Set PDB sequence register at conkit-plot peval and conkit-precision

.github/workflows/main.yml

@@ -15,7 +15,7 @@ jobs:
     strategy:
       matrix:
         os: [ubuntu-latest, macos-latest, windows-latest]
-        python-version: [3.6, 3.7, 3.8, 3.9]
+        python-version: [3.7, 3.8, 3.9]
 
     steps:
     - uses: actions/checkout@v1

conkit/command_line/conkit_plot.py

@@ -516,10 +516,12 @@ def altloc_remove(cmap):
         con.sort("raw_score", reverse=True, inplace=True)
 
         if args.pdbchain:
-            pdb = conkit.io.read(args.pdbfile, "pdb")[args.pdbchain]
+            pdb = conkit.io.read(args.pdbfile, args.pdbformat)[args.pdbchain]
         else:
-            pdb = conkit.io.read(args.pdbfile, "pdb")[0]
+            pdb = conkit.io.read(args.pdbfile, args.pdbformat)[0]
 
+        pdb.sequence = seq
+        pdb.set_sequence_register()
         pdb = pdb.as_contactmap()
         con_matched = con.match(pdb, renumber=True, remove_unmatched=True)
 

conkit/command_line/conkit_precision.py

@@ -79,9 +79,14 @@ def main():
         pdb = conkit.io.read(args.pdbfile, args.pdbformat)[args.pdbchain]
     else:
         pdb = conkit.io.read(args.pdbfile, args.pdbformat)[0]
+
     seq = conkit.io.read(args.seqfile, args.seqformat)[0]
-    con = conkit.io.read(args.confile, args.conformat)[0]
 
+    pdb.sequence = seq
+    pdb.set_sequence_register()
+    pdb = pdb.as_contactmap()
+
+    con = conkit.io.read(args.confile, args.conformat)[0]
     con.sequence = seq
     con.set_sequence_register()
 

conkit/command_line/conkit_predict.py

@@ -177,7 +177,7 @@ def main(argl=None):
         conkit.io.convert(a3m_fname, "a3m", jon_fname, "jones")
 
     else:
-        raise RuntimeError("Should never get to here")
+        raise RuntimeError("Error reading cli arguments - please report this bug")
 
     # CCMpred requires alignments to be in the *jones* format - i.e. the format created
     # and used by David Jones in PSICOV

conkit/core/contactmap.py

@@ -530,15 +530,20 @@ def set_sequence_register(self, altloc=False):
         if self.sequence is None:
             raise ValueError("No sequence defined")
 
+        seq_len = len(self.sequence)
+
         for c in self:
             if altloc:
                 res1_index = c.res1_altseq
                 res2_index = c.res2_altseq
             else:
                 res1_index = c.res1_seq
                 res2_index = c.res2_seq
-            c.res1 = self.sequence.seq[res1_index - 1]
-            c.res2 = self.sequence.seq[res2_index - 1]
+            if res1_index <= seq_len and res2_index <= seq_len:
+                c.res1 = self.sequence.seq[res1_index - 1]
+                c.res2 = self.sequence.seq[res2_index - 1]
+            else:
+                raise ValueError('Contact {} is out of sequence bounds'.format(c.id))
 
     @deprecate("0.11", msg="Use get_jaccard_index instead.")
     def calculate_jaccard_index(self, other):
@@ -826,7 +831,7 @@ def match(
                 else:
                     contact_map1[_id].status = ContactMatchState.false_positive
             else:
-                raise RuntimeError("Error matching two contact maps - this should never happen")
+                raise RuntimeError("Error matching two contact maps - please report this bug")
 
         # ================================================================
         # 3. Add false negatives
@@ -1159,6 +1164,6 @@ def _renumber(contact_map, self_keymap, other_keymap):
                     contact.res2_seq = other_residue.res_seq
                     contact.res2_chain = other_residue.res_chain
                 else:
-                    raise ValueError("Should never get here")
+                    raise ValueError("Error renumbering contact map - please report this bug")
 
         return contact_map

conkit/core/tests/test_contactmap.py

@@ -432,6 +432,22 @@ def test_set_sequence_register_2(self):
             [("A", "E"), ("B", "F"), ("A", "D"), ("C", "F"), ("B", "E")], [(c.res1, c.res2) for c in contact_map1]
         )
 
+    def test_set_sequence_register_3(self):
+        contact_map1 = ContactMap("1")
+        for comb in [(1, 5, 1.0), (2, 6, 1.0), (1, 4, 1.0), (3, 6, 1.0), (2, 5, 1.0)]:
+            contact_map1.add(Contact(*comb))
+        contact_map1.sequence = Sequence("foo", "ABCDE")
+        with self.assertRaises(ValueError):
+            contact_map1.set_sequence_register()
+
+    def test_set_sequence_register_4(self):
+        contact_map1 = ContactMap("1")
+        for comb in [(1, 5, 1.0), (6, 3, 1.0), (1, 4, 1.0), (3, 2, 1.0), (2, 5, 1.0)]:
+            contact_map1.add(Contact(*comb))
+        contact_map1.sequence = Sequence("foo", "ABCDE")
+        with self.assertRaises(ValueError):
+            contact_map1.set_sequence_register()
+
     def test_match_1(self):
         contact_map1 = ContactMap("foo")
         for params in [(1, 5, 1.0), (1, 6, 1.0), (2, 7, 1.0), (3, 5, 1.0), (2, 8, 1.0)]: