improve SEQRES import and AlignToSEQRES

This is based on exhaustive testing on the complete files of the PDB.
There are still a few unresolved issues. However it is not clear to me,
whether the problems are due to errors in the PDB files or our
misunderstanding.

modules/io/src/mol/pdb_reader.cc

@@ -151,9 +151,12 @@ void PDBReader::ParseSeqRes(const StringRef& line, int line_num)
     conop::CompoundPtr compound=comp_lib->FindCompound(trimmed.str(), 
                                                        conop::Compound::PDB);
     if (!compound) {
-      LOG_WARNING("unknown residue '" << trimmed << "' in SEQRES record. "
-                  "Setting one-letter-code to X");
-      curr_seq.Append('X');
+      if (rname!=StringRef("UNK", 3)) {
+     
+        LOG_WARNING("unknown residue '" << trimmed << "' in SEQRES record. "
+                    "Setting one-letter-code to '?'");
+      }
+      curr_seq.Append('?');
       continue;
     }
     curr_seq.Append(compound->GetOneLetterCode());

modules/seq/alg/pymod/__init__.py

@@ -17,14 +17,13 @@ def AlignToSEQRES(chain, seqres):
   """
   from ost import seq
   from ost import mol
-  residues=chain.residues
+  view=chain.Select('ligand=false and peptide=true')
+  residues=view.residues
   if len(residues)==0:
-    return None
+    return seq.CreateAlignment()
   fragments=[residues[0].one_letter_code]
   for r1, r2 in zip(residues[:-2], residues[1:]):
-    if not r2.IsPeptideLinking() or r2.IsLigand():
-      continue
-    if not mol.InSequence(r1, r2):
+    if not mol.InSequence(r1.handle, r2.handle):
       fragments.append('')
     fragments[-1]+=r2.one_letter_code
   ss=str(seqres)
@@ -41,4 +40,4 @@ def AlignToSEQRES(chain, seqres):
                              seq.CreateSequence('atoms', aln_seq))
 
     
-  
+  
\ No newline at end of file