Vector bugfix #148 (#149)

* bugfix to distance edge func #146

* bugfix to distance edge func #146

* bugfix for c-beta vectors not handling altlocs

* update changelog

CHANGELOG.md

@@ -6,7 +6,8 @@
 * [Feature] - #144 adds support for chord diagram visualisations.
 * [Feature] - #144 adds support for automagically downloading new PDB files for obsolete structures.
 * [Misc] - #144 makes visualisation functions accessible in the `graphein.protein` namespace. #138
-* [Bugfix] - #147 fixes error in `add_distance_threshold` introduced in v1.2.1 that would prevent the edges being added to the graph. [#146](https://github.com/a-r-j/graphein/issues/146)
+* [Bugfix] - #147 fixes error in `add_distance_threshold` introduced in v1.2.1 that would prevent the edges being added to the graph. [#146](https://github.com/a-r-j/graphein/issues/146) 
+* [Bugfix] - #149 fixes a bug in `add_beta_carbon_vector` that would cause coordinates to be extracted for multiple positions if the residue has an altloc. Resolves [#148](https://github.com/a-r-j/graphein/issues/148)
 
 ### 1.2.1 - 16/3/21
 

graphein/protein/features/nodes/geometry.py

@@ -78,9 +78,12 @@ def add_beta_carbon_vector(
     :param reverse: Reverse vector. Defaults to ``False``.
     :type reverse: bool
     """
+    # Get or compute R-Group DF
+    if "rgroup_df" not in g.graph.keys():
+        g.graph["rgroup_df"] = compute_rgroup_dataframe(g.graph["raw_pdb_df"])
 
     c_beta_coords = filter_dataframe(
-        g.graph["raw_pdb_df"], "atom_name", ["CB"], boolean=True
+        g.graph["rgroup_df"], "atom_name", ["CB"], boolean=True
     )
     c_beta_coords.index = c_beta_coords["node_id"]
 

tests/protein/nodes/features/test_geometry.py

@@ -67,6 +67,14 @@ def test_add_beta_carbon_vector():
             np.testing.assert_almost_equal(
                 cb_true, d["coords"] + d["c_beta_vector"]
             )
+    # Test altloc handling
+    g = construct_graph(config=config, pdb_code="6rew")
+    for n, d in g.nodes(data=True):
+        assert d["c_beta_vector"].shape == (3,)
+
+    g = construct_graph(config=config, pdb_code="7w9w")
+    for n, d in g.nodes(data=True):
+        assert d["c_beta_vector"].shape == (3,)
 
 
 def test_add_sidechain_vector():