12  H   ALA A   1      -3.478  -5.294   6.716  1.00  0.00
+ATOM     13  HA  ALA A   1      -1.025  -3.946   6.994  1.00  0.00
+ATOM     14  HB1 ALA A   1      -2.653  -3.055   8.848  1.00  0.00
+ATOM     15  HB2 ALA A   1      -1.860  -4.221   9.669  1.00  0.00
+ATOM     16  HB3 ALA A   1      -1.028  -2.996   8.983  1.00  0.00
+ATOM     17  N   NH2 A   2       0.110  -6.138   7.586  1.00  0.00
+ATOM     18  HN1 NH2 A   2       0.717  -5.444   7.199  1.00  0.00
+ATOM     19  HN2 NH2 A   2       0.453  -7.061   7.761  1.00  0.00
+TER
+END

openff/toolkit/tests/test_molecule.py

@@ -3955,6 +3955,16 @@ def test_molecule_from_pdb_name(self):
         )
         assert offmol.name == "bob"
 
+    def test_molecule_from_pdb_ace_ala_nh2(self):
+        offmol = Molecule.from_polymer_pdb(
+            get_data_file_path("proteins/ace-ala-nh2.pdb")
+        )
+        assert offmol.n_atoms == 19
+        expected_mol = Molecule.from_smiles("CC(=O)N[C@H](C)C(=O)N")
+        assert offmol.is_isomorphic_with(
+            expected_mol, atom_stereochemistry_matching=False
+        )
+
     def test_molecule_from_pdb_mainchain_ala_tripeptide(self):
         offmol = Molecule.from_polymer_pdb(
             get_data_file_path("proteins/MainChain_ALA_ALA.pdb")

utilities/make_substructure_dict/_cif_to_substructure_dict.py

@@ -697,11 +697,10 @@ def _add_common_linkages(self):
         """
 
         self.data["PEPTIDE_BOND"] = {
-            "[C:1](=[O:2])[N:3]([C:4])": [
+            "[C:1](=[O:2])[N:3]": [
                 "C",
                 "O",
                 "N",
-                "CA",
             ]
         }
         self.data["DISULFIDE"] = {