#1188 HELM ver 1 scope: support multiple sequences and connection tables (import and export)

api/c/indigo/src/indigo_molecule.cpp

@@ -686,7 +686,7 @@ CEXPORT int indigoLoadHelm(int source)
         std::unique_ptr<IndigoMolecule> molptr = std::make_unique<IndigoMolecule>();
 
         Molecule& mol = molptr->mol;
-        // loader.loadHelm(mol);
+        loader.loadHELM(mol);
         return self.addObject(molptr.release());
     }
     INDIGO_END(-1);

api/c/indigo/src/indigo_savers.cpp

@@ -649,7 +649,7 @@ CEXPORT int indigoSaveHelm(int item, int output)
         {
             SequenceSaver saver(out);
             BaseMolecule& mol = obj.getBaseMolecule();
-            // saver.saveMolecule(mol, SequenceSaver::SeqFormat::HELM);
+            saver.saveMolecule(mol, SequenceSaver::SeqFormat::HELM);
             out.flush();
             return 1;
         }

api/tests/integration/ref/formats/helm_to_ket.py.out

@@ -0,0 +1,7 @@
+*** HELM to KET ***
+helm_annotations.ket:SUCCEED
+helm_chem_peptide.ket:SUCCEED
+helm_multi_char_rna.ket:SUCCEED
+helm_peptide.ket:SUCCEED
+helm_simple_rna.ket:SUCCEED
+Test 'PEPTIDE1{A'2'}$$$$V2.0': got expected error 'Repeating do not supported now.'

api/tests/integration/ref/formats/ket_to_helm.py.out

@@ -0,0 +1,6 @@
+*** KET to HELM ***
+helm_annotations.ket:SUCCEED
+helm_chem_peptide.ket:SUCCEED
+helm_multi_char_rna.ket:SUCCEED
+helm_peptide.ket:SUCCEED
+helm_simple_rna.ket:SUCCEED

api/tests/integration/tests/formats/helm_to_ket.py

@@ -0,0 +1,71 @@
+import difflib
+import os
+import sys
+
+
+def find_diff(a, b):
+    return "\n".join(difflib.unified_diff(a.splitlines(), b.splitlines()))
+
+
+sys.path.append(
+    os.path.normpath(
+        os.path.join(os.path.abspath(__file__), "..", "..", "..", "common")
+    )
+)
+from env_indigo import (  # noqa
+    Indigo,
+    IndigoException,
+    getIndigoExceptionText,
+    joinPathPy,
+)
+
+indigo = Indigo()
+indigo.setOption("json-saving-pretty", True)
+indigo.setOption("ignore-stereochemistry-errors", True)
+
+print("*** HELM to KET ***")
+
+root = joinPathPy("molecules/", __file__)
+ref_path = joinPathPy("ref/", __file__)
+
+helm_data = {
+    "helm_simple_rna": "RNA1{R(U)P.R(T)P.R(G)P.R(C)P.R(A)}$$$$V2.0",
+    "helm_multi_char_rna": "RNA1{R(U)P.R(T)P.R(G)P.R(C)P.R([daA])}$$$$V2.0",
+    "helm_peptide": "PEPTIDE1{A.[meA].C}$$$$V2.0",
+    "helm_chem_peptide": "CHEM1{[PEG2]}|PEPTIDE1{W.N.D.[Pen].G.[Orn].D.A.D.G.S.G.[Cap]}$CHEM1,PEPTIDE1,1:R1-1:R1$$$V2.0",
+    "helm_annotations": 'BLOB1{BEAD}"Animated Polystyrene"|CHEM1{[hxy]"Annotation"}|RNA1{R(A"mutation")P.R(U)P.R(G)P}$$$$V2.0',
+}
+
+lib = indigo.loadMoleculeFromFile(
+    os.path.join(ref_path, "monomer_library.ket")
+)
+
+for filename in sorted(helm_data.keys()):
+    mol = indigo.loadHelm(helm_data[filename])
+    # with open(os.path.join(ref_path, filename) + ".ket", "w") as file:
+    #     file.write(mol.json())
+    with open(os.path.join(ref_path, filename) + ".ket", "r") as file:
+        ket_ref = file.read()
+    ket = mol.json()
+    diff = find_diff(ket_ref, ket)
+    if not diff:
+        print(filename + ".ket:SUCCEED")
+    else:
+        print(filename + ".ket:FAILED")
+        print(diff)
+
+helm_errors = {"PEPTIDE1{A'2'}$$$$V2.0": "Repeating do not supported now."}
+for helm_seq in sorted(helm_errors.keys()):
+    error = helm_errors[helm_seq]
+    try:
+        mol = indigo.loadHelm(helm_seq)
+        print("Test %s failed: exception expected." % helm_seq)
+    except IndigoException as e:
+        text = getIndigoExceptionText(e)
+        if error in text:
+            print("Test '%s': got expected error '%s'" % (helm_seq, error))
+        else:
+            print(
+                "Test '%s': expected error '%s' but got '%s'"
+                % (helm_seq, error, text)
+            )

api/tests/integration/tests/formats/ket_to_helm.py

@@ -0,0 +1,73 @@
+import difflib
+import os
+import sys
+
+
+def find_diff(a, b):
+    return "\n".join(difflib.unified_diff(a.splitlines(), b.splitlines()))
+
+
+sys.path.append(
+    os.path.normpath(
+        os.path.join(os.path.abspath(__file__), "..", "..", "..", "common")
+    )
+)
+from env_indigo import (  # noqa
+    Indigo,
+    IndigoException,
+    getIndigoExceptionText,
+    joinPathPy,
+)
+
+indigo = Indigo()
+indigo.setOption("ignore-stereochemistry-errors", True)
+
+print("*** KET to HELM ***")
+
+root = joinPathPy("molecules/", __file__)
+ref = joinPathPy("ref/", __file__)
+
+indigo.loadMoleculeFromFile(os.path.join(ref, "monomer_library.ket"))
+
+# same ref ket files used to check idt-to-ket and to check ket-to-idt
+helm_data = {
+    "helm_simple_rna": "RNA1{R(U)P.R(T)P.R(G)P.R(C)P.R(A)}$$$$V2.0",
+    "helm_multi_char_rna": "RNA1{R(U)P.R(T)P.R(G)P.R(C)P.R([daA])}$$$$V2.0",
+    "helm_peptide": "PEPTIDE1{A.[meA].C}$$$$V2.0",
+    "helm_chem_peptide": "CHEM1{[PEG2]}|PEPTIDE1{W.N.D.[Pen].G.[Orn].D.A.D.G.S.G.[Cap]}$CHEM1,PEPTIDE1,1:R1-1:R1$$$V2.0",
+    "helm_annotations": "CHEM1{[hxy]}|RNA1{R(A)P.R(U)P.R(G)P}$$$$V2.0",
+}
+
+for filename in sorted(helm_data.keys()):
+    mol = indigo.loadMoleculeFromFile(os.path.join(ref, filename + ".ket"))
+    idt = mol.helm()
+    idt_ref = helm_data[filename]
+    if idt_ref == idt:
+        print(filename + ".ket:SUCCEED")
+    else:
+        print(
+            "%s.idt FAILED : expected '%s', got '%s'"
+            % (filename, idt_ref, idt)
+        )
+
+helm_errors = {}
+for filename in sorted(helm_errors.keys()):
+    error = helm_errors[filename]
+    try:
+        mol = indigo.loadMoleculeFromFile(
+            os.path.join(root, filename + ".ket")
+        )
+        idt = mol.idt()
+        print(
+            "Test %s failed: exception expected but got next idt - '%s'."
+            % (filename, idt)
+        )
+    except IndigoException as e:
+        text = getIndigoExceptionText(e)
+        if error in text:
+            print("Test %s: got expected error '%s'" % (filename, error))
+        else:
+            print(
+                "Test %s: expected error '%s' but got '%s'"
+                % (filename, error, text)
+            )