make sure that every gene base exists once in gene id file (addressin… (

#155) * make sure that every gene base exists once in gene id file (addressing #154) * fixup! Format Python code with psf/black pull_request --------- Co-authored-by: “Marcel-Mueck” <“mueckm1@gmail.com”> Co-authored-by: PMBio <PMBio@users.noreply.github.com>
PMBio · Feb 12, 2025 · 0d91fc9 · 0d91fc9
1 parent a85ee57
commit 0d91fc9
Show file tree

Hide file tree

Showing 4 changed files with 9 additions and 0 deletions.
diff --git a/deeprvat/annotations/annotations.py b/deeprvat/annotations/annotations.py
@@ -2022,6 +2022,10 @@ def create_gene_id_file(gtf_filepath: str, out_file: str):
         .reset_index()
         .rename(columns={"gene_id": "gene", "index": "id"})
     )
+    cols = gtf.columns
+    gtf[["gene_base", "feature"]] = gtf["gene"].str.split(".", expand=True)
+    gtf.drop_duplicates(subset=["gene_base"], inplace=True)
+    gtf = gtf[cols]
     gtf.to_parquet(out_file)
 
 

diff --git a/tests/annotations/test_annotations.py b/tests/annotations/test_annotations.py
@@ -552,6 +552,11 @@ def test_calculate_maf(test_data_name_dir, annotations, expected, tmp_path):
             "gencode.v44.annotation.gtf.gz",
             "protein_coding_genes.parquet",
         ),
+        (
+            "create_gene_id_file_GRCh37_47",
+            "gencode.v47lift37.basic.annotation.gtf.gz",
+            "protein_coding_genes.parquet",
+        ),
     ],
 )
 def test_create_gene_id_file(test_data_name_dir, gtf_file, expected, tmp_path):

diff --git a/...a/create_gene_id_file/create_gene_id_file_GRCh37_47/expected/protein_coding_genes.parquet b/...a/create_gene_id_file/create_gene_id_file_GRCh37_47/expected/protein_coding_genes.parquet
diff --git a/...ene_id_file/create_gene_id_file_GRCh37_47/input/gencode.v47lift37.basic.annotation.gtf.gz b/...ene_id_file/create_gene_id_file_GRCh37_47/input/gencode.v47lift37.basic.annotation.gtf.gz