sars-cov-2/2-MapToPolymerInteractions.ipynb

{
 "cells": [
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Map Mutations to Protein-Protein and Protein-Nucleic Acid Interfaces\n",
    "Here we find and visualize the mutations that occur around protein-protein and protein-nucleic acid interfaces."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import os\n",
    "# Disable Numba on Windows: temporary workaround for https://github.com/sbl-sdsc/mmtf-pyspark/issues/288\n",
    "#os.environ['NUMBA_DISABLE_JIT'] = \"1\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "from pyspark.sql import SparkSession\n",
    "from mmtfPyspark.io import mmtfReader\n",
    "from mmtfPyspark.interactions import InteractionExtractor, InteractionFilter\n",
    "from ipywidgets import interact, IntSlider, FloatSlider, SelectMultiple\n",
    "import py3Dmol\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "code_folding": [
     0
    ]
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2022-01-27 12:53:47 WARN  NativeCodeLoader:62 - Unable to load native-hadoop library for your platform... using builtin-java classes where applicable\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Setting default log level to \"WARN\".\n",
      "To adjust logging level use sc.setLogLevel(newLevel). For SparkR, use setLogLevel(newLevel).\n"
     ]
    }
   ],
   "source": [
    "# Initialize Spark\n",
    "spark = SparkSession.builder.appName(\"2-MapToPolymerInteractions\").getOrCreate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Enable Arrow-based columnar data transfers between Spark and Pandas dataframes\n",
    "# Commented out for deployment on Pangeo Binder since it causes an out of memory error\n",
    "# Exceeds spark.driver.maxResultSize (1024.0 MB)\n",
    "spark.conf.set(\"spark.sql.execution.arrow.enabled\", \"true\")"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Input parameters"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "distance_cutoff = 8 # distance cutoff for finding and visualizing interactions\n",
    "input_file_name = 'mutations3d.csv' # mutations mapped to 3D protein structures\n",
    "output_file_name = 'mutations3d_polymer_inter.csv' # mutations mapped to polymer interactions"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Read mutation file created in the previous step"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>coverage</th>\n",
       "      <th>description</th>\n",
       "      <th>name</th>\n",
       "      <th>resolution</th>\n",
       "      <th>structureChainId</th>\n",
       "      <th>structureId</th>\n",
       "      <th>uniprotPosition</th>\n",
       "      <th>pdbPosition</th>\n",
       "      <th>residue</th>\n",
       "      <th>variationId</th>\n",
       "      <th>annotation</th>\n",
       "      <th>scale</th>\n",
       "      <th>color</th>\n",
       "      <th>targetGroupNumber</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0.153181</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, CR30...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.084</td>\n",
       "      <td>6W41.C</td>\n",
       "      <td>6W41</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>S:p.333T&gt;I(8), S:p.333T&gt;K(4), S:p.333T&gt;A(2)</td>\n",
       "      <td>333T&gt;I(8), 333T&gt;K(4), 333T&gt;A(2)</td>\n",
       "      <td>0.163116</td>\n",
       "      <td>#fdd5c4</td>\n",
       "      <td>333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.100</td>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>S:p.333T&gt;I(8), S:p.333T&gt;K(4), S:p.333T&gt;A(2)</td>\n",
       "      <td>333T&gt;I(8), 333T&gt;K(4), 333T&gt;A(2)</td>\n",
       "      <td>0.163116</td>\n",
       "      <td>#fdd5c4</td>\n",
       "      <td>333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.100</td>\n",
       "      <td>6WPS.B</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>S:p.333T&gt;I(8), S:p.333T&gt;K(4), S:p.333T&gt;A(2)</td>\n",
       "      <td>333T&gt;I(8), 333T&gt;K(4), 333T&gt;A(2)</td>\n",
       "      <td>0.163116</td>\n",
       "      <td>#fdd5c4</td>\n",
       "      <td>333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.100</td>\n",
       "      <td>6WPS.E</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>S:p.333T&gt;I(8), S:p.333T&gt;K(4), S:p.333T&gt;A(2)</td>\n",
       "      <td>333T&gt;I(8), 333T&gt;K(4), 333T&gt;A(2)</td>\n",
       "      <td>0.163116</td>\n",
       "      <td>#fdd5c4</td>\n",
       "      <td>333</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>0.742341</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.700</td>\n",
       "      <td>6WPT.A</td>\n",
       "      <td>6WPT</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>333</td>\n",
       "      <td>S:p.333T&gt;I(8), S:p.333T&gt;K(4), S:p.333T&gt;A(2)</td>\n",
       "      <td>333T&gt;I(8), 333T&gt;K(4), 333T&gt;A(2)</td>\n",
       "      <td>0.163116</td>\n",
       "      <td>#fdd5c4</td>\n",
       "      <td>333</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   coverage                                        description  \\\n",
       "0  0.153181  2-acetamido-2-deoxy-beta-D-glucopyranose, CR30...   \n",
       "1  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "2  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "3  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "4  0.742341  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "\n",
       "                 name  resolution structureChainId structureId  \\\n",
       "0  Spike glycoprotein       3.084           6W41.C        6W41   \n",
       "1  Spike glycoprotein       3.100           6WPS.A        6WPS   \n",
       "2  Spike glycoprotein       3.100           6WPS.B        6WPS   \n",
       "3  Spike glycoprotein       3.100           6WPS.E        6WPS   \n",
       "4  Spike glycoprotein       3.700           6WPT.A        6WPT   \n",
       "\n",
       "   uniprotPosition  pdbPosition  residue  \\\n",
       "0              333          333      333   \n",
       "1              333          333      333   \n",
       "2              333          333      333   \n",
       "3              333          333      333   \n",
       "4              333          333      333   \n",
       "\n",
       "                                   variationId  \\\n",
       "0  S:p.333T>I(8), S:p.333T>K(4), S:p.333T>A(2)   \n",
       "1  S:p.333T>I(8), S:p.333T>K(4), S:p.333T>A(2)   \n",
       "2  S:p.333T>I(8), S:p.333T>K(4), S:p.333T>A(2)   \n",
       "3  S:p.333T>I(8), S:p.333T>K(4), S:p.333T>A(2)   \n",
       "4  S:p.333T>I(8), S:p.333T>K(4), S:p.333T>A(2)   \n",
       "\n",
       "                        annotation     scale    color targetGroupNumber  \n",
       "0  333T>I(8), 333T>K(4), 333T>A(2)  0.163116  #fdd5c4               333  \n",
       "1  333T>I(8), 333T>K(4), 333T>A(2)  0.163116  #fdd5c4               333  \n",
       "2  333T>I(8), 333T>K(4), 333T>A(2)  0.163116  #fdd5c4               333  \n",
       "3  333T>I(8), 333T>K(4), 333T>A(2)  0.163116  #fdd5c4               333  \n",
       "4  333T>I(8), 333T>K(4), 333T>A(2)  0.163116  #fdd5c4               333  "
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pd.set_option('display.max_columns', None)  # show all columns\n",
    "df = pd.read_csv(input_file_name)\n",
    "df['targetGroupNumber'] = df['pdbPosition'].astype('str') # PDB residue numbers must be string to handle insertion codes\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "mutations=spark.createDataFrame(df) "
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Create a list of unique PDB Ids"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "PDB Ids: ['6W41', '6WPS', '6WPT', '6XCM', '6XCN', '6XDG', '6XE1', '6Z2M', '6ZCZ', '6ZDH', '6ZER', '7A5R', '7A5S', '7BEH', '7BEJ', '7BEP', '7BWJ', '7BYR', '7C01', '7C2L', '7C8W', '7CAC', '7CAI', '7CAK', '7CDI', '7CDJ', '7CHB', '7CHE', '7CHF', '7CHH', '7CHO', '7CHP', '7CHS', '7CM4', '7CWS', '7CZP', '7CZQ', '7CZR', '7CZS', '7CZT', '7CZU', '7CZV', '7CZW', '7CZX', '7CZY', '7CZZ', '7D00', '7D03', '7DK4', '7DPM', '7DX4', '7DZX', '7DZY', '7E8M', '7EAM', '7JV4', '7JV6', '7JVA', '7JVC', '7JX3', '7K43', '7K4N', '7K8S', '7K8T', '7K8U', '7K8V', '7K8W', '7K8X', '7K8Z', '7K90', '7K9Z', '7KKK', '7KKL', '7KLG', '7KLH', '7KML', '7KQB', '7KQE', '7L02', '7L06', '7L09', '7L0N', '7L2D', '7L2E', '7L2F', '7L3N', '7L56', '7LAA', '7LAB', '7LCN', '7LD1', '7LJR', '7LOP', '7LS9', '7LSS', '7LXY', '7LXZ', '7LY2', '7M3I', '7M6D', '7M6E', '7M6F', '7M6G', '7M71', '7M7B', '7M7W', '7MFU', '7MJJ', '7MJK', '7MJL', '7MKL', '7MKM', '7N0G', '7N0H', '7ND3', '7ND4', '7ND5', '7ND7', '7ND8', '7ND9', '7NDA', '7NEH', '7NKT', '7NTC', '6XC2', '6XC3', '6XC4', '6XC7', '6ZH9', '7BEI', '7BEK', '7BEL', '7BEO', '7C8V', '7CAH', '7CH4', '7CH5', '7CHC', '7CJF', '7CWL', '7CWM', '7CWN', '7CWO', '7CWU', '7DEO', '7DET', '7DEU', '7JMO', '7JMW', '7K45', '7K8M', '7KFV', '7KFW', '7KFX', '7KFY', '7KLW', '7KMG', '7KMH', '7KMI', '7KN6', '7KN7', '7KZB', '7LM8', '7MF1', '7MMO', '7NEG', '7NX6', '7NX7', '7NX8', '7NX9', '7NXA', '7NXB', '7B3O', '7BEN', '7JMP', '7JV2', '7D4G', '7L2C', '7LY3', '7M8J', '7LXX', '7LXW', '7LY0', '7M53']\n"
     ]
    }
   ],
   "source": [
    "pdb_ids = list(df.structureId.drop_duplicates())\n",
    "print(\"PDB Ids:\", pdb_ids)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Find all polymer-polymer interactions\n",
    "Find groups (residues) that interact with other polymer chains"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "structures = mmtfReader.download_mmtf_files(pdb_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "interaction_filter = InteractionFilter(distanceCutoff=distance_cutoff)\n",
    "\n",
    "interactions = InteractionExtractor().get_polymer_interactions(structures, interaction_filter, level='group')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "cols = ['queryGroupId', 'queryChainId', 'queryGroupNumber', 'sequence']\n",
    "interactions = interactions.drop(*cols)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>structureChainId</th>\n",
       "      <th>targetGroupId</th>\n",
       "      <th>targetChainId</th>\n",
       "      <th>targetGroupNumber</th>\n",
       "      <th>sequenceIndex</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>7E8M.L</td>\n",
       "      <td>GLN</td>\n",
       "      <td>L</td>\n",
       "      <td>90</td>\n",
       "      <td>89</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>7E8M.H</td>\n",
       "      <td>SER</td>\n",
       "      <td>H</td>\n",
       "      <td>183</td>\n",
       "      <td>182</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>7E8M.L</td>\n",
       "      <td>SER</td>\n",
       "      <td>L</td>\n",
       "      <td>176</td>\n",
       "      <td>175</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>7E8M.E</td>\n",
       "      <td>PHE</td>\n",
       "      <td>E</td>\n",
       "      <td>486</td>\n",
       "      <td>153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>7E8M.H</td>\n",
       "      <td>VAL</td>\n",
       "      <td>H</td>\n",
       "      <td>101</td>\n",
       "      <td>100</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  structureChainId targetGroupId targetChainId targetGroupNumber  \\\n",
       "0           7E8M.L           GLN             L                90   \n",
       "1           7E8M.H           SER             H               183   \n",
       "2           7E8M.L           SER             L               176   \n",
       "3           7E8M.E           PHE             E               486   \n",
       "4           7E8M.H           VAL             H               101   \n",
       "\n",
       "   sequenceIndex  \n",
       "0             89  \n",
       "1            182  \n",
       "2            175  \n",
       "3            153  \n",
       "4            100  "
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "interactions.limit(5).toPandas()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Filter mutations by joining with the interaction data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "result = interactions.join(mutations, ['structureChainId', 'targetGroupNumber'], \"inner\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "2022-01-27 12:54:07 WARN  TaskSetManager:66 - Stage 2 contains a task of very large size (15342 KB). The maximum recommended task size is 100 KB.\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "                                                                                \r"
     ]
    }
   ],
   "source": [
    "mt = result.toPandas()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>structureChainId</th>\n",
       "      <th>targetGroupNumber</th>\n",
       "      <th>targetGroupId</th>\n",
       "      <th>targetChainId</th>\n",
       "      <th>sequenceIndex</th>\n",
       "      <th>coverage</th>\n",
       "      <th>description</th>\n",
       "      <th>name</th>\n",
       "      <th>resolution</th>\n",
       "      <th>structureId</th>\n",
       "      <th>uniprotPosition</th>\n",
       "      <th>pdbPosition</th>\n",
       "      <th>residue</th>\n",
       "      <th>variationId</th>\n",
       "      <th>annotation</th>\n",
       "      <th>scale</th>\n",
       "      <th>color</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>1122</td>\n",
       "      <td>VAL</td>\n",
       "      <td>A</td>\n",
       "      <td>1140</td>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.1</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>S:p.1122V&gt;L(2056), S:p.1122V&gt;M(64), S:p.1122V&gt;...</td>\n",
       "      <td>1122V&gt;L(2056), 1122V&gt;M(64), 1122V&gt;A(6)</td>\n",
       "      <td>0.473575</td>\n",
       "      <td>#fb7252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>1122</td>\n",
       "      <td>VAL</td>\n",
       "      <td>A</td>\n",
       "      <td>1140</td>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.1</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>S:p.1122V&gt;L(2056), S:p.1122V&gt;M(64), S:p.1122V&gt;...</td>\n",
       "      <td>1122V&gt;L(2056), 1122V&gt;M(64), 1122V&gt;A(6)</td>\n",
       "      <td>0.473575</td>\n",
       "      <td>#fb7252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>1122</td>\n",
       "      <td>VAL</td>\n",
       "      <td>A</td>\n",
       "      <td>1140</td>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.1</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>S:p.1122V&gt;L(2056), S:p.1122V&gt;M(64), S:p.1122V&gt;...</td>\n",
       "      <td>1122V&gt;L(2056), 1122V&gt;M(64), 1122V&gt;A(6)</td>\n",
       "      <td>0.473575</td>\n",
       "      <td>#fb7252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>1122</td>\n",
       "      <td>VAL</td>\n",
       "      <td>A</td>\n",
       "      <td>1140</td>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.1</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>S:p.1122V&gt;L(2056), S:p.1122V&gt;M(64), S:p.1122V&gt;...</td>\n",
       "      <td>1122V&gt;L(2056), 1122V&gt;M(64), 1122V&gt;A(6)</td>\n",
       "      <td>0.473575</td>\n",
       "      <td>#fb7252</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>6WPS.A</td>\n",
       "      <td>1122</td>\n",
       "      <td>VAL</td>\n",
       "      <td>A</td>\n",
       "      <td>1140</td>\n",
       "      <td>0.750196</td>\n",
       "      <td>2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...</td>\n",
       "      <td>Spike glycoprotein</td>\n",
       "      <td>3.1</td>\n",
       "      <td>6WPS</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>1122</td>\n",
       "      <td>S:p.1122V&gt;L(2056), S:p.1122V&gt;M(64), S:p.1122V&gt;...</td>\n",
       "      <td>1122V&gt;L(2056), 1122V&gt;M(64), 1122V&gt;A(6)</td>\n",
       "      <td>0.473575</td>\n",
       "      <td>#fb7252</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  structureChainId targetGroupNumber targetGroupId targetChainId  \\\n",
       "0           6WPS.A              1122           VAL             A   \n",
       "1           6WPS.A              1122           VAL             A   \n",
       "2           6WPS.A              1122           VAL             A   \n",
       "3           6WPS.A              1122           VAL             A   \n",
       "4           6WPS.A              1122           VAL             A   \n",
       "\n",
       "   sequenceIndex  coverage                                        description  \\\n",
       "0           1140  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "1           1140  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "2           1140  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "3           1140  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "4           1140  0.750196  2-acetamido-2-deoxy-beta-D-glucopyranose, 2-ac...   \n",
       "\n",
       "                 name  resolution structureId  uniprotPosition  pdbPosition  \\\n",
       "0  Spike glycoprotein         3.1        6WPS             1122         1122   \n",
       "1  Spike glycoprotein         3.1        6WPS             1122         1122   \n",
       "2  Spike glycoprotein         3.1        6WPS             1122         1122   \n",
       "3  Spike glycoprotein         3.1        6WPS             1122         1122   \n",
       "4  Spike glycoprotein         3.1        6WPS             1122         1122   \n",
       "\n",
       "   residue                                        variationId  \\\n",
       "0     1122  S:p.1122V>L(2056), S:p.1122V>M(64), S:p.1122V>...   \n",
       "1     1122  S:p.1122V>L(2056), S:p.1122V>M(64), S:p.1122V>...   \n",
       "2     1122  S:p.1122V>L(2056), S:p.1122V>M(64), S:p.1122V>...   \n",
       "3     1122  S:p.1122V>L(2056), S:p.1122V>M(64), S:p.1122V>...   \n",
       "4     1122  S:p.1122V>L(2056), S:p.1122V>M(64), S:p.1122V>...   \n",
       "\n",
       "                               annotation     scale    color  \n",
       "0  1122V>L(2056), 1122V>M(64), 1122V>A(6)  0.473575  #fb7252  \n",
       "1  1122V>L(2056), 1122V>M(64), 1122V>A(6)  0.473575  #fb7252  \n",
       "2  1122V>L(2056), 1122V>M(64), 1122V>A(6)  0.473575  #fb7252  \n",
       "3  1122V>L(2056), 1122V>M(64), 1122V>A(6)  0.473575  #fb7252  \n",
       "4  1122V>L(2056), 1122V>M(64), 1122V>A(6)  0.473575  #fb7252  "
      ]
     },
     "execution_count": 15,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "mt.head()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Save Mappings"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [],
   "source": [
    "mt.to_csv(output_file_name, index=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "scrolled": true
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Chains: ['6W41.C', '6WPS.A', '6WPS.B', '6WPS.E', '6WPT.A', '6WPT.B', '6WPT.C', '6XC2.A', '6XC2.Z', '6XC3.C', '6XC4.A', '6XC4.Z', '6XC7.A', '6XCM.A', '6XCM.B', '6XCM.C', '6XCN.A', '6XCN.C', '6XCN.E', '6XDG.E', '6XE1.E', '6Z2M.A', '6Z2M.E', '6ZCZ.E', '6ZDH.A', '6ZDH.B', '6ZDH.C', '6ZER.A', '6ZER.D', '6ZER.E', '6ZH9.EEE', '7A5R.A', '7A5R.B', '7A5S.A', '7A5S.B', '7B3O.E', '7BEH.E', '7BEI.E', '7BEJ.E', '7BEK.E', '7BEL.R', '7BEL.X', '7BEN.C', '7BEN.E', '7BEO.R', '7BEO.X', '7BEP.C', '7BEP.E', '7BWJ.E', '7BYR.A', '7BYR.B', '7BYR.C', '7C01.A', '7C01.B', '7C2L.A', '7C2L.B', '7C2L.C', '7C8V.B', '7C8W.B', '7CAC.A', '7CAC.B', '7CAC.C', '7CAH.A', '7CAI.A', '7CAI.B', '7CAI.C', '7CAK.A', '7CAK.B', '7CAK.C', '7CDI.E', '7CDJ.E', '7CH4.R', '7CH5.R', '7CHB.R', '7CHC.R', '7CHE.R', '7CHF.R', '7CHH.A', '7CHH.B', '7CHH.C', '7CHO.A', '7CHO.E', '7CHP.E', '7CHS.E', '7CJF.C', '7CM4.A', '7CWL.A', '7CWL.B', '7CWL.C', '7CWM.A', '7CWM.B', '7CWM.C', '7CWN.A', '7CWN.B', '7CWN.C', '7CWO.A', '7CWS.O', '7CWS.Q', '7CWS.R', '7CWU.A', '7CWU.B', '7CWU.C', '7CZP.A', '7CZP.B', '7CZP.C', '7CZQ.A', '7CZQ.B', '7CZQ.C', '7CZR.A', '7CZR.B', '7CZR.C', '7CZS.A', '7CZS.B', '7CZS.C', '7CZT.A', '7CZT.B', '7CZT.C', '7CZU.A', '7CZU.B', '7CZU.C', '7CZV.A', '7CZV.B', '7CZV.C', '7CZW.A', '7CZW.B', '7CZW.C', '7CZX.A', '7CZX.B', '7CZX.C', '7CZY.A', '7CZY.B', '7CZY.C', '7CZZ.A', '7CZZ.B', '7CZZ.C', '7D00.A', '7D00.B', '7D00.C', '7D03.A', '7D03.B', '7D03.C', '7D4G.B', '7DEO.B', '7DEO.D', '7DET.A', '7DET.C', '7DEU.A', '7DK4.A', '7DK4.B', '7DK4.C', '7DPM.C', '7DPM.F', '7DPM.I', '7DPM.L', '7DX4.E', '7DZX.A', '7DZX.B', '7DZX.C', '7DZY.A', '7DZY.B', '7DZY.C', '7E8M.E', '7EAM.A', '7EAM.B', '7JMO.A', '7JMP.A', '7JMW.A', '7JV2.A', '7JV4.A', '7JV4.B', '7JV4.C', '7JV6.A', '7JV6.B', '7JV6.E', '7JVA.A', '7JVC.A', '7JVC.B', '7JVC.E', '7JX3.R', '7K43.A', '7K43.B', '7K43.E', '7K45.B', '7K4N.A', '7K4N.B', '7K4N.E', '7K8M.E', '7K8S.A', '7K8S.B', '7K8S.C', '7K8T.A', '7K8T.B', '7K8T.C', '7K8U.A', '7K8U.B', '7K8U.C', '7K8V.A', '7K8V.B', '7K8V.C', '7K8W.A', '7K8W.B', '7K8W.G', '7K8X.A', '7K8X.B', '7K8X.C', '7K8Z.A', '7K8Z.B', '7K8Z.C', '7K90.A', '7K90.B', '7K90.C', '7K9Z.E', '7KFV.A', '7KFV.B', '7KFV.E', '7KFW.A', '7KFW.B', '7KFW.E', '7KFX.A', '7KFY.A', '7KKK.A', '7KKK.C', '7KKK.E', '7KKL.A', '7KKL.C', '7KKL.D', '7KLG.A', '7KLG.B', '7KLH.A', '7KLH.B', '7KLW.A', '7KMG.C', '7KMG.F', '7KMH.C', '7KMI.C', '7KML.A', '7KML.B', '7KML.C', '7KN6.A', '7KN7.A', '7KQB.A', '7KQB.B', '7KQB.C', '7KQE.A', '7KQE.B', '7KQE.C', '7KZB.C', '7L02.A', '7L02.B', '7L02.C', '7L06.A', '7L06.B', '7L06.C', '7L09.A', '7L09.B', '7L09.C', '7L0N.R', '7L0N.S', '7L2C.A', '7L2C.B', '7L2D.A', '7L2D.B', '7L2D.C', '7L2E.A', '7L2E.B', '7L2E.C', '7L2F.A', '7L2F.B', '7L2F.C', '7L3N.A', '7L3N.B', '7L3N.C', '7L56.A', '7L56.B', '7L56.C', '7LAA.A', '7LAA.B', '7LAA.C', '7LAB.A', '7LAB.B', '7LAB.C', '7LCN.A', '7LCN.C', '7LCN.K', '7LD1.A', '7LD1.B', '7LD1.C', '7LJR.A', '7LJR.B', '7LJR.C', '7LM8.A', '7LOP.A', '7LOP.Z', '7LS9.A', '7LS9.B', '7LS9.C', '7LSS.A', '7LSS.B', '7LSS.C', '7LXW.A', '7LXX.A', '7LXY.A', '7LXY.B', '7LXY.J', '7LXZ.A', '7LXZ.B', '7LXZ.K', '7LY0.A', '7LY2.A', '7LY2.B', '7LY2.J', '7LY3.A', '7LY3.B', '7M3I.C', '7M3I.R', '7M53.A', '7M6D.C', '7M6E.A', '7M6E.B', '7M6E.E', '7M6F.A', '7M6F.B', '7M6F.E', '7M6G.A', '7M6G.B', '7M6G.C', '7M71.A', '7M71.B', '7M7B.A', '7M7W.R', '7M7W.S', '7M8J.A', '7MF1.A', '7MFU.A', '7MFU.D', '7MJJ.A', '7MJJ.B', '7MJJ.C', '7MJK.A', '7MJK.B', '7MJK.C', '7MJL.A', '7MKL.A', '7MKL.B', '7MKL.C', '7MKM.A', '7MMO.C', '7MMO.F', '7N0G.A', '7N0G.B', '7N0G.C', '7N0H.A', '7N0H.B', '7N0H.C', '7ND3.A', '7ND3.B', '7ND3.C', '7ND4.A', '7ND4.B', '7ND4.C', '7ND5.A', '7ND5.B', '7ND5.C', '7ND7.A', '7ND7.B', '7ND7.C', '7ND8.A', '7ND8.B', '7ND8.C', '7ND9.A', '7ND9.B', '7ND9.C', '7NDA.A', '7NDA.B', '7NDA.C', '7NEG.E', '7NEH.E', '7NKT.AAA', '7NTC.A', '7NTC.B', '7NTC.C', '7NX6.E', '7NX7.E', '7NX8.E', '7NX9.E', '7NXA.E', '7NXB.E']\n"
     ]
    }
   ],
   "source": [
    "chains = mt.groupby('structureChainId')\n",
    "print(\"Chains:\", list(chains.groups.keys()))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## View mutations grouped by protein chain"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "Mutations are mapped onto protein chains for available 3D protein structures.\n",
    "\n",
    "Display options:\n",
    "\n",
    "|||\n",
    "|:-|:-|\n",
    "| *show_bio_assembly* | Toggle display of the biologically relevant quaternary structure |\n",
    "| *show_surface* | Toggle surface for protein chain |\n",
    "| *show_short_label* | Toggle display of mutation information<br>{UniProtResidue}{aminoAcid1}>{aminoAcid2}(# observations)<br>Example: 501N>Y(350436)|\n",
    "| *show_long_label* | Toggle display of mutation information<br>{PDBId}.{chainId}.{PDBResidue}: {geneName}.p{UniProtResidue}{aminoAcid1}>{aminoAcid2}(# observations)<br>Example: 6XDG.E.501: S:p.501N>Y(350436) |\n",
    "| *size* | Change size of visualization |\n",
    "| *font* | Change font size of annotations |\n",
    "| *logFreq* | Change minimum threshold to display mutations based on normalized log of mutation frequency [0.0 - 1.0]|\n",
    "| *structure* | Move slider to browse through available structures |"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "#### Example: Move the structure slider to PDB ID:6XDG to see how mutations (e.g., 501N>Y) effect the binding of the Regeneron antibodies"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "code_folding": [
     0
    ],
    "jupyter": {
     "source_hidden": true
    },
    "tags": []
   },
   "outputs": [],
   "source": [
    "# Setup viewer\n",
    "def view_grouped_mutations(grouped_df, *args):\n",
    "    chainIds = list(grouped_df.groups.keys())\n",
    "\n",
    "    def view3d(show_bio_assembly, show_surface, show_short_label, show_long_label, size, font, logFreq, i):\n",
    "        group = grouped_df.get_group(chainIds[i])\n",
    "        \n",
    "        pdb_id, chain_id = chainIds[i].split('.')\n",
    "        global viewer1\n",
    "        viewer1 = py3Dmol.view(query='pdb:' + pdb_id, options={'doAssembly': show_bio_assembly}, width=size, height=size)\n",
    "\n",
    "        # polymer style\n",
    "        viewer1.setStyle({'cartoon': {'colorscheme': 'chain', 'width': 0.6, 'opacity':0.9}})\n",
    " \n",
    "        # highlight chain of interest in blue\n",
    "        viewer1.setStyle({'chain': chain_id},{'cartoon': {'color': 'blue'}})\n",
    "        \n",
    "        # non-polymer style\n",
    "        viewer1.setStyle({'hetflag': True}, {'stick':{'radius': 0.3, 'singleBond': False}})\n",
    "    \n",
    "        # don't display water molecules\n",
    "        viewer1.setStyle({'resn': ['HOH','DOD']}, {})\n",
    "        \n",
    "        modified_residues = set()\n",
    "        rows = group.shape[0]\n",
    "        for j in range(0, rows):\n",
    "            if group.iloc[j]['scale'] > logFreq:\n",
    "                res_num = str(group.iloc[j]['pdbPosition'])\n",
    "                mod_res = {'resi': res_num, 'chain': chain_id} \n",
    "                modified_residues.add(res_num)\n",
    "            \n",
    "                # style for mutated residue\n",
    "                col = group.iloc[j]['color']\n",
    "                c_col = col + 'Carbon'\n",
    "                viewer1.addStyle(mod_res, {'stick':{'colorscheme':c_col, 'radius': 0.2}})\n",
    "                viewer1.addStyle(mod_res, {'sphere':{'color':col, 'opacity': 0.6}}) \n",
    "           \n",
    "                # style for interacting residues\n",
    "                surroundings = {'not': {'chain': chain_id}, 'byres': True, 'within': {'distance': distance_cutoff, 'sel': mod_res}}\n",
    "                viewer1.setStyle(surroundings,{'cartoon':{'color':'orange', 'width': 0.6}})\n",
    "                viewer1.addStyle(surroundings,{'stick':{'colorscheme':'orangeCarbon', 'radius': 0.15}})\n",
    "                # style for interacting waters\n",
    "                waters = {'resn': ['HOH','DOD']}\n",
    "                waters.update(surroundings)\n",
    "                viewer1.addStyle(waters,{'sphere':{'color':'orange', 'radius': 0.5}})\n",
    "                \n",
    "                if show_short_label or show_long_label:\n",
    "                    viewer1.addResLabels(surroundings, {'fontSize':font-2})\n",
    "            \n",
    "                # text label\n",
    "                annotation = group.iloc[j]['annotation']\n",
    "                variationId = group.iloc[j]['variationId']\n",
    "                \n",
    "                if show_short_label:\n",
    "                    label = annotation\n",
    "                if show_long_label:\n",
    "                    label = chain_id + \".\" + str(res_num) + \": \" + variationId\n",
    "                if show_short_label or show_long_label:\n",
    "                    viewer1.addLabel(label, {'fontSize':font,'fontColor': 'black','backgroundColor':'ivory', 'opacity': 1.0}, mod_res)\n",
    "              \n",
    "        viewer1.zoomTo({'chain': chain_id})\n",
    "        viewer1.center({'chain': chain_id})\n",
    "        \n",
    "        if show_surface:\n",
    "             viewer1.addSurface(py3Dmol.SES,{'opacity':0.8,'color':'lightblue'},{'chain': chain_id})\n",
    "                \n",
    "        # print header\n",
    "        resolution = group.iloc[0]['resolution']\n",
    "        coverage = group.iloc[0]['coverage']\n",
    "        description = group.iloc[0]['description']\n",
    "        print(f\"PDB Id:{pdb_id}, chain Id:{chain_id}, resolution:{resolution}, sequence coverage:{coverage:.2f}\")\n",
    "        print(description)\n",
    "                \n",
    "        return viewer1.show()\n",
    "       \n",
    "    f_widget = IntSlider(value=9, min=5, max=20, description='font size', continuous_update=False)\n",
    "    z_widget = IntSlider(value=750, min=500, max=1200, description='size', continuous_update=False)\n",
    "    s_widget = IntSlider(min=0, max=len(chainIds)-1, description='structure', continuous_update=False)\n",
    "    l_widget = FloatSlider(value=0.8, min=0, max=1, step=0.05, description='logFreq:', \n",
    "                           continuous_update=False, orientation='horizontal', readout=True, readout_format='.2f')\n",
    "    \n",
    "    return interact(view3d, show_bio_assembly=False, show_surface=False, show_short_label=True, show_long_label=False, \n",
    "                    size=z_widget, font=f_widget, logFreq=l_widget, i=s_widget)\n",
    "\n",
    "def view_image1():\n",
    "    return viewer1.png()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f5d409df352f4e0aa084bba9497a57fa",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(Checkbox(value=False, description='show_bio_assembly'), Checkbox(value=False, descriptio…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "view_grouped_mutations(chains);"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## View one mutation at a time\n",
    "Use the slider to view each mutation. Interacting residues within the `distance_cutoff` are rendered as orange sticks."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "code_folding": [
     0
    ],
    "jupyter": {
     "source_hidden": true
    }
   },
   "outputs": [],
   "source": [
    "# Setup viewer\n",
    "def view_single_mutation(df, distance_cutoff, *args):\n",
    "\n",
    "    def view3d(show_bio_assembly, show_surface, show_short_label, show_long_label, size, font, i):        \n",
    "        pdb_id, chain_id = df.iloc[i]['structureChainId'].split('.')\n",
    "        \n",
    "        global viewer2\n",
    "        viewer2 = py3Dmol.view(query='pdb:' + pdb_id, options={'doAssembly': show_bio_assembly}, width=size, height=size)\n",
    "\n",
    "        # polymer style\n",
    "        viewer2.setStyle({'cartoon': {'colorscheme': 'chain', 'width': 0.6, 'opacity':0.9}})\n",
    "        \n",
    "        # highlight chain of interest in blue\n",
    "        viewer2.setStyle({'chain': chain_id},{'cartoon': {'color': 'blue', 'opacity':0.7}})\n",
    "        \n",
    "        # non-polymer style\n",
    "        viewer2.setStyle({'hetflag': True}, {'stick':{'radius': 0.3, 'singleBond': False}})\n",
    "        \n",
    "        # interacting residue style\n",
    "        res_num = str(df.iloc[i]['pdbPosition'])\n",
    "        label = df.iloc[i]['variationId']     \n",
    "        mod_res = {'resi': res_num, 'chain': chain_id} \n",
    "        col = df.iloc[i]['color']\n",
    "        c_col = col + 'Carbon'\n",
    "        viewer2.addStyle(mod_res, {'stick':{'colorscheme':c_col, 'radius': 0.2}})\n",
    "        viewer2.addStyle(mod_res, {'sphere':{'color':col, 'opacity': 0.6}})   \n",
    "        \n",
    "        # don't display water molecules (except below for interactions)\n",
    "        viewer2.setStyle({'resn': ['HOH','DOD']}, {})\n",
    "            \n",
    "        # select residues in interacting chains by distance from mutation site (same chain is excluded)\n",
    "        surroundings = {'not': {'chain': chain_id}, 'byres': True, 'within': {'distance': distance_cutoff, 'sel': mod_res}}\n",
    "        \n",
    "        # set style for interacting residues\n",
    "        viewer2.setStyle(surroundings,{'cartoon':{'color':'orange', 'width': 0.6}})\n",
    "        viewer2.addStyle(surroundings,{'stick':{'colorscheme':'orangeCarbon', 'radius': 0.15}})\n",
    "    \n",
    "        # set style for interacting waters\n",
    "        waters = {'resn': ['HOH','DOD']}\n",
    "        waters.update(surroundings)\n",
    "        viewer2.addStyle(waters,{'sphere':{'color':'orange', 'radius': 0.5}})\n",
    "        \n",
    "        annotation = df.iloc[i]['annotation']\n",
    "        variationId = df.iloc[i]['variationId']      \n",
    "        \n",
    "        if show_short_label:\n",
    "            label = annotation\n",
    "        if show_long_label:\n",
    "            label = chain_id + \".\" + str(res_num) + \": \" + variationId\n",
    "        if show_short_label or show_long_label:\n",
    "            viewer2.addResLabels(surroundings, {'fontSize':font-2})\n",
    "            viewer2.addLabel(label, {'fontSize':font,'fontColor': 'black','backgroundColor':'ivory', 'opacity': 1.0}, mod_res)\n",
    "            \n",
    "        viewer2.zoomTo(surroundings)\n",
    "        viewer2.center(mod_res)\n",
    "        \n",
    "        if show_surface:\n",
    "             viewer2.addSurface(py3Dmol.SES, {'opacity':0.8,'color':'lightblue'}, {'chain': chain_id})\n",
    "                \n",
    "        #print header\n",
    "        print(\"PDB Id:\", pdb_id, \"chain Id:\" , chain_id, \"residue:\", res_num, \"mutation:\", variationId)\n",
    "        \n",
    "        # print any specified additional columns from the dataframe\n",
    "        for a in args:\n",
    "            print(a + \": \" + df.iloc[i][a])\n",
    "                \n",
    "        return viewer2.show()\n",
    "       \n",
    "    f_widget = IntSlider(value=9, min=5, max=20, description='font size', continuous_update=False)\n",
    "    z_widget = IntSlider(value=750, min=500, max=1200, description='size', continuous_update=False)\n",
    "    s_widget = IntSlider(min=0, max=len(df)-1, description='structure', continuous_update=False)\n",
    "    \n",
    "    return interact(view3d, show_bio_assembly=False, show_surface=False, show_short_label=True, show_long_label=False, \n",
    "                    size=z_widget, font=f_widget, i=s_widget)\n",
    "\n",
    "def view_image2():\n",
    "    return viewer2.png()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "mt_unique = mt.drop_duplicates([\"structureChainId\",\"variationId\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "76f764f4ebca4343992bc4bd15936d01",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "interactive(children=(Checkbox(value=False, description='show_bio_assembly'), Checkbox(value=False, descriptio…"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "view_single_mutation(mt_unique, distance_cutoff);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "code_folding": [
     0
    ]
   },
   "outputs": [],
   "source": [
    "# Shutdown Spark\n",
    "spark.stop()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Now run the next step\n",
    "Map mutations occuring at protein-ligand binding sites: [3-MapToLigandInteractions.ipynb](3-MapToLigandInteractions.ipynb)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}