Merge branch 'issue-17-stub-vlm-request-endpoint' into issue-13-build-vlm-network-response

Author: jennifer-bowser

src/anyvlm/functions/get_caf.py

@@ -5,19 +5,19 @@
 from anyvlm.anyvar.base_client import BaseAnyVarClient
 from anyvlm.utils.types import (
     ChromosomeName,
-    GenomicSequence,
     GrcAssemblyId,
-    UscsAssemblyBuild,
+    NucleotideSequence,
+    UcscAssemblyBuild,
 )
 
 
 def get_caf(
     anyvar_client: BaseAnyVarClient,
-    assembly_id: GrcAssemblyId | UscsAssemblyBuild,
+    assembly_id: GrcAssemblyId | UcscAssemblyBuild,
     reference_name: ChromosomeName,
     start: int,
-    reference_bases: GenomicSequence,
-    alternate_bases: GenomicSequence,
+    reference_bases: NucleotideSequence,
+    alternate_bases: NucleotideSequence,
 ) -> list[CohortAlleleFrequencyStudyResult]:
     """Retrieve Cohort Allele Frequency data for all known variants matching provided search params
 

src/anyvlm/restapi/vlm.py

@@ -16,9 +16,9 @@
 from anyvlm.utils.types import (
     ChromosomeName,
     EndpointTag,
-    GenomicSequence,
     GrcAssemblyId,
-    UscsAssemblyBuild,
+    NucleotideSequence,
+    UcscAssemblyBuild,
 )
 
 
@@ -36,33 +36,24 @@ def ingest_vcf(vcf_path: Path) -> None:
     description="Search for a single sequence variant and receive allele counts by zygosity, in accordance with the Variant-Level Matching protocol",
     tags=[EndpointTag.SEARCH],
 )
+# ruff: noqa: D103, N803 (allow camelCase args and don't require docstrings)
 def variant_counts(
     request: Request,
-    assemblyId: Annotated[  # noqa: N803
-        GrcAssemblyId | UscsAssemblyBuild,
+    assemblyId: Annotated[
+        GrcAssemblyId | UcscAssemblyBuild,
         Query(..., description="Genome reference assembly"),
     ],
-    referenceName: Annotated[  # noqa: N803
+    referenceName: Annotated[
         ChromosomeName, Query(..., description="Chromosome with optional 'chr' prefix")
     ],
     start: Annotated[int, Query(..., description="Variant position")],
-    referenceBases: Annotated[  # noqa: N803
-        GenomicSequence, Query(..., description="Genomic bases ('T', 'AC', etc.)")
+    referenceBases: Annotated[
+        NucleotideSequence, Query(..., description="Genomic bases ('T', 'AC', etc.)")
     ],
-    alternateBases: Annotated[  # noqa: N803
-        GenomicSequence, Query(..., description="Genomic bases ('T', 'AC', etc.)")
+    alternateBases: Annotated[
+        NucleotideSequence, Query(..., description="Genomic bases ('T', 'AC', etc.)")
     ],
 ) -> VlmResponse:
-    """Accept a Variant-Level Matching network request and return allele counts by zygosity.
-
-    :param request: FastAPI `Request` object
-    :param assemblyId: The genome reference assembly. Must be a GRC assembly identifier (e.g., "GRCh38) or a USCS assembly build (e.g., "hg38")
-    :param referenceName: The name of the reference chromosome, with optional 'chr' prefix
-    :param start: The start of the variant's position
-    :param referenceBases: Genomic bases ('T', 'AC', etc.)
-    :param alternateBases: Genomic bases ('T', 'AC', etc.)
-    :return: A VlmResponse object containing cohort allele frequency data. If no matches are found, endpoint will return a status code of 200 with an empty set of results.
-    """
     anyvar_client: BaseAnyVarClient = request.app.state.anyvar_client
     caf_data: list[CohortAlleleFrequencyStudyResult] = get_caf(
         anyvar_client, assemblyId, referenceName, start, referenceBases, alternateBases

src/anyvlm/utils/types.py

@@ -20,57 +20,42 @@ class GrcAssemblyId(StrEnum):
     GRCH38 = "GRCh38"
 
 
-class UscsAssemblyBuild(StrEnum):
-    """Supported USCS assembly builds"""
+class UcscAssemblyBuild(StrEnum):
+    """Supported UCSC assembly builds"""
 
     HG38 = "hg38"
     HG19 = "hg19"
 
 
-GenomicSequence = Annotated[
+NucleotideSequence = Annotated[
     str,
     BeforeValidator(str.upper),
-    StringConstraints(pattern=r"^[AGCT]*$"),
+    StringConstraints(pattern=r"^[ACGTURYKMSWBDHVN]*$"),
 ]
 
 
-def is_valid_chromosome_name(chromosome_name: str) -> bool:
-    """Checks whether or not a provided chromosome name is valid.
-
-    :param chromosome_name: The chromosome name to validate.
-    :return: `True` if the chromosome name is a number between 1-22, or the values "X" or "Y"; else `False`.
-    """
-    min_chromosome_number = 1
-    max_chromosome_number = 22
-    try:
-        return (
-            chromosome_name in {"X", "Y"}
-            or min_chromosome_number <= int(chromosome_name) <= max_chromosome_number
-        )
-    except ValueError:
-        return False
-
-
 def _normalize_chromosome_name(chromosome_name: str) -> str:
     """Normalize a chromosome name. Input must be a string consisting of either a number between 1-22,
-    or 'X' or 'Y'; optionally prefixed with 'chr'.
+    or one of the values 'X', 'Y', or 'MT'; optionally prefixed with 'chr'.
 
     :param chromosome_name: The name of the chromosome to normalize, following the rules stated above.
     :return: The chromosome name, stripped of it's 'chr' prefix if it was added
     """
-    # strip the 'chr' prefix if it was included
-    chromosome_name = (
-        chromosome_name[3:]
-        if chromosome_name.lower().startswith("chr")
-        else chromosome_name
-    ).upper()
-
-    if is_valid_chromosome_name(chromosome_name):
+    chromosome_name = chromosome_name.upper().removeprefix("CHR")
+
+    min_chromosome_number = 1
+    max_chromosome_number = 22
+
+    if chromosome_name in {"X", "Y", "MT"} or (
+        chromosome_name.isdigit()
+        and min_chromosome_number <= int(chromosome_name) <= max_chromosome_number
+    ):
         return chromosome_name
-    error_message = (
-        "Invalid chromosome. Must be 1-22, 'X', or 'Y'; with optional 'chr' prefix."
+
+    raise ValueError(
+        "Invalid chromosome. Must be either a number between 1-22, or "
+        "'one of the values 'X', 'Y', or 'MT'; optionally prefixed with 'chr'."
     )
-    raise ValueError(error_message)
 
 
 ChromosomeName = Annotated[str, BeforeValidator(_normalize_chromosome_name)]