{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg = pd.read_csv('PICO8_nome/nome.NOMe.CpG.cov', sep='\\t', header=None)\n",
    "gpc = pd.read_csv('PICO8_nome/nome.NOMe.GpC.cov', sep='\\t', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg = pd.read_csv('./GSM2220271_GM_1_CpG_clean.cov.txt', sep='\\t', header=None)\n",
    "gpc = pd.read_csv('./GSM2220271_GM_1_GpC_clean.cov.txt', sep='\\t', header=None)"
   ]
  },
  {
   "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></th>\n",
       "      <th>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>chr1</td>\n",
       "      <td>111</td>\n",
       "      <td>111</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>chr1</td>\n",
       "      <td>120</td>\n",
       "      <td>120</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>chr1</td>\n",
       "      <td>130</td>\n",
       "      <td>130</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>2</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>chr1</td>\n",
       "      <td>202</td>\n",
       "      <td>202</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>chr1</td>\n",
       "      <td>270</td>\n",
       "      <td>270</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>459015</th>\n",
       "      <td>chrZ</td>\n",
       "      <td>82309610</td>\n",
       "      <td>82309610</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>459016</th>\n",
       "      <td>chrZ</td>\n",
       "      <td>82309611</td>\n",
       "      <td>82309611</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>459017</th>\n",
       "      <td>chrZ</td>\n",
       "      <td>82309665</td>\n",
       "      <td>82309665</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>459018</th>\n",
       "      <td>chrZ</td>\n",
       "      <td>82309971</td>\n",
       "      <td>82309971</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>459019</th>\n",
       "      <td>chrZ</td>\n",
       "      <td>82309980</td>\n",
       "      <td>82309980</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>459020 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "           0         1         2      3  4  5\n",
       "0       chr1       111       111    0.0  0  2\n",
       "1       chr1       120       120    0.0  0  1\n",
       "2       chr1       130       130    0.0  0  2\n",
       "3       chr1       202       202    0.0  0  4\n",
       "4       chr1       270       270    0.0  0  4\n",
       "...      ...       ...       ...    ... .. ..\n",
       "459015  chrZ  82309610  82309610  100.0  1  0\n",
       "459016  chrZ  82309611  82309611  100.0  1  0\n",
       "459017  chrZ  82309665  82309665  100.0  1  0\n",
       "459018  chrZ  82309971  82309971  100.0  1  0\n",
       "459019  chrZ  82309980  82309980  100.0  1  0\n",
       "\n",
       "[459020 rows x 6 columns]"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cpg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg_out = cpg.iloc[:,:4]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg_out[3]=cpg_out[3].replace(0,-100)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg_out.to_csv('cpgGM.bedGraph', sep='\\t', index=False, header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpc_out = gpc.iloc[:,:4]\n",
    "gpc_out[3]=gpc_out[3].replace(0,-100)\n",
    "gpc_out.to_csv('gpcGM.bedGraph', sep='\\t', index=False, header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>chr1</td>\n",
       "      <td>16243</td>\n",
       "      <td>16244</td>\n",
       "      <td>100.0</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>chr1</td>\n",
       "      <td>129075</td>\n",
       "      <td>129076</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>chr1</td>\n",
       "      <td>136875</td>\n",
       "      <td>136876</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>chr1</td>\n",
       "      <td>136894</td>\n",
       "      <td>136895</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>chr1</td>\n",
       "      <td>136910</td>\n",
       "      <td>136911</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554347</th>\n",
       "      <td>chrY</td>\n",
       "      <td>56885733</td>\n",
       "      <td>56885734</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554348</th>\n",
       "      <td>chrY</td>\n",
       "      <td>56885736</td>\n",
       "      <td>56885737</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554349</th>\n",
       "      <td>chrY</td>\n",
       "      <td>57027509</td>\n",
       "      <td>57027510</td>\n",
       "      <td>0.0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554350</th>\n",
       "      <td>chrY</td>\n",
       "      <td>57178007</td>\n",
       "      <td>57178008</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1554351</th>\n",
       "      <td>chrY</td>\n",
       "      <td>57178073</td>\n",
       "      <td>57178074</td>\n",
       "      <td>100.0</td>\n",
       "      <td>1</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1554352 rows × 6 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "            0         1         2      3  4  5\n",
       "0        chr1     16243     16244  100.0  2  0\n",
       "1        chr1    129075    129076  100.0  1  0\n",
       "2        chr1    136875    136876    0.0  0  1\n",
       "3        chr1    136894    136895    0.0  0  1\n",
       "4        chr1    136910    136911  100.0  1  0\n",
       "...       ...       ...       ...    ... .. ..\n",
       "1554347  chrY  56885733  56885734    0.0  0  1\n",
       "1554348  chrY  56885736  56885737    0.0  0  1\n",
       "1554349  chrY  57027509  57027510    0.0  0  1\n",
       "1554350  chrY  57178007  57178008  100.0  1  0\n",
       "1554351  chrY  57178073  57178074  100.0  1  0\n",
       "\n",
       "[1554352 rows x 6 columns]"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "cpg"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.12918763851615767"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(gpc[3]>50).sum()/len(gpc)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.26706305907542177"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(cpg[3]>50).sum()/len(cpg)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "cpg8 = pd.read_csv('../PICO8_nome/nome.NOMe.CpG.cov', sep='\\t', header=None)\n",
    "gpc8 = pd.read_csv('../PICO8_nome/nome.NOMe.GpC.cov', sep='\\t', header=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.08912184952090842"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(gpc8[3]>50).sum()/len(gpc8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0.4921001082530027"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "(cpg8[3]>50).sum()/len(cpg8)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "gpc8_out = gpc8.iloc[:,:4]\n",
    "#gpc8_out[3]=gpc8_out[3].replace(0,-100)\n",
    "gpc8_out.to_csv('PICO8_gpc0.bedGraph', sep='\\t', index=False, header=None)\n",
    "cpg8_out = cpg8.iloc[:,:4]\n",
    "#cpg8_out[3]=cpg8_out[3].replace(0,-100)\n",
    "cpg8_out.to_csv('PICO8_cpg0.bedGraph', sep='\\t', index=False, header=None)"
   ]
  },
  {
   "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": "3.8.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}