{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Secondary Structure Element Demo\n",
    "\n",
    "This demo shows how to get a dataset of secondary structure elements\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkConf, SparkContext\n",
    "from mmtfPyspark.io import mmtfReader\n",
    "from mmtfPyspark.mappers import StructureToPolymerChains\n",
    "from mmtfPyspark.filters import ContainsLProteinChain\n",
    "from mmtfPyspark.datasets import secondaryStructureElementExtractor"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf = SparkConf().setMaster(\"local[*]\") \\\n",
    "                      .setAppName(\"secondaryStructureElementDemo\")\n",
    "sc = SparkContext(conf = conf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Download protein (1STP)\n",
    "\n",
    "### Note: Need to use SparkContext as parameter to download Mmtf files"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdb = mmtfReader.download_mmtf_files(['1STP'], sc).cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Map protein to polymer chains and apply LProteinChain filter"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "pdb = pdb.flatMap(StructureToPolymerChains()) \\\n",
    "         .filter(ContainsLProteinChain())"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Extract secondary structure element 'E'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "+-------------+-----+\n",
      "|sequence     |label|\n",
      "+-------------+-----+\n",
      "|TFIVTA       |E    |\n",
      "|ALTGTYE      |E    |\n",
      "|VLTGRY       |E    |\n",
      "|TALGWTVAWK   |E    |\n",
      "|NAHSATTWSGQYV|E    |\n",
      "|INTQWLLTS    |E    |\n",
      "|TLVGHDTFT    |E    |\n",
      "+-------------+-----+\n",
      "\n"
     ]
    }
   ],
   "source": [
    "ds = secondaryStructureElementExtractor.get_dataset(pdb, 'E', 6)\n",
    "\n",
    "ds.show(50, False)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {
    "collapsed": true
   },
   "source": [
    "## Terminate Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "sc.stop()"
   ]
  }
 ],
 "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": "3.6.0"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}