From 6ec0d45baf48eeefa04c79632645c893f128b150 Mon Sep 17 00:00:00 2001
From: Yakov <yt4@sanger.ac.uk>
Date: Tue, 5 Nov 2024 15:30:56 +0000
Subject: [PATCH] fix: do not impute `isProteinCoding` (#902)

* fix: fix col names for imputation

* fix: fix v1

* fix: test
---
 src/gentropy/dataset/l2g_feature_matrix.py        | 5 ++++-
 tests/gentropy/dataset/test_l2g_feature_matrix.py | 2 +-
 2 files changed, 5 insertions(+), 2 deletions(-)

diff --git a/src/gentropy/dataset/l2g_feature_matrix.py b/src/gentropy/dataset/l2g_feature_matrix.py
index 9caa4b58a..f59e1e725 100644
--- a/src/gentropy/dataset/l2g_feature_matrix.py
+++ b/src/gentropy/dataset/l2g_feature_matrix.py
@@ -143,7 +143,10 @@ def fill_na(
         Returns:
             L2GFeatureMatrix: L2G feature matrix dataset
         """
-        cols_to_impute = ["proteinGeneCount500kb", "geneCount500kb", "isProteinCoding"]
+        cols_to_impute = [
+            "proteinGeneCount500kb",
+            "geneCount500kb",
+        ]
         for col in cols_to_impute:
             if col not in self._df.columns:
                 continue
diff --git a/tests/gentropy/dataset/test_l2g_feature_matrix.py b/tests/gentropy/dataset/test_l2g_feature_matrix.py
index f821daaac..4fe338254 100644
--- a/tests/gentropy/dataset/test_l2g_feature_matrix.py
+++ b/tests/gentropy/dataset/test_l2g_feature_matrix.py
@@ -228,7 +228,7 @@ def test_fill_na(spark: SparkSession) -> None:
                 "geneId": "gene3",
                 "proteinGeneCount500kb": 3.5,
                 "geneCount500kb": 9.0,
-                "isProteinCoding": 1.0,
+                "isProteinCoding": 0.0,
                 "anotherFeature": 0.0,
             },
         ],