From 70958bd46902200ef9976522d6a22a6ff60f19ef Mon Sep 17 00:00:00 2001
From: MelisCakan <cakanmelis27@gmail.com>
Date: Wed, 2 Apr 2025 21:41:12 +0300
Subject: [PATCH 1/8] preprocess - normalization methods are added

---
 src/modules/preprocessing.py | 11 +++++++++++
 1 file changed, 11 insertions(+)

diff --git a/src/modules/preprocessing.py b/src/modules/preprocessing.py
index e69de29..66c233f 100644
--- a/src/modules/preprocessing.py
+++ b/src/modules/preprocessing.py
@@ -0,0 +1,11 @@
+import scanpy as sc
+
+def preprocess(adata, target_sum = 1e4, max_value = 10):
+    data_normalization(adata, target_sum, max_value)
+    #other preprocessing methods here
+
+def data_normalization(adata, target_sum, max_value):
+    sc.pp.normalize_total(adata, target_sum)
+    sc.pp.log1p(adata)
+    sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
+    sc.pp.scale(adata, max_value)
\ No newline at end of file

From 7fde7ac6179c4185c0f6eae4a16775a061750d88 Mon Sep 17 00:00:00 2001
From: MelisCakan <cakanmelis27@gmail.com>
Date: Wed, 2 Apr 2025 21:55:58 +0300
Subject: [PATCH 2/8] added return adata to preprocess method

---
 src/modules/preprocessing.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/src/modules/preprocessing.py b/src/modules/preprocessing.py
index 66c233f..24b5257 100644
--- a/src/modules/preprocessing.py
+++ b/src/modules/preprocessing.py
@@ -3,6 +3,7 @@
 def preprocess(adata, target_sum = 1e4, max_value = 10):
     data_normalization(adata, target_sum, max_value)
     #other preprocessing methods here
+    return adata
 
 def data_normalization(adata, target_sum, max_value):
     sc.pp.normalize_total(adata, target_sum)

From 960a6cbddd9972b14b5f801de59a75208e0c9698 Mon Sep 17 00:00:00 2001
From: MelisCakan <cakanmelis27@gmail.com>
Date: Wed, 2 Apr 2025 22:09:21 +0300
Subject: [PATCH 3/8] function data_normalization name changed to normalize_and
 scale and function moved upper

---
 src/modules/preprocessing.py | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/src/modules/preprocessing.py b/src/modules/preprocessing.py
index 24b5257..efc00f1 100644
--- a/src/modules/preprocessing.py
+++ b/src/modules/preprocessing.py
@@ -1,12 +1,12 @@
 import scanpy as sc
 
-def preprocess(adata, target_sum = 1e4, max_value = 10):
-    data_normalization(adata, target_sum, max_value)
-    #other preprocessing methods here
-    return adata
-
-def data_normalization(adata, target_sum, max_value):
+def normalize_and_scale(adata, target_sum, max_value):
     sc.pp.normalize_total(adata, target_sum)
     sc.pp.log1p(adata)
     sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
-    sc.pp.scale(adata, max_value)
\ No newline at end of file
+    sc.pp.scale(adata, max_value)
+
+def preprocess(adata, target_sum = 1e4, max_value = 10):
+    normalize_and_scale(adata, target_sum, max_value)
+    #other preprocessing methods here
+    return adata

From 4f0df53f2f627f5443b115754ee548b0f446517f Mon Sep 17 00:00:00 2001
From: MelisCakan <cakanmelis27@gmail.com>
Date: Wed, 2 Apr 2025 22:36:53 +0300
Subject: [PATCH 4/8] try except block has been aded to check var name
 parameters

---
 src/modules/preprocessing.py | 12 +++++++++++-
 1 file changed, 11 insertions(+), 1 deletion(-)

diff --git a/src/modules/preprocessing.py b/src/modules/preprocessing.py
index efc00f1..f18deba 100644
--- a/src/modules/preprocessing.py
+++ b/src/modules/preprocessing.py
@@ -3,9 +3,19 @@
 def normalize_and_scale(adata, target_sum, max_value):
     sc.pp.normalize_total(adata, target_sum)
     sc.pp.log1p(adata)
-    sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt'])
     sc.pp.scale(adata, max_value)
 
+    vars_to_check = ["total_counts", "pct_counts_mt"]
+    try:
+        for var in vars_to_check: #checking for the var names if adata has them
+            if var not in adata.obs.columns:
+                raise ValueError(f"{var} is not found in adata.var_names")
+            
+        sc.pp.regress_out(adata, ['total_counts', 'pct_counts_mt']) #if adata has the parameters do regress out
+    except Exception as e:
+        print(f"An error has occurred: {e}") 
+
+
 def preprocess(adata, target_sum = 1e4, max_value = 10):
     normalize_and_scale(adata, target_sum, max_value)
     #other preprocessing methods here

From 503b79883c28802a6a584e1dfb569d48f7c121a4 Mon Sep 17 00:00:00 2001
From: MelisCakan <cakanmelis27@gmail.com>
Date: Wed, 2 Apr 2025 22:41:54 +0300
Subject: [PATCH 5/8] save_result function has been added

---
 src/modules/save.py | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/src/modules/save.py b/src/modules/save.py
index e69de29..3a39d07 100644
--- a/src/modules/save.py
+++ b/src/modules/save.py
@@ -0,0 +1,2 @@
+def save_result(adata, result_file):
+    adata.write(result_file)
\ No newline at end of file

From 87f232a4c4d4de2fd965b4f9743c546faa185323 Mon Sep 17 00:00:00 2001
From: AZRA TUNCAY <aazrtncy@gmail.com>
Date: Fri, 4 Apr 2025 16:09:54 +0300
Subject: [PATCH 6/8] Move DEMO_save_result.ipynb to src/modules and add it

---
 src/modules/DEMO_save_result.ipynb | 6 ++++++
 1 file changed, 6 insertions(+)
 create mode 100644 src/modules/DEMO_save_result.ipynb

diff --git a/src/modules/DEMO_save_result.ipynb b/src/modules/DEMO_save_result.ipynb
new file mode 100644
index 0000000..363fcab
--- /dev/null
+++ b/src/modules/DEMO_save_result.ipynb
@@ -0,0 +1,6 @@
+{
+ "cells": [],
+ "metadata": {},
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

From cbc791d3c26423465162e0b40c79707933c0e878 Mon Sep 17 00:00:00 2001
From: happymealinthebuilding <aazrtncy@gmail.com>
Date: Fri, 4 Apr 2025 16:18:42 +0300
Subject: [PATCH 7/8] Removed wrong file

---
 src/modules/DEMO_save_result.ipynb | 6 ------
 1 file changed, 6 deletions(-)
 delete mode 100644 src/modules/DEMO_save_result.ipynb

diff --git a/src/modules/DEMO_save_result.ipynb b/src/modules/DEMO_save_result.ipynb
deleted file mode 100644
index 363fcab..0000000
--- a/src/modules/DEMO_save_result.ipynb
+++ /dev/null
@@ -1,6 +0,0 @@
-{
- "cells": [],
- "metadata": {},
- "nbformat": 4,
- "nbformat_minor": 5
-}

From 896c59f6970c44d1ac0531769a0099b7badab127 Mon Sep 17 00:00:00 2001
From: happymealinthebuilding <aazrtncy@gmail.com>
Date: Fri, 4 Apr 2025 16:21:22 +0300
Subject: [PATCH 8/8] add demo file for save_result

---
 src/modules/DEMO_save_result.ipynb | 119 +++++++++++++++++++++++++++++
 1 file changed, 119 insertions(+)
 create mode 100644 src/modules/DEMO_save_result.ipynb

diff --git a/src/modules/DEMO_save_result.ipynb b/src/modules/DEMO_save_result.ipynb
new file mode 100644
index 0000000..c174672
--- /dev/null
+++ b/src/modules/DEMO_save_result.ipynb
@@ -0,0 +1,119 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "efb8299d-379f-4e0b-aaca-e342e64226ff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import scanpy as sc\n",
+    "import os\n",
+    "\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "da42d05f-266b-4610-9fcf-33c1006f24c7",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "61f523d945954c429e3152c8b60686bf",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0.00/5.58M [00:00<?, ?B/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Saving AnnData object to: pbmc3k_processed.h5ad\n",
+      "AnnData object saved successfully to: pbmc3k_processed.h5ad\n",
+      "\n",
+      "Verification: The file 'pbmc3k_processed.h5ad' has been created.\n"
+     ]
+    }
+   ],
+   "source": [
+    "def demo_save_result():\n",
+    "    \"\"\"Demo function to save an AnnData object to a file.\"\"\"\n",
+    "    # Load a sample dataset (or use the one preprocessed in the previous demo)\n",
+    "    try:\n",
+    "        adata = sc.datasets.pbmc3k()\n",
+    "        data_normalization_for_demo(adata) # Apply minimal normalization for the demo\n",
+    "    except Exception as e:\n",
+    "        print(f\"Error loading sample dataset: {e}\")\n",
+    "        print(\"Using a dummy AnnData object for the save demo.\")\n",
+    "        import numpy as np\n",
+    "        dummy_matrix = np.array([[1, 2], [3, 4]])\n",
+    "        dummy_var = ['gene1', 'gene2']\n",
+    "        dummy_obs = ['cell1', 'cell2']\n",
+    "        adata = sc.AnnData(dummy_matrix, obs={'obs_names': dummy_obs}, var={'var_names': dummy_var})\n",
+    "        adata.var_names = dummy_var\n",
+    "        adata.obs_names = dummy_obs\n",
+    "\n",
+    "    # Define the result file name\n",
+    "    result_file = \"pbmc3k_processed.h5ad\"  # .h5ad is the recommended format for AnnData\n",
+    "\n",
+    "    print(f\"Saving AnnData object to: {result_file}\")\n",
+    "    save_result(adata, result_file)\n",
+    "    print(f\"AnnData object saved successfully to: {result_file}\")\n",
+    "\n",
+    "    # Verify if the file was created (optional)\n",
+    "    if os.path.exists(result_file):\n",
+    "        print(f\"\\nVerification: The file '{result_file}' has been created.\")\n",
+    "    else:\n",
+    "        print(f\"\\nVerification: The file '{result_file}' was NOT created.\")\n",
+    "\n",
+    "    # Clean up the created file (optional)\n",
+    "    # os.remove(result_file)\n",
+    "    # print(f\"Cleaned up: Removed '{result_file}'\")\n",
+    "\n",
+    "def save_result(adata, result_file):\n",
+    "    \"\"\"Saves the AnnData object to the specified file.\"\"\"\n",
+    "    try:\n",
+    "        adata.write_h5ad(result_file) # Use .write_h5ad for the recommended format\n",
+    "    except Exception as e:\n",
+    "        print(f\"Error during saving: {e}\")\n",
+    "\n",
+    "def data_normalization_for_demo(adata, target_sum=1e4):\n",
+    "    \"\"\"Simplified normalization for the save demo.\"\"\"\n",
+    "    sc.pp.normalize_total(adata, target_sum=target_sum)\n",
+    "    sc.pp.log1p(adata)\n",
+    "\n",
+    "# Run the demo\n",
+    "demo_save_result()"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.12.4"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}