Resolve #456 change sequenceTerminals to adjoinedSequences in Adjacen…

…cy (#457) * applied 'connection' to all related artifacts * changed `connection` to `adjoinedSequences` --------- Co-authored-by: Alex H. Wagner, PhD <[email protected]>
ga4gh · Jan 3, 2024 · 86067b8 · 86067b8
1 parent ae5cc61
commit 86067b8
Show file tree

Hide file tree

Showing 22 changed files with 120 additions and 70 deletions.
diff --git a/docs/source/images/ex_ambiguous_linker.png b/docs/source/images/ex_ambiguous_linker.png
diff --git a/docs/source/images/ex_precise_linker.png b/docs/source/images/ex_precise_linker.png
diff --git a/docs/source/images/ex_revcomp_breakpoint.png b/docs/source/images/ex_revcomp_breakpoint.png
diff --git a/docs/source/images/ex_sequence_homology.png b/docs/source/images/ex_sequence_homology.png
diff --git a/docs/source/images/ex_simple_breakpoint.png b/docs/source/images/ex_simple_breakpoint.png
diff --git a/docs/source/images/ex_sv_haplotype.png b/docs/source/images/ex_sv_haplotype.png
diff --git a/docs/source/images/ex_terminal_breakend.png b/docs/source/images/ex_terminal_breakend.png
diff --git a/examples/ambiguous_linker.yaml b/examples/ambiguous_linker.yaml
@@ -3,7 +3,7 @@ type: Adjacency
 linker:
   type: LengthExpression
   length: 20000
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/examples/precise_linker.yaml b/examples/precise_linker.yaml
@@ -3,7 +3,7 @@ type: Adjacency
 linker:
   type: LiteralSequenceExpression
   sequence: CCCGTC
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/examples/revcomp_breakpoint.yaml b/examples/revcomp_breakpoint.yaml
@@ -1,6 +1,6 @@
 id: truthset_1_1
 type: Adjacency
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       id: NC_000001.10

diff --git a/examples/sequence_homology.yaml b/examples/sequence_homology.yaml
@@ -1,6 +1,6 @@
 id: sequence_homology
 type: Adjacency
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/examples/simple_breakpoint.yaml b/examples/simple_breakpoint.yaml
@@ -1,6 +1,6 @@
 id: simple_breakpoint
 type: Adjacency
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/examples/sv_haplotype.yaml b/examples/sv_haplotype.yaml
@@ -6,7 +6,7 @@ members:
     linker:
       type: LiteralSequenceExpression
       sequence: GTC
-    sequenceTerminals:
+    adjoinedSequences:
       - type: SequenceLocation
         sequenceReference:
           refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU
@@ -29,8 +29,9 @@ members:
       sequence: C
   - id: ga4gh:AJ.iQ1RGkhW9AyVBLl53silKqgGSBOJaFOr
     type: Adjacency
-    sequenceTerminals:
-    - end: 15000
+    adjoinedSequences:
+    - type: SequenceLocation
+      end: 15000
     - type: SequenceLocation
       sequenceReference:
         refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/examples/terminal_breakend.yaml b/examples/terminal_breakend.yaml
@@ -1,6 +1,6 @@
 id: terminal_breakend
 type: Adjacency
-sequenceTerminals:
+adjoinedSequences:
   - type: SequenceLocation
     sequenceReference:
       refgetAccession: SQ.S_KjnFVz-FE7M0W6yoaUDgYxLPc1jyWU

diff --git a/schema/defs/vrs/Adjacency.rst b/schema/defs/vrs/Adjacency.rst
@@ -1,6 +1,6 @@
 **Computational Definition**
 
-The `Adjacency` class represents the termination of a sequence and (when present) the beginning of an adjacent sequence, potentially with an intervening linker sequence.
+The `Adjacency` class can represent either the termination of a sequence or the adjoining of the end of a sequence with the beginning of an adjacent sequence, potentially with an intervening linker sequence.
 
     **Information Model**
 
@@ -44,11 +44,11 @@ Some Adjacency attributes are inherited from :ref:`Variation`.
           - :ref:`Expression`
           - 0..m
           - 
-       *  - sequenceTerminals
+       *  - adjoinedSequences
           - `IRI <gks.common.json#/$defs/IRI>`_ | :ref:`Location`
           - 1..2
-          - Sequence terminals involved in the adjacency.
+          - The terminal sequence or pair of adjoined sequences that defines in the adjacency.
        *  - linker
           - :ref:`SequenceExpression`
           - 0..1
-          - A linker sequence found between the sequence terminals.
+          - The sequence found between adjoined sequences.
diff --git a/schema/defs/vrs/Haplotype.rst b/schema/defs/vrs/Haplotype.rst
@@ -47,4 +47,4 @@ Some Haplotype attributes are inherited from :ref:`Variation`.
        *  - members
           - :ref:`Adjacency` | :ref:`Allele` | `IRI <gks.common.json#/$defs/IRI>`_
           - 2..m
-          - A list of :ref:`Alleles <Allele>` and :ref:`Adjacencies <Adjacency>` that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an end-defined sequence  terminal), in which case they should be ordered in descending coordinates. Sequence references MUST be consistent for all members between and including the end of one Adjacency and the beginning of  another.
+          - A list of :ref:`Alleles <Allele>` and :ref:`Adjacencies <Adjacency>` that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an Adjacency with  end-defined adjoinedSequences), in which case they should be ordered in descending coordinates.  Sequence references MUST be consistent for all members between and including the end of one  Adjacency and the beginning of another.
diff --git a/schema/merged.json b/schema/merged.json
@@ -242,7 +242,7 @@
                      }
                   ]
                },
-               "description": "A list of Alleles that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an end-defined sequence  terminal), in which case they should be ordered in descending coordinates. Sequence references MUST be consistent for all members between and including the end of one Adjacency and the beginning of  another."
+               "description": "A list of Alleles that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an Adjacency with  end-defined adjoinedSequences), in which case they should be ordered in descending coordinates.  Sequence references MUST be consistent for all members between and including the end of one  Adjacency and the beginning of another."
             }
          },
          "required": [
@@ -916,12 +916,12 @@
          "ga4ghDigest": {
             "prefix": "AJ",
             "keys": [
+               "adjoinedSequences",
                "linker",
-               "sequenceTerminals",
                "type"
             ]
          },
-         "description": "The `Adjacency` class represents the termination of a sequence and (when present) the beginning of an adjacent sequence, potentially with an intervening linker sequence.",
+         "description": "The `Adjacency` class can represent either the termination of a sequence or the adjoining of the end of a sequence with the beginning of an adjacent sequence, potentially with an intervening linker sequence.",
          "type": "object",
          "properties": {
             "id": {
@@ -961,7 +961,7 @@
                   "$ref": "#/$defs/Expression"
                }
             },
-            "sequenceTerminals": {
+            "adjoinedSequences": {
                "type": "array",
                "uniqueItems": false,
                "ordered": true,
@@ -975,12 +975,12 @@
                      }
                   ]
                },
-               "description": "Sequence terminals involved in the adjacency.",
+               "description": "The terminal sequence or pair of adjoined sequences that defines in the adjacency.",
                "minItems": 1,
                "maxItems": 2
             },
             "linker": {
-               "description": "A linker sequence found between the sequence terminals.",
+               "description": "The sequence found between adjoined sequences.",
                "oneOf": [
                   {
                      "$ref": "#/$defs/LengthExpression"
@@ -995,7 +995,7 @@
             }
          },
          "required": [
-            "sequenceTerminals"
+            "adjoinedSequences"
          ],
          "additionalProperties": false
       },

diff --git a/schema/merged.yaml b/schema/merged.yaml
@@ -171,10 +171,10 @@ $defs:
           the same reference sequence as adjacent members. Alleles should not have
           overlapping or adjacent coordinates with neighboring Alleles. Neighboring
           alleles should be ordered  by ascending coordinates, unless represented
-          on a DNA inversion (following an end-defined sequence  terminal), in which
-          case they should be ordered in descending coordinates. Sequence references
-          MUST be consistent for all members between and including the end of one
-          Adjacency and the beginning of  another.
+          on a DNA inversion (following an Adjacency with  end-defined adjoinedSequences),
+          in which case they should be ordered in descending coordinates.  Sequence
+          references MUST be consistent for all members between and including the
+          end of one  Adjacency and the beginning of another.
     required:
     - members
     additionalProperties: false
@@ -699,12 +699,12 @@ $defs:
     ga4ghDigest:
       prefix: AJ
       keys:
+      - adjoinedSequences
       - linker
-      - sequenceTerminals
       - type
-    description: The `Adjacency` class represents the termination of a sequence and
-      (when present) the beginning of an adjacent sequence, potentially with an intervening
-      linker sequence.
+    description: The `Adjacency` class can represent either the termination of a sequence
+      or the adjoining of the end of a sequence with the beginning of an adjacent
+      sequence, potentially with an intervening linker sequence.
     type: object
     properties:
       id:
@@ -739,25 +739,26 @@ $defs:
         ordered: false
         items:
           $ref: '#/$defs/Expression'
-      sequenceTerminals:
+      adjoinedSequences:
         type: array
         uniqueItems: false
         ordered: true
         items:
           oneOf:
           - $ref: '#/$defs/IRI'
           - $ref: '#/$defs/SequenceLocation'
-        description: Sequence terminals involved in the adjacency.
+        description: The terminal sequence or pair of adjoined sequences that defines
+          in the adjacency.
         minItems: 1
         maxItems: 2
       linker:
-        description: A linker sequence found between the sequence terminals.
+        description: The sequence found between adjoined sequences.
         oneOf:
         - $ref: '#/$defs/LengthExpression'
         - $ref: '#/$defs/LiteralSequenceExpression'
         - $ref: '#/$defs/ReferenceLengthExpression'
     required:
-    - sequenceTerminals
+    - adjoinedSequences
     additionalProperties: false
   Coding:
     type: object

diff --git a/schema/vrs-source.yaml b/schema/vrs-source.yaml
@@ -178,10 +178,10 @@ $defs:
           A list of :ref:`Alleles <Allele>` and :ref:`Adjacencies <Adjacency>` that comprise a Haplotype. 
           Members must share the same reference sequence as adjacent members. Alleles should not have
           overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered 
-          by ascending coordinates, unless represented on a DNA inversion (following an end-defined sequence 
-          terminal), in which case they should be ordered in descending coordinates. Sequence references MUST
-          be consistent for all members between and including the end of one Adjacency and the beginning of 
-          another.
+          by ascending coordinates, unless represented on a DNA inversion (following an Adjacency with 
+          end-defined adjoinedSequences), in which case they should be ordered in descending coordinates. 
+          Sequence references MUST be consistent for all members between and including the end of one 
+          Adjacency and the beginning of another.
     required: [ "members" ]
 
   # - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
@@ -558,32 +558,72 @@ $defs:
       prefix: AJ
       keys:
         - type
-        - sequenceTerminals
+        - adjoinedSequences
         - linker
     inherits: MolecularVariation
     description:
-      The `Adjacency` class represents the termination of a sequence and (when present)
-      the beginning of an adjacent sequence, potentially with an intervening linker sequence.
+      The `Adjacency` class can represent either the termination of a sequence 
+      or the adjoining of the end of a sequence with the beginning of an
+      adjacent sequence, potentially with an intervening linker sequence.
     type: object
     properties:
       type:
         type: string
         const: Adjacency
         default: Adjacency
         description: MUST be "Adjacency".
-      sequenceTerminals:
+      adjoinedSequences:
         type: array
         uniqueItems: false
         ordered: true
         items:
           oneOf:
           - $refCurie: gks.core:IRI
           - $ref: '#/$defs/Location'
-        description: Sequence terminals involved in the adjacency.
+        description: The terminal sequence or pair of adjoined sequences that defines in the adjacency.
         minItems: 1
         maxItems: 2
       linker:
         $ref: '#/$defs/SequenceExpression'
-        description: A linker sequence found between the sequence terminals.
+        description: The sequence found between adjoined sequences.
+#      homology:
+#        # Only valid for breakends=2
+#        type: boolean
+#        default: false
+#        description:
+#          A flag indicating whether the location interval of the breakend
+#          is due to the sequences at the breakends being homologous or
+#          whether the interval is due to uncertainty regarding the actual
+#          locations of the breakends.
+#      terminal:
+#        # TODO: can the schema encode a constraint that a terminal breakend cannot
+#        # be part of a breakpoint?
+#        type: boolean
+#        default: false
+#        description:
+#          # Only valid for breakends=1
+#          Indicates the end of the molecule
     required:
-      - sequenceTerminals
+      - adjoinedSequences
+
+#  Event:
+#    description:
+#      An event that results in a set of variants.
+#    type: object
+#    properties:
+#      type:
+#        type: string
+#        const: Event
+#        default: Event
+#        description: MUST be "Event"
+#      variants:
+#        $ref: '#/definitions/VariationSet'
+#      classification:
+#        # TODO: what event ontology should we use?
+#        type: string
+#        description: Category of event
+#    required:
+#      - type
+#      - variants
+#      - classification
+#    additionalProperties: true
diff --git a/schema/vrs.json b/schema/vrs.json
@@ -242,7 +242,7 @@
                      }
                   ]
                },
-               "description": "A list of Alleles that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an end-defined sequence  terminal), in which case they should be ordered in descending coordinates. Sequence references MUST be consistent for all members between and including the end of one Adjacency and the beginning of  another."
+               "description": "A list of Alleles that comprise a Haplotype.  Members must share the same reference sequence as adjacent members. Alleles should not have overlapping or adjacent coordinates with neighboring Alleles. Neighboring alleles should be ordered  by ascending coordinates, unless represented on a DNA inversion (following an Adjacency with  end-defined adjoinedSequences), in which case they should be ordered in descending coordinates.  Sequence references MUST be consistent for all members between and including the end of one  Adjacency and the beginning of another."
             }
          },
          "required": [
@@ -916,12 +916,12 @@
          "ga4ghDigest": {
             "prefix": "AJ",
             "keys": [
+               "adjoinedSequences",
                "linker",
-               "sequenceTerminals",
                "type"
             ]
          },
-         "description": "The `Adjacency` class represents the termination of a sequence and (when present) the beginning of an adjacent sequence, potentially with an intervening linker sequence.",
+         "description": "The `Adjacency` class can represent either the termination of a sequence or the adjoining of the end of a sequence with the beginning of an adjacent sequence, potentially with an intervening linker sequence.",
          "type": "object",
          "properties": {
             "id": {
@@ -961,7 +961,7 @@
                   "$ref": "#/$defs/Expression"
                }
             },
-            "sequenceTerminals": {
+            "adjoinedSequences": {
                "type": "array",
                "uniqueItems": false,
                "ordered": true,
@@ -975,12 +975,12 @@
                      }
                   ]
                },
-               "description": "Sequence terminals involved in the adjacency.",
+               "description": "The terminal sequence or pair of adjoined sequences that defines in the adjacency.",
                "minItems": 1,
                "maxItems": 2
             },
             "linker": {
-               "description": "A linker sequence found between the sequence terminals.",
+               "description": "The sequence found between adjoined sequences.",
                "oneOf": [
                   {
                      "$ref": "#/$defs/LengthExpression"
@@ -995,7 +995,7 @@
             }
          },
          "required": [
-            "sequenceTerminals"
+            "adjoinedSequences"
          ],
          "additionalProperties": false
       }