{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "# Data pre-processing\n",
    "156,049 mice nuclei from developing brain and spinal cord at age of p2 or\n",
    "p11 mice were profiled by [SPLiT-seq](https://www.ncbi.nlm.nih.gov/geo/query/acc.cgi?acc=GSE110823),\n",
    "where 26,894 genes were detected."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import scipy.io\n",
    "import pandas as pd\n",
    "import loompy\n",
    "import rpy2.robjects as robjects\n",
    "saveRDS = robjects.r[\"saveRDS\"]\n",
    "from rpy2.robjects import pandas2ri\n",
    "pandas2ri.activate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "pycharm": {
     "is_executing": false,
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "E:/DISC/reproducibility/data/BRAIN_SPLiT/raw.loom\n",
      "(26894, 156049)\n"
     ]
    }
   ],
   "source": [
    "data_path = \"E:/DISC/reproducibility/data/BRAIN_SPLiT/original_data/GSM3017261_150000_CNS_nuclei.mat\"\n",
    "data = scipy.io.loadmat(data_path)\n",
    "gene_bc_sparse = data[\"DGE\"].transpose()\n",
    "gene_name = pd.Series(data['genes']).str.strip(' ').values\n",
    "sample_type = pd.Series(data['sample_type']).str.strip(' ').values\n",
    "barcode_str = data[\"barcodes\"].squeeze().astype(np.str)\n",
    "cell_id = pd.Series(np.repeat(\"Cell\", barcode_str.size)).str.cat(barcode_str, sep='_').values\n",
    "saveRDS(pd.Series(pd.Series(data['cluster_assignment']).str.strip(' ').values, index=cell_id), \"E:/DISC/reproducibility/data/BRAIN_SPLiT/cell_type.rds\")\n",
    "\n",
    "output_path = \"E:/DISC/reproducibility/data/BRAIN_SPLiT/raw.loom\"\n",
    "row_attrs = {\"Gene\": gene_name}\n",
    "col_attrs = {\"CellID\": cell_id, \"SampleID\": sample_type}\n",
    "loompy.create(output_path, gene_bc_sparse, row_attrs, col_attrs)\n",
    "print(output_path)\n",
    "print(gene_bc_sparse.shape)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "pycharm": {
     "name": "#%% md\n"
    }
   },
   "source": [
    "Reference: \n",
    "\n",
    "1. Rosenberg, A. B. et al. Single-cell profiling of the developing mouse brain and spinal cord with split-pool barcoding. Science 360, 176-182 (2018)."
   ]
  }
 ],
 "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": "3.7.2"
  },
  "pycharm": {
   "stem_cell": {
    "cell_type": "raw",
    "metadata": {
     "collapsed": false
    },
    "source": []
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}