{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "a9ac2491-124b-4032-8a58-70b9613841c8",
   "metadata": {},
   "source": [
    "# Sample quality control"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "5ed7cef2-9031-47e1-8d51-6191baba5cd2",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pylluminator.samples import Samples\n",
    "from pylluminator.utils import set_logger\n",
    "from pylluminator.annotations import Channel\n",
    "from pylluminator.quality_control import *\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd\n",
    "\n",
    "set_logger('WARNING')  # set the verbosity level, can be DEBUG, INFO, WARNING, ERROR"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "3a036692-253f-40db-b5c0-dab9007db71b",
   "metadata": {},
   "source": [
    "## Load pylluminator Samples\n",
    "\n",
    "We assume that you have already processed the .idat files according to your preferences and saved them. If not, please refer to notebook `1 - Read data and get beta values` before going any further."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0170564a-0d57-4cd5-8c5e-5d779dd1bb78",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_samples = Samples.load('preprocessed_samples')\n",
    "my_samples"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "361773da-c388-4f3b-84de-f1a83e073b55",
   "metadata": {},
   "source": [
    "## Chose a sample and print QCs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "00eb6ccd-4987-4d84-ae25-c8c010d512a4",
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_name = 'LNCAP_500_3'\n",
    "detection_stats(my_samples, sample_name)\n",
    "intensity_stats(my_samples, sample_name)\n",
    "nb_probes_stats(my_samples, sample_name)\n",
    "type1_color_channels_stats(my_samples, sample_name)\n",
    "dye_bias_stats(my_samples, sample_name)\n",
    "betas_stats(my_samples, sample_name)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "fc19e3c4-e208-4b65-a45a-e100bb3f1256",
   "metadata": {},
   "source": [
    "## Plot the number of beads per probe"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "312542d6-00b4-49a2-8d22-f2738d43378e",
   "metadata": {},
   "source": [
    "This will work only if you have kept the .idat data when reading the samples (parameter `keep_idat=True`)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "aad3e01b-35fe-46c0-9e9b-6ab72f3ed9d5",
   "metadata": {},
   "outputs": [],
   "source": [
    "count_beads = my_samples.idata[sample_name][Channel.RED].groupby('n_beads').count()\n",
    "\n",
    "# don't display the (very) long tail of the graph, stop at the last bin that contains at least 5 probes\n",
    "five_probes_min = count_beads[count_beads.mean_value > 5]\n",
    "max_more_than_five_probe = five_probes_min.index.max()\n",
    "\n",
    "# plot\n",
    "plt.figure(figsize=(10, 7))\n",
    "plt.bar(five_probes_min.index, five_probes_min['std_dev'])\n",
    "plt.xlabel('Number of detected beads per probe')\n",
    "_ = plt.ylabel('Probes count')"
   ]
  }
 ],
 "metadata": {
  "language_info": {
   "name": "python"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}