fix: return result for protein/cdna with no mane data found

- Also creates an enum for vrs sequence location accession status. This
  will be replaced by TranscriptPriority enum in cool-seq-tool once it
is updated

tests/test_normalize.py

@@ -1563,7 +1563,6 @@ async def test_valid_queries(test_handler):
     assert await test_handler.normalize("CCND1 Y44D")
 
     resp = await test_handler.normalize("NC_000002.12:g.73448098_73448100delCTC")
-    assert resp
     assert resp.variation_descriptor.variation.state.sequence == "CTC"
     assert (
         resp.variation_descriptor.variation.id
@@ -1582,6 +1581,11 @@ async def test_valid_queries(test_handler):
         resp = await test_handler.normalize(q)
         assert resp.variation_descriptor, q
 
+    # Test where Mane data not found
+    resp = await test_handler.normalize("ALK p.A1280V")
+    assert resp.variation_descriptor.variation
+    assert resp.warnings == ["Unable to find MANE representation"]
+
 
 @pytest.mark.asyncio
 async def test_no_matches(test_handler):

variation/normalize.py

@@ -5,6 +5,7 @@
 
 from cool_seq_tool.data_sources import SeqRepoAccess, TranscriptMappings, UTADatabase
 from ga4gh.vrsatile.pydantic.vrs_models import CopyChange
+from ga4gh.vrsatile.pydantic.vrsatile_models import MoleculeContext
 from gene.query import QueryHandler as GeneQueryHandler
 
 from variation.classify import Classify
@@ -19,6 +20,7 @@
 from variation.schemas.translation_response_schema import (
     AC_PRIORITY_LABELS,
     TranslationResult,
+    VrsSeqLocAcStatus,
 )
 from variation.to_vrsatile import ToVRSATILE
 from variation.tokenize import Tokenize
@@ -65,7 +67,7 @@ def __init__(
 
     @staticmethod
     def _get_priority_translation_result(
-        translations: List[TranslationResult], ac_status: str
+        translations: List[TranslationResult], ac_status: VrsSeqLocAcStatus
     ) -> Optional[TranslationResult]:
         """Get prioritized translation result. Tries to find translation results with
         the same `vrs_seq_loc_ac_status` as `ac_status`. If more than one translation
@@ -251,6 +253,16 @@ async def normalize(
                         translations, ac_status
                     )
                     if translation_result:
+                        if (
+                            translation_result.vrs_seq_loc_ac_status
+                            == VrsSeqLocAcStatus.NA
+                        ):
+                            molecule_context = (
+                                translation_result.validation_result.classification.molecule_context
+                            )
+                            if molecule_context != MoleculeContext.GENOMIC:
+                                # Only supports protein/cDNA at the moment
+                                warnings.append("Unable to find MANE representation")
                         break
 
                 # Get variation descriptor information

variation/schemas/translation_response_schema.py

@@ -1,4 +1,5 @@
 """Module for Translation Response Schema."""
+from enum import Enum
 from typing import Dict, Optional
 
 from cool_seq_tool.schemas import TranscriptPriorityLabel
@@ -7,21 +8,31 @@
 from variation.schemas.validation_response_schema import ValidationResult
 
 
+class VrsSeqLocAcStatus(str, Enum):
+    """Create enum for VRS SequenceLocation accession status.
+    Order when defining matters.
+        First has highest priority, last has lowest priority
+    Once issue-191 is resolved in cool-seq-tool, we should use the
+    TranscriptPriorityLabel enum
+    """
+
+    MANE_SELECT = TranscriptPriorityLabel.MANESelect.value
+    MANE_PLUS_CLINICAL = TranscriptPriorityLabel.MANEPlusClinical.value
+    LONGEST_COMPATIBLE_REMAINING = (
+        TranscriptPriorityLabel.LongestCompatibleRemaining.value
+    )
+    GRCH38 = "GRCh38"  # will change to lowercase in cool-seq-tool issue-191
+    NA = "na"
+
+
+AC_PRIORITY_LABELS = [m for m in VrsSeqLocAcStatus.__members__.values()]
+
+
 class TranslationResult(BaseModel):
     """Translation Result"""
 
     vrs_variation: Optional[Dict]
     vrs_seq_loc_ac: Optional[StrictStr]
-    vrs_seq_loc_ac_status: StrictStr = "na"
+    vrs_seq_loc_ac_status: VrsSeqLocAcStatus = VrsSeqLocAcStatus.NA
     og_ac: Optional[StrictStr]
     validation_result: ValidationResult
-
-
-# Define accession priority. First has highest priority, last has lowest priority
-AC_PRIORITY_LABELS = [
-    TranscriptPriorityLabel.MANESelect.value,
-    TranscriptPriorityLabel.MANEPlusClinical.value,
-    TranscriptPriorityLabel.LongestCompatibleRemaining.value,
-    "GRCh38",
-    "na",
-]

variation/translators/genomic_del_dup_base.py

@@ -16,7 +16,10 @@
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.service_schema import ClinVarAssembly
 from variation.schemas.token_response_schema import AltType
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.translators.translator import Translator
 from variation.utils import get_assembly
@@ -107,7 +110,7 @@ async def translate(
 
         grch38_data = None
         vrs_variation = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if do_liftover or endpoint_name == Endpoint.NORMALIZE:
             errors = []

variation/translators/genomic_delins.py

@@ -12,7 +12,10 @@
 )
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.token_response_schema import AltType
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.translators.translator import Translator
 
@@ -54,7 +57,7 @@ async def translate(
         classification: GenomicDelInsClassification = validation_result.classification
         vrs_allele = None
         vrs_seq_loc_ac = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if endpoint_name == Endpoint.NORMALIZE:
             gene = (

variation/translators/genomic_insertion.py

@@ -12,7 +12,10 @@
 )
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.token_response_schema import AltType
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.translators.translator import Translator
 
@@ -57,7 +60,7 @@ async def translate(
         )
         vrs_allele = None
         vrs_seq_loc_ac = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if endpoint_name == Endpoint.NORMALIZE:
             gene = (

variation/translators/genomic_reference_agree.py

@@ -12,7 +12,10 @@
 )
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.token_response_schema import AltType
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.translators.translator import Translator
 
@@ -56,7 +59,7 @@ async def translate(
         )
         vrs_allele = None
         vrs_seq_loc_ac = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if endpoint_name == Endpoint.NORMALIZE:
             gene = (

variation/translators/genomic_substitution.py

@@ -12,7 +12,10 @@
 )
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.token_response_schema import AltType
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.translators.translator import Translator
 
@@ -59,7 +62,7 @@ async def translate(
         )
         vrs_allele = None
         vrs_seq_loc_ac = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if endpoint_name == Endpoint.NORMALIZE:
             gene = (

variation/translators/translator.py

@@ -11,7 +11,10 @@
 from variation.schemas.classification_response_schema import ClassificationType
 from variation.schemas.normalize_response_schema import HGVSDupDelModeOption
 from variation.schemas.token_response_schema import AltType, GeneToken
-from variation.schemas.translation_response_schema import TranslationResult
+from variation.schemas.translation_response_schema import (
+    TranslationResult,
+    VrsSeqLocAcStatus,
+)
 from variation.schemas.validation_response_schema import ValidationResult
 from variation.validators.genomic_base import GenomicBase
 from variation.vrs_representation import VRSRepresentation
@@ -179,7 +182,7 @@ async def get_p_or_cdna_translation_result(
         """
         vrs_allele = None
         vrs_seq_loc_ac = None
-        vrs_seq_loc_ac_status = "na"
+        vrs_seq_loc_ac_status = VrsSeqLocAcStatus.NA
 
         if endpoint_name == Endpoint.NORMALIZE:
             mane = await self.mane_transcript.get_mane_transcript(
@@ -205,7 +208,8 @@ async def get_p_or_cdna_translation_result(
                     cds_start=mane.get("coding_start_site", None),
                     alt=alt,
                 )
-        else:
+
+        if not vrs_allele:
             vrs_seq_loc_ac = validation_result.accession
             vrs_allele = self.vrs.to_vrs_allele(
                 vrs_seq_loc_ac,