#2615 - Export to three letter amino acid codes cause convert error.

Fix code. Add UTs
epam · Nov 6, 2024 · f65ca56 · f65ca56
1 parent 904d2d9
commit f65ca56
Show file tree

Hide file tree

Showing 5 changed files with 50 additions and 5 deletions.
diff --git a/api/wasm/indigo-ketcher/indigo-ketcher.cpp b/api/wasm/indigo-ketcher/indigo-ketcher.cpp
@@ -144,7 +144,7 @@ namespace indigo
             {
                 result = _checkResultString(indigoSequence(id(), library));
             }
-            else if (outputFormat == "sequence-3-letter" || outputFormat == "chemical/x-sequence-3-letter")
+            else if (outputFormat == "peptide-sequence-3-letter" || outputFormat == "chemical/x-peptide-sequence-3-letter")
             {
                 result = _checkResultString(indigoSequence3Letter(id(), library));
             }
@@ -541,8 +541,9 @@ namespace indigo
 
         bool use_document = false;
         if (input_format == "ket" && outputFormat.size() > 0 &&
-            (outputFormat == "sequence" || outputFormat == "chemical/x-sequence" || outputFormat == "fasta" || outputFormat == "chemical/x-fasta" ||
-             outputFormat == "idt" || outputFormat == "chemical/x-idt" || outputFormat == "helm" || outputFormat == "chemical/x-helm"))
+            (outputFormat == "sequence" || outputFormat == "chemical/x-sequence" || "chemical/x-peptide-sequence-3-letter" || outputFormat == "fasta" ||
+             outputFormat == "chemical/x-fasta" || outputFormat == "idt" || outputFormat == "chemical/x-idt" || outputFormat == "helm" ||
+             outputFormat == "chemical/x-helm"))
             use_document = true;
         IndigoKetcherObject iko = loadMoleculeOrReaction(data, options_copy, library, use_document);
 

diff --git a/api/wasm/indigo-ketcher/test/test.js b/api/wasm/indigo-ketcher/test/test.js
@@ -839,6 +839,28 @@ M  END
         });
     }
 
+    {
+        test("PEPTIDE-3-LETTER", "basic", () => {
+            var fs = require('fs');
+            let options = new indigo.MapStringString();
+            const monomersLib = fs.readFileSync("monomer_library.ket");
+            options.set("monomerLibrary", monomersLib);
+            options.set("output-content-type", "application/json");
+            options.set("input-format", "chemical/x-peptide-sequence-3-letter");
+            const peptide_seq_ref = "AlaCysAspGluPheGlyHisIleLysLeuMetAsnPylProGlnArgSerArgSecValTrpTyr";
+            const peptide_ket = indigo.convert(peptide_seq_ref, "ket", options);
+            // fs.writeFileSync("peptide_ref.ket", peptide_ket);
+            const peptide_ket_ref = fs.readFileSync("peptide_ref.ket");
+            assert.equal(peptide_ket, peptide_ket_ref.toString());
+
+            options.set("input-format", "application/json");
+            options.set("output-content-type", "chemical/x-peptide-sequence-3-letter");
+            const peptide_seq = indigo.convert(peptide_ket_ref.toString(), "chemical/x-peptide-sequence-3-letter", options);
+            assert.equal(peptide_seq, peptide_seq_ref);
+            options.delete();
+        });
+    }
+
     {
         test("RNA", "basic", () => {
             var fs = require('fs');

diff --git a/utils/indigo-service/backend/service/tests/api/indigo_test.py b/utils/indigo-service/backend/service/tests/api/indigo_test.py
@@ -478,8 +478,9 @@ def test_headers_wrong(self):
 chemical/x-daylight-smiles, chemical/x-cml, chemical/x-inchi, chemical/x-inchi-key, \
 chemical/x-iupac, chemical/x-daylight-smarts, chemical/x-inchi-aux, chemical/x-chemaxon-cxsmiles, \
 chemical/x-cdxml, chemical/x-cdx, chemical/x-sdf, chemical/x-rdf, chemical/x-peptide-sequence, \
-chemical/x-rna-sequence, chemical/x-dna-sequence, chemical/x-sequence, chemical/x-peptide-fasta, \
-chemical/x-rna-fasta, chemical/x-dna-fasta, chemical/x-fasta, chemical/x-idt, chemical/x-helm."
+chemical/x-peptide-sequence-3-letter, chemical/x-rna-sequence, chemical/x-dna-sequence, chemical/x-sequence, \
+chemical/x-peptide-fasta, chemical/x-rna-fasta, chemical/x-dna-fasta, chemical/x-fasta, \
+chemical/x-idt, chemical/x-helm."
         expected_text = (
             "ValidationError: {'input_format': ['Must be one of: %s']}"
             % formats
@@ -3277,6 +3278,18 @@ def test_convert_sequences(self):
             self.url_prefix + "/convert", headers=headers, data=data
         )
 
+        headers, data = self.get_headers(
+            {
+                "struct": "AlaCysGlyThrSec",
+                "options": {"monomerLibrary": monomer_library},
+                "input_format": "chemical/x-peptide-sequence-3-letter",
+                "output_format": "chemical/x-indigo-ket",
+            }
+        )
+        result_peptide_3 = requests.post(
+            self.url_prefix + "/convert", headers=headers, data=data
+        )
+
         headers, data = self.get_headers(
             {
                 "struct": "ACDEFGHIKLMNOPQRSRUVWY",
@@ -3314,6 +3327,7 @@ def test_convert_sequences(self):
         with open(os.path.join(ref_path, "peptide_ref") + ".ket", "r") as file:
             peptide_ref = file.read()
             self.assertEqual(result_peptide.text, peptide_ref)
+            self.assertEqual(result_peptide_3.text, peptide_ref)
 
     def test_convert_fasta(self):
         ref_path = joinPathPy("ref/", __file__)

diff --git a/utils/indigo-service/backend/service/v2/indigo_api.py b/utils/indigo-service/backend/service/v2/indigo_api.py
@@ -335,6 +335,10 @@ def load_moldata(
         md.struct = indigo.loadSequence(molstr, "PEPTIDE", library)
         md.is_rxn = False
         md.is_query = False
+    elif input_format == "chemical/x-peptide-sequence-3-letter":
+        md.struct = indigo.loadSequence(molstr, "PEPTIDE-3-LETTER", library)
+        md.is_rxn = False
+        md.is_query = False
     elif input_format == "chemical/x-rna-sequence":
         md.struct = indigo.loadSequence(molstr, "RNA", library)
         md.is_rxn = False
@@ -431,6 +435,8 @@ def save_moldata(
         return md.struct.json()
     elif output_format == "chemical/x-sequence":
         return md.struct.sequence(library)
+    elif output_format == "chemical/x-peptide-sequence-3-letter":
+        return md.struct.sequence3Letter(library)
     elif output_format == "chemical/x-fasta":
         return md.struct.fasta(library)
     elif output_format == "chemical/x-idt":
@@ -928,6 +934,7 @@ def convert():
             "chemical/x-fasta",
             "chemical/x-idt",
             "chemical/x-helm",
+            "chemical/x-peptide-sequence-3-letter, ",
         ):
             try_document = True
 

diff --git a/utils/indigo-service/backend/service/v2/validation.py b/utils/indigo-service/backend/service/v2/validation.py
@@ -26,6 +26,7 @@ class InputFormatSchema(Schema):
         "chemical/x-sdf",
         "chemical/x-rdf",
         "chemical/x-peptide-sequence",
+        "chemical/x-peptide-sequence-3-letter",
         "chemical/x-rna-sequence",
         "chemical/x-dna-sequence",
         "chemical/x-sequence",