Backmerge: #3661 BILN import/export special cases

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

@@ -1,10 +1,51 @@
 *** BILN interop ***
+biln_bracketed_alias:BILN->HELM SUCCEED
 biln_cap:BILN->HELM SUCCEED
 biln_disulfides:BILN->HELM SUCCEED
+biln_explicit_backbone:BILN->HELM SUCCEED
+biln_large_bond_id:BILN->HELM SUCCEED
+biln_star_alias:BILN->HELM SUCCEED
 biln_three_chains:BILN->HELM SUCCEED
+biln_two_backbones:BILN->HELM SUCCEED
+biln_underscore_alias:BILN->HELM SUCCEED
+biln_alphabetic_order:BILN->BILN SUCCEED
+biln_amino_acid_count_order:BILN->BILN SUCCEED
+biln_backbone_order:BILN->BILN SUCCEED
+biln_bracketed_no_hyphen:BILN->BILN SUCCEED
+biln_cycle_best:BILN->BILN SUCCEED
+biln_cycle_reverse_rotation:BILN->BILN SUCCEED
+biln_cycle_rotation:BILN->BILN SUCCEED
+biln_cycle_with_external_bond_order:BILN->BILN SUCCEED
+biln_cycle_with_extra_bond_order:BILN->BILN SUCCEED
+biln_equal_chain_topology_order:BILN->BILN SUCCEED
+biln_library_alias:BILN->BILN SUCCEED
+biln_multiple_nonbackbone_order:BILN->BILN SUCCEED
+biln_short_chain_order:BILN->BILN SUCCEED
+biln_valid_large_bond_ids:BILN->BILN SUCCEED
+helm_alias_to_biln_alias:HELM->BILN SUCCEED
+helm_bracketed_alias:HELM->BILN SUCCEED
 helm_cap:HELM->BILN SUCCEED
+helm_chem_backbone:HELM->BILN SUCCEED
+helm_chem_with_biln_code:HELM->BILN SUCCEED
 helm_cycle:HELM->BILN SUCCEED
+helm_star_alias:HELM->BILN SUCCEED
 helm_three_chains:HELM->BILN SUCCEED
-Test 'A(1,3)-C': got expected error 'Invalid BILN bond 1: expected two endpoints but found 1.'
-Test 'A--C': got expected error 'Invalid BILN string: empty monomer.'
-Test 'A-C(1,4)': got expected error 'Invalid BILN bond 1: expected two endpoints but found 1.'
+helm_underscore_alias:HELM->BILN SUCCEED
+Test 'CHEM1{[qweqwe]}$$$$V2.0': got expected error 'Only amino acids and CHEMs with BILN codes can get exported to BILN.'
+Test 'PEPTIDE1{A}|RNA1{R(A)P}$$$$V2.0': got expected error 'Only amino acids and CHEMs with BILN codes can get exported to BILN.'
+Test 'PEPTIDE1{[Abu].[Sar].[NMeL].V.[NMeL].A.[DAla].[NMeL].[NMeL].[NMeV].[NMeThr4RBut2enyl]}$PEPTIDE1,PEPTIDE1,1:R1-11:R2$$$V2.0': got expected error 'Only amino acids and CHEMs with BILN codes can get exported to BILN.'
+Test 'PEPTIDE1{[Ac]}|PEPTIDE2{K}$PEPTIDE1,PEPTIDE2,1:R1-1:R3$$$V2.0': got expected error 'Cannot save in BILN format - unsupported attachment point 'R1'.'
+Test KET 'custom_chem_without_biln_code': got expected error 'Only amino acids and CHEMs with BILN codes can get exported to BILN.'
+Test KET 'unresolved_cap_invalid_attachment': got expected error 'Cannot save in BILN format - unsupported attachment point 'R1'.'
+Test 'A(1,3)-C': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A--C': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A-C(-1,3)-D(2,3)-E.F-G-H(-1,3)-I-K(2,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A-C(1,3)-D(1,3)-E.F-G-H(1,3)-I-K(2,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A-C(1,4)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A-C(1,4)-D(2,3)-E.F-G-H(1,3)-I-K(2,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'A-C(1.25,3)-D(2,3)-E.F-G-H(1.25,3)-I-K(2,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'Ac(1,1).K(1,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'Ac(1,4).K(1,3)': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'Cys_SEt': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test 'D-2Thi-D-D-gGlu-meF-G-Lys-al': got expected error 'The string cannot be interpreted as a valid BILN string.'
+Test '[D-Cit](1,2)-aThr(1,1)(2,2)-meS(2,1)': got expected error 'The string cannot be interpreted as a valid BILN string.'

api/tests/integration/tests/formats/biln.py

@@ -25,13 +25,39 @@
 )
 
 biln_to_helm = {
+    # Legacy integration coverage: terminal caps must keep their explicit
+    # non-backbone BILN bonds during import/export roundtrip.
     "biln_cap": (
         "Ac(1,2).A-K(1,3)",
-        "PEPTIDE1{[Ac]}|PEPTIDE2{A.K}$PEPTIDE1,PEPTIDE2,1:R2-2:R3$$$V2.0",
+        "PEPTIDE1{[ac]}|PEPTIDE2{A.K}$PEPTIDE1,PEPTIDE2,1:R2-2:R3$$$V2.0",
     ),
     "biln_three_chains": (
         "Ac(1,2).A-K(1,3)(2,2).Me(2,1)",
-        "PEPTIDE1{[Ac]}|PEPTIDE2{A.K}|PEPTIDE3{[Me]}$PEPTIDE1,PEPTIDE2,1:R2-2:R3|PEPTIDE2,PEPTIDE3,2:R2-1:R1$$$V2.0",
+        "PEPTIDE1{[ac]}|PEPTIDE2{A.K}|PEPTIDE3{[-Me]}$PEPTIDE1,PEPTIDE2,1:R2-2:R3|PEPTIDE2,PEPTIDE3,2:R2-1:R1$$$V2.0",
+    ),
+    "biln_two_backbones": (
+        "A-C-D.E-F-G",
+        "PEPTIDE1{A.C.D}|PEPTIDE2{E.F.G}$$$$V2.0",
+    ),
+    "biln_underscore_alias": (
+        "A-1Nal-Cys_Bn-C",
+        "PEPTIDE1{A.[1Nal].[Cys_Bn].C}$$$$V2.0",
+    ),
+    "biln_bracketed_alias": (
+        "A-[D-1Nal]-[Cys_Bn]-[C]",
+        "PEPTIDE1{A.[D-1Nal].[Cys_Bn].C}$$$$V2.0",
+    ),
+    "biln_star_alias": (
+        "A-D*-C",
+        "PEPTIDE1{A.[D*].C}$$$$V2.0",
+    ),
+    "biln_large_bond_id": (
+        "A-C(7563,3).C(7563,3)",
+        "PEPTIDE1{A.C}|PEPTIDE2{C}$PEPTIDE1,PEPTIDE2,2:R3-1:R3$$$V2.0",
+    ),
+    "biln_explicit_backbone": (
+        "[D-Cit](1,2).aThr(1,1)(2,2).meS(2,1)",
+        "PEPTIDE1{[D-Cit].[aThr].[meS]}$$$$V2.0",
     ),
     "biln_disulfides": (
         "D-T-H-F-P-I-C(1,3)-I-F-C(2,3)-C(3,3)-G-C(2,3)-C(4,3)-H-R-S-K-C(3,3)-G-M-C(4,3)-C(1,3)-K-T",
@@ -53,6 +79,79 @@
     except IndigoException as e:
         print(name + ":FAILED - " + getIndigoExceptionText(e))
 
+biln_to_biln = {
+    "biln_cycle_best": (
+        "A(1,1)-C-D-E(1,2)",
+        "A(1,1)-C-D-E(1,2)",
+    ),
+    "biln_cycle_rotation": (
+        "C(1,1)-D-E-A(1,2)",
+        "A(1,1)-C-D-E(1,2)",
+    ),
+    "biln_cycle_reverse_rotation": (
+        "D(1,2)-C-A-E(1,1)",
+        "A(1,1)-C-D-E(1,2)",
+    ),
+    "biln_bracketed_no_hyphen": (
+        "[D-2Thi]-[D]-[D-gGlu]-[meF]-[G]-[Lys-al]",
+        "[D-2Thi]-D-[D-gGlu]-meF-G-[Lys-al]",
+    ),
+    "biln_backbone_order": (
+        "A-A-A-A-A-A.C-C-C-C.[PEG-2]-C-C-C-C-[PEG-2]",
+        "A-A-A-A-A-A.[PEG-2]-C-C-C-C-[PEG-2].C-C-C-C",
+    ),
+    "biln_short_chain_order": (
+        "A-A-A6OH-A6OH-A6OH.C-C-C-C-C",
+        "A-A-A6OH-A6OH-A6OH.C-C-C-C-C",
+    ),
+    "biln_amino_acid_count_order": (
+        "C-C-A6OH-A6OH-C-C.C-C-C-C-C-A6OH",
+        "C-C-C-C-C-A6OH.C-C-A6OH-A6OH-C-C",
+    ),
+    "biln_alphabetic_order": (
+        "C-D-E-F-G-A6OH.A-C-D-E-F-A6OH",
+        "A-C-D-E-F-A6OH.C-D-E-F-G-A6OH",
+    ),
+    "biln_multiple_nonbackbone_order": (
+        "A-[Test-6-Ch](1,4)(2,3)-C.D(2,1).E(1,2)",
+        "A-[Test-6-Ch](1,3)(2,4)-C.D(1,1).E(2,2)",
+    ),
+    "biln_cycle_with_extra_bond_order": (
+        "C(1,1)(2,3)-C-C(2,3)-C(1,2)",
+        "C(1,1)-C(2,3)-C-C(1,2)(2,3)",
+    ),
+    "biln_cycle_with_external_bond_order": (
+        "C(1,1)-C(2,3)-C(1,2).C(2,3)",
+        "C(1,1)(2,3)-C-C(1,2).C(2,3)",
+    ),
+    "biln_equal_chain_topology_order": (
+        "C(1,3).C(1,1)",
+        "C(1,1).C(1,3)",
+    ),
+    "biln_library_alias": (
+        "Edc",
+        "Edc",
+    ),
+    "biln_valid_large_bond_ids": (
+        "A-C(7563,3)-D(3,3)-E.F-G-H(7563,3)-I-K(3,3)",
+        "F-G-H(1,3)-I-K(2,3).A-C(1,3)-D(2,3)-E",
+    ),
+}
+
+for name in sorted(biln_to_biln.keys()):
+    biln, biln_ref = biln_to_biln[name]
+    try:
+        doc = indigo.loadBiln(biln, lib)
+        canonical_biln = doc.biln(lib)
+        diff = find_diff(biln_ref, canonical_biln)
+        if diff:
+            print(name + ":FAILED")
+            print(diff)
+        else:
+            print(name + ":BILN->BILN SUCCEED")
+    except IndigoException as e:
+        print(name + ":FAILED - " + getIndigoExceptionText(e))
+
 helm_to_biln = {
     "helm_cap": (
         "PEPTIDE1{[Ac]}|PEPTIDE2{A.K}$PEPTIDE1,PEPTIDE2,1:R2-2:R3$$$V2.0",
@@ -62,9 +161,33 @@
         "PEPTIDE1{[Ac]}|PEPTIDE2{A.K}|PEPTIDE3{[Me]}$PEPTIDE1,PEPTIDE2,1:R2-2:R3|PEPTIDE2,PEPTIDE3,2:R2-1:R1$$$V2.0",
         "Ac(1,2).A-K(1,3)(2,2).Me(2,1)",
     ),
+    "helm_underscore_alias": (
+        "PEPTIDE1{A.[1Nal].[Cys_Bn].C}$$$$V2.0",
+        "A-1Nal-Cys_Bn-C",
+    ),
+    "helm_bracketed_alias": (
+        "PEPTIDE1{A.[D-1Nal].[Cys_Bn].C}$$$$V2.0",
+        "A-[D-1Nal]-Cys_Bn-C",
+    ),
+    "helm_star_alias": (
+        "PEPTIDE1{A.[D*].C}$$$$V2.0",
+        "A-D*-C",
+    ),
     "helm_cycle": (
-        "PEPTIDE1{[Abu].[Sar].[NMeL].V.[NMeL].A.[DAla].[NMeL].[NMeL].[NMeV].[NMeThr4RBut2enyl]}$PEPTIDE1,PEPTIDE1,1:R1-11:R2$$$V2.0",
-        "Abu(1,1)-Sar-NMeL-V-NMeL-A-DAla-NMeL-NMeL-NMeV-NMeThr4RBut2enyl(1,2)",
+        "PEPTIDE1{A.C.D.E}$PEPTIDE1,PEPTIDE1,1:R1-4:R2$$$V2.0",
+        "A(1,1)-C-D-E(1,2)",
+    ),
+    "helm_chem_backbone": (
+        "PEPTIDE1{A.A.A.A.A.A}|CHEM1{[PEG-2]}|PEPTIDE2{C.C.C.C}|CHEM2{[PEG-2]}$PEPTIDE1,CHEM1,6:R2-1:R1|CHEM1,PEPTIDE2,1:R2-1:R1|PEPTIDE2,CHEM2,4:R2-1:R1$$$V2.0",
+        "A-A-A-A-A-A-[PEG-2]-C-C-C-C-[PEG-2]",
+    ),
+    "helm_chem_with_biln_code": (
+        "CHEM1{[PEG-2]}$$$$V2.0",
+        "[PEG-2]",
+    ),
+    "helm_alias_to_biln_alias": (
+        "PEPTIDE1{[Cys_SEt]}$$$$V2.0",
+        "Edc",
     ),
 }
 
@@ -82,10 +205,79 @@
     except IndigoException as e:
         print(name + ":FAILED - " + getIndigoExceptionText(e))
 
+helm_errors = {
+    "CHEM1{[qweqwe]}$$$$V2.0": "Only amino acids and CHEMs with BILN codes can get exported to BILN.",
+    # Unresolved HELM aliases that map to real BILN terminal caps must still be
+    # validated against the resolved library template attachment points.
+    "PEPTIDE1{[Ac]}|PEPTIDE2{K}$PEPTIDE1,PEPTIDE2,1:R1-1:R3$$$V2.0": "Cannot save in BILN format - unsupported attachment point 'R1'.",
+    "PEPTIDE1{A}|RNA1{R(A)P}$$$$V2.0": "Only amino acids and CHEMs with BILN codes can get exported to BILN.",
+    # Legacy integration input retained as an error expectation. #3541 export
+    # requirement 1 forbids exporting PEPTIDE monomers without BILN codes.
+    "PEPTIDE1{[Abu].[Sar].[NMeL].V.[NMeL].A.[DAla].[NMeL].[NMeL].[NMeV].[NMeThr4RBut2enyl]}$PEPTIDE1,PEPTIDE1,1:R1-11:R2$$$V2.0": "Only amino acids and CHEMs with BILN codes can get exported to BILN.",
+}
+
+for helm in sorted(helm_errors.keys()):
+    error = helm_errors[helm]
+    try:
+        doc = indigo.loadHelm(helm, lib)
+        doc.biln(lib)
+        print("Test %s failed: exception expected." % helm)
+    except IndigoException as e:
+        text = getIndigoExceptionText(e)
+        if error in text:
+            print("Test '%s': got expected error '%s'" % (helm, error))
+        else:
+            print(
+                "Test '%s': expected error '%s' but got '%s'"
+                % (helm, error, text)
+            )
+
+ket_errors = {
+    "custom_chem_without_biln_code": (
+        "CHEM1{[qweqwe]}$$$$V2.0",
+        "Only amino acids and CHEMs with BILN codes can get exported to BILN.",
+    ),
+    "unresolved_cap_invalid_attachment": (
+        "PEPTIDE1{[Ac]}|PEPTIDE2{K}$PEPTIDE1,PEPTIDE2,1:R1-1:R3$$$V2.0",
+        "Cannot save in BILN format - unsupported attachment point 'R1'.",
+    ),
+}
+
+for name in sorted(ket_errors.keys()):
+    helm, error = ket_errors[name]
+    try:
+        doc = indigo.loadHelm(helm, lib)
+        doc = indigo.loadKetDocument(doc.json())
+        doc.biln(lib)
+        print("Test KET %s failed: exception expected." % name)
+    except IndigoException as e:
+        text = getIndigoExceptionText(e)
+        if error in text:
+            print("Test KET '%s': got expected error '%s'" % (name, error))
+        else:
+            print(
+                "Test KET '%s': expected error '%s' but got '%s'"
+                % (name, error, text)
+            )
+
 biln_errors = {
-    "A(1,3)-C": "Invalid BILN bond 1: expected two endpoints but found 1.",
-    "A--C": "Invalid BILN string: empty monomer.",
-    "A-C(1,4)": "Invalid BILN bond 1: expected two endpoints but found 1.",
+    # #3541 import requirement 1: any invalid BILN string must return the
+    # generic error text below. This intentionally replaces older detailed
+    # error expectations for the pre-existing invalid integration cases.
+    "A(1,3)-C": "The string cannot be interpreted as a valid BILN string.",
+    "A--C": "The string cannot be interpreted as a valid BILN string.",
+    "A-C(1,4)": "The string cannot be interpreted as a valid BILN string.",
+    "[D-Cit](1,2)-aThr(1,1)(2,2)-meS(2,1)": "The string cannot be interpreted as a valid BILN string.",
+    "D-2Thi-D-D-gGlu-meF-G-Lys-al": "The string cannot be interpreted as a valid BILN string.",
+    "A-C(-1,3)-D(2,3)-E.F-G-H(-1,3)-I-K(2,3)": "The string cannot be interpreted as a valid BILN string.",
+    "A-C(1.25,3)-D(2,3)-E.F-G-H(1.25,3)-I-K(2,3)": "The string cannot be interpreted as a valid BILN string.",
+    "A-C(1,3)-D(1,3)-E.F-G-H(1,3)-I-K(2,3)": "The string cannot be interpreted as a valid BILN string.",
+    "A-C(1,4)-D(2,3)-E.F-G-H(1,3)-I-K(2,3)": "The string cannot be interpreted as a valid BILN string.",
+    # Terminal caps must be resolved against their real templates, not imported
+    # as unresolved monomers with synthetic R1..R4 attachment points.
+    "Ac(1,1).K(1,3)": "The string cannot be interpreted as a valid BILN string.",
+    "Ac(1,4).K(1,3)": "The string cannot be interpreted as a valid BILN string.",
+    "Cys_SEt": "The string cannot be interpreted as a valid BILN string.",
 }
 
 for biln in sorted(biln_errors.keys()):