Add satellite ion series to parser and grammar

HUPO-PSI · Aug 31, 2024 · b81952f · b81952f
1 parent 77d2382
commit b81952f
Show file tree

Hide file tree

Showing 8 changed files with 13 additions and 7 deletions.
diff --git a/implementations/python/mzpaf/annotation.py b/implementations/python/mzpaf/annotation.py
@@ -29,7 +29,7 @@
     r"""
 ^(?P<is_auxiliary>&)?
    (?:(?P<analyte_reference>\d+)@)?
-   (?:(?:(?P<series>[axbyczdvw]\.?)(?P<ordinal>\d+)(?:\{(?P<sequence_ordinal>.+)\})?)|
+   (?:(?:(?P<series>(?:da|db|wa|wb)|[axbyczdwv]\.?)(?P<ordinal>\d+)(?:\{(?P<sequence_ordinal>.+)\})?)|
    (?P<series_internal>[m](?P<internal_start>\d+):(?P<internal_end>\d+)(?:\{(?P<sequence_internal>.+)\})?)|
    (?P<precursor>p)|
    (:?I(?P<immonium>[ARNDCEQGHKMFPSTWYVIL])(?:\[(?P<immonium_modification>(?:[^\]]+))\])?)|

diff --git a/implementations/python/tests/test_annotations.py b/implementations/python/tests/test_annotations.py
@@ -36,6 +36,12 @@ def test_parse_unannotated(self):
         assert isinstance(x, Unannotated)
         self._matches_schema(x)
 
+    def test_satellite_ion_series(self):
+        base = "da32"
+        parsed = parse_annotation(base)[0]
+        assert parsed.series == "da"
+        assert parsed.position == 32
+
     def test_parse_annotation_complex(self):
         base = "b14"
         parsed = parse_annotation(base)[0]

diff --git a/specification/annotation-schema.json b/specification/annotation-schema.json
@@ -110,7 +110,7 @@
         "series": {
           "description": "The peptide ion series this ion belongs to",
           "type": "string",
-          "enum": ["b", "y", "a", "x", "c", "z", "d", "v", "w"]
+          "enum": ["b", "y", "a", "x", "c", "z", "d", "v", "w", "da", "db", "wa", "wb"]
         },
         "position": {
           "description": "The position from the appropriate terminal along the peptide this ion was fragmented at (starting with 1)",

diff --git a/specification/grammars/annotation.lark b/specification/grammars/annotation.lark
@@ -30,7 +30,7 @@ is_auxiliary : "&"
 
 analyte_reference_ : (ANALYTE_REFERENCE) "@"
 
-PEPTIDE_SERIES_SYMBOL : "a" | "x" | "b" | "y" | "c" | "z" | "d" | "v" | "w"
+PEPTIDE_SERIES_SYMBOL : "da" | "db" | "wa" | "wb" | "a" | "x" | "b" | "y" | "c" | "z" | "d" | "v" | "w"
 
 ORDINAL : (DIGIT)+
 

diff --git a/specification/grammars/grammar.py b/specification/grammars/grammar.py
@@ -84,7 +84,7 @@
 
 PeptideIon = Group(
     Sequence(
-        Choice(0, *list(map(Terminal, ("a", "b", "c", "x", "y", "z", "d", "v", "w")))),
+        Choice(0, *list(map(Terminal, ("a", "b", "c", "x", "y", "z", "da", "db", "v", "wa", "wb")))),
         NonTerminal("ORDINAL"),
         Optional(
             Sequence(

diff --git a/specification/grammars/regex_ecma.js b/specification/grammars/regex_ecma.js
diff --git a/specification/grammars/regex_sre.py b/specification/grammars/regex_sre.py
@@ -4,7 +4,7 @@
     r"""
 ^(?P<is_auxiliary>&)?
    (?:(?P<analyte_reference>\d+)@)?
-   (?:(?:(?P<series>[axbyczdvw]\.?)(?P<ordinal>\d+)(?:\{(?P<sequence_ordinal>.+)\})?)|
+   (?:(?:(?P<series>(?:da|db|wa|wb)|[axbyczdwv]\.?)(?P<ordinal>\d+)(?:\{(?P<sequence_ordinal>.+)\})?)|
    (?P<series_internal>[m](?P<internal_start>\d+):(?P<internal_end>\d+)(?:\{(?P<sequence_internal>.+)\})?)|
    (?P<precursor>p)|
    (:?I(?P<immonium>[ARNDCEQGHKMFPSTWYVIL])(?:\[(?P<immonium_modification>(?:[^\]]+))\])?)|

diff --git a/specification/grammars/schema_images/Annotation.svg b/specification/grammars/schema_images/Annotation.svg