revert some things

Author: korikuzma

src/anyvlm/anyvar/base_client.py

@@ -35,8 +35,10 @@ def search_by_interval(
         """Get all variation IDs located within the specified range
 
         :param accession: sequence accession
-        :param start: start position for genomic region
-        :param end: end position for genomic region
+        :param start: Inclusive, inter-residue genomic start position of the interval
+            to search
+        :param end: Inclusive, inter-residue genomic end position of the interval to
+            search
         :return: list of matching variant objects
         :raise AnyVarClientError: if connection is unsuccessful during search query
         """

src/anyvlm/anyvar/http_client.py

@@ -65,8 +65,10 @@ def search_by_interval(
         """Get all variation IDs located within the specified range
 
         :param accession: sequence accession
-        :param start: start position for genomic region
-        :param end: end position for genomic region
+        :param start: Inclusive, inter-residue genomic start position of the interval
+            to search
+        :param end: Inclusive, inter-residue genomic end position of the interval to
+            search
         :return: list of matching variant objects
         :raise AnyVarClientError: if connection is unsuccessful during search query
         """

src/anyvlm/anyvar/python_client.py

@@ -44,8 +44,10 @@ def search_by_interval(
         """Get all variation IDs located within the specified range
 
         :param accession: sequence accession
-        :param start: start position for genomic region
-        :param end: end position for genomic region
+        :param start: Inclusive, inter-residue genomic start position of the interval
+            to search
+        :param end: Inclusive, inter-residue genomic end position of the interval to
+            search
         :return: list of matching variant objects
         """
         try:

src/anyvlm/functions/get_caf.py

@@ -7,36 +7,44 @@
 
 from anyvlm.anyvar.base_client import BaseAnyVarClient
 from anyvlm.storage.base_storage import Storage
+from anyvlm.utils.types import ChromosomeName, GrcAssemblyId, UcscAssemblyBuild
 
 
 def get_caf(
-    anyvar: BaseAnyVarClient,
+    anyvar_client: BaseAnyVarClient,
     anyvlm_storage: Storage,
-    accession_id: str,
+    assembly_id: GrcAssemblyId | UcscAssemblyBuild,
+    chromosome_name: ChromosomeName,
     start: int,
     end: int,
 ) -> list[CohortAlleleFrequencyStudyResult]:
-    """Retrieve Cohort Allele Frequency data for all known variants matching provided search params
+    """Retrieve Cohort Allele Frequency data for all known variants matching provided
+    search params
 
-    :param anyvar: AnyVar client (variant lookup)
+    :param anyvar_client: AnyVar client (variant lookup)
     :param anyvlm_storage: AnyVLM Storage (CAF storage and retrieval)
-    :param accession_id: ID for sequence to search upon
-    :param start: start of range search
+    :param assembly_id: The reference assembly to utilize - must be one of: "GRCh37",
+        "GRCh38", "hg38", "hg19"
+    :param chromosome_name: The chromosome to search on, with an optional "chr" prefix
+        - e.g., "1", "chr22", "X", "chrY", etc.
+    :param start: Inclusive, inter-residue genomic start position of the interval to
+        search
+    :param end: Inclusive, inter-residue genomic end position of the interval to search
     :param reference_bases: Genomic bases ('T', 'AC', etc.)
     :param alternate_bases: Genomic bases ('T', 'AC', etc.)
     :return: list of CAFs contained in search interval
     """
-    vrs_variations: list[VrsVariation] = anyvar.search_by_interval(
-        accession_id, start, end
+    vrs_variations: list[VrsVariation] = anyvar_client.search_by_interval(
+        f"{assembly_id}:{chromosome_name}", start, end
     )
     vrs_variations_map: dict[str, Allele] = {
         vrs_variation.id: vrs_variation
         for vrs_variation in vrs_variations
         if vrs_variation.id and isinstance(vrs_variation, Allele)
     }
 
-    cafs: list[CohortAlleleFrequencyStudyResult] = anyvlm_storage.get_caf_by_vrs_ids(
-        list(vrs_variations_map)
+    cafs: list[CohortAlleleFrequencyStudyResult] = (
+        anyvlm_storage.get_caf_by_vrs_allele_ids(list(vrs_variations_map))
     )
 
     for caf in cafs:

src/anyvlm/storage/base_storage.py

@@ -32,12 +32,12 @@ def add_allele_frequencies(self, caf: CohortAlleleFrequencyStudyResult) -> None:
         """
 
     @abstractmethod
-    def get_caf_by_vrs_ids(
-        self, vrs_ids: list[str]
+    def get_caf_by_vrs_allele_ids(
+        self, vrs_allele_ids: list[str]
     ) -> list[CohortAlleleFrequencyStudyResult]:
-        """Retrieve cohort allele frequency study results by VRS IDs
+        """Retrieve cohort allele frequency study results by VRS Allele IDs
 
-        :param vrs_ids: List of VRS variation IDs
+        :param vrs_allele_ids: List of VRS Allele IDs
         :return: List of cohort allele frequency study results matching given VRS
-            variation IDs. Will use iriReference for focusAllele
+            Allele IDs. Will use iriReference for focusAllele
         """

src/anyvlm/storage/postgres.py

@@ -47,14 +47,14 @@ def add_allele_frequencies(self, caf: CohortAlleleFrequencyStudyResult) -> None:
         with self.session_factory() as session, session.begin():
             session.execute(stmt, db_entity.to_dict())
 
-    def get_caf_by_vrs_ids(
+    def get_caf_by_vrs_allele_ids(
         self, vrs_ids: list[str]
     ) -> list[CohortAlleleFrequencyStudyResult]:
-        """Retrieve cohort allele frequency study results by VRS IDs
+        """Retrieve cohort allele frequency study results by VRS Allele IDs
 
-        :param vrs_ids: List of VRS variation IDs
+        :param vrs_allele_ids: List of VRS Allele IDs
         :return: List of cohort allele frequency study results matching given VRS
-            variation IDs. Will use iriReference for focusAllele
+            Allele IDs. Will use iriReference for focusAllele
         """
         cafs: list[CohortAlleleFrequencyStudyResult] = []
         with self.session_factory() as session:

tests/integration/functions/cassettes/test_get_caf/test_get_caf_no_results.yaml

@@ -11,4 +11,25 @@ interactions:
     status:
       code: 404
       message: NOT FOUND
+- request:
+    body: null
+    headers: {}
+    method: GET
+    uri: http://localhost:5000/seqrepo/1/metadata/GRCh37:Y
+  response:
+    body:
+      string: "{\n  \"added\": \"2016-08-24T09:46:03Z\",\n  \"aliases\": [\n    \"GRCh37:Y\",\n
+        \   \"GRCh37:chrY\",\n    \"GRCh37.p10:Y\",\n    \"GRCh37.p10:chrY\",\n    \"GRCh37.p11:Y\",\n
+        \   \"GRCh37.p11:chrY\",\n    \"GRCh37.p12:Y\",\n    \"GRCh37.p12:chrY\",\n
+        \   \"GRCh37.p13:Y\",\n    \"GRCh37.p13:chrY\",\n    \"GRCh37.p2:Y\",\n    \"GRCh37.p2:chrY\",\n
+        \   \"GRCh37.p5:Y\",\n    \"GRCh37.p5:chrY\",\n    \"GRCh37.p9:Y\",\n    \"GRCh37.p9:chrY\",\n
+        \   \"MD5:1e86411d73e6f00a10590f976be01623\",\n    \"NCBI:NC_000024.9\",\n
+        \   \"refseq:NC_000024.9\",\n    \"SEGUID:HRECPk8NXaTlO3q9aTwyJC10bpw\",\n
+        \   \"SHA1:1d11023e4f0d5da4e53b7abd693c32242d746e9c\",\n    \"VMC:GS_BT7QyW5iXaX_1PSX-msSGYsqRdMKqkj-\",\n
+        \   \"sha512t24u:BT7QyW5iXaX_1PSX-msSGYsqRdMKqkj-\",\n    \"ga4gh:SQ.BT7QyW5iXaX_1PSX-msSGYsqRdMKqkj-\"\n
+        \ ],\n  \"alphabet\": \"ACGNT\",\n  \"length\": 59373566\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
 version: 1

tests/integration/functions/cassettes/test_get_caf/test_get_caf_results_returned.yaml

@@ -0,0 +1,25 @@
+interactions:
+- request:
+    body: null
+    headers: {}
+    method: GET
+    uri: http://localhost:5000/seqrepo/1/metadata/GRCh38:chrY
+  response:
+    body:
+      string: "{\n  \"added\": \"2016-08-27T23:57:42Z\",\n  \"aliases\": [\n    \"GRCh38:Y\",\n
+        \   \"GRCh38:chrY\",\n    \"GRCh38.p1:Y\",\n    \"GRCh38.p1:chrY\",\n    \"GRCh38.p10:Y\",\n
+        \   \"GRCh38.p10:chrY\",\n    \"GRCh38.p11:Y\",\n    \"GRCh38.p11:chrY\",\n
+        \   \"GRCh38.p12:Y\",\n    \"GRCh38.p12:chrY\",\n    \"GRCh38.p2:Y\",\n    \"GRCh38.p2:chrY\",\n
+        \   \"GRCh38.p3:Y\",\n    \"GRCh38.p3:chrY\",\n    \"GRCh38.p4:Y\",\n    \"GRCh38.p4:chrY\",\n
+        \   \"GRCh38.p5:Y\",\n    \"GRCh38.p5:chrY\",\n    \"GRCh38.p6:Y\",\n    \"GRCh38.p6:chrY\",\n
+        \   \"GRCh38.p7:Y\",\n    \"GRCh38.p7:chrY\",\n    \"GRCh38.p8:Y\",\n    \"GRCh38.p8:chrY\",\n
+        \   \"GRCh38.p9:Y\",\n    \"GRCh38.p9:chrY\",\n    \"MD5:447f54a94ef525e42ce58d3e0c48b3f8\",\n
+        \   \"NCBI:NC_000024.10\",\n    \"refseq:NC_000024.10\",\n    \"SEGUID:Aa5HItLyfT0VRdz6r0SjqaidoCQ\",\n
+        \   \"SHA1:01ae4722d2f27d3d1545dcfaaf44a3a9a89da024\",\n    \"VMC:GS_8_liLu1aycC0tPQPFmUaGXJLDs5SbPZ5\",\n
+        \   \"sha512t24u:8_liLu1aycC0tPQPFmUaGXJLDs5SbPZ5\",\n    \"ga4gh:SQ.8_liLu1aycC0tPQPFmUaGXJLDs5SbPZ5\"\n
+        \ ],\n  \"alphabet\": \"ACGNRSTWY\",\n  \"length\": 57227415\n}\n"
+    headers: {}
+    status:
+      code: 200
+      message: OK
+version: 1

tests/integration/functions/test_get_caf.py

@@ -8,20 +8,23 @@
 from anyvlm.anyvar.python_client import PythonAnyVarClient
 from anyvlm.functions.get_caf import get_caf
 from anyvlm.storage.postgres import PostgresObjectStore
+from anyvlm.utils.types import GrcAssemblyId
 
 POSITION = 2781760
-REFGET_AC = "SQ.8_liLu1aycC0tPQPFmUaGXJLDs5SbPZ5"
-GA4GH_SEQ_ID = f"ga4gh:{REFGET_AC}"
+ASSEMBLY = GrcAssemblyId.GRCH38
+CHROMOSOME = "chrY"
+CHROMOSOME_IDENTIFIER = f"{ASSEMBLY}:{CHROMOSOME}"
+GA4GH_SEQ_ID = f"ga4gh:{CHROMOSOME_IDENTIFIER}"
 
 
 @pytest.fixture
 def alleles_to_add(alleles: dict):
-    """Create test fixture for alleles whose sequence reference matches REFGET_AC"""
+    """Create test fixture for alleles whose sequence reference matches CHROMOSOME_IDENTIFIER"""
     return [
         value["variation"]
         for value in alleles.values()
         if value["variation"]["location"]["sequenceReference"]["refgetAccession"]
-        == REFGET_AC
+        == CHROMOSOME_IDENTIFIER
     ]
 
 
@@ -70,7 +73,8 @@ def test_get_caf_results_returned(
     cafs = get_caf(
         anyvar_populated_python_client,
         populated_postgres_storage,
-        GA4GH_SEQ_ID,
+        ASSEMBLY,
+        CHROMOSOME,
         POSITION,
         POSITION,
     )
@@ -91,7 +95,8 @@ def test_get_caf_no_results(
     cafs = get_caf(
         anyvar_populated_python_client,
         populated_postgres_storage,
-        "GRCh45.p1:Y",
+        GrcAssemblyId.GRCH37,
+        "Y",
         POSITION,
         POSITION,
     )