{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Loading CCI results\n",
    "\n",
    "This tutorial shows how to load CCI results from different CCI tools"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import mmcci"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## stLearn\n",
    "\n",
    "We can load stLearn outputs from the path of the `h5ad` file that has been run through stLearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stlearn = mmcci.io.read_stLearn('/path/to/stLearn.h5ad')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "We can also convert AnnData objects that have been processed with stLearn"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "stlearn = mmcci.io.convert_stLearn(adata)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CellPhoneDB\n",
    "\n",
    "We can load CellPhoneDB outputs from the interaction scores text file"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cellphonedb = mmcci.io.read_CellPhoneDB('/path/to/interaction_scores.txt')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Squidpy\n",
    "\n",
    "We can load Squidpy results from running `squidpy.gr.ligrec`, which is a Python dict.\n",
    "This can be saved as a pkl file and loaded in."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import pickle\n",
    "\n",
    "with open('/path/to/squidpy_dict.pkl', 'rb') as f:\n",
    "    squidpy_dict = pickle.load(f)\n",
    "\n",
    "squidpy = mmcci.io.read_Squidpy(squidpy_dict)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "You can also load single networks such as `squidpy.gr.interaction_matrix`"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "squidpy = mmcci.io.read_network('/path/to/network.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## CellChat\n",
    "\n",
    "We can load CellChat outputs from the path of the `cellchat_out@dr`, saved as a `csv` file."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "cellchat = mmcci.io.read_CellChat('/path/to/cellchat_dr.csv')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## NATMI\n",
    "\n",
    "We can load NATMI outputs from the `Edges_lrc2p.csv` file that is outputted from NATMI"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "natmi = mmcci.io.read_NATMI('/path/to/Edges_lrc2p.csv')"
   ]
  }
 ],
 "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": "3.9.undefined"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}