#1900 Export of modified RNA to IDT notation (modified IDT monomers)

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

@@ -1,7 +1,31 @@
 *** IDT to KET ***
-idt_a.ket:SUCCEED
-idt_acg.ket:SUCCEED
-idt_maxmgc.ket:SUCCEED
-idt_2moera.ket:SUCCEED
+idt_52moera_with_3phos.ket:SUCCEED
+idt_bases.ket:SUCCEED
+idt_many_molecules.ket:SUCCEED
+idt_mixed.ket:SUCCEED
+idt_mod_phosphates.ket:SUCCEED
 idt_modifications.ket:SUCCEED
-Got expected error 'SEQUENCE loader: SequenceLoader::loadIdt(), Invalid symbols in the sequence: !,-,$,#,1,2,w,1,2,2,3,e,3,2,e,3,3'
+idt_prefix_suffix.ket:SUCCEED
+idt_singe_32moera_nucleoside.ket:SUCCEED
+idt_single_nucleoside.ket:SUCCEED
+idt_std_phosphates.ket:SUCCEED
+Test '!+-$#12w12r23e32e33': got expected error 'SequenceLoader::loadIdt(), Invalid symbols in the sequence: !,-,$,#,1,2,w,1,2,2,3,e,3,2,e,3,3'
+Test '+/5Phos/A': got expected error 'Sugar prefix could not be used with '/5Phos/''
+Test '/': got expected error 'Unexpected end of data'
+Test '//': got expected error 'Invalid modification: empty string.'
+Test '/32MOErA/T': got expected error 'IDT alias 32MOErA not found at five-prime end position.'
+Test '/3Phos/T': expected error 'IDT alias 3Phos not found at three-prime end position.' but got 'SEQUENCE loader: IDT alias 3Phos not found at five-prime end position.'
+Test '/52MOErA/': got expected error 'IDT alias 52MOErA not found at three-prime end position.'
+Test '/5Phos/*A': got expected error '/5Phos/ cannot be modified to 'sP''
+Test '/a/': got expected error 'Invalid modification: a.'
+Test '/i2MOErA/': got expected error 'IDT alias i2MOErA not found at three-prime end position.'
+Test '/i2MOErA/T': got expected error 'IDT alias i2MOErA not found at five-prime end position.'
+Test 'A*': got expected error 'Invalid IDT sequence: '*' couldn't be the last symbol.'
+Test 'A+/3Phos/': got expected error 'Sugar prefix could not be used with '/3Phos/''
+Test 'Am/3Phos/': got expected error 'Sugar prefix could not be used with '/3Phos/''
+Test 'Ar/3Phos/': got expected error 'Sugar prefix could not be used with '/3Phos/''
+Test 'T/52MOErA/': got expected error 'IDT alias 52MOErA not found at three-prime end position.'
+Test 'T/5Phos/': got expected error 'IDT alias 5Phos not found at three-prime end position.'
+Test 'T/i2MOErA/': got expected error 'IDT alias i2MOErA not found at three-prime end position.'
+Test 'm/5Phos/A': got expected error 'Sugar prefix could not be used with '/5Phos/''
+Test 'r/5Phos/A': got expected error 'Sugar prefix could not be used with '/5Phos/''

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

@@ -1,2 +1,20 @@
 *** KET to IDT ***
-1654-dna-to-idt.idt:SUCCEED
+idt_52moera_with_3phos.ket:SUCCEED
+idt_bases.ket:SUCCEED
+idt_many_molecules.ket:SUCCEED
+idt_mixed.ket:SUCCEED
+idt_mod_phosphates.ket:SUCCEED
+idt_modifications.ket:SUCCEED
+idt_prefix_suffix.ket:SUCCEED
+idt_singe_32moera_nucleoside.ket:SUCCEED
+idt_single_nucleoside.ket:SUCCEED
+idt_std_phosphates.ket:SUCCEED
+Test ket-to-idt-invalid-last-phosphate: got expected error 'Canot save molecule in IDT format - phosphate sP cannot be last monomer in sequence.'
+Test ket-to-idt-invalid-nucleotide: got expected error 'IDT alias for group sugar:m2e2r base:z8c3G phosphate:mepo2 not found.'
+Test ket-to-idt-invalid-posphates: got expected error 'Canot save molecule in IDT format - sugar R with too much phosphates connected P and P.'
+Test ket-to-idt-invalid-sugar: got expected error 'IDT alias for sugar:m2e2r not found.'
+Test ket-to-idt-invalid-sugar-base: got expected error 'IDT alias for group sugar:m2e2r base:z8c3G not found.'
+Test ket-to-idt-invalid-sugar-phosphate: got expected error 'IDT alias for group sugar:m2e2r phosphate:mepo2 not found.'
+Test ket-to-idt-peptide: got expected error 'Canot save molecule in IDT format - AA monomer DPhe4C cannot be first.'
+Test ket-to-idt-r1r1connection: got expected error 'Canot save molecule in IDT format - sugar MOE connected to monomer MOE with class SUGAR (only base or phosphate expected).'
+Test ket-to-idt-two-bases: got expected error 'Canot save molecule in IDT format - sugar R with two base connected A and C.'

api/tests/integration/tests/formats/idt_to_ket.py

@@ -28,49 +28,70 @@ def find_diff(a, b):
 root = joinPathPy("molecules/", __file__)
 ref_path = joinPathPy("ref/", __file__)
 
-idt_names = [
-    "idt_a",
-    "idt_acg",
-    "idt_maxmgc",
-    "idt_2moera",
-    "idt_modifications",
-]
-
 idt_data = {
-    "idt_a": "A",
-    "idt_acg": "ACG",
-    "idt_maxmgc": "mA*mGC",
-    "idt_2moera": "/52MOErA//i2MOErA//32MOErA/",
-    "idt_modifications": "/5Phos//i2MOErC//3Phos/",
+    "idt_single_nucleoside": "A",
+    "idt_bases": "ATCGUI",
+    "idt_prefix_suffix": "mA*rT*+C*G*+UrImA",
+    "idt_modifications": "/52MOErA/*/i2MOErA//32MOErA/",
+    "idt_52moera_with_3phos": "/52MOErA//3Phos/",
+    "idt_singe_32moera_nucleoside": "/32MOErA/",
+    "idt_std_phosphates": "/5Phos/ATG/3Phos/",
+    "idt_mod_phosphates": "/5Phos//i2MOErC//3Phos/",
+    "idt_mixed": "/5Phos/+A*/i2MOErA/*rG/3Phos/",
+    "idt_many_molecules": "ACTG\n/52MOErA/*AU/3Phos/\rAC/i2MOErC//3Phos/\n\rTACG",
 }
 
 lib = indigo.loadMoleculeFromFile(
     os.path.join(ref_path, "monomer_library.ket")
 )
 
-for idt_name in idt_names:
-    mol = indigo.loadIdt(idt_data[idt_name])
-    # with open(os.path.join(ref_path, idt_name) + ".ket", "w") as file:
+for filename in sorted(idt_data.keys()):
+    mol = indigo.loadIdt(idt_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, idt_name) + ".ket", "r") as file:
+    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(idt_name + ".ket:SUCCEED")
+        print(filename + ".ket:SUCCEED")
     else:
-        print(idt_name + ".ket:FAILED")
+        print(filename + ".ket:FAILED")
         print(diff)
 
 idt_errors = {
-    "!+-$#12w12r23e32e33": "SEQUENCE loader: SequenceLoader::loadIdt(), Invalid symbols in the sequence: !,-,$,#,1,2,w,1,2,2,3,e,3,2,e,3,3"
+    "!+-$#12w12r23e32e33": "SequenceLoader::loadIdt(), Invalid symbols in the sequence: !,-,$,#,1,2,w,1,2,2,3,e,3,2,e,3,3",
+    "/": "Unexpected end of data",
+    "//": "Invalid modification: empty string.",
+    "/a/": "Invalid modification: a.",
+    "A*": "Invalid IDT sequence: '*' couldn't be the last symbol.",
+    "/i2MOErA/": "IDT alias i2MOErA not found at three-prime end position.",
+    "/i2MOErA/T": "IDT alias i2MOErA not found at five-prime end position.",
+    "T/i2MOErA/": "IDT alias i2MOErA not found at three-prime end position.",
+    "/32MOErA/T": "IDT alias 32MOErA not found at five-prime end position.",
+    "/52MOErA/": "IDT alias 52MOErA not found at three-prime end position.",
+    "T/52MOErA/": "IDT alias 52MOErA not found at three-prime end position.",
+    "/3Phos/T": "IDT alias 3Phos not found at three-prime end position.",
+    "T/5Phos/": "IDT alias 5Phos not found at three-prime end position.",
+    "/5Phos/*A": "/5Phos/ cannot be modified to 'sP'",
+    "r/5Phos/A": "Sugar prefix could not be used with '/5Phos/'",
+    "+/5Phos/A": "Sugar prefix could not be used with '/5Phos/'",
+    "m/5Phos/A": "Sugar prefix could not be used with '/5Phos/'",
+    "Ar/3Phos/": "Sugar prefix could not be used with '/3Phos/'",
+    "A+/3Phos/": "Sugar prefix could not be used with '/3Phos/'",
+    "Am/3Phos/": "Sugar prefix could not be used with '/3Phos/'",
 }
-for idt_seq, error in idt_errors.items():
+for idt_seq in sorted(idt_errors.keys()):
+    error = idt_errors[idt_seq]
     try:
         mol = indigo.loadIdt(idt_seq)
+        print("Test %s failed: exception expected." % idt_seq)
     except IndigoException as e:
         text = getIndigoExceptionText(e)
-        if text == error:
-            print("Got expected error '%s'" % error)
+        if error in text:
+            print("Test '%s': got expected error '%s'" % (idt_seq, error))
         else:
-            print("Expected error '%s' but got '%s'" % (error, text))
+            print(
+                "Test '%s': expected error '%s' but got '%s'"
+                % (idt_seq, error, text)
+            )

api/tests/integration/tests/formats/ket_to_idt.py

@@ -12,31 +12,77 @@ def find_diff(a, b):
         os.path.join(os.path.abspath(__file__), "..", "..", "..", "common")
     )
 )
-from env_indigo import Indigo, joinPathPy  # noqa
+from env_indigo import (  # noqa
+    Indigo,
+    IndigoException,
+    getIndigoExceptionText,
+    joinPathPy,
+)
 
 indigo = Indigo()
 indigo.setOption("ignore-stereochemistry-errors", True)
 
 print("*** KET to IDT ***")
 
 root = joinPathPy("molecules/", __file__)
-ref_path = joinPathPy("ref/", __file__)
-
-files = [
-    "1654-dna-to-idt",
-]
-
-files.sort()
-for filename in files:
-    mol = indigo.loadMoleculeFromFile(os.path.join(root, filename + ".ket"))
-    # with open(os.path.join(ref_path, filename) + ".idt", "w") as file:
-    #     file.write(mol.idt())
-    with open(os.path.join(ref_path, filename) + ".idt", "r") as file:
-        idt_ref = file.read()
+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
+idt_data = {
+    "idt_single_nucleoside": "A",
+    "idt_bases": "ATCGUI",
+    "idt_prefix_suffix": "mA*rT*+C*G*+UrImA",
+    "idt_modifications": "/52MOErA/*/i2MOErA//32MOErA/",
+    "idt_52moera_with_3phos": "/52MOErA//3Phos/",
+    "idt_singe_32moera_nucleoside": "/32MOErA/",
+    "idt_std_phosphates": "/5Phos/ATG/3Phos/",
+    "idt_mod_phosphates": "/5Phos//i2MOErC//3Phos/",
+    "idt_mixed": "/5Phos/+A*/i2MOErA/*rG/3Phos/",
+    "idt_many_molecules": "ACTG\n/52MOErA/*AU/3Phos/\nAC/i2MOErC//3Phos/\nTACG",
+}
+
+for filename in sorted(idt_data.keys()):
+    mol = indigo.loadMoleculeFromFile(os.path.join(ref, filename + ".ket"))
     idt = mol.idt()
-    diff = find_diff(idt_ref, idt)
-    if not diff:
-        print(filename + ".idt:SUCCEED")
+    idt_ref = idt_data[filename]
+    if idt_ref == idt:
+        print(filename + ".ket:SUCCEED")
     else:
-        print(filename + ".idt:FAILED")
-        print(diff)
+        print(
+            "%s.idt FAILED : expected '%s', got '%s'"
+            % (filename, idt_ref, idt)
+        )
+
+idt_errors = {
+    "ket-to-idt-r1r1connection": "Canot save molecule in IDT format - sugar MOE connected to monomer MOE with class SUGAR (only base or phosphate expected).",
+    "ket-to-idt-peptide": "Canot save molecule in IDT format - AA monomer DPhe4C cannot be first.",
+    "ket-to-idt-two-bases": "Canot save molecule in IDT format - sugar R with two base connected A and C.",
+    "ket-to-idt-invalid-posphates": "Canot save molecule in IDT format - sugar R with too much phosphates connected P and P.",
+    "ket-to-idt-invalid-last-phosphate": "Canot save molecule in IDT format - phosphate sP cannot be last monomer in sequence.",
+    "ket-to-idt-invalid-nucleotide": "IDT alias for group sugar:m2e2r base:z8c3G phosphate:mepo2 not found.",
+    "ket-to-idt-invalid-sugar-phosphate": "IDT alias for group sugar:m2e2r phosphate:mepo2 not found.",
+    "ket-to-idt-invalid-sugar": "IDT alias for sugar:m2e2r not found.",
+    "ket-to-idt-invalid-sugar-base": "IDT alias for group sugar:m2e2r base:z8c3G not found.",
+}
+for filename in sorted(idt_errors.keys()):
+    error = idt_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)
+            )