{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Use Case 3: Associating Clinical Variables with Acetylation"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this use case we will show how to analyze the acetylation data with a clinical attribute. We will use the clinical attribute \"Histologic_type\", but you can apply the processes shown here to many other clinical attributes. Our goal is to identify which acetylation sites differ significantly in frequency between non-tumor, serous and endometrial cells."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Step 1: Import Packages and Load Data"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will start by importing the data analysis tools we need, importing the cptac package, and loading the Endometrial dataset."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "                                                \r"
     ]
    }
   ],
   "source": [
    "import pandas as pd\n",
    "import numpy as np\n",
    "import scipy.stats\n",
    "import statsmodels.stats.multitest\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn as sns\n",
    "import math\n",
    "import cptac\n",
    "import cptac.utils as ut\n",
    "\n",
    "cptac.download(dataset=\"endometrial\", version=\"latest\")\n",
    "en = cptac.Endometrial()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Step 2: Choose Clinical Attribute and Join Dataframes"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "For this use case, we will use the 'Histologic_type' clinical attribute in order to find differences in acetylation sites between \"endometrioid\" and \"serous\" cancer cells. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Set desired attribute to variable 'clinical_attribute'\n",
    "clinical_attribute = \"Histologic_type\""
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Here we will join our desired clinical attribute with our acetylation dataframe using the `en.join_metadata_to_omics` method."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th>Name</th>\n",
       "      <th>Histologic_type</th>\n",
       "      <th>A2M_acetylproteomics_K1168</th>\n",
       "      <th>A2M_acetylproteomics_K1176</th>\n",
       "      <th>A2M_acetylproteomics_K135</th>\n",
       "      <th>A2M_acetylproteomics_K145</th>\n",
       "      <th>A2M_acetylproteomics_K516</th>\n",
       "      <th>A2M_acetylproteomics_K664</th>\n",
       "      <th>A2M_acetylproteomics_K682</th>\n",
       "      <th>AACS_acetylproteomics_K391</th>\n",
       "      <th>AAGAB_acetylproteomics_K290</th>\n",
       "      <th>...</th>\n",
       "      <th>ZSCAN31_acetylproteomics_K215</th>\n",
       "      <th>ZSCAN32_acetylproteomics_K659</th>\n",
       "      <th>ZW10_acetylproteomics_K634</th>\n",
       "      <th>ZYX_acetylproteomics_K24</th>\n",
       "      <th>ZYX_acetylproteomics_K25</th>\n",
       "      <th>ZYX_acetylproteomics_K265</th>\n",
       "      <th>ZYX_acetylproteomics_K272</th>\n",
       "      <th>ZYX_acetylproteomics_K279</th>\n",
       "      <th>ZYX_acetylproteomics_K533</th>\n",
       "      <th>ZZZ3_acetylproteomics_K117</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>Patient_ID</th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "      <th></th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>C3L-00006</th>\n",
       "      <td>Endometrioid</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.080</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.461</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C3L-00008</th>\n",
       "      <td>Endometrioid</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.477</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.770</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.104</td>\n",
       "      <td>-0.80300</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.988</td>\n",
       "      <td>-0.343</td>\n",
       "      <td>-0.307</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.0955</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C3L-00032</th>\n",
       "      <td>Endometrioid</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.815</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.459</td>\n",
       "      <td>-1.170</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.7050</td>\n",
       "      <td>0.089</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C3L-00090</th>\n",
       "      <td>Endometrioid</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.608</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.919</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>...</td>\n",
       "      <td>-0.457</td>\n",
       "      <td>-0.00175</td>\n",
       "      <td>-0.33</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.537</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.3700</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>C3L-00098</th>\n",
       "      <td>Serous</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.630</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.4</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.26</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.205</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>0.41100</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.358</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>-0.9700</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 10863 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "Name       Histologic_type  A2M_acetylproteomics_K1168  \\\n",
       "Patient_ID                                               \n",
       "C3L-00006     Endometrioid                         NaN   \n",
       "C3L-00008     Endometrioid                         NaN   \n",
       "C3L-00032     Endometrioid                         NaN   \n",
       "C3L-00090     Endometrioid                         NaN   \n",
       "C3L-00098           Serous                         NaN   \n",
       "\n",
       "Name        A2M_acetylproteomics_K1176  A2M_acetylproteomics_K135  \\\n",
       "Patient_ID                                                          \n",
       "C3L-00006                        1.080                        NaN   \n",
       "C3L-00008                        0.477                        NaN   \n",
       "C3L-00032                          NaN                        NaN   \n",
       "C3L-00090                       -0.608                        NaN   \n",
       "C3L-00098                        1.630                        NaN   \n",
       "\n",
       "Name        A2M_acetylproteomics_K145  A2M_acetylproteomics_K516  \\\n",
       "Patient_ID                                                         \n",
       "C3L-00006                         NaN                        NaN   \n",
       "C3L-00008                         NaN                        NaN   \n",
       "C3L-00032                         NaN                        NaN   \n",
       "C3L-00090                         NaN                     -0.919   \n",
       "C3L-00098                         2.4                        NaN   \n",
       "\n",
       "Name        A2M_acetylproteomics_K664  A2M_acetylproteomics_K682  \\\n",
       "Patient_ID                                                         \n",
       "C3L-00006                         NaN                        NaN   \n",
       "C3L-00008                         NaN                        NaN   \n",
       "C3L-00032                         NaN                        NaN   \n",
       "C3L-00090                         NaN                        NaN   \n",
       "C3L-00098                         NaN                       1.26   \n",
       "\n",
       "Name        AACS_acetylproteomics_K391  AAGAB_acetylproteomics_K290  ...  \\\n",
       "Patient_ID                                                           ...   \n",
       "C3L-00006                          NaN                        0.461  ...   \n",
       "C3L-00008                          NaN                        1.770  ...   \n",
       "C3L-00032                          NaN                       -0.815  ...   \n",
       "C3L-00090                          NaN                          NaN  ...   \n",
       "C3L-00098                          NaN                        0.205  ...   \n",
       "\n",
       "Name        ZSCAN31_acetylproteomics_K215  ZSCAN32_acetylproteomics_K659  \\\n",
       "Patient_ID                                                                 \n",
       "C3L-00006                             NaN                            NaN   \n",
       "C3L-00008                          -0.104                       -0.80300   \n",
       "C3L-00032                             NaN                            NaN   \n",
       "C3L-00090                          -0.457                       -0.00175   \n",
       "C3L-00098                             NaN                        0.41100   \n",
       "\n",
       "Name        ZW10_acetylproteomics_K634  ZYX_acetylproteomics_K24  \\\n",
       "Patient_ID                                                         \n",
       "C3L-00006                          NaN                       NaN   \n",
       "C3L-00008                          NaN                    -0.988   \n",
       "C3L-00032                          NaN                    -0.459   \n",
       "C3L-00090                        -0.33                       NaN   \n",
       "C3L-00098                          NaN                       NaN   \n",
       "\n",
       "Name        ZYX_acetylproteomics_K25  ZYX_acetylproteomics_K265  \\\n",
       "Patient_ID                                                        \n",
       "C3L-00006                        NaN                        NaN   \n",
       "C3L-00008                     -0.343                     -0.307   \n",
       "C3L-00032                     -1.170                        NaN   \n",
       "C3L-00090                     -0.537                        NaN   \n",
       "C3L-00098                     -0.358                        NaN   \n",
       "\n",
       "Name        ZYX_acetylproteomics_K272  ZYX_acetylproteomics_K279  \\\n",
       "Patient_ID                                                         \n",
       "C3L-00006                         NaN                        NaN   \n",
       "C3L-00008                         NaN                    -0.0955   \n",
       "C3L-00032                         NaN                    -0.7050   \n",
       "C3L-00090                         NaN                    -0.3700   \n",
       "C3L-00098                         NaN                    -0.9700   \n",
       "\n",
       "Name        ZYX_acetylproteomics_K533  ZZZ3_acetylproteomics_K117  \n",
       "Patient_ID                                                         \n",
       "C3L-00006                         NaN                         NaN  \n",
       "C3L-00008                         NaN                         NaN  \n",
       "C3L-00032                       0.089                         NaN  \n",
       "C3L-00090                         NaN                         NaN  \n",
       "C3L-00098                         NaN                         NaN  \n",
       "\n",
       "[5 rows x 10863 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Join attribute with acetylation dataframe\n",
    "clinical_and_acetylation = en.join_metadata_to_omics(metadata_df_name=\"clinical\", omics_df_name=\"acetylproteomics\",\n",
    "                                                     metadata_cols=clinical_attribute)\n",
    "\n",
    "# Use the cptac.utils.reduce_multiindex function to combine the\n",
    "# multiple column levels, so it's easier to graph our data\n",
    "clinical_and_acetylation = ut.reduce_multiindex(df=clinical_and_acetylation, flatten=True)\n",
    "\n",
    "clinical_and_acetylation.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Step 3: Format Dataframe to Compare Acetylproteomic Sites Between Histologic Types"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array(['Endometrioid', 'Serous', nan], dtype=object)"
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "clinical_attribute = \"Histologic_type\"\n",
    "#Show possible variations of Histologic_type\n",
    "clinical_and_acetylation[clinical_attribute].unique()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "In this step, we will make two different dataframes for \"Endometrioid\" and \"Serous\" cancer types, as well as fill the NaN columns with \"Non-Tumor.\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#Make dataframes with only endometrioid and only serous data in order to compare \n",
    "endom = clinical_and_acetylation.loc[clinical_and_acetylation[clinical_attribute] == \"Endometrioid\"]\n",
    "serous = clinical_and_acetylation.loc[clinical_and_acetylation[clinical_attribute] == \"Serous\"]\n",
    "#Here is where we set the NaN values to \"Non_Tumor\"\n",
    "clinical_and_acetylation[[clinical_attribute]] = clinical_and_acetylation[[clinical_attribute]].fillna(\n",
    "    value=\"Non_Tumor\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have our different dataframes, we want to make sure that the amount of data we are using for each site is significant. Since there are fewer patients with \"serous\" tumors than with \"endometrioid,\" we will check to make sure that we have at least five values for each acetylation site that we are comparing that have a measurement of intensity for serous patients. We will remove every acetylation site from our dataframe that doesn't have at least five values among the serous patients."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total Sites:  10862\n",
      "Removed:  6926\n",
      "Remaining Sites:  3936\n",
      "Adjusted p-value cutoff will be:  1.2703252032520325e-05\n"
     ]
    }
   ],
   "source": [
    "#Remove every column that doesn't have at least 5 values among the serous patients\n",
    "print(\"Total Sites: \", len(serous.columns) - 1)\n",
    "sites_to_remove = []\n",
    "for num in range(1, len(serous.columns)):\n",
    "    serous_site = serous.columns[num]\n",
    "    one_site = serous[serous_site]\n",
    "    num_datapoints_ser = one_site.count()\n",
    "    if num_datapoints_ser < 5:\n",
    "        sites_to_remove.append(serous_site)\n",
    "\n",
    "clinical_and_acetylation = clinical_and_acetylation.drop(sites_to_remove, axis = 1)\n",
    "\n",
    "#Also remove non-tumor patients from our dataframe to use in comparison, as we want to compare only endometrioid and serous types\n",
    "clinical_and_acetylation_comparison = clinical_and_acetylation.loc[clinical_and_acetylation['Histologic_type'] != 'Non_Tumor']\n",
    "\n",
    "print(\"Removed: \", len(sites_to_remove))\n",
    "print(\"Remaining Sites: \", len(clinical_and_acetylation_comparison.columns) - 1)\n",
    "print(\"Adjusted p-value cutoff will be: \", .05/(len(clinical_and_acetylation_comparison.columns)-1))\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Step 4: Compare Endometrioid and Serous Values"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We will now call the wrap_ttest method, which will loop through the data and compare endometrioid versus serous data for each acetylation site. If we find a site that is significantly different, we will add it to a dataframe, with its p-value. The default alpha used is .05, which will be adjusted to account for multiple testing using a bonferroni correction, dividing alpha by the number of comparisons that will occur (the number of comparison columns)."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Comparison</th>\n",
       "      <th>P_Value</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>TBL1XR1_acetylproteomics_K102</td>\n",
       "      <td>0.000114</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>FOXA2_acetylproteomics_K280</td>\n",
       "      <td>0.000153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>SRRT_acetylproteomics_K720</td>\n",
       "      <td>0.000257</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>TOP2A_acetylproteomics_K1433</td>\n",
       "      <td>0.000660</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>NCL_acetylproteomics_K398</td>\n",
       "      <td>0.001211</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>MEAF6_acetylproteomics_K69</td>\n",
       "      <td>0.002100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>JADE3_acetylproteomics_K32</td>\n",
       "      <td>0.003546</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>NOP2_acetylproteomics_K91</td>\n",
       "      <td>0.008264</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>TOP2A_acetylproteomics_K1422</td>\n",
       "      <td>0.010327</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>MCRS1_acetylproteomics_K136</td>\n",
       "      <td>0.015518</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>PRR15_acetylproteomics_K81</td>\n",
       "      <td>0.027040</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>FUS_acetylproteomics_K332</td>\n",
       "      <td>0.035779</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>SUPT16H_acetylproteomics_K674</td>\n",
       "      <td>0.036792</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                       Comparison   P_Value\n",
       "0   TBL1XR1_acetylproteomics_K102  0.000114\n",
       "1     FOXA2_acetylproteomics_K280  0.000153\n",
       "2      SRRT_acetylproteomics_K720  0.000257\n",
       "3    TOP2A_acetylproteomics_K1433  0.000660\n",
       "4       NCL_acetylproteomics_K398  0.001211\n",
       "5      MEAF6_acetylproteomics_K69  0.002100\n",
       "6      JADE3_acetylproteomics_K32  0.003546\n",
       "7       NOP2_acetylproteomics_K91  0.008264\n",
       "8    TOP2A_acetylproteomics_K1422  0.010327\n",
       "9     MCRS1_acetylproteomics_K136  0.015518\n",
       "10     PRR15_acetylproteomics_K81  0.027040\n",
       "11      FUS_acetylproteomics_K332  0.035779\n",
       "12  SUPT16H_acetylproteomics_K674  0.036792"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "#Make list of all remaining sites in dataframe to pass to wrap_ttest function\n",
    "columns_to_compare = list(clinical_and_acetylation_comparison.columns)\n",
    "\n",
    "#Remove the \"Histologic_type\" column (at index 0) from this list \n",
    "columns_to_compare = columns_to_compare[1:]\n",
    "\n",
    "#Perform ttest on each column in dataframe\n",
    "significant_sites_df = ut.wrap_ttest(df=clinical_and_acetylation_comparison, label_column=\"Histologic_type\", comparison_columns=columns_to_compare)\n",
    "\n",
    "#List significant results\n",
    "significant_sites_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Step 5: Graph Results"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Now that we have eight acetylation sites that differ significantly between endometrioid and serous intensities, we will graph a couple of them using a boxplot and a stripplot in order to visually see the difference, as well as compare with normal cells."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ttest_indResult(statistic=5.991702127182772, pvalue=3.89570439448459e-08)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "graphingSite = 'FOXA2_acetylproteomics_K280'\n",
    "print(scipy.stats.ttest_ind(endom[graphingSite], serous[graphingSite]))\n",
    "sns.boxplot(x=clinical_attribute, y=graphingSite, data=clinical_and_acetylation, showfliers=False, \n",
    "            order=[\"Non_Tumor\", \"Endometrioid\", \"Serous\"])\n",
    "sns.stripplot(x=clinical_attribute, y=graphingSite, data=clinical_and_acetylation, color='.3', \n",
    "              order=[\"Non_Tumor\", \"Endometrioid\", \"Serous\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Ttest_indResult(statistic=-6.058405376720226, pvalue=2.8961545616585784e-08)\n"
     ]
    },
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "graphingSite = 'TBL1XR1_acetylproteomics_K102'\n",
    "print(scipy.stats.ttest_ind(endom[graphingSite], serous[graphingSite]))\n",
    "sns.boxplot(x=clinical_attribute, y=graphingSite, data=clinical_and_acetylation, showfliers = False, \n",
    "            order=[\"Non_Tumor\", \"Endometrioid\", \"Serous\"])\n",
    "sns.stripplot(x=clinical_attribute, y=graphingSite, data=clinical_and_acetylation, color='.3', \n",
    "              order=[\"Non_Tumor\", \"Endometrioid\", \"Serous\"])\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "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": "3.9.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}