#2361 - Wrong error message if SMILES phosphate has lack of attachem…

…t point (#2715)
epam · Dec 27, 2024 · f191642 · f191642
1 parent 43871ef
commit f191642
Show file tree

Hide file tree

Showing 4 changed files with 125 additions and 1 deletion.
diff --git a/api/tests/integration/ref/formats/helm_to_ket.py.out b/api/tests/integration/ref/formats/helm_to_ket.py.out
@@ -13,6 +13,7 @@ helm_peptide.ket:SUCCEED
 helm_rna_without_base.ket:SUCCEED
 helm_simple_rna.ket:SUCCEED
 helm_smiles.ket:SUCCEED
+helm_smiles_no_ap.ket:SUCCEED
 helm_smiles_sugar.ket:SUCCEED
 helm_unsplit.ket:SUCCEED
 Test 'CHEM1{[A6OH]}|PEPTIDE1{A}$CHEM1,PEPTIDE1,1:R2-3:R1$$$V2.0': got expected error 'Polymer 'PEPTIDE1' does not contains monomer with number 3.'
@@ -27,3 +28,4 @@ Test 'PEPTIDE1{A'2'}$$$$V2.0': got expected error 'Repeating not supported now.'
 Test 'PEPTIDE1{D-gGlu}$$$$V2.0': got expected error 'Unexpected symbol. Expected '.' or '}' but found '-'.'
 Test 'RNA1{R(A).R(A)p}$$$$V2.0': got expected error 'Monomer template with class 'Phosphate' and alias 'R' not found in monomer librarys'
 Test 'RNA1{R(bla-bla-bla)p}$$$$V2.0': got expected error 'Unexpected symbol. Expected ')' but found 'l'.'
+Test 'RNA1{R[P(O)(O)(=O)O]}$$$$V2.0': got expected error 'Unknown attachment point 'R1' in monomer Mod0'
diff --git a/api/tests/integration/tests/formats/helm_to_ket.py b/api/tests/integration/tests/formats/helm_to_ket.py
@@ -45,6 +45,7 @@ def find_diff(a, b):
     "helm_fractional_ratio": "PEPTIDE1{(A:1.5+C:0.1+G:3)}$$$$V2.0",
     "helm_chem_rna_hydro": "CHEM1{[MCC]}|RNA1{R(U)P}$CHEM1,RNA1,1:pair-3:pair$$$V2.0",
     "helm_unsplit": "RNA1{[5Br-dU]}$$$$V2.0",
+    "helm_smiles_no_ap": "CHEM1{[P(O)(O)(=O)O]}$$$$V2.0",
 }
 
 lib = indigo.loadMonomerLibraryFromFile(
@@ -78,6 +79,7 @@ def find_diff(a, b):
     "PEPTIDE1{(A:+C:0.1)}$$$$V2.0": "Unexpected symbol. Expected digit but found '+'",
     "RNA1{R(A).R(A)p}$$$$V2.0": "Monomer template with class 'Phosphate' and alias 'R' not found in monomer librarys",
     "PEPTIDE1{(A:1.5.+C:0.1)}$$$$V2.0": "Enexpected symbol. Second dot in number",
+    "RNA1{R[P(O)(O)(=O)O]}$$$$V2.0": "Unknown attachment point 'R1' in monomer Mod0",
 }
 for helm_seq in sorted(helm_errors.keys()):
     error = helm_errors[helm_seq]

diff --git a/api/tests/integration/tests/formats/ref/helm_smiles_no_ap.ket b/api/tests/integration/tests/formats/ref/helm_smiles_no_ap.ket
@@ -0,0 +1,103 @@
+{
+    "root": {
+        "nodes": [
+            {
+                "$ref": "monomer0"
+            }
+        ],
+        "templates": [
+            {
+                "$ref": "monomerTemplate-Mod0"
+            }
+        ]
+    },
+    "monomer0": {
+        "type": "monomer",
+        "id": "0",
+        "seqid": 1,
+        "position": {
+            "x": 0.000000,
+            "y": -0.000000
+        },
+        "alias": "Mod0",
+        "templateId": "Mod0"
+    },
+    "monomerTemplate-Mod0": {
+        "type": "monomerTemplate",
+        "id": "Mod0",
+        "class": "CHEM",
+        "alias": "Mod0",
+        "atoms": [
+            {
+                "label": "P",
+                "location": [
+                    0.000000,
+                    0.000000,
+                    0.000000
+                ]
+            },
+            {
+                "label": "O",
+                "location": [
+                    -0.500000,
+                    -0.866025,
+                    0.000000
+                ]
+            },
+            {
+                "label": "O",
+                "location": [
+                    0.866025,
+                    -0.500000,
+                    0.000000
+                ]
+            },
+            {
+                "label": "O",
+                "location": [
+                    -0.866025,
+                    0.500000,
+                    0.000000
+                ]
+            },
+            {
+                "label": "O",
+                "location": [
+                    0.500000,
+                    0.866025,
+                    0.000000
+                ]
+            }
+        ],
+        "bonds": [
+            {
+                "type": 1,
+                "atoms": [
+                    0,
+                    1
+                ]
+            },
+            {
+                "type": 1,
+                "atoms": [
+                    0,
+                    2
+                ]
+            },
+            {
+                "type": 2,
+                "atoms": [
+                    0,
+                    3
+                ]
+            },
+            {
+                "type": 1,
+                "atoms": [
+                    0,
+                    4
+                ]
+            }
+        ]
+    }
+}
diff --git a/core/indigo-core/molecule/src/sequence_loader.cpp b/core/indigo-core/molecule/src/sequence_loader.cpp
@@ -1330,7 +1330,24 @@ std::string SequenceLoader::readHelmMonomerAlias(KetDocument& document, MonomerC
             throw Error(unexpected_eod);
         if (ch != ']')
             throw Error("Unexpected symbol. Expected ']' but found '%c'.", ch);
-        if (smiles)
+        bool found = false;
+        if (_library.getMonomerTemplateIdByAlias(monomer_class, monomer_alias).size() > 0)
+        {
+            found = true;
+        }
+        else if (monomer_class == MonomerClass::Sugar) // In place of sugar can be phosphate or unsplit rna
+        {
+            if (_library.getMonomerTemplateIdByAlias(MonomerClass::Phosphate, monomer_alias).size() > 0)
+            {
+                found = true;
+            }
+            else
+            {
+                if (_library.getMonomerTemplateIdByAlias(MonomerClass::RNA, monomer_alias).size() > 0)
+                    found = true;
+            }
+        }
+        if (smiles || !found) // Monomer alias not found in library - try read as smiles
         {
             // Convert smiles to molecule
             BufferScanner scanner(monomer_alias.c_str());