Backmerge: #2064 System establishes connection between monomers even …

…if data is wrong (#2095)
epam · Jul 8, 2024 · 51d5876 · 51d5876
1 parent 8147b45
commit 51d5876
Show file tree

Hide file tree

Showing 3 changed files with 23 additions and 3 deletions.
diff --git a/api/tests/integration/ref/formats/helm_to_ket.py.out b/api/tests/integration/ref/formats/helm_to_ket.py.out
@@ -6,4 +6,7 @@ helm_multi_char_rna.ket:SUCCEED
 helm_peptide.ket:SUCCEED
 helm_rna_without_base.ket:SUCCEED
 helm_simple_rna.ket:SUCCEED
+Test 'CHEM1{[A6OH]}|PEPTIDE1{A}$CHEM1,PEPTIDE1,1:R2-3:R1$$$V2.0': got expected error 'Polymer 'PEPTIDE1' does not contains monomer with number 3.'
+Test 'CHEM1{[A6OH]}|PEPTIDE1{A}$CHEM10,PEPTIDE1,1:R2-1:R1$$$V2.0': got expected error 'Polymer 'CHEM10' not found.'
+Test 'CHEM1{[MCC]}|RNA1{R(A)P.R(C)P.R(G)P.R(T)P.R(U)P}$RNA1,PEPTIDE1,15:R2-1:R1$$$V2.0': got expected error 'Polymer 'PEPTIDE1' not found.'
 Test 'PEPTIDE1{A'2'}$$$$V2.0': got expected error 'Repeating do not supported now.'
diff --git a/api/tests/integration/tests/formats/helm_to_ket.py b/api/tests/integration/tests/formats/helm_to_ket.py
@@ -56,7 +56,12 @@ def find_diff(a, b):
         print(filename + ".ket:FAILED")
         print(diff)
 
-helm_errors = {"PEPTIDE1{A'2'}$$$$V2.0": "Repeating do not supported now."}
+helm_errors = {
+    "PEPTIDE1{A'2'}$$$$V2.0": "Repeating do not supported now.",
+    "CHEM1{[MCC]}|RNA1{R(A)P.R(C)P.R(G)P.R(T)P.R(U)P}$RNA1,PEPTIDE1,15:R2-1:R1$$$V2.0": "Polymer 'PEPTIDE1' not found.",
+    "CHEM1{[A6OH]}|PEPTIDE1{A}$CHEM10,PEPTIDE1,1:R2-1:R1$$$V2.0": "Polymer 'CHEM10' not found.",
+    "CHEM1{[A6OH]}|PEPTIDE1{A}$CHEM1,PEPTIDE1,1:R2-3:R1$$$V2.0": "Polymer 'PEPTIDE1' does not contains monomer with number 3.",
+}
 for helm_seq in sorted(helm_errors.keys()):
     error = helm_errors[helm_seq]
     try:

diff --git a/core/indigo-core/molecule/src/sequence_loader.cpp b/core/indigo-core/molecule/src/sequence_loader.cpp
@@ -1059,11 +1059,17 @@ void SequenceLoader::loadHELM(BaseMolecule& mol)
             // CHEM1,RNA1,32:R1-12:R2"annotation"|.....
             std::string left_polymer, right_polymer;
             std::ignore = readHelmSimplePolymerName(left_polymer);
+            auto left_polymer_nums = used_polymer_nums.find(left_polymer);
+            if (left_polymer_nums == used_polymer_nums.end())
+                throw Error("Polymer '%s' not found.", left_polymer.c_str());
             ch = _scanner.lookNext();
             if (ch != ',')
                 throw Error("Unexpected symbol. Expected ',' but found '%c'.", _scanner.lookNext());
             _scanner.skip(1);
             std::ignore = readHelmSimplePolymerName(right_polymer);
+            auto right_polymer_nums = used_polymer_nums.find(right_polymer);
+            if (right_polymer_nums == used_polymer_nums.end())
+                throw Error("Polymer '%s' not found.", right_polymer.c_str());
             ch = _scanner.lookNext();
             if (ch != ',')
                 throw Error("Unexpected symbol. Expected ',' but found '%c'.", _scanner.lookNext());
@@ -1087,8 +1093,14 @@ void SequenceLoader::loadHELM(BaseMolecule& mol)
             if (error_pos != position.size() - 1) // arrray contains 0 at the end
                 throw Error("Only direct connections supported now.");
             _scanner.readWord(right_ap, "\"|$");
-            int left_templ_atom_idx = used_polymer_nums[left_polymer][left_monomer_idx];
-            int right_templ_atom_idx = used_polymer_nums[right_polymer][right_monomer_idx];
+            auto left_mon_it = left_polymer_nums->second.find(left_monomer_idx);
+            if (left_mon_it == left_polymer_nums->second.end())
+                throw Error("Polymer '%s' does not contains monomer with number %d.", left_polymer.c_str(), left_monomer_idx);
+            int left_templ_atom_idx = left_mon_it->second;
+            auto right_mon_it = right_polymer_nums->second.find(right_monomer_idx);
+            if (right_mon_it == right_polymer_nums->second.end())
+                throw Error("Polymer '%s' does not contains monomer with number %d.", right_polymer.c_str(), right_monomer_idx);
+            int right_templ_atom_idx = right_mon_it->second;
             mol.asMolecule().addBond_Silent(left_templ_atom_idx, right_templ_atom_idx, BOND_SINGLE);
             mol.setTemplateAtomAttachmentOrder(left_templ_atom_idx, right_templ_atom_idx, convertAPFromHELM(left_ap.ptr()).c_str());
             mol.setTemplateAtomAttachmentOrder(right_templ_atom_idx, left_templ_atom_idx, convertAPFromHELM(right_ap.ptr()).c_str());