{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# chromVAR"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "jp-MarkdownHeadingCollapsed": true,
    "tags": []
   },
   "source": [
    "`chromVAR` is a method for computing differential motif accessibility. Its original implementation is [available in Bioconductor](https://bioconductor.org/packages/chromVAR), and it has been described in [Schep et al., 2017](https://www.nature.com/articles/nmeth.4401)."
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Prepare a demo object"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "%autoreload 2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "from anndata import AnnData\n",
    "import chame as ch"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "from chame.tl.chromvar import _get_background_peaks, _compute_expectations_core, _compute_deviations_core"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "np.random.seed(1)\n",
    "x = np.random.binomial(5, 0.2, size=(100,10))  # cell x peaks\n",
    "\n",
    "adata = AnnData(x)\n",
    "adata.obs_names = [f\"cell{i+1}\" for i in range(adata.n_obs)]\n",
    "adata.var_names = [f\"peak{j+1}\" for j in range(adata.n_vars)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulate sequences\n",
    "adata.var[\"length\"] = np.random.choice(np.arange(10, 100), size=adata.n_vars)\n",
    "adata.var[\"sequence\"] = [''.join(np.random.choice([\"A\", \"C\", \"G\", \"T\"], size=i)) for i in adata.var.length]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Compute some peak statistics\n",
    "adata.var[\"gc\"] = ch.util.seq.count_gc(adata.var[\"sequence\"])\n",
    "adata.var[\"n_fragments\"] = adata.X.sum(axis=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AnnData object with n_obs × n_vars = 100 × 10\n",
       "    var: 'length', 'sequence', 'gc', 'n_fragments'"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "adata"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Simulate motif scanning results\n",
    "n_motifs = 5\n",
    "motifs_in_peaks = np.random.binomial(1, .3, size=(n_motifs, adata.n_vars))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run chromVAR"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/usr/local/opt/python@3.8/Frameworks/Python.framework/Versions/3.8/lib/python3.8/site-packages/chame/tl/chromvar.py:147: RuntimeWarning: invalid value encountered in true_divide\n",
      "  z[fail_filter] = np.nan\n",
      "2022-06-04 14:55:29.565 | INFO     | chame.tl.chromvar:chromvar:62 - Added key deviations to adata.obsm.\n",
      "2022-06-04 14:55:29.566 | INFO     | chame.tl.chromvar:chromvar:65 - Added key z to adata.obsm.\n"
     ]
    }
   ],
   "source": [
    "ch.tl.chromvar(adata, motifs_in_peaks, bias=\"gc\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "AxisArrays with keys: deviations, z"
      ]
     },
     "execution_count": 26,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "adata.obsm"
   ]
  }
 ],
 "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": "3.8.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}