go

workflow/notebooks/gene-set-enrichment-analysis.ipynb

@@ -123,13 +123,14 @@
     "go_desc_df = load_go_descriptions()\n",
     "gaf_df = gaf_df.merge(go_desc_df, how='left')\n",
     "\n",
+    "gsea_dict = {}\n",
     "# load differential expression data and perform hypergeometric test\n",
     "for comp in comparisons['contrast']:\n",
     "    de_data = pd.read_csv(f\"results/genediff/{comp}.csv\")\n",
     "    sig_genes = de_data.query(\"padj < 0.05 and FC > 2\")['GeneID']\n",
     "    \n",
-    "    gsea_df = go_hypergeometric(sig_genes, gaf_df)\n",
-    "    gsea_df.to_csv(f\"results/gsea/genediff/{comp}.de.tsv\", sep=\"\\t\")\n",
+    "    gsea_dict[[comp]] = go_hypergeometric(sig_genes, gaf_df)\n",
+    "    gsea_dict[[comp]].to_csv(f\"results/gsea/genediff/{comp}.de.tsv\", sep=\"\\t\")\n",
     "    \n",
     "    if selection:\n",
     "        fst_data = pd.read_csv(f\"results/variantAnalysis/selection/FstPerGene.tsv\", sep=\"\\t\")\n",
@@ -182,7 +183,9 @@
    "outputs": [],
    "source": [
     "pd.set_option(\"display.max_rows\", None, \"display.max_columns\", None)\n",
-    "gsea_df"
+    "\n",
+    "for comp in comparisons['contrast']:\n",
+    "    print(gsea_dict[[comp]][:50])"
    ]
   }
  ],