{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Motif Enrichment Analysis\n",
    "\n",
    "After motif scan, we can run motif enrichment analysis by chosing two list of regions, running Fisher's Exact test between the two sets for each motif-cluster (or motif) and perform multiple tests correction"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Import"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-07T21:51:23.019922Z",
     "start_time": "2022-01-07T21:51:20.941308Z"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import xarray as xr\n",
    "import seaborn as sns\n",
    "import matplotlib.pyplot as plt\n",
    "from scipy.stats import fisher_exact\n",
    "from statsmodels.stats.multitest import multipletests\n",
    "from ALLCools.mcds import RegionDS"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Load"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-07T21:51:23.173193Z",
     "start_time": "2022-01-07T21:51:23.022088Z"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Using dmr as region_dim\n"
     ]
    }
   ],
   "source": [
    "dmr = RegionDS.open('HIP_small')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Motif Enrichment Between Two Sets of Regions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T18:57:57.244384Z",
     "start_time": "2022-01-04T18:57:57.242075Z"
    }
   },
   "outputs": [],
   "source": [
    "region_dim = 'dmr'\n",
    "region_state_da = 'dmr_state'\n",
    "feature_dim = 'sample'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T18:57:58.415168Z",
     "start_time": "2022-01-04T18:57:58.411176Z"
    }
   },
   "outputs": [],
   "source": [
    "# this is a helper function to select hypo- and hyper-DMR for one sample\n",
    "hypo_dmr, hyper_dmr = dmr.get_hypo_hyper_index('CA1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T18:58:05.617649Z",
     "start_time": "2022-01-04T18:58:05.044987Z"
    }
   },
   "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>oddsratio</th>\n",
       "      <th>p</th>\n",
       "      <th>q</th>\n",
       "      <th>log2OR</th>\n",
       "      <th>-lgq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>motif-cluster</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>c1</th>\n",
       "      <td>0.369231</td>\n",
       "      <td>0.476190</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.437405</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c10</th>\n",
       "      <td>1.142857</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.192645</td>\n",
       "      <td>-0.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c100</th>\n",
       "      <td>0.474576</td>\n",
       "      <td>0.299267</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.075288</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c101</th>\n",
       "      <td>0.733333</td>\n",
       "      <td>0.701906</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.447459</td>\n",
       "      <td>-0.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c102</th>\n",
       "      <td>0.369231</td>\n",
       "      <td>0.476190</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.437405</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               oddsratio         p         q    log2OR     -lgq\n",
       "motif-cluster                                                  \n",
       "c1              0.369231  0.476190  0.901924 -1.437405  0.04483\n",
       "c10             1.142857  1.000000  1.000000  0.192645 -0.00000\n",
       "c100            0.474576  0.299267  0.901924 -1.075288  0.04483\n",
       "c101            0.733333  0.701906  1.000000 -0.447459 -0.00000\n",
       "c102            0.369231  0.476190  0.901924 -1.437405  0.04483"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = dmr.motif_enrichment(true_regions=hypo_dmr,\n",
    "                              background_regions=hyper_dmr,\n",
    "                              region_dim=None,\n",
    "                              motif_dim='motif-cluster',\n",
    "                              motif_da=None,\n",
    "                              alternative='two-sided')\n",
    "result.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Motif Enrichment For Each Sample\n",
    "Alternatively, you can use `RegionDS.sample_dmr_motif_enrichment()` to achieve the same purpose."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T18:59:08.006868Z",
     "start_time": "2022-01-04T18:59:07.614930Z"
    }
   },
   "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>oddsratio</th>\n",
       "      <th>p</th>\n",
       "      <th>q</th>\n",
       "      <th>log2OR</th>\n",
       "      <th>-lgq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>motif-cluster</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>c1</th>\n",
       "      <td>0.369231</td>\n",
       "      <td>0.476190</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.437405</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c10</th>\n",
       "      <td>1.142857</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>0.192645</td>\n",
       "      <td>-0.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c100</th>\n",
       "      <td>0.474576</td>\n",
       "      <td>0.299267</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.075288</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c101</th>\n",
       "      <td>0.733333</td>\n",
       "      <td>0.701906</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>-0.447459</td>\n",
       "      <td>-0.00000</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c102</th>\n",
       "      <td>0.369231</td>\n",
       "      <td>0.476190</td>\n",
       "      <td>0.901924</td>\n",
       "      <td>-1.437405</td>\n",
       "      <td>0.04483</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               oddsratio         p         q    log2OR     -lgq\n",
       "motif-cluster                                                  \n",
       "c1              0.369231  0.476190  0.901924 -1.437405  0.04483\n",
       "c10             1.142857  1.000000  1.000000  0.192645 -0.00000\n",
       "c100            0.474576  0.299267  0.901924 -1.075288  0.04483\n",
       "c101            0.733333  0.701906  1.000000 -0.447459 -0.00000\n",
       "c102            0.369231  0.476190  0.901924 -1.437405  0.04483"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result = dmr.sample_dmr_motif_enrichment('CA1')\n",
    "result.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "### Motif Enrichment Between Sample Pairs\n",
    "You can also compare hypo-DMRs (non-overlapping) from two different samples. "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T19:00:57.876880Z",
     "start_time": "2022-01-04T19:00:57.496008Z"
    }
   },
   "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>oddsratio</th>\n",
       "      <th>p</th>\n",
       "      <th>q</th>\n",
       "      <th>log2OR</th>\n",
       "      <th>-lgq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>motif-cluster</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>c1</th>\n",
       "      <td>0.491228</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.025535</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c10</th>\n",
       "      <td>0.736364</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.441510</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c100</th>\n",
       "      <td>0.658824</td>\n",
       "      <td>0.523942</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.602036</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c101</th>\n",
       "      <td>0.721154</td>\n",
       "      <td>0.725386</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.471621</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c102</th>\n",
       "      <td>0.491228</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.025535</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               oddsratio         p    q    log2OR  -lgq\n",
       "motif-cluster                                          \n",
       "c1              0.491228  1.000000  1.0 -1.025535  -0.0\n",
       "c10             0.736364  1.000000  1.0 -0.441510  -0.0\n",
       "c100            0.658824  0.523942  1.0 -0.602036  -0.0\n",
       "c101            0.721154  0.725386  1.0 -0.471621  -0.0\n",
       "c102            0.491228  1.000000  1.0 -1.025535  -0.0"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "a_not_b, a_and_b, b_not_a = dmr.get_pairwise_differential_index('CA1', 'ASC', dmr_type='hypo')\n",
    "\n",
    "result = dmr.motif_enrichment(true_regions=a_not_b,\n",
    "                              background_regions=b_not_a,\n",
    "                              region_dim=None,\n",
    "                              motif_dim='motif-cluster',\n",
    "                              motif_da=None,\n",
    "                              alternative='two-sided')\n",
    "result.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2022-01-04T19:01:39.824630Z",
     "start_time": "2022-01-04T19:01:39.430052Z"
    }
   },
   "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>oddsratio</th>\n",
       "      <th>p</th>\n",
       "      <th>q</th>\n",
       "      <th>log2OR</th>\n",
       "      <th>-lgq</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>motif-cluster</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>c1</th>\n",
       "      <td>0.491228</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.025535</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c10</th>\n",
       "      <td>0.736364</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.441510</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c100</th>\n",
       "      <td>0.658824</td>\n",
       "      <td>0.523942</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.602036</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c101</th>\n",
       "      <td>0.721154</td>\n",
       "      <td>0.725386</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-0.471621</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>c102</th>\n",
       "      <td>0.491228</td>\n",
       "      <td>1.000000</td>\n",
       "      <td>1.0</td>\n",
       "      <td>-1.025535</td>\n",
       "      <td>-0.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "               oddsratio         p    q    log2OR  -lgq\n",
       "motif-cluster                                          \n",
       "c1              0.491228  1.000000  1.0 -1.025535  -0.0\n",
       "c10             0.736364  1.000000  1.0 -0.441510  -0.0\n",
       "c100            0.658824  0.523942  1.0 -0.602036  -0.0\n",
       "c101            0.721154  0.725386  1.0 -0.471621  -0.0\n",
       "c102            0.491228  1.000000  1.0 -1.025535  -0.0"
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# this function are the same as above\n",
    "result = dmr.pairwise_dmr_motif_enrichment('CA1', 'ASC', dmr_type='hypo')\n",
    "result.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "hide_input": false,
  "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": "3.8.6"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": true,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": true
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}