{
 "cells": [
  {
   "cell_type": "markdown",
   "id": "94299699-3b41-4149-a870-db571ffd944c",
   "metadata": {},
   "source": [
    "# Copy Number Variation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "88be5cea-2412-41f3-bd2c-8447fb7616a7",
   "metadata": {},
   "outputs": [],
   "source": [
    "from pylluminator.samples import Samples\n",
    "from pylluminator.cnv import copy_number_variation\n",
    "from pylluminator.utils import load_object, save_object, set_logger\n",
    "from pylluminator.visualizations import manhattan_plot_cnv\n",
    "\n",
    "set_logger('WARNING')  # set the verbosity level, can be DEBUG, INFO, WARNING, ERROR"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "1370e2cc-bb01-40c4-828f-98df3dabc7f2",
   "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": "0988935f-7779-46e0-b546-145c0652bcdc",
   "metadata": {},
   "outputs": [],
   "source": [
    "my_samples = Samples.load('preprocessed_samples')\n",
    "my_samples"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "b63ff882-d0a4-421a-83c4-8f4131f784f3",
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_sheet = my_samples.sample_sheet\n",
    "sample_sheet"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "5868c013-7901-46e1-8504-e9dc9c33590f",
   "metadata": {},
   "source": [
    "## Get CNVs for a sample"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "33992775-4ff4-41b3-8adc-749d93e01bc0",
   "metadata": {},
   "outputs": [],
   "source": [
    "name = 'LNCAP_500_1'  # sample name\n",
    "normalization_samples = sample_sheet[sample_sheet.sample_type == 'PREC'].sample_name.values\n",
    "print('normalization_samples : ', normalization_samples)\n",
    "\n",
    "ranges, signal_bins_df, segments_df = copy_number_variation(my_samples, sample_label=name, normalization_sample_labels=normalization_samples)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "85f5adb1-d7c8-4f87-a21f-71a27dec1b31",
   "metadata": {},
   "source": [
    "## Visualize CNVs and segments"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "819b8510-78ba-49f3-8d14-b91606f40b9a",
   "metadata": {},
   "source": [
    "Plot the identified segments and CNV values"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "336ccc68-5994-455b-aeb0-d7eb5273c2c1",
   "metadata": {},
   "outputs": [],
   "source": [
    "manhattan_plot_cnv(signal_bins_df, segments_df)"
   ]
  }
 ],
 "metadata": {
  "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": "3.12.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}