Merge pull request #75 from Clinical-Genomics/remove_accession

Do not parse dbSNP IDs as Accession key/values

CHANGELOG.md

@@ -1,6 +1,8 @@
 ## [unreleased]
 ### Changed
 - Provide the URL to the prod service running on the Clinical Genomics server instead of the stage one on README page
+### Fixed
+- Do not parse dbSNP IDs as `Accession` key/values
 
 ## [2.1]
 ### Added

preClinVar/demo/__init__.py

@@ -5,7 +5,6 @@
 variants_old_csv = "Variant_before_221121.csv"
 
 variants_hgvs_csv = "Variant_snv_hgvs.csv"
-variants_accession_csv = "Variant_accession.csv"
 variants_sv_breakpoints_csv = "Variant_sv_breakpoints.csv"
 variants_sv_range_coords_csv = "Variant_sv_range_coords.csv"
 casedata_snv_csv = "CaseData_snv.csv"
@@ -18,7 +17,6 @@
 variants_old_csv_path = pkg_resources.resource_filename(
     "preClinVar", "/".join(["demo", variants_old_csv])
 )
-
 casedata_snv_csv_path = pkg_resources.resource_filename(
     "preClinVar", "/".join(["demo", casedata_snv_csv])
 )
@@ -28,9 +26,6 @@
 variants_hgvs_csv_path = pkg_resources.resource_filename(
     "preClinVar", "/".join(["demo", variants_hgvs_csv])
 )
-variants_accession_csv_path = pkg_resources.resource_filename(
-    "preClinVar", "/".join(["demo", variants_accession_csv])
-)
 variants_sv_breakpoints_csv_path = pkg_resources.resource_filename(
     "preClinVar", "/".join(["demo", variants_sv_breakpoints_csv])
 )

preClinVar/file_parser.py

@@ -197,10 +197,6 @@ def _set_chrom_coordinates(variant_dict):
         coords(dict)
     """
     coords = {}
-    accession = variant_dict.get("Variation identifiers")
-    if accession:  # example: rs116916706
-        coords["accession"] = accession
-        return coords
 
     # Parse coordinates from file instead
     if variant_dict.get("Variant type"):  # SV variant

tests/test_main.py

@@ -15,8 +15,6 @@
     casedata_sv_csv,
     casedata_sv_csv_path,
     subm_json_path,
-    variants_accession_csv,
-    variants_accession_csv_path,
     variants_hgvs_csv,
     variants_hgvs_csv_path,
     variants_old_csv,
@@ -180,28 +178,6 @@ def test_csv_2_json_hgvs():
     assert json_resp["clinvarSubmission"][0]["variantSet"]["variant"][0]["hgvs"]
 
 
-def test_csv_2_json_accession():
-    """Test csv_2_json endpoint with a Variant file containing a SNV described by accession ID (example: rs116916706)"""
-
-    # GIVEN a POST request to the endpoint with multipart-encoded files:
-    # (https://requests.readthedocs.io/en/latest/user/advanced/#post-multiple-multipart-encoded-files)
-    files = [
-        ("files", (variants_accession_csv, open(variants_accession_csv_path, "rb"))),
-        ("files", (casedata_snv_csv, open(casedata_snv_csv_path, "rb"))),
-    ]
-
-    # THEN the response should be successful (code 200)
-    response = client.post("/csv_2_json", params=OPTIONAL_PARAMETERS, files=files)
-    assert response.status_code == 200
-
-    # AND it should be a json object with the expected fields
-    json_resp = response.json()
-    assert json_resp["clinvarSubmission"][0]["variantSet"]["variant"][0]["gene"]
-    assert json_resp["clinvarSubmission"][0]["variantSet"]["variant"][0]["chromosomeCoordinates"][
-        "accession"
-    ]
-
-
 def test_csv_2_json_SV_breakpoints():
     """Test csv_2_json endpoint with a Variant file containing a SV described by exact coordinates (breakpoints)"""