Clean up

Author: maxim-k

appyters/Bulk_RNA_seq/RNA_seq_Analysis_Pipeline.ipynb

@@ -41,6 +41,7 @@
     "import base64  \n",
     "import json\n",
     "from pandas.api.types import CategoricalDtype\n",
+    "from collections import defaultdict\n",
     "\n",
     "# Visualization\n",
     "import plotly\n",
@@ -327,7 +328,7 @@
     "\n",
     "{% set enrichr_libraries = MultiChoiceField(\n",
     "    name='enrichr_libraries',\n",
-    "    label='Enrichr Libraries (upto 2)',\n",
+    "    label='Enrichr Libraries',\n",
     "    descriptions='Enrichr libraries to be visualized. Select one or two libraries',\n",
     "    choices=['Gene Ontology',\n",
     "            'Pathway',\n",
@@ -423,10 +424,7 @@
     "warnings.filterwarnings('ignore')\n",
     "random.seed(0)\n",
     "pandas2ri.activate()\n",
-    "notebook_metadata = dict()\n",
-    "notebook_metadata[\"tables\"] = dict()\n",
-    "notebook_metadata[\"figures\"] = dict()\n",
-    "notebook_metadata[\"input_parameters\"] = dict()\n",
+    "notebook_metadata = defaultdict(dict)\n",
     "if interactive_plot == True:\n",
     "    plot_type='interactive'\n",
     "else:\n",
@@ -444,35 +442,14 @@
    "source": [
     "%%appyter code_exec\n",
     "\n",
+    "ip = dict()\n",
     "\n",
-    "notebook_metadata[\"input_parameters\"][\"rnaseq_data_filename\"] = rnaseq_data_filename\n",
-    "notebook_metadata[\"input_parameters\"][\"meta_data_filename\"] = meta_data_filename\n",
-    "notebook_metadata[\"input_parameters\"][\"meta_class_column_name\"] = meta_class_column_name\n",
-    "notebook_metadata[\"input_parameters\"][\"control_name\"] = control_name\n",
-    "\n",
-    "notebook_metadata[\"input_parameters\"][\"filter_genes\"] = filter_genes\n",
-    "notebook_metadata[\"input_parameters\"][\"low_expression_threshold\"] = low_expression_threshold\n",
-    "notebook_metadata[\"input_parameters\"][\"logCPM_normalization\"] = {{logCPM_normalization.value}}\n",
-    "notebook_metadata[\"input_parameters\"][\"log_normalization\"] = {{log_normalization.value}}\n",
-    "notebook_metadata[\"input_parameters\"][\"z_normalization\"] = {{z_normalization.value}}\n",
-    "notebook_metadata[\"input_parameters\"][\"q_normalization\"] = {{q_normalization.value}}\n",
-    "\n",
-    "notebook_metadata[\"input_parameters\"][\"visualization_method\"] = \"{{visualization_method.value}}\"\n",
-    "notebook_metadata[\"input_parameters\"][\"nr_genes\"] = nr_genes\n",
-    "notebook_metadata[\"input_parameters\"][\"gene_list_for_clustergrammer\"] = gene_list_for_clustergrammer\n",
-    "notebook_metadata[\"input_parameters\"][\"clustering_topk\"] = clustering_topk\n",
-    "\n",
-    "notebook_metadata[\"input_parameters\"][\"diff_gex_method\"] = diff_gex_method\n",
-    "notebook_metadata[\"input_parameters\"][\"diff_gex_plot_method\"] = diff_gex_plot_method\n",
-    "notebook_metadata[\"input_parameters\"][\"pvalue_threshold\"] = pvalue_threshold\n",
-    "notebook_metadata[\"input_parameters\"][\"logfc_threshold\"] = logfc_threshold\n",
-    "notebook_metadata[\"input_parameters\"][\"gene_topk\"] = gene_topk\n",
-    "notebook_metadata[\"input_parameters\"][\"enrichr_libraries\"] = enrichr_libraries\n",
-    "notebook_metadata[\"input_parameters\"][\"nr_genesets\"] = nr_genesets\n",
-    "notebook_metadata[\"input_parameters\"][\"small_molecule_method\"] = small_molecule_method\n",
-    "notebook_metadata[\"input_parameters\"][\"l1000_topk\"] = l1000_topk\n",
-    "notebook_metadata[\"input_parameters\"][\"nr_drugs\"] = nr_drugs\n",
-    "\n"
+    "ip |= dict(zip([\"rnaseq_data_filename\", \"meta_data_filename\", \"meta_class_column_name\", \"control_name\"], [rnaseq_data_filename, meta_data_filename, meta_class_column_name, control_name]))\n",
+    "ip |= dict(zip([\"filter_genes\", \"low_expression_threshold\", \"logCPM_normalization\", \"log_normalization\", \"z_normalization\", \"q_normalization\"], [filter_genes, low_expression_threshold, {{logCPM_normalization.value}}, {{log_normalization.value}}, {{z_normalization.value}}, {{q_normalization.value}}]))\n",
+    "ip |= dict(zip([\"visualization_method\", \"nr_genes\", \"gene_list_for_clustergrammer\", \"clustering_topk\"], [\"{{visualization_method.value}}\", nr_genes, gene_list_for_clustergrammer, clustering_topk]))\n",
+    "ip |= dict(zip([\"diff_gex_method\", \"diff_gex_plot_method\", \"pvalue_threshold\", \"logfc_threshold\", \"gene_topk\", \"enrichr_libraries\", \"nr_genesets\", \"small_molecule_method\", \"l1000_topk\", \"nr_drugs\"], [diff_gex_method, diff_gex_plot_method, pvalue_threshold, logfc_threshold, gene_topk, enrichr_libraries, nr_genesets, small_molecule_method, l1000_topk, nr_drugs]))\n",
+    "\n",
+    "notebook_metadata[\"input_parameters\"] = ip\n"
    ]
   },
   {
@@ -1112,6 +1089,7 @@
    "outputs": [],
    "source": [
     "# save metadata of the notebook as json\n",
+    "notebook_metadata['references'] = ref_counter\n",
     "with open(\"notebook_metadata.json\", \"w\") as fw:\n",
     "    json.dump(notebook_metadata, fw)"
    ]