identify unique genes

sophie22 · May 7, 2022 · 613aec6 · 613aec6
1 parent d453684
commit 613aec6
Showing 1 changed file with 6 additions and 0 deletions.
diff --git a/genes_coverage.py b/genes_coverage.py
@@ -21,3 +21,9 @@
 sambamba_df["ExonLength"] = sambamba_df["EndPosition"] - sambamba_df["StartPosition"]
 # Calculate number of bases above 30x coverage
 sambamba_df["AboveThreshold"] = sambamba_df[coverage_column] / 100 * sambamba_df["ExonLength"]
+
+# Identify unique genes
+panel_genes = sambamba_df["GeneSymbol;Accession"].unique().tolist()
+# Split 'GeneSymbol;Accession' into separate columns
+sambamba_df[["GeneSymbol", "Accession"]] = sambamba_df[
+    "GeneSymbol;Accession"].str.split(';', 1, expand=True)