{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "source": [
    "# Quick start"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download sample data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "%%bash\n",
    "mkdir -p data\n",
    "cd data\n",
    "wget --quiet http://biodatageeks.ii.pw.edu.pl/sequila/data/NA12878.multichrom.md.bam\n",
    "wget --quiet http://biodatageeks.ii.pw.edu.pl/sequila/data/NA12878.multichrom.md.bam.bai\n",
    "wget --quiet http://biodatageeks.ii.pw.edu.pl/sequila/data/Homo_sapiens_assembly18_chr1_chrM.small.fasta\n",
    "wget --quiet http://biodatageeks.ii.pw.edu.pl/sequila/data/Homo_sapiens_assembly18_chr1_chrM.small.fasta.fai\n",
    "wget --quiet https://raw.githubusercontent.com/bigdatagenomics/mango/master/mango-pileup/examples/data/alignments.ga4gh.chr17.1-250.json"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "base_path = f\"{os.getcwd()}/data\"\n",
    "\n",
    "bam_path = f'{base_path}/NA12878.multichrom.md.bam'\n",
    "ref_path=f'{base_path}/Homo_sapiens_assembly18_chr1_chrM.small.fasta'\n",
    "sample_id= 'NA12878'\n",
    "table_name = 'reads'\n",
    "\n",
    "app_name = \"sequila\"\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Check if your env variables are properly set"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Ensure that:\n",
    "\n",
    "* you use Java 11 in have set JAVA_HOME accordingly,\n",
    "*  Apache Spark 3.1.2 in SPARK_HOME,\n",
    "*  SeQuiLa Scala package is in your PYSPARK_SUBMIT_ARGS (i.e. --package parameter)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "%%bash\n",
    "echo \"JAVA_HOME is $JAVA_HOME\"\n",
    "echo \"SPARK_HOME is $SPARK_HOME\"\n",
    "echo \"PYSPARK_SUBMIT_ARGS is $PYSPARK_SUBMIT_ARGS\"\n",
    "java -version\n",
    "spark-shell --version"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Install pysequila and pandas"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "!pip install pysequila==$VERSION pandas"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Initialize PySequila Session"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from pysequila import SequilaSession\n",
    "ss = SequilaSession \\\n",
    "    .builder \\\n",
    "    .appName(f'{app_name}') \\\n",
    "    .getOrCreate()\n"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create a table over BAM files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "ss.sql(f'''CREATE TABLE IF NOT EXISTS {table_name} \\\n",
    "         USING org.biodatageeks.sequila.datasources.BAM.BAMDataSource \\\n",
    "         OPTIONS(path \"{bam_path}\")''')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Run a simple select statement"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "pd.options.display.max_columns = None\n",
    "ss.sql(f'''SELECT sample_id, contig, pos, cigar, seq \\\n",
    "        FROM {table_name} LIMIT 5''').toPandas()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Calculate pileup"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    },
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "ss.sql(f'''SELECT contig, pos_start, pos_end, ref, coverage, countRef, alts \\\n",
    "      FROM  pileup('{table_name}', '{sample_id}', '{ref_path}', true, true ) LIMIT 10''').toPandas()\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "ss.stop()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "pysequila",
   "language": "python",
   "name": "pysequila"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.9"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}