Merge pull request #73 from STRIDES/drafts

Publishing Amazon Q tutorial

Author: zbyosufzai

docs/images/Q-IAM-role.png

@@ -0,0 +1,26 @@
+import pandas as pd
+import subprocess
+
+# Step 1: Read the sample sheet
+sample_sheet = pd.read_csv('samplesheet.csv')
+
+# Step 2: Run FastQC
+for index, row in sample_sheet.iterrows():
+    fastqc_command = f"fastqc {row['file_path']} -o ./fastqc_results/"
+    subprocess.run(fastqc_command, shell=True)
+
+# Step 3: Run MultiQC
+multiqc_command = "multiqc ./fastqc_results/ -o ./multiqc_report/"
+subprocess.run(multiqc_command, shell=True)
+
+# Step 4: Run STAR aligner
+for index, row in sample_sheet.iterrows():
+    star_command = f"STAR --genomeDir /path/to/genome --readFilesIn {row['file_path']} --outFileNamePrefix ./star_results/{row['sample_id']}"
+    subprocess.run(star_command, shell=True)
+
+# Step 5: Index BAM files with Samtools
+for index, row in sample_sheet.iterrows():
+    bam_file = f"./star_results/{row['sample_id']}.bam"
+    samtools_command = f"samtools index {bam_file}"
+    subprocess.run(samtools_command, shell=True) 
+

docs/images/Q-R-script.png

@@ -0,0 +1,133 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "bed9c0c9-4756-4161-b4be-e32ce3a58bff",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Cell 1\n",
+    "#import libraries\n",
+    "\n",
+    "import pandas as pd\n",
+    "import numpy as np"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "64f8d006-28f3-4d83-ae3a-9e23cccff5d7",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "    Gene  Expression_Level Sample_ID Condition\n",
+      "0  GeneA              12.5        S1   Control\n",
+      "1  GeneB               8.3        S2   Treated\n",
+      "2  GeneC              15.2        S3   Control\n",
+      "3  GeneD               7.8        S4   Treated\n"
+     ]
+    }
+   ],
+   "source": [
+    "#Cell 2\n",
+    "\n",
+    "# Initialize data of lists\n",
+    "data = {\n",
+    "    'Gene': ['GeneA', 'GeneB', 'GeneC', 'GeneD'],\n",
+    "    'Expression_Level': [12.5, 8.3, 15.2, 7.8],\n",
+    "    'Sample_ID': ['S1', 'S2', 'S3', 'S4'],\n",
+    "    'Condition': ['Control', 'Treated', 'Control', 'Treated']\n",
+    "}\n",
+    "\n",
+    "# Create DataFrame\n",
+    "df = pd.DataFrame(data)\n",
+    "\n",
+    "# Display the DataFrame\n",
+    "print(df)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "8ca19300-1635-4a8a-9ef8-f9554bc1baac",
+   "metadata": {},
+   "outputs": [
+    {
+     "ename": "NameError",
+     "evalue": "name 'describe' is not defined",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
+      "Cell \u001b[0;32mIn[5], line 2\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;66;03m# View summary statistics\u001b[39;00m\n\u001b[0;32m----> 2\u001b[0m \u001b[43mdescribe\u001b[49m()\u001b[38;5;241m.\u001b[39mdf\n",
+      "\u001b[0;31mNameError\u001b[0m: name 'describe' is not defined"
+     ]
+    }
+   ],
+   "source": [
+    "#Cell 3\n",
+    "\n",
+    "# Error debugging test /fix\n",
+    "# View summary statistics\n",
+    "describe().df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "550a402e-66bd-4890-a063-e3d82679c0a8",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Cell 4\n",
+    "\n",
+    "# Optimize selection test /optimize\n",
+    "# Add additional data to the dataframe\n",
+    "df['Sample_Type'] = ['Tissue1', 'Tissue2', 'Tissue1', 'Tissue2']\n",
+    "df['P_Value'] = [0.05, 0.01, 0.03, 0.07]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "0d45c1aa-2075-4c8a-9ecc-94fb03a71f78",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "#Cell 5\n",
+    "\n",
+    "#Explain selection test /explain\n",
+    "#Plot results\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "df.plot(x='Sample_ID', y='Expression_Level', kind='line')\n",
+    "plt.show()"
+   ]
+  }
+ ],
+ "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": "3.11.10"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}