{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Poly-peptide Chain Statistics Example\n",
    "\n",
    "Example demonstrating how to extract protein cahins from PDB entries. This example uses a flatMap function to transform a structure to its polymer chains.\n",
    "\n",
    "## Imports"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark import SparkConf, SparkContext\n",
    "from mmtfPyspark.filters import PolymerComposition\n",
    "from mmtfPyspark.io import mmtfReader\n",
    "from mmtfPyspark.mappers import StructureToPolymerChains"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Configure Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "conf = SparkConf().setMaster(\"local[*]\") \\\n",
    "                  .setAppName(\"polypeptideCahinStats\")\n",
    "sc = SparkContext(conf = conf)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read in mmtf files, flatMap to polymer chains, filter by polymer composition, and get number of groups"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "path = \"../../resources/mmtf_full_sample/\"\n",
    "\n",
    "chainLengths = mmtfReader.read_sequence_file(path, sc) \\\n",
    "                         .flatMap(StructureToPolymerChains(False, True)) \\\n",
    "                         .filter(PolymerComposition(PolymerComposition.AMINO_ACIDS_20)) \\\n",
    "                         .map(lambda t: t[1].num_groups) \\\n",
    "                         .cache()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Print out poly-peptide chain statistics"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Total number of chains: 7489\n",
      "Total number of groups: 1655462\n",
      "Min chain length: 3\n",
      "Mean chain length: 221.05247696621703\n",
      "Max chain length: 1231\n"
     ]
    }
   ],
   "source": [
    "print(f\"Total number of chains: {chainLengths.count()}\")\n",
    "print(f\"Total number of groups: {chainLengths.sum()}\")\n",
    "print(f\"Min chain length: {chainLengths.min()}\")\n",
    "print(f\"Mean chain length: {chainLengths.mean()}\")\n",
    "print(f\"Max chain length: {chainLengths.max()}\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Terminate Spark"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "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
}