feat: support for more annotations (#2041)

backend/protos/seqvars/protos/output.proto

@@ -156,6 +156,30 @@ message GeneIdentity {
   string gene_symbol = 2;
 }
 
+// Transcript type.
+enum TranscriptType {
+  // Unknown transcript type.
+  TRANSCRIPT_TYPE_UNSPECIFIED = 0;
+  // Coding transcript.
+  TRANSCRIPT_TYPE_CODING = 1;
+  // Non-coding transcript.
+  TRANSCRIPT_TYPE_NON_CODING = 2;
+}
+
+// Location where the variant falls in relation to a transcript.
+enum VariantLocation {
+  // Unspecified location.
+  VARIANT_LOCATION_UNSPECIFIED = 0;
+  // Upstream of gene.
+  VARIANT_LOCATION_UPSTREAM = 1;
+  // Exonic.
+  VARIANT_LOCATION_EXON = 2;
+  // Intronic.
+  VARIANT_LOCATION_INTRON = 3;
+  // Downstream of the gene.
+  VARIANT_LOCATION_DOWNSTREAM = 4;
+}
+
 /// Gene-related consequences of a variant.
 message GeneRelatedConsequences {
   // HGVS. {c,n} code of variant.
@@ -164,6 +188,16 @@ message GeneRelatedConsequences {
   optional string hgvs_p = 2;
   // Predicted variant consequences.
   repeated seqvars.pbs.query.Consequence consequences = 3;
+  // Transcript accession without version.
+  optional string tx_accession = 4;
+  // Transcript version.
+  optional int32 tx_version = 5;
+  // Whether exon or intron is hit.
+  VariantLocation location = 6;
+  // Exon/intron number (1-based).
+  optional int32 rank_ord = 7;
+  // Exon/intron total count.
+  optional int32 rank_total = 8;
 }
 
 // Enumerations with modes of inheritance from HPO.

backend/seqvars/factory_defaults.py

@@ -830,6 +830,41 @@ def create_seqvarsquerypresetsclinvar(faker: Faker) -> list[SeqvarsQueryPresetsC
         name="payload.variant_annotation.gene.consequences.hgvs_p",
         description="HGVS description at protein level",
     ),
+    SeqvarsColumnConfigPydantic(
+        label="Transcript Accession",
+        name="payload.variant_annotation.gene.consequences.tx_accession",
+        description="Transcript accession without version",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Transcript Version",
+        name="payload.variant_annotation.gene.consequences.tx_version",
+        description="Transcript version",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Transcript",
+        name="__tx_accession_version__",
+        description="Transcript accession with version",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Variant Location",
+        name="payload.variant_annotation.gene.consequences.location",
+        description="Variant location with respect to gene",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Variant Location Rank No",
+        name="payload.variant_annotation.gene.consequences.rank_ord",
+        description="Number of exon/intron that variant is in",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Variant Location Rank Total",
+        name="payload.variant_annotation.gene.consequences.rank_total",
+        description="Total number of exons/introns in transcript",
+    ),
+    SeqvarsColumnConfigPydantic(
+        label="Variant Location Rank No/Total",
+        name="__rank__",
+        description="Rank of exon/intron and total",
+    ),
     SeqvarsColumnConfigPydantic(
         label="ClinGen HI",
         name="__clingen_hi__",

backend/seqvars/models/base.py

@@ -2047,6 +2047,19 @@ class GeneIdentityPydantic(pydantic.BaseModel):
     gene_symbol: str
 
 
+class VariantLocationChoice(str, Enum):
+    """Enumeration for the variant location."""
+
+    #: Upstream of gene.
+    UPSTREAM = "upstream"
+    #: Exonic.
+    EXON = "exon"
+    #: Intronic.
+    INTRON = "intron"
+    #: Downstream of gene.
+    DOWNSTREAM = "downstream"
+
+
 class GeneRelatedConsequencesPydantic(pydantic.BaseModel):
     """Store gene-related consequences."""
 
@@ -2056,6 +2069,16 @@ class GeneRelatedConsequencesPydantic(pydantic.BaseModel):
     hgvs_p: typing.Optional[str]
     #: Predicted variant consequences.
     consequences: list[SeqvarsVariantConsequenceChoice]
+    # Transcript accession without version.
+    tx_accession: typing.Optional[str]
+    # Transcript version.
+    tx_version: typing.Optional[int]
+    # Whether exon or intron is hit.
+    location: VariantLocationChoice
+    # Exon/intron number (1-based).
+    rank_ord: typing.Optional[int]
+    # Exon/intron total count.
+    rank_total: typing.Optional[int]
 
 
 class SeqvarsModeOfInheritance(str, Enum):

backend/seqvars/models/protobufs.py

@@ -66,6 +66,7 @@
     SeqvarsVariantTypeChoice,
     SeqvarsVcfVariantPydantic,
     ShetConstraintsPydantic,
+    VariantLocationChoice,
 )
 from seqvars.protos.output_pb2 import (
     AggregateGermlineReviewStatus,
@@ -95,6 +96,7 @@
     ScoreAnnotations,
     ShetConstraints,
     VariantAnnotation,
+    VariantLocation,
     VariantRelatedAnnotation,
     VariantScoreColumn,
     VariantScoreColumnType,
@@ -761,6 +763,20 @@ def _gene_identity_from_protobuf(identity: GeneIdentity) -> GeneIdentityPydantic
     )
 
 
+VARIANT_LOCATION_MAPPING: dict[VariantLocation.ValueType : VariantLocationChoice] = {
+    VariantLocation.VARIANT_LOCATION_UPSTREAM: VariantLocationChoice.UPSTREAM,
+    VariantLocation.VARIANT_LOCATION_EXON: VariantLocationChoice.EXON,
+    VariantLocation.VARIANT_LOCATION_INTRON: VariantLocationChoice.INTRON,
+    VariantLocation.VARIANT_LOCATION_DOWNSTREAM: VariantLocationChoice.DOWNSTREAM,
+}
+
+
+def _location_from_protobuf(
+    location: VariantLocation.ValueType,
+) -> VariantLocationChoice:
+    return VARIANT_LOCATION_MAPPING[location]
+
+
 def _consequences_from_protobuf(
     consequences: GeneRelatedConsequences,
 ) -> GeneRelatedConsequencesPydantic:
@@ -771,6 +787,11 @@ def _consequences_from_protobuf(
             _seqvars_variant_consequence_choice_from_protobuf(csq)
             for csq in consequences.consequences
         ],
+        tx_accession=consequences.tx_accession if consequences.HasField("tx_accession") else None,
+        tx_version=consequences.tx_version if consequences.HasField("tx_version") else None,
+        location=_location_from_protobuf(consequences.location),
+        rank_ord=consequences.rank_ord if consequences.HasField("rank_ord") else None,
+        rank_total=consequences.rank_total if consequences.HasField("rank_total") else None,
     )
 
 

backend/seqvars/protos/output_pb2.pyi

@@ -78,6 +78,68 @@ GENOME_RELEASE_GRCH38: GenomeRelease.ValueType  # 2
 """GRCh38."""
 global___GenomeRelease = GenomeRelease
 
+class _TranscriptType:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _TranscriptTypeEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_TranscriptType.ValueType],
+    builtins.type,
+):  # noqa: F821
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    TRANSCRIPT_TYPE_UNSPECIFIED: _TranscriptType.ValueType  # 0
+    """Unknown transcript type."""
+    TRANSCRIPT_TYPE_CODING: _TranscriptType.ValueType  # 1
+    """Coding transcript."""
+    TRANSCRIPT_TYPE_NON_CODING: _TranscriptType.ValueType  # 2
+    """Non-coding transcript."""
+
+class TranscriptType(_TranscriptType, metaclass=_TranscriptTypeEnumTypeWrapper):
+    """Transcript type."""
+
+TRANSCRIPT_TYPE_UNSPECIFIED: TranscriptType.ValueType  # 0
+"""Unknown transcript type."""
+TRANSCRIPT_TYPE_CODING: TranscriptType.ValueType  # 1
+"""Coding transcript."""
+TRANSCRIPT_TYPE_NON_CODING: TranscriptType.ValueType  # 2
+"""Non-coding transcript."""
+global___TranscriptType = TranscriptType
+
+class _VariantLocation:
+    ValueType = typing.NewType("ValueType", builtins.int)
+    V: typing_extensions.TypeAlias = ValueType
+
+class _VariantLocationEnumTypeWrapper(
+    google.protobuf.internal.enum_type_wrapper._EnumTypeWrapper[_VariantLocation.ValueType],
+    builtins.type,
+):  # noqa: F821
+    DESCRIPTOR: google.protobuf.descriptor.EnumDescriptor
+    VARIANT_LOCATION_UNSPECIFIED: _VariantLocation.ValueType  # 0
+    """Unspecified location."""
+    VARIANT_LOCATION_UPSTREAM: _VariantLocation.ValueType  # 1
+    """Upstream of gene."""
+    VARIANT_LOCATION_EXON: _VariantLocation.ValueType  # 2
+    """Exonic."""
+    VARIANT_LOCATION_INTRON: _VariantLocation.ValueType  # 3
+    """Intronic."""
+    VARIANT_LOCATION_DOWNSTREAM: _VariantLocation.ValueType  # 4
+    """Downstream of the gene."""
+
+class VariantLocation(_VariantLocation, metaclass=_VariantLocationEnumTypeWrapper):
+    """Location where the variant falls in relation to a transcript."""
+
+VARIANT_LOCATION_UNSPECIFIED: VariantLocation.ValueType  # 0
+"""Unspecified location."""
+VARIANT_LOCATION_UPSTREAM: VariantLocation.ValueType  # 1
+"""Upstream of gene."""
+VARIANT_LOCATION_EXON: VariantLocation.ValueType  # 2
+"""Exonic."""
+VARIANT_LOCATION_INTRON: VariantLocation.ValueType  # 3
+"""Intronic."""
+VARIANT_LOCATION_DOWNSTREAM: VariantLocation.ValueType  # 4
+"""Downstream of the gene."""
+global___VariantLocation = VariantLocation
+
 class _ModeOfInheritance:
     ValueType = typing.NewType("ValueType", builtins.int)
     V: typing_extensions.TypeAlias = ValueType
@@ -880,6 +942,11 @@ class GeneRelatedConsequences(google.protobuf.message.Message):
     HGVS_T_FIELD_NUMBER: builtins.int
     HGVS_P_FIELD_NUMBER: builtins.int
     CONSEQUENCES_FIELD_NUMBER: builtins.int
+    TX_ACCESSION_FIELD_NUMBER: builtins.int
+    TX_VERSION_FIELD_NUMBER: builtins.int
+    LOCATION_FIELD_NUMBER: builtins.int
+    RANK_ORD_FIELD_NUMBER: builtins.int
+    RANK_TOTAL_FIELD_NUMBER: builtins.int
     hgvs_t: builtins.str
     """HGVS. {c,n} code of variant."""
     hgvs_p: builtins.str
@@ -891,7 +958,16 @@ class GeneRelatedConsequences(google.protobuf.message.Message):
         seqvars.protos.query_pb2.Consequence.ValueType
     ]:
         """Predicted variant consequences."""
-
+    tx_accession: builtins.str
+    """Transcript accession without version."""
+    tx_version: builtins.int
+    """Transcript version."""
+    location: global___VariantLocation.ValueType
+    """Whether exon or intron is hit."""
+    rank_ord: builtins.int
+    """Exon/intron number (1-based)."""
+    rank_total: builtins.int
+    """Exon/intron total count."""
     def __init__(
         self,
         *,
@@ -900,11 +976,39 @@ class GeneRelatedConsequences(google.protobuf.message.Message):
         consequences: (
             collections.abc.Iterable[seqvars.protos.query_pb2.Consequence.ValueType] | None
         ) = ...,
+        tx_accession: builtins.str | None = ...,
+        tx_version: builtins.int | None = ...,
+        location: global___VariantLocation.ValueType = ...,
+        rank_ord: builtins.int | None = ...,
+        rank_total: builtins.int | None = ...,
     ) -> None: ...
     def HasField(
         self,
         field_name: typing_extensions.Literal[
-            "_hgvs_p", b"_hgvs_p", "_hgvs_t", b"_hgvs_t", "hgvs_p", b"hgvs_p", "hgvs_t", b"hgvs_t"
+            "_hgvs_p",
+            b"_hgvs_p",
+            "_hgvs_t",
+            b"_hgvs_t",
+            "_rank_ord",
+            b"_rank_ord",
+            "_rank_total",
+            b"_rank_total",
+            "_tx_accession",
+            b"_tx_accession",
+            "_tx_version",
+            b"_tx_version",
+            "hgvs_p",
+            b"hgvs_p",
+            "hgvs_t",
+            b"hgvs_t",
+            "rank_ord",
+            b"rank_ord",
+            "rank_total",
+            b"rank_total",
+            "tx_accession",
+            b"tx_accession",
+            "tx_version",
+            b"tx_version",
         ],
     ) -> builtins.bool: ...
     def ClearField(
@@ -914,12 +1018,30 @@ class GeneRelatedConsequences(google.protobuf.message.Message):
             b"_hgvs_p",
             "_hgvs_t",
             b"_hgvs_t",
+            "_rank_ord",
+            b"_rank_ord",
+            "_rank_total",
+            b"_rank_total",
+            "_tx_accession",
+            b"_tx_accession",
+            "_tx_version",
+            b"_tx_version",
             "consequences",
             b"consequences",
             "hgvs_p",
             b"hgvs_p",
             "hgvs_t",
             b"hgvs_t",
+            "location",
+            b"location",
+            "rank_ord",
+            b"rank_ord",
+            "rank_total",
+            b"rank_total",
+            "tx_accession",
+            b"tx_accession",
+            "tx_version",
+            b"tx_version",
         ],
     ) -> None: ...
     @typing.overload
@@ -930,6 +1052,22 @@ class GeneRelatedConsequences(google.protobuf.message.Message):
     def WhichOneof(
         self, oneof_group: typing_extensions.Literal["_hgvs_t", b"_hgvs_t"]
     ) -> typing_extensions.Literal["hgvs_t"] | None: ...
+    @typing.overload
+    def WhichOneof(
+        self, oneof_group: typing_extensions.Literal["_rank_ord", b"_rank_ord"]
+    ) -> typing_extensions.Literal["rank_ord"] | None: ...
+    @typing.overload
+    def WhichOneof(
+        self, oneof_group: typing_extensions.Literal["_rank_total", b"_rank_total"]
+    ) -> typing_extensions.Literal["rank_total"] | None: ...
+    @typing.overload
+    def WhichOneof(
+        self, oneof_group: typing_extensions.Literal["_tx_accession", b"_tx_accession"]
+    ) -> typing_extensions.Literal["tx_accession"] | None: ...
+    @typing.overload
+    def WhichOneof(
+        self, oneof_group: typing_extensions.Literal["_tx_version", b"_tx_version"]
+    ) -> typing_extensions.Literal["tx_version"] | None: ...
 
 global___GeneRelatedConsequences = GeneRelatedConsequences