#2356 - Library ambiguous peptides loaded as mixtures from FASTA

Fix import subtype. Fix UTs
epam · Sep 14, 2024 · 604ff18 · 604ff18
1 parent 3f841ab
commit 604ff18
Show file tree

Hide file tree

Showing 8 changed files with 60 additions and 60 deletions.
diff --git a/api/tests/integration/tests/formats/ket_to_helm.py b/api/tests/integration/tests/formats/ket_to_helm.py
@@ -45,8 +45,8 @@ def find_diff(a, b):
     "helm_mixed_base": "RNA1{[dR](A)P.[dR](A+G)P.[dR](A)P.[dR](G+C)}$$$$V2.0",
     "helm_mixed_custom": "RNA1{[dR](A:10+[Xan]:20+G:30+T:50)P.[dR](A:10+C:20+G:30+T:50)P.[dR](A+C+G+T)}$$$$V2.0",
     "helm_aminoacids_variants": "PEPTIDE1{([Dha]+N).(L+I).(E+Q).(A+C+D+E+F+G+H+I+K+L+M+N+O+P+Q+R+S+T+U+V+W+Y)}$$$$V2.0",
-    "dna_variants": "RNA1{[dR](C+G+T)P.[dR](A+C+G+T)}$$$$V2.0",
-    "rna_variants": "RNA1{R(G+T)P.R(A+C+G+T)}$$$$V2.0",
+    "dna_variants": "RNA1{[dR](C,G,T)P.[dR](A,C,G,T)}$$$$V2.0",
+    "rna_variants": "RNA1{R(G,T)P.R(A,C,G,T)}$$$$V2.0",
     "helm_monomer_molecule": "PEPTIDE1{A}|PEPTIDE2{G}|CHEM1{[C(N[*:2])=C[*:1] |$;;_R2;;_R1$|]}$CHEM1,PEPTIDE1,1:R2-1:R1$$$V2.0",
 }
 

diff --git a/api/tests/integration/tests/formats/ref/aminoacids_variants.ket b/api/tests/integration/tests/formats/ref/aminoacids_variants.ket
@@ -4667,7 +4667,7 @@
     },
     "ambiguousMonomerTemplate-B": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "B",
         "alias": "B",
         "options": [
@@ -4681,7 +4681,7 @@
     },
     "ambiguousMonomerTemplate-J": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "J",
         "alias": "J",
         "options": [
@@ -4695,7 +4695,7 @@
     },
     "ambiguousMonomerTemplate-Z": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "Z",
         "alias": "Z",
         "options": [
@@ -4709,7 +4709,7 @@
     },
     "ambiguousMonomerTemplate-X": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "X",
         "alias": "X",
         "options": [

diff --git a/api/tests/integration/tests/formats/ref/dna_variants.ket b/api/tests/integration/tests/formats/ref/dna_variants.ket
@@ -1201,7 +1201,7 @@
     },
     "ambiguousMonomerTemplate-B": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "B",
         "alias": "B",
         "options": [
@@ -1218,7 +1218,7 @@
     },
     "ambiguousMonomerTemplate-N": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "N",
         "alias": "N",
         "options": [

diff --git a/api/tests/integration/tests/formats/ref/helm_aminoacids_variants.ket b/api/tests/integration/tests/formats/ref/helm_aminoacids_variants.ket
@@ -123,13 +123,13 @@
                 "$ref": "ambiguousMonomerTemplate-Var0"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-J"
+                "$ref": "ambiguousMonomerTemplate-J1"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-Z"
+                "$ref": "ambiguousMonomerTemplate-Z2"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-X"
+                "$ref": "ambiguousMonomerTemplate-X3"
             }
         ]
     },
@@ -152,8 +152,8 @@
             "y": -0.000000
         },
         "seqid": 2,
-        "alias": "J",
-        "templateId": "J"
+        "alias": "J1",
+        "templateId": "J1"
     },
     "ambiguousMonomer-2": {
         "type": "ambiguousMonomer",
@@ -163,8 +163,8 @@
             "y": -0.000000
         },
         "seqid": 3,
-        "alias": "Z",
-        "templateId": "Z"
+        "alias": "Z2",
+        "templateId": "Z2"
     },
     "ambiguousMonomer-3": {
         "type": "ambiguousMonomer",
@@ -174,8 +174,8 @@
             "y": -0.000000
         },
         "seqid": 4,
-        "alias": "X",
-        "templateId": "X"
+        "alias": "X3",
+        "templateId": "X3"
     },
     "monomerTemplate-Dha___2-aminoprop-2-enoic acid": {
         "type": "monomerTemplate",
@@ -4813,11 +4813,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-J": {
+    "ambiguousMonomerTemplate-J1": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "J",
-        "alias": "J",
+        "id": "J1",
+        "alias": "J1",
         "options": [
             {
                 "templateId": "L___Leucine"
@@ -4827,11 +4827,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-Z": {
+    "ambiguousMonomerTemplate-Z2": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "Z",
-        "alias": "Z",
+        "id": "Z2",
+        "alias": "Z2",
         "options": [
             {
                 "templateId": "E___Glutamic acid"
@@ -4841,11 +4841,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-X": {
+    "ambiguousMonomerTemplate-X3": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "X",
-        "alias": "X",
+        "id": "X3",
+        "alias": "X3",
         "options": [
             {
                 "templateId": "A___Alanine"

diff --git a/api/tests/integration/tests/formats/ref/helm_mixed_base.ket b/api/tests/integration/tests/formats/ref/helm_mixed_base.ket
@@ -164,10 +164,10 @@
                 "$ref": "monomerTemplate-C___Cytosine"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-R"
+                "$ref": "ambiguousMonomerTemplate-Var0"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-S"
+                "$ref": "ambiguousMonomerTemplate-Var1"
             }
         ]
     },
@@ -223,8 +223,8 @@
             "y": -1.600000
         },
         "seqid": 5,
-        "alias": "R",
-        "templateId": "R"
+        "alias": "Var0",
+        "templateId": "Var0"
     },
     "monomer5": {
         "type": "monomer",
@@ -289,8 +289,8 @@
             "y": -1.600000
         },
         "seqid": 11,
-        "alias": "S",
-        "templateId": "S"
+        "alias": "Var1",
+        "templateId": "Var1"
     },
     "monomerTemplate-dR___Deoxy-Ribose": {
         "type": "monomerTemplate",
@@ -1172,11 +1172,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-R": {
+    "ambiguousMonomerTemplate-Var0": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "R",
-        "alias": "R",
+        "id": "Var0",
+        "alias": "Var0",
         "options": [
             {
                 "templateId": "A___Adenine"
@@ -1186,11 +1186,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-S": {
+    "ambiguousMonomerTemplate-Var1": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "S",
-        "alias": "S",
+        "id": "Var1",
+        "alias": "Var1",
         "options": [
             {
                 "templateId": "G___Guanine"

diff --git a/api/tests/integration/tests/formats/ref/helm_mixed_custom.ket b/api/tests/integration/tests/formats/ref/helm_mixed_custom.ket
@@ -131,10 +131,10 @@
                 "$ref": "ambiguousMonomerTemplate-Var0"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-N1"
+                "$ref": "ambiguousMonomerTemplate-Var1"
             },
             {
-                "$ref": "ambiguousMonomerTemplate-N"
+                "$ref": "ambiguousMonomerTemplate-Var2"
             }
         ]
     },
@@ -190,8 +190,8 @@
             "y": -1.600000
         },
         "seqid": 5,
-        "alias": "N1",
-        "templateId": "N1"
+        "alias": "Var1",
+        "templateId": "Var1"
     },
     "monomer5": {
         "type": "monomer",
@@ -223,8 +223,8 @@
             "y": -1.600000
         },
         "seqid": 8,
-        "alias": "N",
-        "templateId": "N"
+        "alias": "Var2",
+        "templateId": "Var2"
     },
     "monomerTemplate-dR___Deoxy-Ribose": {
         "type": "monomerTemplate",
@@ -1515,11 +1515,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-N1": {
+    "ambiguousMonomerTemplate-Var1": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "N1",
-        "alias": "N1",
+        "id": "Var1",
+        "alias": "Var1",
         "options": [
             {
                 "templateId": "A___Adenine",
@@ -1539,11 +1539,11 @@
             }
         ]
     },
-    "ambiguousMonomerTemplate-N": {
+    "ambiguousMonomerTemplate-Var2": {
         "type": "ambiguousMonomerTemplate",
         "subtype": "mixture",
-        "id": "N",
-        "alias": "N",
+        "id": "Var2",
+        "alias": "Var2",
         "options": [
             {
                 "templateId": "A___Adenine"

diff --git a/api/tests/integration/tests/formats/ref/rna_variants.ket b/api/tests/integration/tests/formats/ref/rna_variants.ket
@@ -1218,7 +1218,7 @@
     },
     "ambiguousMonomerTemplate-K": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "K",
         "alias": "K",
         "options": [
@@ -1232,7 +1232,7 @@
     },
     "ambiguousMonomerTemplate-N": {
         "type": "ambiguousMonomerTemplate",
-        "subtype": "mixture",
+        "subtype": "alternatives",
         "id": "N",
         "alias": "N",
         "options": [

diff --git a/core/indigo-core/molecule/src/sequence_loader.cpp b/core/indigo-core/molecule/src/sequence_loader.cpp
@@ -369,24 +369,24 @@ void SequenceLoader::addMonomer(KetDocument& document, const std::string& monome
         _alias_to_id.emplace(monomer, checkAddTemplate(document, monomer_class, monomer));
     else if (!document.hasVariantMonomerTemplate(monomer))
     {
-        std::optional<std::reference_wrapper<const std::vector<std::string>>> mixture;
+        std::optional<std::reference_wrapper<const std::vector<std::string>>> alternatives;
         if (seq_type == SeqType::PEPTIDESeq)
         {
             const auto& it = STANDARD_MIXED_PEPTIDES.find(monomer);
             if (it == STANDARD_MIXED_PEPTIDES.end())
                 throw Error("Unknown mixed peptide '%s'", monomer.c_str());
-            mixture.emplace(std::cref(it->second));
+            alternatives.emplace(std::cref(it->second));
         }
         else
         {
             const auto& it = STANDARD_MIXED_BASES.find(monomer);
             if (it == STANDARD_MIXED_BASES.end())
                 throw Error("Unknown mixed base '%s'", monomer.c_str());
-            mixture.emplace(std::cref(it->second));
+            alternatives.emplace(std::cref(it->second));
         }
 
         std::vector<KetVariantMonomerOption> options;
-        for (auto template_alias : mixture.value().get())
+        for (auto template_alias : alternatives.value().get())
         {
             auto& template_id = _library.getMonomerTemplateIdByAlias(monomer_class, template_alias);
             if (template_id.size() == 0)
@@ -396,7 +396,7 @@ void SequenceLoader::addMonomer(KetDocument& document, const std::string& monome
             checkAddTemplate(document, monomer_template);
             _alias_to_id.emplace(template_alias, template_id);
         }
-        auto& templ = document.addVariantMonomerTemplate("mixture", monomer, monomer, IdtAlias(), options);
+        auto& templ = document.addVariantMonomerTemplate("alternatives", monomer, monomer, IdtAlias(), options);
         static const std::map<std::string, KetAttachmentPoint> aa_aps{{"R1", -1}, {"R2", -1}};
         static const std::map<std::string, KetAttachmentPoint> base_aps{{"R1", -1}};
         if (seq_type == SeqType::PEPTIDESeq)
@@ -1488,7 +1488,7 @@ SequenceLoader::MonomerInfo SequenceLoader::readHelmMonomer(KetDocument& documen
         if (monomer_class == MonomerClass::AminoAcid)
         {
             if (STANDARD_MIXED_PEPTIDES_TO_ALIAS.count(aliases) > 0)
-                if (is_mixture && no_counts)
+                if (!is_mixture && no_counts)
                     monomer_alias = STANDARD_MIXED_PEPTIDES_TO_ALIAS.at(aliases);
                 else
                     monomer_alias = STANDARD_MIXED_PEPTIDES_TO_ALIAS.at(aliases) + std::to_string(_unknown_variants_count++);
@@ -1497,8 +1497,8 @@ SequenceLoader::MonomerInfo SequenceLoader::readHelmMonomer(KetDocument& documen
         }
         else if (monomer_class == MonomerClass::Base)
         {
-            if (is_mixture && STANDARD_MIXED_BASES_TO_ALIAS.count(aliases) > 0)
-                if (is_mixture && no_counts)
+            if (!is_mixture && STANDARD_MIXED_BASES_TO_ALIAS.count(aliases) > 0)
+                if (!is_mixture && no_counts)
                     monomer_alias = STANDARD_MIXED_BASES_TO_ALIAS.at(aliases);
                 else
                     monomer_alias = STANDARD_MIXED_BASES_TO_ALIAS.at(aliases) + std::to_string(_unknown_variants_count++);