From 458376b2e4975ae361eacffdbd7ff388ca310d34 Mon Sep 17 00:00:00 2001
From: rxu17 <26471741+rxu17@users.noreply.github.com>
Date: Fri, 24 Jan 2025 02:08:48 -0800
Subject: [PATCH] add casing support for status col

---
 genie/database_to_staging.py      | 16 +++++++++++-----
 tests/test_database_to_staging.py | 11 ++++++++++-
 2 files changed, 21 insertions(+), 6 deletions(-)

diff --git a/genie/database_to_staging.py b/genie/database_to_staging.py
index 1e817d6a..4c1d3576 100644
--- a/genie/database_to_staging.py
+++ b/genie/database_to_staging.py
@@ -683,18 +683,24 @@ def store_gene_panel_files(
 
 
 def filter_out_germline_variants(
-    input_data: pd.DataFrame, status_col: str
+    input_data: pd.DataFrame, status_col_str: str
 ) -> pd.DataFrame:
-    """Filters out germline variants given a status col. Genie pipeline
-        cannot have any of these variants.
+    """Filters out germline variants given a status col str. Genie pipeline
+        cannot have any of these variants. NOTE: We have to search for the 
+        status column because there's no column name validation in the release
+        steps so the status column may have different casing.
 
     Args:
         input_data (pd.DataFrame): input data with germline variants to filter out
-        status_col (str): status column for the data
+        status_col_str (str): search string for the status column for the data
 
     Returns:
         pd.DataFrame: filtered out germline variant data
     """
+    # find status col SV_Status
+    status_col = [
+        col for col in input_data.columns if col.lower() == status_col_str.lower()
+    ][0]
     return input_data[input_data[status_col] != "GERMLINE"].reset_index(drop=True)
 
 
@@ -750,7 +756,7 @@ def store_sv_files(
                 )
 
     sv_df = sv_df[sv_df["SAMPLE_ID"].isin(keep_for_merged_consortium_samples)]
-    sv_df = filter_out_germline_variants(input_data=sv_df, status_col="SV_STATUS")
+    sv_df = filter_out_germline_variants(input_data=sv_df)
     sv_df.rename(columns=transform._col_name_to_titlecase, inplace=True)
     sv_text = process_functions.removePandasDfFloat(sv_df)
     sv_path = os.path.join(GENIE_RELEASE_DIR, "data_sv.txt")
diff --git a/tests/test_database_to_staging.py b/tests/test_database_to_staging.py
index 70d3c0c8..f1c22f7c 100644
--- a/tests/test_database_to_staging.py
+++ b/tests/test_database_to_staging.py
@@ -140,8 +140,17 @@ def test_store_assay_info_files(syn):
                 dict(SV_STATUS=["SOMATIC", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
             ),
         ),
+        (
+            pd.DataFrame(
+                dict(SV_Status=["GERMLINE", "SOMATIC"], Sample_ID=["GENIE-1", "GENIE-2"])
+            ),
+            "SV_STATUS",
+            pd.DataFrame(
+                dict(SV_Status=["SOMATIC"], Sample_ID=["GENIE-2"])
+            ),
+        ),
     ],
-    ids=["all_germline", "some_germline", "no_germline"],
+    ids=["all_germline", "some_germline", "no_germline", "diff_status_col_case"],
 )
 def test_that_filter_out_germline_variants_returns_expected(
     input_data, filter_col, expected_result