#1912 Support unresolved IDT monomers (no structure, IDT only) (#1988)

Merge from master to 1.21

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

@@ -1,6 +1,9 @@
 *** IDT to KET ***
+idt_52moera.ket:SUCCEED
 idt_52moera_with_3phos.ket:SUCCEED
 idt_bases.ket:SUCCEED
+idt_i2moera.ket:SUCCEED
+idt_i2moera_t.ket:SUCCEED
 idt_many_molecules.ket:SUCCEED
 idt_mixed.ket:SUCCEED
 idt_mod_phosphates.ket:SUCCEED
@@ -9,25 +12,23 @@ idt_prefix_suffix.ket:SUCCEED
 idt_singe_32moera_nucleoside.ket:SUCCEED
 idt_single_nucleoside.ket:SUCCEED
 idt_std_phosphates.ket:SUCCEED
+idt_t_i2moera.ket:SUCCEED
+idt_unresolved.ket:SUCCEED
 Test '!+A-$#12w12r23e32e33': got expected error 'Invalid symbols in the sequence: !,-,$,#,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 modified monomer.'
 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 '/32MOErA/T': got expected error 'IDT alias '32MOErA' cannot be used at five prime end.'
+Test '/3Phos/T': got expected error 'IDT alias '3Phos' cannot be used at five prime end.'
 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 'Phosphor /3Phos/ cannod be modified with '*'.'
 Test 'A+/3Phos/': got expected error 'Sugar prefix could not be used with modified monomer.'
 Test 'Am/3Phos/': got expected error 'Sugar prefix could not be used with modified monomer.'
 Test 'Ar/3Phos/': got expected error 'Sugar prefix could not be used with modified monomer.'
-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 'T/52MOErA/': got expected error 'IDT alias '52MOErA' cannot be used at three prime end.'
+Test 'T/5Phos/': got expected error 'IDT alias '5Phos' cannot be used at three prime end.'
 Test 'm/5Phos/A': got expected error 'Sugar prefix could not be used with modified monomer.'
 Test 'r+A': got expected error 'Sugar prefix 'r' whithout base.'
 Test 'r/5Phos/A': got expected error 'Sugar prefix could not be used with modified monomer.'

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

@@ -1,6 +1,7 @@
 *** KET to IDT ***
 idt_52moera_with_3phos.ket:SUCCEED
 idt_bases.ket:SUCCEED
+idt_i2moera_t.ket:SUCCEED
 idt_many_molecules.ket:SUCCEED
 idt_mixed.ket:SUCCEED
 idt_mod_phosphates.ket:SUCCEED
@@ -9,6 +10,7 @@ idt_prefix_suffix.ket:SUCCEED
 idt_singe_32moera_nucleoside.ket:SUCCEED
 idt_single_nucleoside.ket:SUCCEED
 idt_std_phosphates.ket:SUCCEED
+idt_unresolved.ket:SUCCEED
 Test ket-to-idt-invalid-last-phosphate: got expected error 'Cannot 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 'Cannot save molecule in IDT format - sugar R with too much phosphates connected P and P.'

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

@@ -39,6 +39,11 @@ def find_diff(a, b):
     "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",
+    "idt_i2moera": "/i2MOErA/",
+    "idt_52moera": "/52MOErA/",
+    "idt_i2moera_t": "/i2MOErA/T",
+    "idt_t_i2moera": "T/i2MOErA/",
+    "idt_unresolved": "/unr1//unr2/",
 }
 
 lib = indigo.loadMoleculeFromFile(
@@ -66,14 +71,10 @@ def find_diff(a, b):
     "/a/": "Invalid modification: a.",
     "r+A": "Sugar prefix 'r' whithout base.",
     "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.",
+    "/32MOErA/T": "IDT alias '32MOErA' cannot be used at five prime end.",
+    "T/52MOErA/": "IDT alias '52MOErA' cannot be used at three prime end.",
+    "/3Phos/T": "IDT alias '3Phos' cannot be used at five prime end.",
+    "T/5Phos/": "IDT alias '5Phos' cannot be used at three prime end.",
     "/5Phos/*A": "/5Phos/ cannot be modified to 'sP'",
     "r/5Phos/A": "Sugar prefix could not be used with modified monomer.",
     "+/5Phos/A": "Sugar prefix could not be used with modified monomer.",

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

@@ -41,6 +41,11 @@ def find_diff(a, b):
     "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",
+    # "idt_i2moera": "/i2MOErA/",
+    # "idt_52moera": "/52MOErA/",
+    "idt_i2moera_t": "/52MOErA/T",
+    # "idt_t_i2moera": "T/i2MOErA/",
+    "idt_unresolved": "/unr1//unr2/",
 }
 
 for filename in sorted(idt_data.keys()):

api/tests/integration/tests/formats/ref/chem.ket

@@ -17,6 +17,7 @@
         "name": "cch",
         "attachmentPoints": [
             {
+                "id": "Br",
                 "type": "right",
                 "label": "R2",
                 "attachmentAtom": 8,
@@ -27,6 +28,7 @@
                 }
             },
             {
+                "id": "Cx",
                 "type": "side",
                 "label": "R3",
                 "attachmentAtom": 6,
@@ -37,6 +39,7 @@
                 }
             },
             {
+                "id": "Ex",
                 "type": "side",
                 "label": "R5",
                 "attachmentAtom": 3,

api/tests/integration/tests/formats/ref/conj_no_class.mol

@@ -64,7 +64,8 @@ M  V30 41 Cys 20.1724 -16.6666 0.0 0 CLASS=AA SEQID=16 ATTCHORD=(4 34 Al 35 B-
 M  V30 r)
 M  V30 42 Cys 17.8843 -16.6666 0.0 0 CLASS=AA SEQID=10 ATTCHORD=(4 29 Al 30 B-
 M  V30 r)
-M  V30 43 SMCC 14.1885 -2.31085 0.0 0 CLASS=LINKER ATTCHORD=(4 40 Br 39 Al)
+M  V30 43 SMCC 14.1885 -2.31085 0.0 0 CLASS=LINKER SEQID=1 ATTCHORD=(4 40 Br -
+M  V30 39 Al)
 M  V30 END ATOM
 M  V30 BEGIN BOND
 M  V30 1 1 2 1

api/tests/integration/tests/formats/ref/fmoc.ket

@@ -4091,6 +4091,7 @@
         "name": "Fmoc",
         "attachmentPoints": [
             {
+                "id": "Cx",
                 "type": "side",
                 "label": "R3",
                 "attachmentAtom": 16

api/tests/integration/tests/formats/ref/fmoc.mol

@@ -52,7 +52,7 @@ M  V30 )
 M  V30 30 Gly 23.2645 -6.2109 0.0 0 CLASS=AA SEQID=31 ATTCHORD=(2 29 Al)
 M  V30 31 E 16.1313 -5.15906 0.0 0 CLASS=MODAA SEQID=21 ATTCHORD=(6 32 Cx 20 -
 M  V30 Al 21 Br)
-M  V30 32 Fmoc 15.7704 -3.60196 0.0 0 CLASS=LINKER ATTCHORD=(2 31 Cx)
+M  V30 32 Fmoc 15.7704 -3.60196 0.0 0 CLASS=LINKER SEQID=1 ATTCHORD=(2 31 Cx)
 M  V30 END ATOM
 M  V30 BEGIN BOND
 M  V30 1 1 1 2