3 - fusion efficiency analysis - three+ groups.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "66894f60",
   "metadata": {},
   "source": [
    "# Import modules"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "83cd8a0f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from scipy import stats\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy.stats import shapiro, levene\n",
    "from statsmodels.formula.api import ols\n",
    "from statsmodels.stats.anova import anova_lm\n",
    "from statsmodels.stats.multicomp import pairwise_tukeyhsd\n",
    "import numpy as np\n",
    "from scipy.stats import sem\n",
    "from statsmodels.graphics.gofplots import qqplot\n",
    "from pingouin import pairwise_tukey"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5c803722",
   "metadata": {},
   "source": [
    "## Read in dataframe containing the fusion efficiency data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "39996609",
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "input path to .xlsx file containing fusion efficiency data: /Users/steinar/Documents/Data/4 - cell vs. endosomal membrane in fusion/2 - fusion with PMV/4 - liposomes and PMV content mixing by FT Calcein incorporation/reanalysed data with trace type classification (P4E25T1 and P4E25T2)/dequenching efficiency/compiled efficiency.xlsx\n"
     ]
    }
   ],
   "source": [
    "df_path = input(\"input path to .xlsx file containing fusion efficiency data: \")\n",
    "\n",
    "df = pd.read_excel(df_path)\n",
    "\n",
    "# Extract the column names\n",
    "group_column = df.columns[0]\n",
    "values_column = df.columns[-1]"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "8ca5713c",
   "metadata": {},
   "source": [
    "## Perform One-Way ANOVA and Post-Hoc test"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "202037f5",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "ANOVA Table:\n",
      "                df     sum_sq   mean_sq          F        PR(>F)\n",
      "vesicle_type   3.0  14.947308  4.982436  41.344028  1.723344e-07\n",
      "Residual      15.0   1.807674  0.120512        NaN           NaN\n",
      "\n",
      "Tukey's HSD Post Hoc Test:\n",
      "                  Multiple Comparison of Means - Tukey HSD, FWER=0.05                   \n",
      "========================================================================================\n",
      "         group1                   group2          meandiff p-adj   lower   upper  reject\n",
      "----------------------------------------------------------------------------------------\n",
      "      IAV + BMP liposome                IAV + PMV   -2.186    0.0 -2.8318 -1.5402   True\n",
      "      IAV + BMP liposome IAV + PMV + 50 mol % BMP  -2.3306    0.0 -3.0018 -1.6594   True\n",
      "      IAV + BMP liposome   IAV + control liposome  -1.5771 0.0001 -2.2846 -0.8696   True\n",
      "               IAV + PMV IAV + PMV + 50 mol % BMP  -0.1446 0.9001 -0.7505  0.4612  False\n",
      "               IAV + PMV   IAV + control liposome   0.6089 0.0679 -0.0369  1.2547  False\n",
      "IAV + PMV + 50 mol % BMP   IAV + control liposome   0.7535 0.0255  0.0823  1.4247   True\n",
      "----------------------------------------------------------------------------------------\n"
     ]
    }
   ],
   "source": [
    "#One-way ANOVA\n",
    "formula = f'{values_column} ~ {group_column}'\n",
    "model = ols(formula, data=df).fit()\n",
    "anova_table = anova_lm(model)\n",
    "print('\\nANOVA Table:')\n",
    "print(anova_table)\n",
    "\n",
    "#Tukey's HSD post hoc test\n",
    "tukey_results = pairwise_tukeyhsd(df[values_column], df[group_column])\n",
    "print('\\nTukey\\'s HSD Post Hoc Test:')\n",
    "print(tukey_results)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "3f68a767",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                          A                         B       p-tukey\n",
      "0        IAV + BMP liposome                 IAV + PMV  3.795763e-07\n",
      "1        IAV + BMP liposome  IAV + PMV + 50 mol % BMP  2.716981e-07\n",
      "2        IAV + BMP liposome    IAV + control liposome  6.093246e-05\n",
      "3                 IAV + PMV  IAV + PMV + 50 mol % BMP  9.001050e-01\n",
      "4                 IAV + PMV    IAV + control liposome  6.791416e-02\n",
      "5  IAV + PMV + 50 mol % BMP    IAV + control liposome  2.545868e-02\n"
     ]
    }
   ],
   "source": [
    "# Perform Tukey's HSD test with unbalanced data\n",
    "result = pairwise_tukey(data=df, dv=values_column, between=group_column)\n",
    "\n",
    "# Display only columns 'A', 'B', and 'p-tukey'\n",
    "result_subset = result[['A', 'B', 'p-tukey']]\n",
    "print(result_subset)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "2567a501",
   "metadata": {},
   "source": [
    "## Plot barplot of data and save as .pdf"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "4d43430f",
   "metadata": {
    "scrolled": false
   },
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 800x600 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Calculate mean and standard error for each group\n",
    "group_means = df.groupby(group_column, sort=False)[values_column].mean()\n",
    "group_sem = df.groupby(group_column, sort=False)[values_column].apply(sem)\n",
    "\n",
    "# Define a color scheme for each dataset\n",
    "colors = ['dodgerblue', 'blue', 'lightcoral', 'tomato','red', 'grey', 'grey', 'grey']\n",
    "\n",
    "# Create a barplot with pyplot\n",
    "groups = group_means.index\n",
    "means = group_means.values\n",
    "errors = group_sem.values\n",
    "\n",
    "fig, ax = plt.subplots(figsize=(8, 6))\n",
    "ax.bar(groups, means, yerr=errors, capsize=5, color=colors, edgecolor='black')\n",
    "plt.xticks(rotation=30, ha='right')\n",
    "plt.ylabel('content mixing efficiency (fold change)')\n",
    "\n",
    "# add annotations for significant differences\n",
    "#plt.hlines(6, xmin=0, xmax=3, color = 'black')\n",
    "#plt.vlines(1.5, ymin=6, ymax=11.5, color = 'black')\n",
    "#plt.hlines(11.5, xmin=1.5, xmax=4, color = 'black')\n",
    "#plt.annotate(text = \"***\", xy = (2.60,11.5), size = 28)\n",
    "#plt.vlines(4, ymin=11, ymax=11.5, color = 'black')\n",
    "\n",
    "# Save the figure as a PDF file\n",
    "folder = '/Users/steinar/Desktop'\n",
    "filename = '/efficiency plot.pdf'\n",
    "plt.savefig(folder + filename, format='pdf', bbox_inches = 'tight')\n",
    "\n",
    "# Show the plot\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1791a27e",
   "metadata": {},
   "source": [
    "## Assumptions for a one-way ANOVA"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "1fc0f5d7",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "\n",
      "Levene's test for homogeneity of variances: Statistic=0.1449, p-value=0.9314\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "# Levene's test for homogeneity of variances\n",
    "stat, p_value = levene(*[group_data for _, group_data in df.groupby(group_column)[values_column]])\n",
    "print(f'\\nLevene\\'s test for homogeneity of variances: Statistic={stat:.4f}, p-value={p_value:.4f}')\n",
    "\n",
    "# QQ plot of residuals\n",
    "qqplot(model.resid, line='s')\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "71d76c00",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "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": "3.10.2"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}