152 lines (151 with data), 4.7 kB

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%pylab inline"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "from IPython.display import display\n",
    "import re"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "counts = pd.read_table('read_counts.txt', index_col=0).T\n",
    "\n",
    "rna_types = [s.split('.')[0] for s in counts.index.tolist() if s.endswith('.mapped')]\n",
    "rna_types = 'univec,spikein,rRNA,miRNA,piRNA,Y_RNA,srpRNA,tRNA,snRNA,snoRNA,lncRNA,mRNA,tucpRNA'.split(',')\n",
    "nongene_types = ['intron', 'promoter', 'enhancer', 'repeats']\n",
    "\n",
    "def gradient_func(val):\n",
    "    return '<span style=\"background: linear-gradient(90deg, #d65f5f {0}%, transparent 0%)\">{0:.3f}</span>'.format(val)\n",
    "\n",
    "columns = ['clean.unmapped']\n",
    "rna_types_enabled = []\n",
    "for rna_type in rna_types + nongene_types:\n",
    "    if rna_type + '.mapped' in counts.columns:\n",
    "        columns.append(rna_type + '.mapped')\n",
    "        rna_types_enabled.append(rna_type)\n",
    "rna_types = rna_types_enabled\n",
    "columns += ['other.mapped']\n",
    "counts_unmapped = counts.loc[:, 'other.unmapped']\n",
    "counts = counts.loc[:, columns]\n",
    "counts.rename(columns={key:re.sub('(\\.mapped)|(\\.unmapped)$', '', key) for key in columns}, inplace=True)\n",
    "counts['unannotated'] = counts['other'].subtract(counts.loc[:, nongene_types].sum(axis=1), axis=0)\n",
    "counts['unmapped'] = counts_unmapped\n",
    "#counts['unmapped'] = counts['clean'].subtract(counts.loc[:, rna_types + ['other']].sum(axis=1), axis=0)\n",
    "counts = counts.loc[:, ['clean'] + rna_types_enabled + ['unannotated', 'unmapped']]\n",
    "display(counts.style \\\n",
    "        .set_caption('Read counts'))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "percent_by_clean = counts.copy()\n",
    "percent_by_clean = 100*percent_by_clean.div(percent_by_clean.loc[:, 'clean'], axis=0)\n",
    "percent_by_clean.drop(columns='clean', inplace=True)\n",
    "display(percent_by_clean.style \\\n",
    "            .set_caption('Reads percentage by clean reads') \\\n",
    "            .format(gradient_func))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "display(percent_by_clean.mean(axis=0).to_frame().T.style \\\n",
    "            .set_caption('Average reads percentage by clean reads') \\\n",
    "            .format(gradient_func))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "percent_by_mapped = counts.copy()\n",
    "rna_types_remove = [rna_type for rna_type in ['univec', 'rRNA', 'spikein', 'unmapped'] if rna_type in percent_by_mapped.columns]\n",
    "percent_by_mapped = 100*percent_by_mapped.div(percent_by_mapped['clean'] \\\n",
    "                                              - percent_by_mapped.loc[:, rna_types_remove].sum(axis=1), axis=0)\n",
    "percent_by_mapped.drop(columns=['clean'] + rna_types_remove, inplace=True)\n",
    "display(percent_by_mapped.style \\\n",
    "            .set_caption('Reads percentage by mapped') \\\n",
    "            .format(gradient_func))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "display(percent_by_mapped.mean(axis=0).to_frame().T.style \\\n",
    "            .set_caption('Averge reads percentage by mapped reads') \\\n",
    "            .format(gradient_func))"
   ]
  },
  {
   "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": "3.6.7"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}