01-refr-genome-summary.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%matplotlib inline\n",
    "\n",
    "import matplotlib\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "import seaborn\n",
    "\n",
    "matplotlib.rcParams['axes.labelsize'] = 16\n",
    "matplotlib.rcParams['xtick.labelsize'] = 12\n",
    "matplotlib.rcParams['ytick.labelsize'] = 12\n",
    "matplotlib.rcParams['savefig.dpi'] = 300\n",
    "seaborn.set_context({\"figure.figsize\": (15, 10)})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "specieslist = ['Scer', 'Cele', 'Crei', 'Mtru', 'Dmel',\n",
    "               'Agam', 'Xtro', 'Drer', 'Mmus', 'Hsap']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAA4MAAAJCCAYAAAB6VBJfAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy8QZhcZAAAgAElEQVR4nO3de5hlZ1kn7N9DWgkD6aKbBBAkRGjwhAPjtMKIEpRRxkMPzOCgAkI80APCoIgoCkM6jDgonsfgfC0qyiEifIC0hxHRTwQFMUERQUUEY+QgCd1USIAA4Zk/1m6/SqWreleyd+2qve77uurK3mutWv3Um3367fd911vdHQAAAMblFosuAAAAgO0nDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACM0J5FFzBPZ599dp933nmLLgMAAGAhLrvssqu6+5xT7VvqMHjeeefl0ksvXXQZAAAAC1FVl2+0zzBRAACAERIGAQAARkgYBAAAGCFhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAERIGAQAARkgYBAAAGCFhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYoT2LLgAAAGCnqKq5nLe753Lem0MYBAAAmNhKaKuqHRnypmWYKAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIzQrgmDVXVeVV1ZVX84+Tln0TUBAADsVnsWXcAWva67v3HRRQAAAOx2u6ZncOL+VfX6qvqRqqpFFwMAALBbbXsYrKonVtWlVXVdVb1g3b79VfXKqrq2qi6vqkes2f3+JAeSPCDJ7ZP85+2rGgAAYLksomfwfUl+OMkvnWLfxUk+keQOSR6Z5Oer6guTpLuv6+5ru7uTvCLJvbepXgAAgKWz7WGwu1/R3a9K8qG126vq1kkeluS/d/c13f2GJK9O8q2T/XvXHP4VSd61TSUDAAAsnZ00Z/CeSa7v7neu2fbWJF84uX1+VV1WVa9PcuckLznVSarq8GQY6qVXXnnlfCsGAIAFq6q5/LD8dtLVRG+TZHXdttUkZyVJdx9Lcux0J+nuo0mOJsnBgwd7xjUCAMCOMsyimk5Vbel4lttO6hm8Jsneddv2JvnIAmoBAABYajspDL4zyZ6quseabfdO8vYF1QMAALC0FrG0xJ6qOjPJGUnOqKozq2pPd1+b4Sqhz6qqW1fV/ZM8JMkLt7tGAACAZbeInsFnJPlYkqcledTk9jMm+74rya2SfDDJJUke3916BgEAAGZs2y8g091HkhzZYN/xJA/dznoAAADGaCfNGQQAAGCbCIMAAAAjJAwCAACM0FKGwao6VFVHV1fXr2EPAABAsqRhsLuPdffhlZWVRZcCAACwIy1lGAQAAGBzwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMEJLGQar6lBVHV1dXV10KQAAADvSUobB7j7W3YdXVlYWXQoAAMCOtJRhEAAAgM0JgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjtGfRBQAA7AZVNZfzdvdczgtwOsIgAMAUpg1tVSXgAbuCYaIAAAAjJAwCAACM0FIOE62qQ0kOHThwYNGlAABwCuZgwuItZc9gdx/r7sMrKyuLLgUAgFPo7ql+tnKsIAhbs5RhEAAAgM0JgwAAACMkDAIAAIyQMAgAADBCwiAAAMAILeXSEgAAAGvt378/J06cmPl5Z7lMyr59+3L8+PGZne90hEEAAGDpnThxYscvPzKv9Tc3YpgoAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgtZRisqkNVdXR1dXXRpQAAAOxISxkGu/tYdx9eWVlZdCkAAAA70lKGQQAAADYnDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIzQUobBqjpUVUdXV1cXXQoAAMCOtJRhsLuPdffhlZWVRZcCAACwIy1lGAQAAGBzwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAjtWXQBAADAje3fvz8nTpyY+Xmraqbn27dvX44fPz7Tc7I9hEEAANiBTpw4ke5edBmnNetwyfYxTBQAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAERIGAQAARmgpw2BVHaqqo6urq4suBQAAYEdayjDY3ce6+/DKysqiSwEAANiRljIMAgAAsDlhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAERIGAQAARkgYBAAAGCFhEAAAYISEQQAAgBHas+gCAAAWaf/+/Tlx4sRMz1lVMz3fvn37cvz48ZmeE0AYBABG7cSJE+nuRZexqVmHS4DEMFEAAIBREgYBAABGyDBRAABmYh7zLxNzMGFehEEAAGZiN8y/TMzBhJMMEwUAABghYRAAAGCEhEEAAIARWsowWFWHquro6urqoksBAADYkZYyDHb3se4+vLKysuhSAAAAdqSlDIMAAABsThgEAAAYIWEQAABghIRBAACAERIGAQAARkgYBAAAGCFhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAEdqz6AIAAADmrS/cmxxZWXQZm+oL927rvycMAgAAS68uujrdvegyNlVV6SPb9+8ZJgoAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQlu6mmhV3THJnZLcKslVSd7T3Z+YR2EAAADMz2nDYFUdTPKdSf5Dkrus2/2JqvqzJJckeXF3Xz37EgEAAJi1DcPgJAT+eJIHJHlbkmNJ/jzJlUk+lmR/ks9Jct8kz0nynKr6sSQ/0d0fn3PdAAAA3Ayb9Qy+LskvJHl8d//1ZiepqjOTPCTJ92eYh/g/ZlYhAAAAM7dZGLx7d39gmpNMegJfmuSlVXWHmVQGAADA3Gx4NdFpg+Apfu+fb3o5AAAAbIetXk30QJIvTXLnJO9N8ubuftc8CgMAAGB+pgqDkzmBz0vyrUnOWLPr+qr6lSRP6O7r5lAfAAAAczDtovM/nuSRSS5MciDJWZP/HskQEJ87j+IAAACYj2mHiX5zkou6+0fWbHt3kmdXVZI8OcmTZlwbAAAAczJtz+Atk7x5g31/muQzZ1MOAAAA22HaMPjaJF+zwb6vSfIHsykHAACA7TDtMNGfTPLCqrp1kpcl+eckd0jy8CRfl+RRVXW3kwd397tnXehWVNWhJIcOHDiwyDIAAAB2rOru0x9U9ek1d9f+Qp1iW7p77RVHF+bgwYN96aWXLroMAGAHq6pM83lokXZDjYk6Z02ds7Ub6pxHjVV1WXcfPNW+aXsGv22G9QAAALBgU4XB7v6VeRcCAADA9pm2Z/BfVNWdktw5yXu7+32zLwkAAIB5m/ZqoqmqR1fVe5JckeRNSa6oqvdU1aPmVh0AAABzMVUYrKonJnlBkr9L8tgk/3Hy33cl+ZWqesK8CgQAAGD2ph0m+pQkL+jub1+3/Zeq6gVJvi/JxbMsDAAAgPmZdpjoHZP82gb7XpJhzUEAAAB2iWnD4NuS3H2DffdI8lezKQcAAIDtMO0w0e9O8mtVdVWSV3T39VV1RpKHJXlqkm+eV4EAAADM3oZhsKquSNJrNq1kGCp6fVWdSLIvyRlJrkny0iR3nWOdAAAwKn3h3uTIyqLLOK2+cO+iS+Am2qxn8PdzwzAIAABsk7ro6nTv/I/jVZU+sugquCk2DIPdfcE21gEAAMA2mnrReQAAAJbHhmGwqv7TVk9WVZ9VVfe7eSUBAAAwb5v1DF5cVW+tqsdV1f7NTlJVX1FVR5O8K8m/nmmFAAAAzNxmF5A5kOT7kjwryf+qqr9O8tYkVya5LsPVRO+W5GCGK43+UZKv7u4/mWvFAAAA3GybXUDmo0meVVX/M8l/TvLgJPdLcqckZyb5UJK/SfIzSV7a3X8z/3IBAACYhdMuOt/dn8ywjuBL518OAAAA28HVRAEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYodMuLbFeVd0+wzqDN9Dd/ziTigAAAJi7qcJgVe3NsLj8NyW55QaHnTGrogAAAJivaXsGL07ysCS/mORtSa6bW0UAANuoL9ybHFlZdBmb6gv3LroEYAlNGwYfnOSp3X3xPIsBANhuddHV6e5Fl7GpqkofWXQVwLKZ9gIyleRv51kIAAAA22faMPhrSQ7NsxAAAAC2z4bDRKvqq9bcfU2Sn66qs5L8dpLj64/v7j+YfXkAAADMw2ZzBl+bpDMMET35389JcsGaY9budzVRAIAR2w0X40lckAdO2iwMfuW2VQEAwK63Gy7Gk7ggD5y0YRjs7tdtZyEAAABsn6kuIFNV766qe2+w715V9e7ZlgUAAMA8TXs10fOS3HKDfWcmuetMqgEAAGBbTBsGk+EiMadyMMmHZ1ALAAAA22SzpSWenOTJk7ud5FhVfWLdYbdKsj/DOoQAAADsEptdTfTdSX5/cvsxSS5NcuW6Y65L8o4kz599aQAAAMzLZlcT/Y0kv5EMl99N8qzufs821QUAAMAcbdYz+C+6+9vmXQgAAADbZ6owWFXP3GT3p5OsJnlLd//xTKoCAABgrqYKg0mOZLiITJ1i38ntXVVvTPL13b06m/IAAACYh2mXlvj8JO9K8pQMawqeXFvwqZPtX5bkmyfH/cjsywQAAGCWpu0ZvDjJ87v7p9ZsuyLJT1TVGUme3d0PqqrPSfLfkjxhxnUCAAAwQ9P2DP67JG/ZYN9bktxvcvvSJLe/uUUBAAAwX9OGwdUkD9pg37+f7E+G4aNX39yiAAAAmK9ph4n+UpIfrKqzkrw8yQcz9AD+lySPS/I/J8fdN8lfzbpIYLYma4fOXHfP5bwAAMzetGHw5NIS353kuya3K8m1GYLgyf2/leSlM6sOmIuthLaqEvIAAJbQtIvOfzrJM6rqx5N8UZLPSvL+JG/r7g+vOe7Nc6kSAACAmZq2ZzBJMgl+r59TLQAAAGyTqcNgVd0iyZcmOTfDhWJuoLt/dYZ1AQA3k/nBAGxmqjBYVV+Q5FVJ7p5hruB6nUQYBIAdxPxgADYzbc/g8ybHPjzJ25JcN7eKAAAAmLtpw+AXJ7mgu18xz2IAwNBGANge0y46f1WST8yzkGlV1bdU1ZWLrgOA+ejuqX62cqwgCAA3Nm0Y/KkkT6iqM+ZZzOlMLmLzjUmuWGQdAAAAu920w0TPSfK5Sd5RVb+X5Pi6/d3dF860slN7RJKXJ3nKNvxbAAAAS2vaMPiMNbfvcYr9nWSqMFhVT0xyQYbF6y/p7gvW7Nuf5BeTfE2Goak/2N0vmew7I8MFbB4aYRAAAOBmmSoMdve0w0mn8b4kP5zkwUlutW7fxRnmJt4hyX2S/FZVvbW7357kUUl+vbs/Pa+LCwAAAIzFLEPeVLr7Fd39qiQfWru9qm6d5GFJ/nt3X9Pdb0jy6iTfOjnkC5I8uqr+T5J7VNXPbmfdAAAAy2TaYaKpoTvuUJIHJLldkiPdfXlVnZ/k77r7fTezlnsmub6737lm21uTnJ8k3f0Da2q5tLuftEGdh5McTpJzzz33ZpYEAACwnKbqGayqfUn+JMmrknxnkkdnCIRJ8tgkT5tBLbdJsrpu22qSs9Yf2N0HNzpJdx/t7oPdffCcc86ZQVkAAADLZ9phos9Ncpck909ydpK1k/Zem+RBM6jlmiR7123bm+QjMzg3AAAAa0wbBh+S5Ond/cYMVw5d6x8zBMWb651J9lTV2quV3jvJ22dwbgAAANaYNgzeJsl7N9h3Zm7YU7ipqtpTVWcmOSPJGVV1ZlXt6e5rk7wiybOq6tZVdf8MIfSF054bAACA6UwbBv82w9p/p3J+krdt4d98RpKPZZhn+KjJ7ZPrGH5XhuUmPpjkkiSPnywrAQAAwAxNezXRi5NcXFWrSV4y2Xbbqvq2JE/M5Oqd0+juI0mObLDveIZF5QEAAJijaRed/4WqunuSi5I8a7L595J8OsmPdfeL51QfAADATAyr5e1c+/bt29Z/b+p1Brv7aVX180m+OsntMywa/3vd/e55FQcAADAL3euvg3nzVdVczrtdpg6DSdLdlyd5/tptVXXvJN+x0SLwAAAA7DzTXkBmMweSPGEG55mZqjpUVUdXV9evYQ8we1U1lx8AgHmaRRjccbr7WHcfXllZWXQpwAh091Q/Wzl2Nw85AQB2h6UMgwAAAGxOGAQAABghYRAAAGCENryaaFVdkWSaSSu3ml05AAAAbIfNlpb4/UwXBgEAANhlNgyD3X3BNtYBAADANjJnEAAAYISEQQAAgBESBgEAAEZoKcNgVR2qqqOrq6uLLgUAAGBHWsow2N3HuvvwysrKoksBAADYkZYyDAIAALC5qcJgVX1ZVX3Dmvu3q6pLquptVfXjVXXG/EoEAABg1qbtGXxOkn+75v5zk3xdkncmeXySH5pxXQAAAMzRtGHw85NcmiRV9RlJvjHJk7v7YUmenuQR8ykPAACAeZg2DN4mydWT21+a5NZJfnNy/y1Jzp1xXQAAAMzRtGHwvUnuPbn9tUn+qrs/OLm/L8lHZ10YrFVVc/kBAICx2jPlcZck+ZGqemCGuYIXrtn3xUn+bsZ1wQ1099THVtWWjgcAgDGaNgweSfLxJPfLcDGZn1yz795JXjbbsgAAAJinqcJgd1+f5Nkb7HvoTCsCAABg7iw6DwAAMEJT9QxW1XuSbDoJq7vvNpOKZqCqDiU5dODAgUWXAgAAsCNNO2fwdblxGLxdki9Lck2SP5hlUTdXdx9LcuzgwYOPXXQtAAAAO9G0cwYvONX2qrptkv+T5LUzrAkAAIA5u1lzBrv7w0mem+SZsykHAACA7TCLC8h8PMlnz+A8AAAAbJNp5wzeSFXtSXKvDGsQvn1WBQEAsHtV1aJLOK19+/YtugTYEaa9muins/HVRK9O8vUzqwgAYJvt9ACzW8JL96YXn79Jqmou590tdvpjM9k9j09ubNqewWflxmHw40kuT/I73b0606oAALbJrIPG2MMLsyNcM2/TXk30yJzrAAAAYBtNdQGZqjqnqu65wb57VtXZsy0LuCn279+fqprpT5KZn3P//v0LbikAAKYdJvq8JMeT/NdT7HtyhgXoHz6rooCb5sSJE7ti6MdumP8AALDspl1a4suT/O4G+16T5P6zKQcAAIDtMG0Y3Jdko4vEXJ2hZxAAAIBdYtow+E9J7rvBvvsmef9sygEAAGA7TBsGX57kh6rqBusJTu4/Lcmvz7qwm6OqDlXV0dVVK14AAACcyrRh8FlJ/jLJq6vqvVX15qp6b5JXJ3lbkovmVeBN0d3HuvvwysrKoksBAADYkaZdZ/CjVXV+km9N8tUZ5gi+K8PFY17U3Z+aX4kAAADM2rRLS6S7P5nklyY/AMCC7N+/PydOnJj5eWe97Mu+ffty/PjxmZ4TgNmZOgwmSVXdK8n5SfYnuSrJ67v7r+ZRGABwatYUBWAWpgqDVbUnyQuSfEuSta/sXVUvSXJBd18/+/IAWAZ6sgBg55m2Z/DCJA9P8swkL0rygSR3TPKoyb53T/4LADeiJwsAdp5pw+CjkvyP7n72mm2XJ3l2VZ2R5NsiDAIAAOwa0y4tcackb9xg359M9gMAALBLTBsG35fk/hvs+7LJfgAAAHaJaYeJvjjJ06vq05Pb788wZ/Cbkzw9yY/OpzwAAADmYdoweCTJ3ZJcNLl9UiW5ZLIdAACAXWKqMNjdn0ryiKp6dpIHZFhn8HiS13X3O+ZYHwAAAHOwpUXnu/vtSd6+dltV3TvJd3T3k2ZZGAAAAPMz7QVkNnMgyRNmcB4AAAC2ySzCIAAAALuMMAgAADBCSxkGq+pQVR1dXV1ddCkAAAA70lKGwe4+1t2HV1ZWFl0KAADAjrTh1USr6ookPcU5bjW7cgAAANgOmy0t8fuZLgwCAACwy2wYBrv7gm2sAwAAgG20lHMGAQAA2NxmcwYfkOQt3X3N5PamuvuPZloZwALt378/J06cmPl5q2qm59u3b1+OHz8+03MCAOOw2ZzBP0xyvyRvntzeaP5gTfadMcvClsGsP/Sd1G0qJ8zbiRMndsVzbV6vMwDA8tssDH5lknesuc0WTftBsqp2xYdOAABgeWx2AZnXneo2AAAAu99mPYP/oqpukeQW3f2pNdsenOReSf6gu/98TvUBAAAwB1OFwSSXJLkuyaOTpKoel+R5k32frKqv7+7XzqE+AAAA5mDapSXul+S319x/apLnJ1lJ8ookT59xXQAAAMzRtGHw9knemyRVdSDJ5yT5ue7+SJJfTvJF8ykPAACAeZg2DF6d5HaT2w9MclV3/+Xk/vVJzpxxXQAAAMzRtHMG/yTJ06rqU0m+JzccMnogyT/NujAAAADmZ9qewe9Psj/JqzP0Ah5Zs++bkrxxtmUxFvv3709VzfQnyczPuX///gW3FAAAzNZUPYPd/XdJ7llVt+vuD63b/d1JPjDzyhiFEydOpLsXXcZpnQyZAACwLKYdJpokOUUQTHe/bXblADdHX7g3ObKy6DJOqy/cu+gSAABGb0thENjZ6qKrd01Pax9ZdBUAAOM27ZzBXaWqDlXV0dXV1UWXAgAAsCMtZRjs7mPdfXhlZecPlwMAAFiEpQyDAAAAbE4YBAAAGCFhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAERIGAQAARkgYBAAAGCFhEAAAYISEQQAAgBESBgEAAEZIGAQAABghYRAAAGCEhEEAAIAREgYBAABGaM+iCwBg+fWFe5MjK4su47T6wr2LLgEAto0wCMDc1UVXp7sXXcZpVVX6yKKrAIDtYZgoAADACC1lz2BVHUpy6MCBA4suBQBmzrBbAGahdsOwnZvq4MGDfemlly66jNOqql0xfGoedsvfrs7Z2g117oYaE3XOmjpna7fUOWtj/bvnRXvOlvacrd3QnlV1WXcfPNU+w0QBAABGSBgEAAAYoaWcMzhP+/fvz4kTJ2Z+3qqa6fn27duX48ePz/ScAADA8hAGt+jEiRM7flxwMvtwCQAALBdhkIVyRTwAAFgMYZCFshA1AAAshjAIcAp6rQGAZScMwpLZDfNF9+3bt+gSTkuvNQCw7IRBWCLzCC+7YTFVAAC2zjqDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACO0Z9EF7DZ94d7kyMqiyzitvnDvoksAAAB2MGFwi+qiq9Pdiy7jtKoqfWTRVQAAADuVMAjAtqiqRZdwWvv27Vt0CQCwbYRBAOZuHiMqqmpXjNSYF+EagJtLGASAXUa4BmAWXE0UAABghIRBAACAETJMlIUz7wUAALafMMhCmfcCAACLsZTDRKvqUFUdXV1dXXQpAAAAO9JShsHuPtbdh1dWVhZdCgAAwI60lGEQAACAzQmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjtGfRBQDsVFW16BJOa9++fYsuAQDYpYRBgFPo7pmfs6rmcl4AgJtCGLwJ9BYAAAC7nTC4RXoLAACAZeACMgAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjNCeRRcAAADcdFU1l+O7+6aUwy4iDAKwo2zlQ81WjvWhBlhWXt+4qYRBAHYUH2oAYHuYMwgAADBCwiAAAMAICYMAAAAjJAwCAACM0K65gExV3SHJK5N8Msn1SR7Z3e9fbFUAAAC7027qGbwqyZd39/lJfjXJdyy4HgAAgF1r1/QMdvf1a+6eleTti6oFAABgt9v2nsGqemJVXVpV11XVC9bt219Vr6yqa6vq8qp6xLr996mqP03yxCRv2cayb5KqmupnK8duZYFlAACAjSyiZ/B9SX44yYOT3GrdvouTfCLJHZLcJ8lvVdVbu/vtSdLdf5HkvlX18CQ/mORx21b1TWDh5NnZagie9nj/jwAAGKttD4Pd/YokqaqDST775PaqunWShyW5V3dfk+QNVfXqJN+a5GlVdcvuvm5y+GqSj25v5SyS0AYAwHYYUyfETpozeM8k13f3O9dse2uS8ye3v7iqfjTDlUQ/nuTbT3WSqjqc5HCSnHvuufOrFgAAWDo7MbTNy04Kg7fJ0OO31mqGi8Wku9+Y5AGnO0l3H01yNEkOHjw4nv+TAAAAW7CTlpa4Jsneddv2JvnIAmoBAABYajspDL4zyZ6quseabfeOJSQAAABmbhFLS+ypqjOTnJHkjKo6s6r2dPe1SV6R5FlVdeuqun+ShyR54RQjJowAAA7cSURBVHbXCAAAsOwW0TP4jCQfS/K0JI+a3H7GZN93ZVhu4oNJLkny+JPLSgAAADA7i1ha4kiSIxvsO57kodtZDwAAwBjtpDmDAAAAbBNhEAAAYISEQQAAgBFayjBYVYeq6ujq6vo17AEAAEiWNAx297HuPryysrLoUgAAAHakpQyDAAAAbE4YBAAAGCFhEAAAYISEQQAAgBHas+gCAAAYn6qay7HdfVPKgVESBgEApiC8zNZY/27YSYRBAIApCC/AsjFnEAAAYISEQQAAgBFayjBYVYeq6ujq6uqiSwEAANiRljIMdvex7j68srKy6FIAAAB2pKUMgwAAAGxOGAQAABghYRAAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAERIGAQAARkgYBAAAGKGlDINVdaiqjq6uri66FAAAgB1pKcNgdx/r7sMrKyuLLgUAAGBH2rPoAgB2u6qay7HdfVPKAQCYijAIcDMJbexUW/nyYSvHe8wDLAdhEACWlNAGwGaWcs4gAAAAm9MzCCNk6BgAAMIgjJDQBgCAYaIAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjNBShsGqOlRVR1dXVxddCgAAwI60lGGwu4919+GVlZVFlwIAALAjLWUYBAAAYHPCIAAAwAgJgwAAACMkDAIAAIyQMAgAADBCwiAAAMAICYMAAAAjJAwCAACMkDAIAAAwQsIgAADACAmDAAAAIyQMAgAAjJAwCAAAMELCIAAAwAgJgwAAACO0Z9EFzENVHUpyKMnVVfV3i65nCmcnuWrRRSwR7Tlb2nN2tOVsac/Z0p6zoy1nS3vOlvacrd3QnnfdaEd193YWwilU1aXdfXDRdSwL7Tlb2nN2tOVsac/Z0p6zoy1nS3vOlvacrd3enoaJAgAAjJAwCAAAMELC4M5wdNEFLBntOVvac3a05Wxpz9nSnrOjLWdLe86W9pytXd2e5gwCAACMkJ5BAACAERIGWVpVdV5VdVUt5RIqO0VVnVtV11TVGYuuBTZTVUeq6kWLrgMAdgphcE6q6sur6k+qarWqjlfVH1fVlyy6rt2qqh5RVZdOQsf7q+p3qurLF13XbjarNu3uf+zu23T39fOocyerqn+oqk9U1dnrtv/F5IuI86rqBVX1w4uqcaebtOHHquojVfXhyevm46rK+9NNUFV/WFUnquqWi65lmVTVbSaP1Ues2XZWVf1jVX2j5/nWeN7fdNO87yymst1t0q7/ft22C6rqDYuqabt40s1BVe1N8ptJ/leS/UnunOSiJNfN8N8YTW9XVX1vkp9O8iNJ7pDk3CTPS/KQRda1m22lTcf0WLuJ3pPkW07eqaovSnKraX9Z+yZJDnX3WRkWxX1Okh9I8ouLLWn3mXwI/IokneQ/LrSYJdPd1yQ5nORnquqcyeYfS3Jpd7/8dL/veX5KUz/vtzryZATtfbPed2AtYXA+7pkk3X1Jd1/f3R/r7td0918mSVU9tqr+evKN2Duq6osn2+9UVf9vVV1ZVe+pqiedPOFkeNPLq+pFVXV1kgsW8Ydtt6paSfKsJE/o7ld097Xd/cnuPtbdT62qW1TV06rq76vqQ1X161W1f6NzVdUvTnrB3ltVPzzGoY1TtOmNHmubtbPhuHlhkkevuf+YJL86uf01SR6Z5PsnPbDHkn/5BvIHquovk1xbVXsmbXjg5EnG2NPQ3avd/eok35TkMVV1r0k7PG/Sc33NZJTFHavqpyc9YH9TVf/m5Dk2ex0dgUcneVOSF2R4HCZJqup2VXWsqq6uqj+bvPa9Yc3+n6mqKyb7L6uqr1iz70hVvWzyevCRqnpbVd2zqn6wqj44+b2v2c4/clG6+zVJfivJz1bVA5M8PMkTqupwpn+ef34Nvbcfrqq3V9XoQ/smz/ufr6rfrqprk3xlVd2yqn68ht7Yf66q/11Vt0qSqnpgVf3TpL0/kOSXF/k3bYPN3ndOvn9s5XVzw/efqjq7qn5z8pg9XlWvrxH24E4eW++dvA7+bVU9aLL9S6vqjZP2eX9V/VxVfeaa3+uqelJVvbuqrqqq5+609ttRxSyRdya5vqp+paq+tqr2ndxRVf8lyZEMT+K9Gb69/dDkgXEsyVsz9CQ+KMn3VNWD15z3IUlenuS2SV68HX/IDvDvkpyZ5JUb7H9SkocmOT/JnZKcSHLxBsf+SpJPJTmQ5N9k+KD+nbMsdpc4XZsmN36sbaWdx+ZNSfZOPuSdkeEDzcl5aa/J0H4/NhlKe2jN731Lkq9Pctvu/tS2VrzDdfebk/xThl6uZPjQ/YwkZ2cYYfHGJG+Z3H95kp9MkilfR5fZozM83l6c5MFVdYfJ9ouTXJvkjhk+ND5m3e/9WZL7ZBjJ8pIkL6uqM9fsP5Thw+e+JH+e5HczfH64c4Yvlv6fefwxO9STkzwww+Pu+7r7/d19NFM8z5NUhsfna5LcPsl/S/Liqvrcbax/xzrF8/4RSZ6d5Kwkb0jyoxm+bL9PhvfxOyd55ppT3DHDY/iuGXpxl9lm7zsnTfW6OYWnZPj/ck6GkUQ/lGH0wWhMnqNPTPIlk97sByf5h8nu6zO8Lpyd4fPVg5J817pT/KckB5N8cYbPV98+/6qnJwzOQXdfneTLMzxZfiHJlVX16skb83dmeMP4sx68q7svT/IlSc7p7md19ye6+92T3/3mNad+Y3e/qrs/3d0f2+Y/a1Ful+SqTT4s/9ckT+/uf+ru6zIE7W+sdb1Uk7b/2iTfM+kJ+2CSn8oN23csTtemyY0fa1O184id/Jb2q5P8TZL3TvE7P9vdV4zoubxV78vwwS5JXtndl3X3xzN8ifHx7v7VyTzVl2b4cieZ7nV0KdUw3/euSX69uy9L8vdJHjH5oPiwJBd290e7+x0Zvhj7F939ou7+UHd/qrt/Isktk6wNKK/v7t+dvGa8LMOHwud09yeT/FqS86rqtnP/I3eA7j6R5O1J/lWSV0zxK2uf5/dLcpsMbfeJ7v6DDFNKvmXTM4zL2uf9b3T3H3f3pzOEmccmeXJ3H+/uj2SY5rD2uf3pDI/z60byunq6951pXzdP55NJPivJXSejiF7fy7su3asmPXwfrqoPZ5g+kwyB75ZJvqCqPqO7/6G7/z5JJm38psnr5z9k+HLs/HXn/dHJ4/YfM0zR2VHPeR/k5qS7/zqToZxV9XkZvrH56SR3yfAmvd5dk9xp8uA76Ywkr19z/4q5FLuzfSjJ2VW1Z4Pwctckr6yqT6/Zdn2Gb6/WH/cZSd5fVSe33SLadKNAuL5dpm3nsXphkj9K8jlZM1TnNMb42NuKOyc5Prn9z2u2f+wU928zuT3N6+iyekyS13T3VZP7L5lsuyTDe/3ax9sNHntV9ZQMX1TeKcOXmHszfMt90vr2vmrNBaNOfui+TZK17b6UqupRSc5L8toMPVWPO82vrG3rOyW5YhJuTro8w2Odwdrn/dq2OydDAL9szXt4ZXh+n3TlJPiMxened6Z93Tyd52b4Avg1k7Y/2t3P2Wqxu8RDu/u1J+9U1QVJvrO731VV35OhHb6wqn43yfd29/uq6p4ZelkPZniM7kly2brzrn0sX57htWDH0DO4Dbr7bzLM4bhXhgfE3U9x2BVJ3tPdt13zc1Z3f93aU82/2h3njUk+nmGI4qlckeRr17Xbmd29/huyKzJ8s3j2muP2dvcXzrH2nep0bZrc+LE2bTuP0qR3/z1Jvi437i3Y6Hm7fvtHM7yRnHTH2VS3+9Rw5eU7ZxgathXTvI4uncm8qYcnOb+qPjCZM/XkJPfO8IXNp5J89ppfucua3/2KDBfueHiSfd192ySrGT5os0ZV3T7DiJLHZhgt8fCqesBk9zTP8/clucu6+ULnZrqRBEvvFM/7tW13VYYA84Vrntsr3b020IzqM9Jp3ne2asP3n+7+SHc/pbvvlmHI+PeenC83Jt39ku4+OQKjM3wZlCQ/n6Fn9h7dvTfDMNr1r593WXP73AyvBTuGMDgHVfV5VfWUqvrsyf27ZOgSflOS5yf5vqr6tzU4UFV3TfLmJFdPJqjeqqrOmEyiHvVyFN29mmFOwMVV9dCq+ldV9RmTuZg/luR/J3n2pA1TVedU1Y2uiNnd788wT+MnqmpvDRdEuXtVre/KX3pTtOmpTNXOI/cdSb6qu69dt/2fk9xtit//i0yG9VXVf8iNh5ksvclz8xsyDD18UXe/bYunGOvr6EMz9NR/QYb5VPdJ8vkZekQfneGD4pHJc/3zcsMLT5yVISxemWRPVT0zQ88gN/ZzSV7V3f/f5D3l+5P8Qg3LeEzzPP/TDHM3v3/ymvvADB+uf22ONe940zzvJ72pv5DkpyahPFV15xHNB97IRu87W7Xh+09VfcPks2oluTrDa82olpKqqs+tqq+aPNc/nuGLiZNtcFaGdrlm8vr6+FOc4qlVtW+SB747wzDdHUMYnI+PJLlvkj+t4SpYb0ryV0me0t0vyzAh+iWT416VZP9kyM2hDG/i78nwLdjzk6xsf/k7S3f/ZJLvzTAR+soM3/4/MUPb/UySV2cYvvCRDG193w1O9egkn5nkHRkugPLyDOPgR+c0bXoqW2nnUeruv+/uS0+x6xczzDP4cFVt1L7J8AZxKMNQu0dm4/8Xy+jY5HF1RZKnZxhy821bPcmIX0cfk+SXe1jz8wMnfzKEl0dmeG6vJPlAhqFll+T/X+rod5P8ToYLn12e4YOOIczrVNVDM1wL4Kknt3X38zNcWOOZmeJ53t2fyHDRuK/N8Nh8XpJHT0YPjdFWn/c/kORdSd5Uw5WuX5sbzm0dnU3ed7Zqs/efe2Ro62syjCx6Xnf/4Qz+zd3klhmWP7kqw+vo7TP0ACbJ92W42NFHMnxhcaqg9xsZho7+RYYrEu+opZNqeeeAAgDrVdWPJrljd6+/qigAM1RVnWEI6bsWXctG9AwCwBKbTF3415OpCV+aYWjZZkvLADASriYKAMvtrAxDQ++U5INJfiLDsCUARs4wUQAAgBEyTBQAAGCEhEEAAIAREgYBAABGSBgEAAAYIWEQAABghIRBAACAEfq/Ry06FdNP4rEAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 1080x720 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "files = ['data/{}/{}.iloci.tsv'.format(s, s) for s in specieslist]\n",
    "test = []\n",
    "for f in files:\n",
    "    data = pd.read_csv(f, sep='\\t')\n",
    "    siloci = data.loc[data.LocusClass.isin(['siLocus'])]\n",
    "    test.append(siloci.Length)\n",
    "plt.boxplot(test, labels = specieslist, showfliers = False)\n",
    "plt.ylabel('siLocus Length (bp)')\n",
    "plt.yscale('log')\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": "3.7.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}