From 52bda0f6b3bb3681f5867d836ec56c4d8afc394d Mon Sep 17 00:00:00 2001
From: Kedi Cao <kedic715@gmail.com>
Date: Mon, 24 Mar 2025 17:34:07 +0100
Subject: [PATCH] save distribution analysis

---
 snakemodules/analysis.smk                            |  3 ++-
 snakemodules/notebooks/content_distribution.py.ipynb | 11 +++++++++++
 2 files changed, 13 insertions(+), 1 deletion(-)

diff --git a/snakemodules/analysis.smk b/snakemodules/analysis.smk
index 35a08af..0806bef 100644
--- a/snakemodules/analysis.smk
+++ b/snakemodules/analysis.smk
@@ -417,7 +417,8 @@ rule assembly_analysis:
         len = RESULTS_DIR + "/contig_length_dist.pdf",
         gc = RESULTS_DIR + "/gc_content_dist.pdf",
         len_txt = RESULTS_DIR + "/distribution_length.txt",
-        gc_txt = RESULTS_DIR + "/distribution_gc.txt"
+        gc_txt = RESULTS_DIR + "/distribution_gc.txt",
+        distribution = RESULTS_DIR + "/sample_distribution_info.txt"
     conda:
         os.path.join(WORKFLOW_PATH,"snakemodules/envs/notebooks.yml")
     benchmark:
diff --git a/snakemodules/notebooks/content_distribution.py.ipynb b/snakemodules/notebooks/content_distribution.py.ipynb
index 891d75f..f91d0e5 100644
--- a/snakemodules/notebooks/content_distribution.py.ipynb
+++ b/snakemodules/notebooks/content_distribution.py.ipynb
@@ -105,6 +105,17 @@
     "sample_list, sample_dict = calculator.process_sequences(sample_seq, sample_names)\n"
    ]
   },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "with open(snakemake.output.distribution,\"w\") as outfile:\n",
+    "    json.dump(sample_list, outfile, indent=4)\n"
+   ]
+  },
   {
    "cell_type": "markdown",
    "metadata": {},
-- 
GitLab