05.analyze_antibiotic_hits.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "7e64e85a-de23-4240-8c9b-fce7230854b5",
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pandas as pd\n",
    "import matplotlib.pyplot as plt\n",
    "from collections import defaultdict\n",
    "from copy import deepcopy\n",
    "import time\n",
    "import random\n",
    "from scipy import stats\n",
    "from scipy.stats import mode\n",
    "import seaborn as sns\n",
    "import warnings\n",
    "from collections import defaultdict\n",
    "warnings.filterwarnings(\"ignore\")\n",
    "from scipy.stats import chisquare"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "512b422e-0884-4607-a1e5-1c3749842bbb",
   "metadata": {},
   "source": [
    "## Hits where antibiotic resistance evolves first\n",
    "#### Exclude hits with two non-related antibiotics -> these go in co-linearity section"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "id": "a917b7e8-c7e6-4456-9123-e56b03a58053",
   "metadata": {},
   "outputs": [],
   "source": [
    "# Merge sequential and simultaneous hits into a single table\n",
    "\n",
    "all_hits_sequential = pd.read_csv(\"output/04A.pair_annotation/results_allpairs_annotation_withcategories.csv\", index_col=0)\n",
    "all_simultaneous = pd.read_csv(\"output/04B.pair_annotation/results_allpairs_annotation_withcategories.csv\", index_col=0)\n",
    "\n",
    "sequential_merged = all_hits_sequential.merge(all_simultaneous[[\"position_i\", \"position_j\", \"pval_beta_i_on_j\", 'pval_beta_i_on_j_BH_sig']], \n",
    "                                                on=[\"position_i\", \"position_j\"], how=\"left\", suffixes=[\"_sequential\", \"_simultaneous\"])\n",
    "\n",
    "simultaneous_merged = all_simultaneous.merge(all_hits_sequential[[\"position_i\", \"position_j\", \"pval_beta_i_on_j\", 'pval_beta_i_on_j_BH_sig']], \n",
    "                                                on=[\"position_i\", \"position_j\"], how=\"left\", suffixes=[ \"_simultaneous\", \"_sequential\"])\n",
    "\n",
    "all_hits = pd.concat([simultaneous_merged, sequential_merged])\n",
    "all_hits = all_hits.drop_duplicates(subset=[\"position_i\", \"position_j\"]).reset_index(drop=True)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "e3b33ce7-de51-400d-87cc-c8ac15e12fa1",
   "metadata": {},
   "outputs": [],
   "source": [
    "display_positions =['position_i', 'gene_name_i', 'position_j', 'gene_name_j',\n",
    "       'n_mutations_i', 'n_mutations_j', 'n_branches_with_i',\n",
    "    'n_muts_i_on_branch_j', 'n_muts_same_branch','pval_beta_i_on_j',\n",
    "       'pval_beta_i_on_j_BH_sig']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "id": "2c5c1db3-2ee1-4daa-9a15-94b0d0240e15",
   "metadata": {
    "tags": []
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1879\n"
     ]
    }
   ],
   "source": [
    "known_antibiotic_first = all_hits.dropna(subset=[\"known_drug_j\"]).query(\"pval_beta_i_on_j_BH_sig_sequential or pval_beta_i_on_j_BH_sig_simultaneous\")\n",
    "\n",
    "known_antibiotic_first['num_dependent'] = known_antibiotic_first.n_muts_i_on_branch_j + known_antibiotic_first.n_muts_same_branch\n",
    "know_ab_first = known_antibiotic_first.loc[known_antibiotic_first.possible_drug_i.isnull(), :]\n",
    "know_ab_first.sort_values('num_dependent', ascending=False).head(40)\n",
    "print(len(know_ab_first))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "eef7949c-fc61-47ad-aa93-2856efad3d7e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "3724\n"
     ]
    }
   ],
   "source": [
    "def _process_known_hits(input_list):\n",
    "    \"\"\"\n",
    "    splits the possible associated drugs (string separated by ,) into a list\n",
    "    \"\"\"\n",
    "    output_list = []\n",
    "    for item in input_list:\n",
    "        #print(item)\n",
    "        if type(item) != str:\n",
    "            output_list.append(np.nan)\n",
    "        else:\n",
    "            splitted = item.split(\",\")\n",
    "            exclusive= list(set(splitted))\n",
    "            output_list.append(exclusive)\n",
    "    return output_list\n",
    "\n",
    "known_antibiotic_first = all_hits.dropna(subset=[\"known_drug_j\"]).query(\"pval_beta_i_on_j_BH_sig_sequential or pval_beta_i_on_j_BH_sig_simultaneous\")\n",
    "\n",
    "known_antibiotic_first[\"known_drug_i\"] = _process_known_hits(known_antibiotic_first.known_drug_i)\n",
    "known_antibiotic_first[\"possible_drug_i\"] = _process_known_hits(known_antibiotic_first.possible_drug_i)\n",
    "\n",
    "known_antibiotic_first[\"known_drug_j\"] = _process_known_hits(known_antibiotic_first.known_drug_j)\n",
    "known_antibiotic_first[\"possible_drug_j\"] = _process_known_hits(known_antibiotic_first.possible_drug_j)\n",
    "\n",
    "print(len(known_antibiotic_first))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "id": "c9917889-1006-4883-9a23-cdd3c497f6da",
   "metadata": {},
   "outputs": [],
   "source": [
    "between_antibiotic_indices = []\n",
    "antibiotic_indices = []\n",
    "\n",
    "known_antibiotic_first[\"within_same_drug\"] = False\n",
    "\n",
    "for idx, row in known_antibiotic_first.iterrows():\n",
    "    \n",
    "    set_of_known_first = set(row.known_drug_j)\n",
    "    set_of_known_second = set()\n",
    "    known_drug_second = False\n",
    "    \n",
    "    if type(row.known_drug_i) is list:\n",
    "        set_of_known_second= set(row.known_drug_i)\n",
    "        known_drug_second = True\n",
    "        \n",
    "    elif type(row.possible_drug_i) is list:\n",
    "        set_of_known_second= set(row.possible_drug_i)\n",
    "        known_drug_second = True\n",
    "        \n",
    "    if not known_drug_second:\n",
    "        antibiotic_indices.append(idx)\n",
    "    \n",
    "    elif len(set_of_known_first.intersection(set_of_known_second)) > 0:\n",
    "        antibiotic_indices.append(idx)\n",
    "        known_antibiotic_first.loc[idx, \"within_same_drug\"] = True\n",
    "        \n",
    "    else:\n",
    "        between_antibiotic_indices.append(idx)\n",
    "        \n",
    "between_antibiotic_hits = known_antibiotic_first.loc[between_antibiotic_indices]\n",
    "antibiotic_hits = known_antibiotic_first.loc[antibiotic_indices]\n",
    "    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "id": "4de021a5-b3e0-4d0b-a0f6-183fb04b5249",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mkdir: cannot create directory ‘output/05.antibiotic’: File exists\n",
      "3724\n"
     ]
    }
   ],
   "source": [
    "!mkdir output/05.antibiotic\n",
    "print(len(antibiotic_hits))\n",
    "antibiotic_hits.to_csv(\"output/05.antibiotic/antibiotic_hits.csv\")\n",
    "between_antibiotic_hits.to_csv(\"output/05.antibiotic/between_antibiotic_hits.csv\")\n",
    "all_hits.to_csv(\"output/05.antibiotic/all_pairs.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "87d07b62-5fe3-42f1-a77d-7ed04033d3bf",
   "metadata": {},
   "source": [
    "## Compute per-drug output tables"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "id": "6f2c9bf1-24f6-46bf-955e-67422e094ae0",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RIF 524\n",
      "ETH 85\n",
      "LEV 13\n",
      "MXF 13\n",
      "PZA 130\n",
      "CAP 113\n",
      "INH 410\n",
      "KAN 175\n",
      "STM 422\n",
      "LZD 108\n",
      "EMB 387\n",
      "AMI 176\n"
     ]
    }
   ],
   "source": [
    "## These will contain all hits except the between-antibiotic hits\n",
    "\n",
    "## First get the list of all names of drugs in the dataset\n",
    "drug_list = []\n",
    "for idx, row in antibiotic_hits.iterrows():\n",
    "    drugs1 = row.possible_drug_j\n",
    "    drugs2 = row.possible_drug_i\n",
    "    \n",
    "    if type(drugs1) != list:\n",
    "        drugs1= []\n",
    "    if type(drugs2) != list:\n",
    "        drugs2=[]\n",
    "    \n",
    "    for drug in drugs1 + drugs2:\n",
    "        drug_list.append(drug)\n",
    "\n",
    "drug_list = list(set(drug_list))\n",
    "\n",
    "## Then create an empty df for each\n",
    "df_dict = {drug:pd.DataFrame() for drug in drug_list}\n",
    "\n",
    "## now concatenate each row to the appropriate drug dataframe\n",
    "for idx, row in antibiotic_hits.iterrows():\n",
    "    drugs1 = row.possible_drug_j\n",
    "    drugs2 = row.possible_drug_i\n",
    "    \n",
    "    if type(drugs1) != list:\n",
    "        drugs1= []\n",
    "    if type(drugs2) != list:\n",
    "        drugs2=[]\n",
    "    \n",
    "    for drug in drugs1:\n",
    "        df_dict[drug] = df_dict[drug].append(row)\n",
    "        \n",
    "    for drug in drugs2:\n",
    "        df_dict[drug] = df_dict[drug].append(row)\n",
    "        \n",
    "for drug, df in df_dict.items():\n",
    "    print(drug, len(df))\n",
    "    df.sort_values(\"n_muts_i_on_branch_j\", ascending=False).to_csv(f\"output/05.antibiotic/{drug}_antibiotic_hits.csv\")\n",
    "    df.query(\"pval_beta_i_on_j_BH_sig_sequential != 0\").query(\"pval_beta_i_on_j_BH_sig_sequential\").sort_values(\n",
    "        \"n_muts_i_on_branch_j\", ascending=False\n",
    "    ).to_csv(f\"output/05.antibiotic/{drug}_antibiotic_hits_sequential.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "id": "35390a43-ecb2-457c-b08f-b472b4b9c1a3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RIF 739\n",
      "ETH 176\n",
      "LEV 238\n",
      "DLM 1\n",
      "MXF 238\n",
      "CAP 211\n",
      "PZA 663\n",
      "CFZ 6\n",
      "INH 390\n",
      "KAN 321\n",
      "STM 501\n",
      "LZD 204\n",
      "BDQ 6\n",
      "EMB 570\n",
      "AMI 323\n"
     ]
    }
   ],
   "source": [
    "## These will contain all hits except the between-antibiotic hits\n",
    "\n",
    "## First get the list of all names of drugs in the dataset\n",
    "drug_list = []\n",
    "for idx, row in between_antibiotic_hits.iterrows():\n",
    "    drugs1 = row.possible_drug_j\n",
    "    drugs2 = row.possible_drug_i\n",
    "    \n",
    "    if type(drugs1) != list:\n",
    "        drugs1= []\n",
    "    if type(drugs2) != list:\n",
    "        drugs2=[]\n",
    "    \n",
    "    for drug in drugs1 + drugs2:\n",
    "        drug_list.append(drug)\n",
    "\n",
    "drug_list = list(set(drug_list))\n",
    "\n",
    "## Then create an empty df for each\n",
    "df_dict = {drug:pd.DataFrame() for drug in drug_list}\n",
    "\n",
    "## now concatenate each row to the appropriate drug dataframe\n",
    "for idx, row in between_antibiotic_hits.iterrows():\n",
    "    drugs1 = row.possible_drug_j\n",
    "    drugs2 = row.possible_drug_i\n",
    "    \n",
    "    if type(drugs1) != list:\n",
    "        drugs1= []\n",
    "    if type(drugs2) != list:\n",
    "        drugs2=[]\n",
    "    \n",
    "    for drug in drugs1:\n",
    "        df_dict[drug] = df_dict[drug].append(row)\n",
    "        \n",
    "    for drug in drugs2:\n",
    "        df_dict[drug] = df_dict[drug].append(row)\n",
    "        \n",
    "for drug, df in df_dict.items():\n",
    "    print(drug, len(df))\n",
    "    df.sort_values(\"n_muts_i_on_branch_j\", ascending=False).to_csv(f\"output/05.antibiotic/{drug}_between_antibiotic_hits.csv\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "7a7d5458-73d3-44dd-ae70-f12630fd21cf",
   "metadata": {},
   "source": [
    "\\## Fraction of resistant strains with a dependent mutation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "id": "a756e317-e72c-4fc1-93a8-dd2c3043a1c3",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1446\n"
     ]
    }
   ],
   "source": [
    "# Here let strains with a resistance-conferring mutation be defined as resistant\n",
    "# Then count the number of resistant strains that have another mutation\n",
    "\n",
    "snps = pd.read_csv(\"output/03.annotation/snps_with_all_annotation.csv\", index_col=0)\n",
    "snps = snps.query(\"not is_lineage\")\n",
    "\n",
    "# list of resistance mutations\n",
    "resistance_mutations = snps.query(\"in_known_ABR_position\")\n",
    "resistance_mutations[\"known_drug\"] = _process_known_hits(resistance_mutations.known_drug)\n",
    "\n",
    "antibiotic_hits = antibiotic_hits.query(\"pval_beta_i_on_j_BH_sig_sequential\")\n",
    "print(len(antibiotic_hits))\n",
    "# list of all other mutations\n",
    "other_positions = list(set(antibiotic_hits.position_i))\n",
    "other_mutations = snps.query(\"pos in @other_positions\")\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "id": "ed30d77b-b863-4654-86ff-5a38249708c6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mkdir: cannot create directory ‘output/05.antibiotic’: File exists\n"
     ]
    }
   ],
   "source": [
    "!mkdir output/05.antibiotic"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "id": "52f41be3-a205-4f79-b4ff-cf494cb7d04b",
   "metadata": {},
   "outputs": [],
   "source": [
    "# # Read in the matrix of isolate x genotype\n",
    "# # Input information from Roger\n",
    "genotype_translator = {\n",
    "0:\"A\", 1:\"C\", 2:\"G\", 3:\"T\", 9:\"N\"\n",
    "}\n",
    "isolate_annotation_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_isolate_annotation.pkl\"\n",
    "genotype_array_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_matrix.npy\"\n",
    "snp_annotation_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_SNP_annotation.pkl\"\n",
    "genotype_translator_r = {y:x for x,y in genotype_translator.items()}\n",
    "\n",
    "isolates = pd.read_pickle(isolate_annotation_file)\n",
    "genotypes = np.load(genotype_array_file)\n",
    "snps_older = pd.read_pickle(snp_annotation_file)\n",
    "# # Filter out the snps we don't need\n",
    "snps_to_retain = snps_older.query(\"pos in @other_positions or pos in @resistance_mutations.pos\")\n",
    "indices_to_keep = snps_to_retain.index\n",
    "\n",
    "g = genotypes[indices_to_keep, :]\n",
    "del genotypes\n",
    "np.save(\"output/05.antibiotic/antibiotic_genotypes_matrix.npy\", g)\n",
    "g = np.load(\"output/05.antibiotic/antibiotic_genotypes_matrix.npy\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "521fb9db-79cd-4a92-ab98-96f35d08d4e9",
   "metadata": {},
   "outputs": [],
   "source": [
    "snps_to_retain = snps_to_retain.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "id": "62524e65-5df9-4902-8b3d-28a1aa704a25",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "mkdir: cannot create directory ‘output/05.antibiotic/strains_with_dependencies_per_AB/’: File exists\n"
     ]
    }
   ],
   "source": [
    "!mkdir output/05.antibiotic/strains_with_dependencies_per_AB/"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "id": "034d5293-f18c-417a-bb36-4e1227d56692",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "no file for DLM\n",
      "no file for CFZ\n",
      "no file for BDQ\n"
     ]
    },
    {
     "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>drug</th>\n",
       "      <th>num_R_strains</th>\n",
       "      <th>num_R_strains_with_dependency</th>\n",
       "      <th>fraction</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>RIF</td>\n",
       "      <td>10083</td>\n",
       "      <td>8930</td>\n",
       "      <td>0.885649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>ETH</td>\n",
       "      <td>5744</td>\n",
       "      <td>2256</td>\n",
       "      <td>0.392758</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>LEV</td>\n",
       "      <td>3153</td>\n",
       "      <td>198</td>\n",
       "      <td>0.062797</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>MXF</td>\n",
       "      <td>3153</td>\n",
       "      <td>198</td>\n",
       "      <td>0.062797</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CAP</td>\n",
       "      <td>3194</td>\n",
       "      <td>1493</td>\n",
       "      <td>0.467439</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>PZA</td>\n",
       "      <td>9563</td>\n",
       "      <td>9467</td>\n",
       "      <td>0.989961</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>INH</td>\n",
       "      <td>11143</td>\n",
       "      <td>8957</td>\n",
       "      <td>0.803823</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>KAN</td>\n",
       "      <td>4410</td>\n",
       "      <td>2490</td>\n",
       "      <td>0.564626</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>STM</td>\n",
       "      <td>10967</td>\n",
       "      <td>9078</td>\n",
       "      <td>0.827756</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>LZD</td>\n",
       "      <td>109</td>\n",
       "      <td>54</td>\n",
       "      <td>0.495413</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>EMB</td>\n",
       "      <td>7235</td>\n",
       "      <td>5038</td>\n",
       "      <td>0.696337</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>AMI</td>\n",
       "      <td>3431</td>\n",
       "      <td>1855</td>\n",
       "      <td>0.540659</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   drug  num_R_strains  num_R_strains_with_dependency  fraction\n",
       "0   RIF          10083                           8930  0.885649\n",
       "1   ETH           5744                           2256  0.392758\n",
       "2   LEV           3153                            198  0.062797\n",
       "3   MXF           3153                            198  0.062797\n",
       "4   CAP           3194                           1493  0.467439\n",
       "5   PZA           9563                           9467  0.989961\n",
       "6   INH          11143                           8957  0.803823\n",
       "7   KAN           4410                           2490  0.564626\n",
       "8   STM          10967                           9078  0.827756\n",
       "9   LZD            109                             54  0.495413\n",
       "10  EMB           7235                           5038  0.696337\n",
       "11  AMI           3431                           1855  0.540659"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# For each drug, get the set of mutations we are looking for\n",
    "drug_to_sensitive_sites = {drug:[] for drug in drug_list}\n",
    "for idx, row in resistance_mutations.iterrows():\n",
    "    for drug in row.known_drug:\n",
    "        drug_to_sensitive_sites[drug].append((row.pos, row.ref))\n",
    "\n",
    "# Find strains that have any of those mutations\n",
    "drug_to_indices_R_strains = {}\n",
    "\n",
    "_num_sequential_dependencies = []\n",
    "for drug, list_of_tuples in drug_to_sensitive_sites.items():\n",
    "    \n",
    "    has_sensitive_alleles = np.ones(shape=(len(list_of_tuples), g.shape[1]))\n",
    "    #print(drug)\n",
    "    \n",
    "    for idx, (pos, nt) in enumerate(list_of_tuples):\n",
    "    \n",
    "        matrix_index = snps_to_retain.query(\"pos==@pos\").index\n",
    "        has_sensitive_alleles[idx,:] = g[matrix_index, :] == genotype_translator_r[nt]\n",
    "        \n",
    "    #print(np.sum(np.sum(has_sensitive_alleles, axis=0) < has_sensitive_alleles.shape[0]))\n",
    "    indices_R_strains = np.where(np.sum(has_sensitive_alleles, axis=0) < has_sensitive_alleles.shape[0])[0]\n",
    "    drug_to_indices_R_strains[drug] = indices_R_strains\n",
    "    \n",
    "    try:\n",
    "        drug_specific_dependencies = pd.read_csv(f\"output/05.antibiotic/{drug}_antibiotic_hits.csv\", index_col=0)\n",
    "    except:\n",
    "        print(\"no file for\", drug)\n",
    "        continue\n",
    "    drug_specific_dependencies = drug_specific_dependencies.query(\n",
    "        \"pval_beta_i_on_j_BH_sig_sequential\")\n",
    "    \n",
    "    # Get the dependent positions - exclude any known resistance mutation from dependent sites\n",
    "    dependent_positions = set(drug_specific_dependencies.position_i) - set(resistance_mutations.pos)\n",
    "    dependencies = snps_to_retain.query(\"pos in @dependent_positions\")\n",
    "    #print(drug, \"has\", len(dependencies), \"dependencies excluding known R positions\")\n",
    "    assert(len(dependent_positions) == len(dependencies))\n",
    "    \n",
    "    # Create a matrix of which strains have a dependent mutation\n",
    "    _dependency_df = []\n",
    "    has_dependent_alleles = np.ones(shape=(len(dependencies), len(indices_R_strains)))\n",
    "    for mat_idx, (idx, row) in enumerate(dependencies.iterrows()):\n",
    "        has_dependency = g[:, indices_R_strains][idx, :] != genotype_translator_r[row.ref]\n",
    "        total_has_dependency = g[idx, :] != genotype_translator_r[row.ref]\n",
    "        _dependency_df.append([idx, row.pos, row.ref, np.sum(has_dependency), np.sum(total_has_dependency)])\n",
    "        has_dependent_alleles[mat_idx, :] = has_dependency\n",
    "    \n",
    "    dependency_df = pd.DataFrame(_dependency_df, columns=[\"matrix_idx\", \"pos\", \"ref\", \"num_R_strains_with_dependency\", \"total_strains_with_mutation\"])\n",
    "    dependency_df.to_csv(f\"output/05.antibiotic/strains_with_dependencies_per_AB/{drug}.csv\")\n",
    "    \n",
    "    _num_sequential_dependencies.append([drug, len(indices_R_strains), np.sum(np.sum(has_dependent_alleles, axis=0) > 0)])\n",
    "\n",
    "df = pd.DataFrame(_num_sequential_dependencies, columns=[\"drug\", \"num_R_strains\", \"num_R_strains_with_dependency\"])\n",
    "df[\"fraction\"] = df.num_R_strains_with_dependency / df.num_R_strains\n",
    "df.to_csv(\"output/05.antibiotic/num_strains_with_dependency.csv\")    \n",
    "df"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "f1c71a71-c3c0-49eb-b1d3-9a93c00378d6",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1987\n",
      "1973\n"
     ]
    }
   ],
   "source": [
    "# Here let strains with a resistance-conferring mutation be defined as resistant\n",
    "# Then count the number of resistant strains that have another mutation\n",
    "#include simultaenous and sequential\n",
    "\n",
    "snps = pd.read_csv(\"output/03.annotation/snps_with_all_annotation.csv\", index_col=0)\n",
    "snps = snps.query(\"not is_lineage\")\n",
    "\n",
    "# list of resistance mutations\n",
    "resistance_mutations = snps.query(\"in_known_ABR_position\")\n",
    "resistance_mutations[\"known_drug\"] = _process_known_hits(resistance_mutations.known_drug)\n",
    "antibiotic_hits = pd.read_csv(\"output/05.antibiotic/antibiotic_hits.csv\")\n",
    "print(len(antibiotic_hits))\n",
    "# list of all other mutations\n",
    "antibiotic_hits[\"dist\"] = np.abs(antibiotic_hits.position_j - antibiotic_hits.position_i)\n",
    "antibiotic_hits = antibiotic_hits.query(\"pval_beta_i_on_j_BH_sig_sequential or (pval_beta_i_on_j_BH_sig_simultaneous and dist >100)\")\n",
    "print(len(antibiotic_hits))\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "id": "2e65d604-0c8e-44fa-a219-3c3a31f80021",
   "metadata": {},
   "outputs": [],
   "source": [
    "\n",
    "other_positions = list(set(antibiotic_hits.position_i))\n",
    "other_mutations = snps.query(\"pos in @other_positions\")\n",
    "\n",
    "# # Read in the matrix of isolate x genotype\n",
    "# # Input information from Roger\n",
    "genotype_translator = {\n",
    "0:\"A\", 1:\"C\", 2:\"G\", 3:\"T\", 9:\"N\"\n",
    "}\n",
    "isolate_annotation_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_isolate_annotation.pkl\"\n",
    "genotype_array_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_matrix.npy\"\n",
    "snp_annotation_file = \"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_SNP_annotation.pkl\"\n",
    "genotype_translator_r = {y:x for x,y in genotype_translator.items()}\n",
    "\n",
    "isolates = pd.read_pickle(isolate_annotation_file)\n",
    "genotypes = np.load(genotype_array_file)\n",
    "snps_older = pd.read_pickle(snp_annotation_file)\n",
    "# # Filter out the snps we don't need\n",
    "snps_to_retain = snps_older.query(\"pos in @other_positions or pos in @resistance_mutations.pos\")\n",
    "indices_to_keep = snps_to_retain.index\n",
    "\n",
    "g = genotypes[indices_to_keep, :]\n",
    "del genotypes\n",
    "np.save(\"output/05.antibiotic/antibiotic_genotypes_matrix.npy\", g)\n",
    "g = np.load(\"output/05.antibiotic/antibiotic_genotypes_matrix.npy\")\n",
    "\n",
    "snps_to_retain = snps_to_retain.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "id": "2df64579-2a05-4ccb-8f52-3c1acc18b903",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "RIF has 404 dependencies excluding known R positions\n",
      "ETH has 81 dependencies excluding known R positions\n",
      "LEV has 6 dependencies excluding known R positions\n",
      "no file for DLM\n",
      "MXF has 6 dependencies excluding known R positions\n",
      "CAP has 98 dependencies excluding known R positions\n",
      "PZA has 121 dependencies excluding known R positions\n",
      "no file for CFZ\n",
      "INH has 396 dependencies excluding known R positions\n",
      "KAN has 129 dependencies excluding known R positions\n",
      "STM has 375 dependencies excluding known R positions\n",
      "LZD has 93 dependencies excluding known R positions\n",
      "no file for BDQ\n",
      "EMB has 309 dependencies excluding known R positions\n",
      "AMI has 130 dependencies excluding known R positions\n"
     ]
    }
   ],
   "source": [
    "# For each drug, get the set of mutations we are looking for\n",
    "drug_to_sensitive_sites = {drug:[] for drug in drug_list}\n",
    "for idx, row in resistance_mutations.iterrows():\n",
    "    for drug in row.known_drug:\n",
    "        drug_to_sensitive_sites[drug].append((row.pos, row.ref))\n",
    "\n",
    "# Find strains that have any of those mutations\n",
    "drug_to_indices_R_strains = {}\n",
    "\n",
    "_num_sequential_dependencies = []\n",
    "for drug, list_of_tuples in drug_to_sensitive_sites.items():\n",
    "    \n",
    "    has_sensitive_alleles = np.ones(shape=(len(list_of_tuples), g.shape[1]))\n",
    "    #print(drug)\n",
    "    \n",
    "    # Determine if each isolate has any sensitive allele\n",
    "    for idx, (pos, nt) in enumerate(list_of_tuples):\n",
    "    \n",
    "        matrix_index = snps_to_retain.query(\"pos==@pos\").index\n",
    "        has_sensitive_alleles[idx,:] = g[matrix_index, :] == genotype_translator_r[nt]\n",
    "        \n",
    "    #print(np.sum(np.sum(has_sensitive_alleles, axis=0) < has_sensitive_alleles.shape[0]))\n",
    "    indices_R_strains = np.where(np.sum(has_sensitive_alleles, axis=0) < has_sensitive_alleles.shape[0])[0]\n",
    "    drug_to_indices_R_strains[drug] = indices_R_strains\n",
    "    \n",
    "    try:\n",
    "        drug_specific_dependencies = pd.read_csv(f\"output/05.antibiotic/{drug}_antibiotic_hits.csv\", index_col=0)\n",
    "    except:\n",
    "        print(\"no file for\", drug)\n",
    "        continue\n",
    "    #drug_specific_dependencies = drug_specific_dependencies.query(\"pval_beta_i_on_j_BH_sig_sequential == 'True'\")\n",
    "    \n",
    "    # Get the dependent positions - exclude any known resistance mutation from dependent sites\n",
    "    dependent_positions = set(drug_specific_dependencies.position_i) - set(resistance_mutations.pos)\n",
    "    dependencies = snps_to_retain.query(\"pos in @dependent_positions\")\n",
    "    print(drug, \"has\", len(dependencies), \"dependencies excluding known R positions\")\n",
    "    #assert(len(dependent_positions) == len(dependencies))\n",
    "    \n",
    "    # Create a matrix of which strains have a dependent mutation\n",
    "    _dependency_df = []\n",
    "    has_dependent_alleles = np.ones(shape=(len(dependencies), len(indices_R_strains)))\n",
    "    for mat_idx, (idx, row) in enumerate(dependencies.iterrows()):\n",
    "        has_dependency = g[:, indices_R_strains][idx, :] != genotype_translator_r[row.ref]\n",
    "        total_has_dependency = g[idx, :] != genotype_translator_r[row.ref]\n",
    "        _dependency_df.append([idx, row.pos, row.ref, np.sum(has_dependency), np.sum(total_has_dependency)])\n",
    "        has_dependent_alleles[mat_idx, :] = has_dependency\n",
    "    \n",
    "    dependency_df = pd.DataFrame(_dependency_df, columns=[\"matrix_idx\", \"pos\", \"ref\", \"num_R_strains_with_dependency\", \"total_strains_with_mutation\"])\n",
    "    dependency_df.to_csv(f\"output/05.antibiotic/strains_with_dependencies_per_AB/{drug}.csv\")\n",
    "    \n",
    "    _num_sequential_dependencies.append([drug, len(indices_R_strains), np.sum(np.sum(has_dependent_alleles, axis=0) > 0)])\n",
    "    \n",
    "df = pd.DataFrame(_num_sequential_dependencies, columns=[\"drug\", \"num_R_strains\", \"num_R_strains_with_dependency\"])\n",
    "df[\"fraction\"] = df.num_R_strains_with_dependency / df.num_R_strains\n",
    "df.to_csv(\"output/05.antibiotic/num_strains_with_dependency_simultaneous.csv\")    \n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "id": "abc44554-e038-48cc-8e27-db6f44ab7cf9",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "130"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(dependent_positions)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "848e62b2-2405-410a-aef8-c3a41a9a447a",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "696"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(other_positions)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "e1949acd-ce76-40af-96c5-9fc53f0d0ce3",
   "metadata": {},
   "source": [
    "### Plot fraction of resistant strains with a dependent mutation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "id": "fff17b40-128e-4a8a-9a49-290842f24c0c",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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\n",
      "text/plain": [
       "<Figure size 720x504 with 1 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "list_of_colors = [\n",
    "    (30, 204, 0),\n",
    "    (9, 96, 19),\n",
    "    (255, 146, 135),\n",
    "    (221, 160, 21),\n",
    "    (210,78,193),\n",
    "    (210,78,193),\n",
    "    (210,78,193),\n",
    "    \n",
    "    (210,78,193),\n",
    "    \n",
    "    (128,54,115),\n",
    "    (128,54,115),\n",
    "    (30,204,0),\n",
    "    (9, 50, 105),\n",
    "    \n",
    "    (128,54,115),\n",
    "    (128,54,115),\n",
    "    (128,54,115),\n",
    "    (128,54,115),\n",
    "    (139,192,221),\n",
    "    (9, 50, 105),\n",
    "\n",
    "    (189,189,189)\n",
    "]\n",
    "list_of_colors = [(x/255,y/255, z/255) for x,y,z in list_of_colors]\n",
    "\n",
    "# Make plot\n",
    "\n",
    "df_both = pd.read_csv(\"output/05.antibiotic/num_strains_with_dependency_simultaneous.csv\", index_col=0) \n",
    "df_single = pd.read_csv(\"output/05.antibiotic/num_strains_with_dependency.csv\", index_col=0)  \n",
    "\n",
    "df_both[\"label\"]= \"both\"\n",
    "df_single[\"label\"] = \"sequential_only\"\n",
    "\n",
    "sorted_drug_list = [ 'INH', \"RIF\", \"EMB\", \"PZA\", \n",
    "                     'STM', 'AMI','KAN', 'CAP',\n",
    "                     'MXF', 'LEV', 'ETH',\n",
    "                    'DLM','CFZ','LZD','BDQ'\n",
    "]\n",
    "\n",
    "#df = pd.concat([df_both, df_single])\n",
    "df = df_single\n",
    "# Generate a rank column that will be used to sort\n",
    "# the dataframe numerically\n",
    "sorterIndex = dict(zip(sorted_drug_list, range(len(sorted_drug_list))))\n",
    "df['ab_rank'] = df['drug'].map(sorterIndex)\n",
    "df = df.sort_values(\"ab_rank\")\n",
    "sns.set_palette(sns.color_palette(list_of_colors))\n",
    "figure=plt.figure(figsize=(10,7))\n",
    "sns.barplot(data=df,x=\"drug\", y=\"fraction\", palette= sns.color_palette(list_of_colors))\n",
    "sns.despine()\n",
    "plt.savefig(\"figures/percent_strains_with_dependency.pdf\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c149302f-139b-421a-90d2-a31092c84ba6",
   "metadata": {},
   "source": [
    "## Presence of Featured mutations in the paper"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "id": "b137341c-f0eb-43de-9279-76d6762070ad",
   "metadata": {},
   "outputs": [],
   "source": [
    "antibiotic_hits = pd.read_csv(\"output/05.antibiotic/antibiotic_hits.csv\")\n",
    "display_positions =['position_i', 'gene_name_i', 'position_j', 'gene_name_j',\n",
    "                    \n",
    "       'n_mutations_i', 'n_mutations_j', 'n_branches_with_i',\n",
    "    'n_muts_i_on_branch_j', 'n_muts_same_branch',\n",
    "       'pval_beta_i_on_j_BH_sig_sequential', 'pval_beta_i_on_j_BH_sig_simultaneous']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "8a3b7e4a-1fb2-46f1-8218-ea294dadcd8f",
   "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>Unnamed: 0.1</th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_branches_with_j</th>\n",
       "      <th>...</th>\n",
       "      <th>in_antigen_protein_j</th>\n",
       "      <th>in_known_ABR_position_j</th>\n",
       "      <th>known_drug_j</th>\n",
       "      <th>in_possible_ABR_gene_j</th>\n",
       "      <th>possible_drug_j</th>\n",
       "      <th>annotation</th>\n",
       "      <th>pval_beta_i_on_j_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>median_distance</th>\n",
       "      <th>within_same_drug</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>644</th>\n",
       "      <td>539315</td>\n",
       "      <td>168228</td>\n",
       "      <td>764817</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>281</td>\n",
       "      <td>1687</td>\n",
       "      <td>921</td>\n",
       "      <td>9165</td>\n",
       "      <td>...</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>['RIF']</td>\n",
       "      <td>True</td>\n",
       "      <td>['RIF']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>1.948885e-70</td>\n",
       "      <td>True</td>\n",
       "      <td>32.419193</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>45352</td>\n",
       "      <td>211</td>\n",
       "      <td>1673425</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>786</td>\n",
       "      <td>2098</td>\n",
       "      <td>3817</td>\n",
       "      <td>12564</td>\n",
       "      <td>...</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>between_known_AB</td>\n",
       "      <td>1.000000e+00</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>45598</td>\n",
       "      <td>475</td>\n",
       "      <td>1673432</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>107</td>\n",
       "      <td>2098</td>\n",
       "      <td>523</td>\n",
       "      <td>12564</td>\n",
       "      <td>...</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>between_known_AB</td>\n",
       "      <td>2.550422e-13</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>539375</td>\n",
       "      <td>168292</td>\n",
       "      <td>764840</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>63</td>\n",
       "      <td>1687</td>\n",
       "      <td>192</td>\n",
       "      <td>9165</td>\n",
       "      <td>...</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>['RIF']</td>\n",
       "      <td>True</td>\n",
       "      <td>['RIF']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>1.883517e-34</td>\n",
       "      <td>True</td>\n",
       "      <td>29.348090</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1024</th>\n",
       "      <td>547017</td>\n",
       "      <td>234166</td>\n",
       "      <td>2986827</td>\n",
       "      <td>Rv2670c</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>96</td>\n",
       "      <td>2098</td>\n",
       "      <td>671</td>\n",
       "      <td>12564</td>\n",
       "      <td>...</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>True</td>\n",
       "      <td>['INH']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>2.627668e-09</td>\n",
       "      <td>True</td>\n",
       "      <td>57.014217</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>434</th>\n",
       "      <td>59373</td>\n",
       "      <td>63355</td>\n",
       "      <td>4235607</td>\n",
       "      <td>Rv3789</td>\n",
       "      <td>4247730</td>\n",
       "      <td>embB</td>\n",
       "      <td>16</td>\n",
       "      <td>337</td>\n",
       "      <td>30</td>\n",
       "      <td>839</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>['EMB']</td>\n",
       "      <td>True</td>\n",
       "      <td>['EMB']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>584</th>\n",
       "      <td>71196</td>\n",
       "      <td>113482</td>\n",
       "      <td>666107</td>\n",
       "      <td>pncB2</td>\n",
       "      <td>4327033</td>\n",
       "      <td>ethA</td>\n",
       "      <td>18</td>\n",
       "      <td>8</td>\n",
       "      <td>196</td>\n",
       "      <td>22</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>['ETH']</td>\n",
       "      <td>True</td>\n",
       "      <td>['ETH']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>436</th>\n",
       "      <td>59425</td>\n",
       "      <td>63409</td>\n",
       "      <td>4056258</td>\n",
       "      <td>espA</td>\n",
       "      <td>4247730</td>\n",
       "      <td>embB</td>\n",
       "      <td>5</td>\n",
       "      <td>337</td>\n",
       "      <td>14</td>\n",
       "      <td>839</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>['EMB']</td>\n",
       "      <td>True</td>\n",
       "      <td>['EMB']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>583</th>\n",
       "      <td>71195</td>\n",
       "      <td>113481</td>\n",
       "      <td>2699402</td>\n",
       "      <td>Rv2402</td>\n",
       "      <td>4327033</td>\n",
       "      <td>ethA</td>\n",
       "      <td>19</td>\n",
       "      <td>8</td>\n",
       "      <td>204</td>\n",
       "      <td>22</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>['ETH']</td>\n",
       "      <td>True</td>\n",
       "      <td>['ETH']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>524</th>\n",
       "      <td>65428</td>\n",
       "      <td>94726</td>\n",
       "      <td>3488122</td>\n",
       "      <td>Rv3122</td>\n",
       "      <td>4407992</td>\n",
       "      <td>gid</td>\n",
       "      <td>6</td>\n",
       "      <td>9</td>\n",
       "      <td>6388</td>\n",
       "      <td>8</td>\n",
       "      <td>...</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "      <td>['STM']</td>\n",
       "      <td>True</td>\n",
       "      <td>['STM']</td>\n",
       "      <td>known_AB_first</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>1987 rows × 40 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "      Unnamed: 0.1  Unnamed: 0  position_i gene_name_i  position_j  \\\n",
       "644         539315      168228      764817        rpoC      761155   \n",
       "22           45352         211     1673425        None     2155168   \n",
       "37           45598         475     1673432        None     2155168   \n",
       "670         539375      168292      764840        rpoC      761155   \n",
       "1024        547017      234166     2986827     Rv2670c     2155168   \n",
       "...            ...         ...         ...         ...         ...   \n",
       "434          59373       63355     4235607      Rv3789     4247730   \n",
       "584          71196      113482      666107       pncB2     4327033   \n",
       "436          59425       63409     4056258        espA     4247730   \n",
       "583          71195      113481     2699402      Rv2402     4327033   \n",
       "524          65428       94726     3488122      Rv3122     4407992   \n",
       "\n",
       "     gene_name_j  n_mutations_i  n_mutations_j  n_branches_with_i  \\\n",
       "644         rpoB            281           1687                921   \n",
       "22          katG            786           2098               3817   \n",
       "37          katG            107           2098                523   \n",
       "670         rpoB             63           1687                192   \n",
       "1024        katG             96           2098                671   \n",
       "...          ...            ...            ...                ...   \n",
       "434         embB             16            337                 30   \n",
       "584         ethA             18              8                196   \n",
       "436         embB              5            337                 14   \n",
       "583         ethA             19              8                204   \n",
       "524          gid              6              9               6388   \n",
       "\n",
       "      n_branches_with_j  ...  in_antigen_protein_j  in_known_ABR_position_j  \\\n",
       "644                9165  ...                  True                     True   \n",
       "22                12564  ...                  True                     True   \n",
       "37                12564  ...                  True                     True   \n",
       "670                9165  ...                  True                     True   \n",
       "1024              12564  ...                  True                     True   \n",
       "...                 ...  ...                   ...                      ...   \n",
       "434                 839  ...                 False                     True   \n",
       "584                  22  ...                 False                     True   \n",
       "436                 839  ...                 False                     True   \n",
       "583                  22  ...                 False                     True   \n",
       "524                   8  ...                 False                     True   \n",
       "\n",
       "      known_drug_j  in_possible_ABR_gene_j  possible_drug_j        annotation  \\\n",
       "644        ['RIF']                    True          ['RIF']    known_AB_first   \n",
       "22         ['INH']                    True          ['INH']  between_known_AB   \n",
       "37         ['INH']                    True          ['INH']  between_known_AB   \n",
       "670        ['RIF']                    True          ['RIF']    known_AB_first   \n",
       "1024       ['INH']                    True          ['INH']    known_AB_first   \n",
       "...            ...                     ...              ...               ...   \n",
       "434        ['EMB']                    True          ['EMB']    known_AB_first   \n",
       "584        ['ETH']                    True          ['ETH']    known_AB_first   \n",
       "436        ['EMB']                    True          ['EMB']    known_AB_first   \n",
       "583        ['ETH']                    True          ['ETH']    known_AB_first   \n",
       "524        ['STM']                    True          ['STM']    known_AB_first   \n",
       "\n",
       "      pval_beta_i_on_j_sequential  pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "644                  1.948885e-70                                True   \n",
       "22                   1.000000e+00                               False   \n",
       "37                   2.550422e-13                                True   \n",
       "670                  1.883517e-34                                True   \n",
       "1024                 2.627668e-09                                True   \n",
       "...                           ...                                 ...   \n",
       "434                           NaN                               False   \n",
       "584                           NaN                               False   \n",
       "436                           NaN                               False   \n",
       "583                           NaN                               False   \n",
       "524                           NaN                               False   \n",
       "\n",
       "     median_distance  within_same_drug  \n",
       "644        32.419193              True  \n",
       "22               NaN              True  \n",
       "37               NaN              True  \n",
       "670        29.348090              True  \n",
       "1024       57.014217             False  \n",
       "...              ...               ...  \n",
       "434              NaN             False  \n",
       "584              NaN             False  \n",
       "436              NaN             False  \n",
       "583              NaN             False  \n",
       "524              NaN             False  \n",
       "\n",
       "[1987 rows x 40 columns]"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "antibiotic_hits.sort_values(\"n_muts_i_on_branch_j\", ascending=False)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "4938b144-f8f9-48e9-902d-b705e2857d42",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>124</th>\n",
       "      <td>734624</td>\n",
       "      <td>nusG</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>14</td>\n",
       "      <td>1687</td>\n",
       "      <td>32</td>\n",
       "      <td>6</td>\n",
       "      <td>7</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>131</th>\n",
       "      <td>734458</td>\n",
       "      <td>nusG</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>10</td>\n",
       "      <td>1687</td>\n",
       "      <td>4</td>\n",
       "      <td>6</td>\n",
       "      <td>2</td>\n",
       "      <td>True</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>138</th>\n",
       "      <td>734470</td>\n",
       "      <td>nusG</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>6</td>\n",
       "      <td>1687</td>\n",
       "      <td>10</td>\n",
       "      <td>3</td>\n",
       "      <td>3</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "124      734624        nusG      761155        rpoB             14   \n",
       "131      734458        nusG      761155        rpoB             10   \n",
       "138      734470        nusG      761155        rpoB              6   \n",
       "\n",
       "     n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "124           1687                 32                     6   \n",
       "131           1687                  4                     6   \n",
       "138           1687                 10                     3   \n",
       "\n",
       "     n_muts_same_branch  pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "124                   7                               False   \n",
       "131                   2                                True   \n",
       "138                   3                               False   \n",
       "\n",
       "    pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "124                                 True  \n",
       "131                                False  \n",
       "138                                 True  "
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "antibiotic_hits.query('gene_name_i==\"nusG\" and gene_name_j==\"rpoB\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "538f358b-0761-4e46-a47b-5dfa82c24fd1",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>548715</th>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>39</td>\n",
       "      <td>2098</td>\n",
       "      <td>20</td>\n",
       "      <td>5</td>\n",
       "      <td>4</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "548715     2726142        None     2155168        katG             39   \n",
       "\n",
       "        n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "548715           2098                 20                     5   \n",
       "\n",
       "        n_muts_same_branch pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "548715                   4                              False   \n",
       "\n",
       "       pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "548715                                  NaN  "
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_hits.query('position_i==2726142 and gene_name_j==\"katG\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "id": "074d19a3-cde6-4b3f-a708-f5036bf7d57d",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>8864</th>\n",
       "      <td>2154083</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>7</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8871</th>\n",
       "      <td>2155541</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>35</td>\n",
       "      <td>39</td>\n",
       "      <td>32</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8872</th>\n",
       "      <td>2156110</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>6</td>\n",
       "      <td>39</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8873</th>\n",
       "      <td>2155295</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>6</td>\n",
       "      <td>39</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49113</th>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>2098</td>\n",
       "      <td>39</td>\n",
       "      <td>12564</td>\n",
       "      <td>0</td>\n",
       "      <td>4</td>\n",
       "      <td>False</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49120</th>\n",
       "      <td>2155167</td>\n",
       "      <td>katG</td>\n",
       "      <td>2726142</td>\n",
       "      <td>None</td>\n",
       "      <td>56</td>\n",
       "      <td>39</td>\n",
       "      <td>136</td>\n",
       "      <td>0</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>False</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "       position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "8864      2154083        katG     2726142        None              7   \n",
       "8871      2155541        katG     2726142        None             35   \n",
       "8872      2156110        katG     2726142        None              6   \n",
       "8873      2155295        katG     2726142        None              6   \n",
       "49113     2155168        katG     2726142        None           2098   \n",
       "49120     2155167        katG     2726142        None             56   \n",
       "\n",
       "       n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "8864              39                  0                     0   \n",
       "8871              39                 32                     0   \n",
       "8872              39                  0                     0   \n",
       "8873              39                  2                     0   \n",
       "49113             39              12564                     0   \n",
       "49120             39                136                     0   \n",
       "\n",
       "       n_muts_same_branch pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "8864                    1                                NaN   \n",
       "8871                    1                                NaN   \n",
       "8872                    1                                NaN   \n",
       "8873                    1                                NaN   \n",
       "49113                   4                              False   \n",
       "49120                   1                                NaN   \n",
       "\n",
       "      pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "8864                                  True  \n",
       "8871                                 False  \n",
       "8872                                  True  \n",
       "8873                                  True  \n",
       "49113                                False  \n",
       "49120                                False  "
      ]
     },
     "execution_count": 33,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "all_hits.query('position_j==2726142 and gene_name_i==\"katG\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "id": "086d3f58-99ba-4cca-8f3a-594a2c72a79c",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>732110</td>\n",
       "      <td>hadA</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>57</td>\n",
       "      <td>2098</td>\n",
       "      <td>84</td>\n",
       "      <td>19</td>\n",
       "      <td>32</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>732111</td>\n",
       "      <td>hadA</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>16</td>\n",
       "      <td>2098</td>\n",
       "      <td>42</td>\n",
       "      <td>5</td>\n",
       "      <td>10</td>\n",
       "      <td>False</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "    position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "24      732110        hadA     2155168        katG             57   \n",
       "33      732111        hadA     2155168        katG             16   \n",
       "\n",
       "    n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "24           2098                 84                    19   \n",
       "33           2098                 42                     5   \n",
       "\n",
       "    n_muts_same_branch  pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "24                  32                               False   \n",
       "33                  10                               False   \n",
       "\n",
       "   pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "24                                 True  \n",
       "33                                 True  "
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "antibiotic_hits.query('gene_name_i==\"hadA\" and gene_name_j==\"katG\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 35,
   "id": "d0fd52bc-f9f1-481e-b0fc-e586c97b1416",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "Empty DataFrame\n",
       "Columns: [position_i, gene_name_i, position_j, gene_name_j, n_mutations_i, n_mutations_j, n_branches_with_i, n_muts_i_on_branch_j, n_muts_same_branch, pval_beta_i_on_j_BH_sig_sequential, pval_beta_i_on_j_BH_sig_simultaneous]\n",
       "Index: []"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# whiB7 upstream region\n",
    "all_hits.query('gene_name_i==\"r_whiB7\" and gene_name_j==\"whiB6\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "id": "bab4c560-338d-4fc6-b6d3-9a8f3e67f17d",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>702660</th>\n",
       "      <td>3568795</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>15</td>\n",
       "      <td>8</td>\n",
       "      <td>64</td>\n",
       "      <td>6</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>702686</th>\n",
       "      <td>3568759</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>31</td>\n",
       "      <td>8</td>\n",
       "      <td>62</td>\n",
       "      <td>2</td>\n",
       "      <td>0</td>\n",
       "      <td>False</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>702796</th>\n",
       "      <td>3568736</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>8</td>\n",
       "      <td>8</td>\n",
       "      <td>2</td>\n",
       "      <td>5</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "702660     3568795        None     4338371       whiB6             15   \n",
       "702686     3568759        None     4338371       whiB6             31   \n",
       "702796     3568736        None     4338371       whiB6              8   \n",
       "\n",
       "        n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "702660              8                 64                     6   \n",
       "702686              8                 62                     2   \n",
       "702796              8                  2                     5   \n",
       "\n",
       "        n_muts_same_branch pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "702660                   0                               True   \n",
       "702686                   0                              False   \n",
       "702796                   0                               True   \n",
       "\n",
       "       pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "702660                                  NaN  \n",
       "702686                                  NaN  \n",
       "702796                                  NaN  "
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# whiB7\n",
    "all_hits.query('position_i > 3568679 and position_i <3569109 and gene_name_j==\"whiB6\"')[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 37,
   "id": "0c394e43-6b69-4b00-a06c-1111e37844ab",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "104\n"
     ]
    },
    {
     "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>618518</th>\n",
       "      <td>2715342</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>141</td>\n",
       "      <td>8</td>\n",
       "      <td>350</td>\n",
       "      <td>57</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>618522</th>\n",
       "      <td>2715346</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>83</td>\n",
       "      <td>8</td>\n",
       "      <td>190</td>\n",
       "      <td>9</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>618524</th>\n",
       "      <td>2715344</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>76</td>\n",
       "      <td>8</td>\n",
       "      <td>526</td>\n",
       "      <td>18</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>618527</th>\n",
       "      <td>2715369</td>\n",
       "      <td>None</td>\n",
       "      <td>4338371</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>41</td>\n",
       "      <td>8</td>\n",
       "      <td>506</td>\n",
       "      <td>17</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>631887</th>\n",
       "      <td>2715342</td>\n",
       "      <td>None</td>\n",
       "      <td>4338326</td>\n",
       "      <td>whiB6</td>\n",
       "      <td>141</td>\n",
       "      <td>5</td>\n",
       "      <td>350</td>\n",
       "      <td>3</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "        position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "618518     2715342        None     4338371       whiB6            141   \n",
       "618522     2715346        None     4338371       whiB6             83   \n",
       "618524     2715344        None     4338371       whiB6             76   \n",
       "618527     2715369        None     4338371       whiB6             41   \n",
       "631887     2715342        None     4338326       whiB6            141   \n",
       "\n",
       "        n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "618518              8                350                    57   \n",
       "618522              8                190                     9   \n",
       "618524              8                526                    18   \n",
       "618527              8                506                    17   \n",
       "631887              5                350                     3   \n",
       "\n",
       "        n_muts_same_branch pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "618518                   0                               True   \n",
       "618522                   0                               True   \n",
       "618524                   0                               True   \n",
       "618527                   0                               True   \n",
       "631887                   0                               True   \n",
       "\n",
       "       pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "618518                                  NaN  \n",
       "618522                                  NaN  \n",
       "618524                                  NaN  \n",
       "618527                                  NaN  \n",
       "631887                                  NaN  "
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\n",
    "# eis upstream region\n",
    "subset = all_hits.query('position_i > 2714124 and position_i<2715472 and gene_name_j==\"whiB6\"')\n",
    "subset = subset.query(\"pval_beta_i_on_j_BH_sig_sequential or pval_beta_i_on_j_BH_sig_simultaneous\")\n",
    "print(subset.n_muts_i_on_branch_j.sum() + subset.n_muts_same_branch.sum())\n",
    "subset[display_positions]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "id": "d40e766b-737d-4ed6-8d28-87db340a7693",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "46\n"
     ]
    }
   ],
   "source": [
    "\n",
    "# eis upstream region and rrs - 38 mutations\n",
    "all_hits.query('position_i > 2714124 and position_i<2715472 and position_j > 1471846 and position_j<1473382 and pval_beta_i_on_j_BH_sig_sequential ')[display_positions]\n",
    "subset = all_hits.query('position_i > 2714124 and position_i<2715472 and position_j > 1471846 and position_j<1473382 and pval_beta_i_on_j_BH_sig_sequential ')\n",
    "subset = subset.query(\"pval_beta_i_on_j_BH_sig_sequential or pval_beta_i_on_j_BH_sig_simultaneous\")\n",
    "print(subset.n_muts_i_on_branch_j.sum() + subset.n_muts_same_branch.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "id": "71794573-94cf-4a34-8397-ba60c5e77c0e",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "5\n"
     ]
    }
   ],
   "source": [
    "# rrsto WhiB6 10 mutations\n",
    "subset= all_hits.query('position_i > 1471846 and position_i<1473382  and gene_name_j==\"whiB6\"and pval_beta_i_on_j_BH_sig_simultaneous ')[display_positions].head(10)\n",
    "subset = subset.query(\"pval_beta_i_on_j_BH_sig_sequential or pval_beta_i_on_j_BH_sig_simultaneous\")\n",
    "print(subset.n_muts_i_on_branch_j.sum() + subset.n_muts_same_branch.sum())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "id": "e99bede5-fc3a-4d14-9d80-e4422df42ebb",
   "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>position_i</th>\n",
       "      <th>gene_name_i</th>\n",
       "      <th>position_j</th>\n",
       "      <th>gene_name_j</th>\n",
       "      <th>n_mutations_i</th>\n",
       "      <th>n_mutations_j</th>\n",
       "      <th>n_branches_with_i</th>\n",
       "      <th>n_muts_i_on_branch_j</th>\n",
       "      <th>n_muts_same_branch</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_sequential</th>\n",
       "      <th>pval_beta_i_on_j_BH_sig_simultaneous</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>644</th>\n",
       "      <td>764817</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>281</td>\n",
       "      <td>1687</td>\n",
       "      <td>921</td>\n",
       "      <td>145</td>\n",
       "      <td>125</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>37</th>\n",
       "      <td>1673432</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>107</td>\n",
       "      <td>2098</td>\n",
       "      <td>523</td>\n",
       "      <td>49</td>\n",
       "      <td>17</td>\n",
       "      <td>True</td>\n",
       "      <td>True</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>670</th>\n",
       "      <td>764840</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>63</td>\n",
       "      <td>1687</td>\n",
       "      <td>192</td>\n",
       "      <td>44</td>\n",
       "      <td>19</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1024</th>\n",
       "      <td>2986827</td>\n",
       "      <td>Rv2670c</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>96</td>\n",
       "      <td>2098</td>\n",
       "      <td>671</td>\n",
       "      <td>40</td>\n",
       "      <td>35</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>972</th>\n",
       "      <td>3073679</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>53</td>\n",
       "      <td>2098</td>\n",
       "      <td>192</td>\n",
       "      <td>39</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>690</th>\n",
       "      <td>764363</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>58</td>\n",
       "      <td>1687</td>\n",
       "      <td>78</td>\n",
       "      <td>38</td>\n",
       "      <td>17</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1002</th>\n",
       "      <td>2747471</td>\n",
       "      <td>folC</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>74</td>\n",
       "      <td>2098</td>\n",
       "      <td>86</td>\n",
       "      <td>38</td>\n",
       "      <td>19</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>648</th>\n",
       "      <td>3073679</td>\n",
       "      <td>None</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>53</td>\n",
       "      <td>1687</td>\n",
       "      <td>192</td>\n",
       "      <td>36</td>\n",
       "      <td>7</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>691</th>\n",
       "      <td>764948</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>51</td>\n",
       "      <td>1687</td>\n",
       "      <td>70</td>\n",
       "      <td>35</td>\n",
       "      <td>16</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>665</th>\n",
       "      <td>3877949</td>\n",
       "      <td>rpoA</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>55</td>\n",
       "      <td>1687</td>\n",
       "      <td>50</td>\n",
       "      <td>35</td>\n",
       "      <td>18</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1738</th>\n",
       "      <td>3073679</td>\n",
       "      <td>None</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>53</td>\n",
       "      <td>918</td>\n",
       "      <td>192</td>\n",
       "      <td>35</td>\n",
       "      <td>2</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>705</th>\n",
       "      <td>2986827</td>\n",
       "      <td>Rv2670c</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>96</td>\n",
       "      <td>1687</td>\n",
       "      <td>671</td>\n",
       "      <td>34</td>\n",
       "      <td>25</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1278</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>1472362</td>\n",
       "      <td>None</td>\n",
       "      <td>32</td>\n",
       "      <td>116</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>695</th>\n",
       "      <td>765462</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>43</td>\n",
       "      <td>1687</td>\n",
       "      <td>156</td>\n",
       "      <td>31</td>\n",
       "      <td>11</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>967</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>32</td>\n",
       "      <td>2098</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1675</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>2715369</td>\n",
       "      <td>None</td>\n",
       "      <td>32</td>\n",
       "      <td>41</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>681</th>\n",
       "      <td>2747471</td>\n",
       "      <td>folC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>74</td>\n",
       "      <td>1687</td>\n",
       "      <td>86</td>\n",
       "      <td>31</td>\n",
       "      <td>17</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>642</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>32</td>\n",
       "      <td>1687</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1375</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>4327480</td>\n",
       "      <td>None</td>\n",
       "      <td>32</td>\n",
       "      <td>7</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1399</th>\n",
       "      <td>2765888</td>\n",
       "      <td>lipP</td>\n",
       "      <td>4247574</td>\n",
       "      <td>embB</td>\n",
       "      <td>32</td>\n",
       "      <td>111</td>\n",
       "      <td>62</td>\n",
       "      <td>31</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1071</th>\n",
       "      <td>3067961</td>\n",
       "      <td>None</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>78</td>\n",
       "      <td>2098</td>\n",
       "      <td>286</td>\n",
       "      <td>30</td>\n",
       "      <td>31</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>873</th>\n",
       "      <td>767123</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>62</td>\n",
       "      <td>1687</td>\n",
       "      <td>124</td>\n",
       "      <td>29</td>\n",
       "      <td>31</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1488</th>\n",
       "      <td>4238385</td>\n",
       "      <td>aftA</td>\n",
       "      <td>1673425</td>\n",
       "      <td>None</td>\n",
       "      <td>30</td>\n",
       "      <td>786</td>\n",
       "      <td>6</td>\n",
       "      <td>29</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1765</th>\n",
       "      <td>2747471</td>\n",
       "      <td>folC</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>74</td>\n",
       "      <td>918</td>\n",
       "      <td>86</td>\n",
       "      <td>28</td>\n",
       "      <td>16</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>968</th>\n",
       "      <td>1853001</td>\n",
       "      <td>rpmI</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>28</td>\n",
       "      <td>2098</td>\n",
       "      <td>280</td>\n",
       "      <td>28</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1734</th>\n",
       "      <td>1853001</td>\n",
       "      <td>rpmI</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>28</td>\n",
       "      <td>918</td>\n",
       "      <td>280</td>\n",
       "      <td>28</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>643</th>\n",
       "      <td>1853001</td>\n",
       "      <td>rpmI</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>28</td>\n",
       "      <td>1687</td>\n",
       "      <td>280</td>\n",
       "      <td>27</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1774</th>\n",
       "      <td>2986827</td>\n",
       "      <td>Rv2670c</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>96</td>\n",
       "      <td>918</td>\n",
       "      <td>671</td>\n",
       "      <td>25</td>\n",
       "      <td>14</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1040</th>\n",
       "      <td>2747480</td>\n",
       "      <td>folC</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>38</td>\n",
       "      <td>2098</td>\n",
       "      <td>74</td>\n",
       "      <td>25</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>769</th>\n",
       "      <td>766488</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>58</td>\n",
       "      <td>1687</td>\n",
       "      <td>38</td>\n",
       "      <td>24</td>\n",
       "      <td>34</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>700</th>\n",
       "      <td>764841</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>35</td>\n",
       "      <td>1687</td>\n",
       "      <td>184</td>\n",
       "      <td>23</td>\n",
       "      <td>12</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>782</th>\n",
       "      <td>764918</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>38</td>\n",
       "      <td>1687</td>\n",
       "      <td>54</td>\n",
       "      <td>23</td>\n",
       "      <td>15</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>689</th>\n",
       "      <td>764703</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>27</td>\n",
       "      <td>1687</td>\n",
       "      <td>28</td>\n",
       "      <td>23</td>\n",
       "      <td>4</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>751</th>\n",
       "      <td>3067961</td>\n",
       "      <td>None</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>78</td>\n",
       "      <td>1687</td>\n",
       "      <td>286</td>\n",
       "      <td>22</td>\n",
       "      <td>23</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>848</th>\n",
       "      <td>761156</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>37</td>\n",
       "      <td>1687</td>\n",
       "      <td>152</td>\n",
       "      <td>22</td>\n",
       "      <td>17</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>926</th>\n",
       "      <td>764916</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>46</td>\n",
       "      <td>1687</td>\n",
       "      <td>36</td>\n",
       "      <td>22</td>\n",
       "      <td>22</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>969</th>\n",
       "      <td>3521253</td>\n",
       "      <td>nuoJ</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>21</td>\n",
       "      <td>2098</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1489</th>\n",
       "      <td>4394864</td>\n",
       "      <td>Rv3909</td>\n",
       "      <td>1673425</td>\n",
       "      <td>None</td>\n",
       "      <td>21</td>\n",
       "      <td>786</td>\n",
       "      <td>32</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1784</th>\n",
       "      <td>2747480</td>\n",
       "      <td>folC</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>38</td>\n",
       "      <td>918</td>\n",
       "      <td>74</td>\n",
       "      <td>21</td>\n",
       "      <td>3</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>971</th>\n",
       "      <td>2487024</td>\n",
       "      <td>Rv2219A</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>21</td>\n",
       "      <td>2098</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1490</th>\n",
       "      <td>3899339</td>\n",
       "      <td>Rv3480c</td>\n",
       "      <td>1673425</td>\n",
       "      <td>None</td>\n",
       "      <td>22</td>\n",
       "      <td>786</td>\n",
       "      <td>10</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>970</th>\n",
       "      <td>2241091</td>\n",
       "      <td>ctpF</td>\n",
       "      <td>2155168</td>\n",
       "      <td>katG</td>\n",
       "      <td>21</td>\n",
       "      <td>2098</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1736</th>\n",
       "      <td>2241091</td>\n",
       "      <td>ctpF</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>21</td>\n",
       "      <td>918</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1735</th>\n",
       "      <td>3521253</td>\n",
       "      <td>nuoJ</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>21</td>\n",
       "      <td>918</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1737</th>\n",
       "      <td>2487024</td>\n",
       "      <td>Rv2219A</td>\n",
       "      <td>781687</td>\n",
       "      <td>rpsL</td>\n",
       "      <td>21</td>\n",
       "      <td>918</td>\n",
       "      <td>632</td>\n",
       "      <td>21</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>646</th>\n",
       "      <td>2241091</td>\n",
       "      <td>ctpF</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>21</td>\n",
       "      <td>1687</td>\n",
       "      <td>632</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>721</th>\n",
       "      <td>2747480</td>\n",
       "      <td>folC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>38</td>\n",
       "      <td>1687</td>\n",
       "      <td>74</td>\n",
       "      <td>20</td>\n",
       "      <td>6</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>647</th>\n",
       "      <td>2487024</td>\n",
       "      <td>Rv2219A</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>21</td>\n",
       "      <td>1687</td>\n",
       "      <td>632</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>645</th>\n",
       "      <td>3521253</td>\n",
       "      <td>nuoJ</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>21</td>\n",
       "      <td>1687</td>\n",
       "      <td>632</td>\n",
       "      <td>20</td>\n",
       "      <td>0</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>940</th>\n",
       "      <td>766487</td>\n",
       "      <td>rpoC</td>\n",
       "      <td>761155</td>\n",
       "      <td>rpoB</td>\n",
       "      <td>45</td>\n",
       "      <td>1687</td>\n",
       "      <td>234</td>\n",
       "      <td>20</td>\n",
       "      <td>24</td>\n",
       "      <td>True</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "      position_i gene_name_i  position_j gene_name_j  n_mutations_i  \\\n",
       "644       764817        rpoC      761155        rpoB            281   \n",
       "37       1673432        None     2155168        katG            107   \n",
       "670       764840        rpoC      761155        rpoB             63   \n",
       "1024     2986827     Rv2670c     2155168        katG             96   \n",
       "972      3073679        None     2155168        katG             53   \n",
       "690       764363        rpoC      761155        rpoB             58   \n",
       "1002     2747471        folC     2155168        katG             74   \n",
       "648      3073679        None      761155        rpoB             53   \n",
       "691       764948        rpoC      761155        rpoB             51   \n",
       "665      3877949        rpoA      761155        rpoB             55   \n",
       "1738     3073679        None      781687        rpsL             53   \n",
       "705      2986827     Rv2670c      761155        rpoB             96   \n",
       "1278     2765888        lipP     1472362        None             32   \n",
       "695       765462        rpoC      761155        rpoB             43   \n",
       "967      2765888        lipP     2155168        katG             32   \n",
       "1675     2765888        lipP     2715369        None             32   \n",
       "681      2747471        folC      761155        rpoB             74   \n",
       "642      2765888        lipP      761155        rpoB             32   \n",
       "1375     2765888        lipP     4327480        None             32   \n",
       "1399     2765888        lipP     4247574        embB             32   \n",
       "1071     3067961        None     2155168        katG             78   \n",
       "873       767123        rpoC      761155        rpoB             62   \n",
       "1488     4238385        aftA     1673425        None             30   \n",
       "1765     2747471        folC      781687        rpsL             74   \n",
       "968      1853001        rpmI     2155168        katG             28   \n",
       "1734     1853001        rpmI      781687        rpsL             28   \n",
       "643      1853001        rpmI      761155        rpoB             28   \n",
       "1774     2986827     Rv2670c      781687        rpsL             96   \n",
       "1040     2747480        folC     2155168        katG             38   \n",
       "769       766488        rpoC      761155        rpoB             58   \n",
       "700       764841        rpoC      761155        rpoB             35   \n",
       "782       764918        rpoC      761155        rpoB             38   \n",
       "689       764703        rpoC      761155        rpoB             27   \n",
       "751      3067961        None      761155        rpoB             78   \n",
       "848       761156        rpoB      761155        rpoB             37   \n",
       "926       764916        rpoC      761155        rpoB             46   \n",
       "969      3521253        nuoJ     2155168        katG             21   \n",
       "1489     4394864      Rv3909     1673425        None             21   \n",
       "1784     2747480        folC      781687        rpsL             38   \n",
       "971      2487024     Rv2219A     2155168        katG             21   \n",
       "1490     3899339     Rv3480c     1673425        None             22   \n",
       "970      2241091        ctpF     2155168        katG             21   \n",
       "1736     2241091        ctpF      781687        rpsL             21   \n",
       "1735     3521253        nuoJ      781687        rpsL             21   \n",
       "1737     2487024     Rv2219A      781687        rpsL             21   \n",
       "646      2241091        ctpF      761155        rpoB             21   \n",
       "721      2747480        folC      761155        rpoB             38   \n",
       "647      2487024     Rv2219A      761155        rpoB             21   \n",
       "645      3521253        nuoJ      761155        rpoB             21   \n",
       "940       766487        rpoC      761155        rpoB             45   \n",
       "\n",
       "      n_mutations_j  n_branches_with_i  n_muts_i_on_branch_j  \\\n",
       "644            1687                921                   145   \n",
       "37             2098                523                    49   \n",
       "670            1687                192                    44   \n",
       "1024           2098                671                    40   \n",
       "972            2098                192                    39   \n",
       "690            1687                 78                    38   \n",
       "1002           2098                 86                    38   \n",
       "648            1687                192                    36   \n",
       "691            1687                 70                    35   \n",
       "665            1687                 50                    35   \n",
       "1738            918                192                    35   \n",
       "705            1687                671                    34   \n",
       "1278            116                 62                    31   \n",
       "695            1687                156                    31   \n",
       "967            2098                 62                    31   \n",
       "1675             41                 62                    31   \n",
       "681            1687                 86                    31   \n",
       "642            1687                 62                    31   \n",
       "1375              7                 62                    31   \n",
       "1399            111                 62                    31   \n",
       "1071           2098                286                    30   \n",
       "873            1687                124                    29   \n",
       "1488            786                  6                    29   \n",
       "1765            918                 86                    28   \n",
       "968            2098                280                    28   \n",
       "1734            918                280                    28   \n",
       "643            1687                280                    27   \n",
       "1774            918                671                    25   \n",
       "1040           2098                 74                    25   \n",
       "769            1687                 38                    24   \n",
       "700            1687                184                    23   \n",
       "782            1687                 54                    23   \n",
       "689            1687                 28                    23   \n",
       "751            1687                286                    22   \n",
       "848            1687                152                    22   \n",
       "926            1687                 36                    22   \n",
       "969            2098                632                    21   \n",
       "1489            786                 32                    21   \n",
       "1784            918                 74                    21   \n",
       "971            2098                632                    21   \n",
       "1490            786                 10                    21   \n",
       "970            2098                632                    21   \n",
       "1736            918                632                    21   \n",
       "1735            918                632                    21   \n",
       "1737            918                632                    21   \n",
       "646            1687                632                    20   \n",
       "721            1687                 74                    20   \n",
       "647            1687                632                    20   \n",
       "645            1687                632                    20   \n",
       "940            1687                234                    20   \n",
       "\n",
       "      n_muts_same_branch  pval_beta_i_on_j_BH_sig_sequential  \\\n",
       "644                  125                                True   \n",
       "37                    17                                True   \n",
       "670                   19                                True   \n",
       "1024                  35                                True   \n",
       "972                    6                                True   \n",
       "690                   17                                True   \n",
       "1002                  19                                True   \n",
       "648                    7                                True   \n",
       "691                   16                                True   \n",
       "665                   18                                True   \n",
       "1738                   2                                True   \n",
       "705                   25                                True   \n",
       "1278                   0                                True   \n",
       "695                   11                                True   \n",
       "967                    0                                True   \n",
       "1675                   0                                True   \n",
       "681                   17                                True   \n",
       "642                    0                                True   \n",
       "1375                   0                                True   \n",
       "1399                   0                                True   \n",
       "1071                  31                                True   \n",
       "873                   31                                True   \n",
       "1488                   0                                True   \n",
       "1765                  16                                True   \n",
       "968                    0                                True   \n",
       "1734                   0                                True   \n",
       "643                    0                                True   \n",
       "1774                  14                                True   \n",
       "1040                   6                                True   \n",
       "769                   34                                True   \n",
       "700                   12                                True   \n",
       "782                   15                                True   \n",
       "689                    4                                True   \n",
       "751                   23                                True   \n",
       "848                   17                                True   \n",
       "926                   22                                True   \n",
       "969                    0                                True   \n",
       "1489                   0                                True   \n",
       "1784                   3                                True   \n",
       "971                    0                                True   \n",
       "1490                   0                                True   \n",
       "970                    0                                True   \n",
       "1736                   0                                True   \n",
       "1735                   0                                True   \n",
       "1737                   0                                True   \n",
       "646                    0                                True   \n",
       "721                    6                                True   \n",
       "647                    0                                True   \n",
       "645                    0                                True   \n",
       "940                   24                                True   \n",
       "\n",
       "     pval_beta_i_on_j_BH_sig_simultaneous  \n",
       "644                                   NaN  \n",
       "37                                   True  \n",
       "670                                   NaN  \n",
       "1024                                  NaN  \n",
       "972                                   NaN  \n",
       "690                                   NaN  \n",
       "1002                                  NaN  \n",
       "648                                   NaN  \n",
       "691                                   NaN  \n",
       "665                                   NaN  \n",
       "1738                                  NaN  \n",
       "705                                   NaN  \n",
       "1278                                  NaN  \n",
       "695                                   NaN  \n",
       "967                                   NaN  \n",
       "1675                                  NaN  \n",
       "681                                   NaN  \n",
       "642                                   NaN  \n",
       "1375                                  NaN  \n",
       "1399                                  NaN  \n",
       "1071                                  NaN  \n",
       "873                                   NaN  \n",
       "1488                                  NaN  \n",
       "1765                                  NaN  \n",
       "968                                   NaN  \n",
       "1734                                  NaN  \n",
       "643                                   NaN  \n",
       "1774                                  NaN  \n",
       "1040                                  NaN  \n",
       "769                                   NaN  \n",
       "700                                   NaN  \n",
       "782                                   NaN  \n",
       "689                                   NaN  \n",
       "751                                   NaN  \n",
       "848                                   NaN  \n",
       "926                                   NaN  \n",
       "969                                   NaN  \n",
       "1489                                  NaN  \n",
       "1784                                  NaN  \n",
       "971                                   NaN  \n",
       "1490                                  NaN  \n",
       "970                                   NaN  \n",
       "1736                                  NaN  \n",
       "1735                                  NaN  \n",
       "1737                                  NaN  \n",
       "646                                   NaN  \n",
       "721                                   NaN  \n",
       "647                                   NaN  \n",
       "645                                   NaN  \n",
       "940                                   NaN  "
      ]
     },
     "execution_count": 40,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "antibiotic_hits.query(\"pval_beta_i_on_j_BH_sig_sequential\").sort_values(\"n_muts_i_on_branch_j\", ascending=False)[display_positions].head(50)"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "c8f008b6-fa10-433f-b3d7-043d0a4b6461",
   "metadata": {},
   "source": [
    "## Get the nucleotide changes for individual SNPs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "id": "422d4076-e3f6-4e7d-9dd9-cc7e245d0bfd",
   "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>pos</th>\n",
       "      <th>ref</th>\n",
       "      <th>alt</th>\n",
       "      <th>gene_category</th>\n",
       "      <th>gene_name</th>\n",
       "      <th>gene_id</th>\n",
       "      <th>gene_pos</th>\n",
       "      <th>SNP_type</th>\n",
       "      <th>AA_change</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2153889_C</th>\n",
       "      <td>2153889</td>\n",
       "      <td>T</td>\n",
       "      <td>C</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2223</td>\n",
       "      <td>N</td>\n",
       "      <td>*741W</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2153891_G</th>\n",
       "      <td>2153891</td>\n",
       "      <td>A</td>\n",
       "      <td>G</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2221</td>\n",
       "      <td>N</td>\n",
       "      <td>*741R</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2153897_T</th>\n",
       "      <td>2153897</td>\n",
       "      <td>C</td>\n",
       "      <td>T</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2215</td>\n",
       "      <td>N</td>\n",
       "      <td>V739M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2153905_T</th>\n",
       "      <td>2153905</td>\n",
       "      <td>C</td>\n",
       "      <td>T</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2207</td>\n",
       "      <td>N</td>\n",
       "      <td>R736K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2153908_G</th>\n",
       "      <td>2153908</td>\n",
       "      <td>T</td>\n",
       "      <td>G</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2204</td>\n",
       "      <td>N</td>\n",
       "      <td>D735A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2156104_C</th>\n",
       "      <td>2156104</td>\n",
       "      <td>T</td>\n",
       "      <td>C</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>8</td>\n",
       "      <td>N</td>\n",
       "      <td>E3G</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2156106_A</th>\n",
       "      <td>2156106</td>\n",
       "      <td>G</td>\n",
       "      <td>A</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>6</td>\n",
       "      <td>S</td>\n",
       "      <td>P2P</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2156109_A</th>\n",
       "      <td>2156109</td>\n",
       "      <td>C</td>\n",
       "      <td>A</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>3</td>\n",
       "      <td>S</td>\n",
       "      <td>V1V</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2156109_T</th>\n",
       "      <td>2156109</td>\n",
       "      <td>C</td>\n",
       "      <td>T</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>3</td>\n",
       "      <td>S</td>\n",
       "      <td>V1V</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2156110_G</th>\n",
       "      <td>2156110</td>\n",
       "      <td>A</td>\n",
       "      <td>G</td>\n",
       "      <td>Antibiotic Resistance</td>\n",
       "      <td>katG</td>\n",
       "      <td>Rv1908c</td>\n",
       "      <td>2</td>\n",
       "      <td>N</td>\n",
       "      <td>V1A</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>845 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "               pos ref alt          gene_category gene_name  gene_id gene_pos  \\\n",
       "2153889_C  2153889   T   C  Antibiotic Resistance      katG  Rv1908c     2223   \n",
       "2153891_G  2153891   A   G  Antibiotic Resistance      katG  Rv1908c     2221   \n",
       "2153897_T  2153897   C   T  Antibiotic Resistance      katG  Rv1908c     2215   \n",
       "2153905_T  2153905   C   T  Antibiotic Resistance      katG  Rv1908c     2207   \n",
       "2153908_G  2153908   T   G  Antibiotic Resistance      katG  Rv1908c     2204   \n",
       "...            ...  ..  ..                    ...       ...      ...      ...   \n",
       "2156104_C  2156104   T   C  Antibiotic Resistance      katG  Rv1908c        8   \n",
       "2156106_A  2156106   G   A  Antibiotic Resistance      katG  Rv1908c        6   \n",
       "2156109_A  2156109   C   A  Antibiotic Resistance      katG  Rv1908c        3   \n",
       "2156109_T  2156109   C   T  Antibiotic Resistance      katG  Rv1908c        3   \n",
       "2156110_G  2156110   A   G  Antibiotic Resistance      katG  Rv1908c        2   \n",
       "\n",
       "          SNP_type AA_change  \n",
       "2153889_C        N     *741W  \n",
       "2153891_G        N     *741R  \n",
       "2153897_T        N     V739M  \n",
       "2153905_T        N     R736K  \n",
       "2153908_G        N     D735A  \n",
       "...            ...       ...  \n",
       "2156104_C        N       E3G  \n",
       "2156106_A        S       P2P  \n",
       "2156109_A        S       V1V  \n",
       "2156109_T        S       V1V  \n",
       "2156110_G        N       V1A  \n",
       "\n",
       "[845 rows x 9 columns]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "snps = pd.read_pickle(\"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_SNP_functional_annotation.pkl\")\n",
    "snps.query(\"gene_name=='katG'\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "id": "8140230f-1b6b-4fb7-88eb-91548bb043e1",
   "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>pos</th>\n",
       "      <th>ref</th>\n",
       "      <th>alt</th>\n",
       "      <th>gene_category</th>\n",
       "      <th>gene_name</th>\n",
       "      <th>gene_id</th>\n",
       "      <th>gene_pos</th>\n",
       "      <th>SNP_type</th>\n",
       "      <th>AA_change</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>734254_A</th>\n",
       "      <td>734254</td>\n",
       "      <td>G</td>\n",
       "      <td>A</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>1</td>\n",
       "      <td>N</td>\n",
       "      <td>V1M</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734258_A</th>\n",
       "      <td>734258</td>\n",
       "      <td>C</td>\n",
       "      <td>A</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>5</td>\n",
       "      <td>N</td>\n",
       "      <td>T2N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734261_A</th>\n",
       "      <td>734261</td>\n",
       "      <td>C</td>\n",
       "      <td>A</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>8</td>\n",
       "      <td>N</td>\n",
       "      <td>T3N</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734262_G</th>\n",
       "      <td>734262</td>\n",
       "      <td>C</td>\n",
       "      <td>G</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>9</td>\n",
       "      <td>S</td>\n",
       "      <td>T3T</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734264_C</th>\n",
       "      <td>734264</td>\n",
       "      <td>T</td>\n",
       "      <td>C</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>11</td>\n",
       "      <td>N</td>\n",
       "      <td>F4S</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734905_T</th>\n",
       "      <td>734905</td>\n",
       "      <td>C</td>\n",
       "      <td>T</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>652</td>\n",
       "      <td>S</td>\n",
       "      <td>L218L</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734948_G</th>\n",
       "      <td>734948</td>\n",
       "      <td>T</td>\n",
       "      <td>G</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>695</td>\n",
       "      <td>N</td>\n",
       "      <td>F232C</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734959_G</th>\n",
       "      <td>734959</td>\n",
       "      <td>T</td>\n",
       "      <td>G</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>706</td>\n",
       "      <td>N</td>\n",
       "      <td>S236A</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734964_A</th>\n",
       "      <td>734964</td>\n",
       "      <td>G</td>\n",
       "      <td>A</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>711</td>\n",
       "      <td>S</td>\n",
       "      <td>K237K</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734966_C</th>\n",
       "      <td>734966</td>\n",
       "      <td>T</td>\n",
       "      <td>C</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>713</td>\n",
       "      <td>N</td>\n",
       "      <td>I238T</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>132 rows × 9 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "             pos ref alt  gene_category gene_name gene_id gene_pos SNP_type  \\\n",
       "734254_A  734254   G   A  Non-Essential      nusG  Rv0639        1        N   \n",
       "734258_A  734258   C   A  Non-Essential      nusG  Rv0639        5        N   \n",
       "734261_A  734261   C   A  Non-Essential      nusG  Rv0639        8        N   \n",
       "734262_G  734262   C   G  Non-Essential      nusG  Rv0639        9        S   \n",
       "734264_C  734264   T   C  Non-Essential      nusG  Rv0639       11        N   \n",
       "...          ...  ..  ..            ...       ...     ...      ...      ...   \n",
       "734905_T  734905   C   T  Non-Essential      nusG  Rv0639      652        S   \n",
       "734948_G  734948   T   G  Non-Essential      nusG  Rv0639      695        N   \n",
       "734959_G  734959   T   G  Non-Essential      nusG  Rv0639      706        N   \n",
       "734964_A  734964   G   A  Non-Essential      nusG  Rv0639      711        S   \n",
       "734966_C  734966   T   C  Non-Essential      nusG  Rv0639      713        N   \n",
       "\n",
       "         AA_change  \n",
       "734254_A       V1M  \n",
       "734258_A       T2N  \n",
       "734261_A       T3N  \n",
       "734262_G       T3T  \n",
       "734264_C       F4S  \n",
       "...            ...  \n",
       "734905_T     L218L  \n",
       "734948_G     F232C  \n",
       "734959_G     S236A  \n",
       "734964_A     K237K  \n",
       "734966_C     I238T  \n",
       "\n",
       "[132 rows x 9 columns]"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "snps = pd.read_pickle(\"/n/data1/hms/dbmi/farhat/Roger/homoplasy_project/rolling_DB_scrape/Genotypes_Filtered_2/genotypes_SNP_functional_annotation.pkl\")\n",
    "snps.query(\"gene_name=='nusG'\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "id": "ccb2a65e-3230-45c6-a339-705c8c31266c",
   "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>pos</th>\n",
       "      <th>ref</th>\n",
       "      <th>alt</th>\n",
       "      <th>gene_category</th>\n",
       "      <th>gene_name</th>\n",
       "      <th>gene_id</th>\n",
       "      <th>gene_pos</th>\n",
       "      <th>SNP_type</th>\n",
       "      <th>AA_change</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>734624_A</th>\n",
       "      <td>734624</td>\n",
       "      <td>G</td>\n",
       "      <td>A</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>371</td>\n",
       "      <td>N</td>\n",
       "      <td>R124H</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>734624_T</th>\n",
       "      <td>734624</td>\n",
       "      <td>G</td>\n",
       "      <td>T</td>\n",
       "      <td>Non-Essential</td>\n",
       "      <td>nusG</td>\n",
       "      <td>Rv0639</td>\n",
       "      <td>371</td>\n",
       "      <td>N</td>\n",
       "      <td>R124L</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "             pos ref alt  gene_category gene_name gene_id gene_pos SNP_type  \\\n",
       "734624_A  734624   G   A  Non-Essential      nusG  Rv0639      371        N   \n",
       "734624_T  734624   G   T  Non-Essential      nusG  Rv0639      371        N   \n",
       "\n",
       "         AA_change  \n",
       "734624_A     R124H  \n",
       "734624_T     R124L  "
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "snps.query(\"pos==734624\")"
   ]
  },
  {
   "cell_type": "markdown",
   "id": "38f48b1f-e9e8-41cc-9cc9-9fcbd2eb7c7d",
   "metadata": {},
   "source": [
    "## Analysis of sequentiall mutations"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "id": "e3d86d78-eec5-466b-9ad5-5d13f589da26",
   "metadata": {},
   "outputs": [],
   "source": [
    "drug_list = [ 'INH',\n",
    " 'RIF', \n",
    " 'EMB', \n",
    " 'PZA', \n",
    " 'STM',\n",
    " 'AMI',\n",
    " 'KAN',\n",
    " 'CAP',\n",
    " 'MXF',\n",
    " 'LEV',          \n",
    " 'ETH',\n",
    "'LZD',\n",
    "             'CFZ',\n",
    "             'BDQ'\n",
    "            ]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 45,
   "id": "c910f137-63ed-4aa3-b859-af70276928da",
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "INH 125\n",
      "RIF 138\n",
      "EMB 104\n",
      "PZA 281\n",
      "STM 160\n",
      "AMI 104\n",
      "KAN 104\n",
      "CAP 69\n",
      "MXF 100\n",
      "LEV 100\n",
      "ETH 66\n",
      "LZD 64\n",
      "CFZ 0\n",
      "BDQ 0\n"
     ]
    },
    {
     "data": {
      "image/png": "iVBORw0KGgoAAAANSUhEUgAAAXMAAAD4CAYAAAAeugY9AAAAOXRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjUuMiwgaHR0cHM6Ly9tYXRwbG90bGliLm9yZy8qNh9FAAAACXBIWXMAAAsTAAALEwEAmpwYAAAky0lEQVR4nO3df7hcVX3v8ffnJBCiEeR3Q5ICpoEWIg0kcqlIDf4oAfGStKiJKNhLjSK2CtIroI+NtQFaUa6UQgtCAavEWIhQCkhAUsM1gqGJJCEiCYkQkgsBFBMNgSTf+8deB3cmc2b2nDNzzpw9n1ee/czM2nuttWdOznfWWXvttRQRmJnZ4NY10CdgZmZ952BuZlYCDuZmZiXgYG5mVgIO5mZmJTB0oE+g0svbaOnwmo98c0kriwdgyWPPtbT8448+qKXlX336m1taPsCBZ36jpeW/svKhlpa/97HvaGn5AL94Zn3L62il9XPPaXkde79uiPpaxvCjP1ko5mxZclWf62qltgvmZmb9SuXooHAwN7POprZucBfmYG5mnc0tczOzEnDL3MysBLqGDPQZNEXDf19I2pweD5EUkv4yt+8qSR9Jz2+UdHq1vGZmbUNdxbY219czfA74lKTdm3EyZmb9Tiq2tbm+BvONwP3AWU04FzOz/ueW+WsuAz4jqVrH05clLe3emlCXmVlzuWWeiYg1wMPAB6vs/uuImNC99VSGpJmSFktafP111/b1lMzMiitJy7xZo1kuAf4d+EFvMkfEtcC10Prb+c3MdtKpo1mqiYifAo8BpzajPDOzfuOW+S5mA62fxcrMrJm62r8/vIiGg3lEjEiPa4HxufSfkGvpR8RHesprZtY2BkGruwjfAWpmnW0QjFQpwsHczDpbSS6AOpibWWdzN4uZWQm4m8XMrATcMm+NaPEtQzeecXRrKwC+8L3HW1r+PsPb7sfWsAlveVNLy1/9xje0tPyjjmrtOqwAvxq3f8vraKUhg2XIX0la5uX4SjIz660m3TQkaQ9JD0v6iaQVkr6Y0mdJeiY3T9UpuTwXSVol6XFJJ+XSJ0palvZdKdX/xhn8TTwzs75o3miWrcA7ImKzpN2AByXdnfZdERGX5w+WdAQwHTgSOAi4T9JhEbEduAaYCfwIuAuYAtxNDW6Zm1lna1LLPDLdC/DslrZaHcenAXMiYmuasHAVcKykkcCeEbEoIgK4GZhar34HczPrbAWnwM3P7pq2mbsWpSFpuu/ngPkR8VDa9UlJj0q6QdLeKW0U8HQu+7qUNio9r0yvycHczDpbwZZ5RFwbEZNy2y7zdUfE9jTd92iyVvZ4si6TscAEYAPwle6aq5xN1EivqdfBXNL21Jm/XNJ/SHpjSj9E0vL0fLKkl3Id//f1tj4zs5ZoweIUEfFLYAEwJSKeTUF+B3AdcGw6bB0wJpdtNLA+pY+ukl5TX1rmW9KiE+OBF4FzezhuYW6Binf1oT4zs+Zr3miW/XON2uHAu4Cfpj7wbtOA5en5HcB0ScMkHQqMAx6OiA3AJknHpVEsZwK316u/WaNZFgFHNaksM7N+o66m9TaPBG5KS2h2AXMj4k5J35A0gayrZC3wMYCIWCFpLtlaENuAc9NIFoBzgBuB4WSjWGqOZIEmBPN04u8Eru/hkBNy639+JyJm97VOM7NmKTCEu5CIeBTY5a7EiPhwjTyzydaCqExfTG6K8SL68pU0PAXpF4B9gPk9HJfvZqkayHdaA/TrXgPUzPqRCm5tri8t8y0RMUHSXsCdZH3mV/amoPwaoFte9RqgZtZ/mtUyH2h97iyKiJeAvwIuSHc9mZkNGsrGkNfd2l2zFnReAvyE7NZUM7NBo6urq9DW7nrdzVK5nmdEvDf3cnxKW0A21tLMrD21f6O7EE+0ZWYdbTB0oRThYG5mHc3B3MysBBzMzcxKwMHczKwENFiWt6uj7YJ5Gb4k//akw1ta/q+2vNrS8vvDWW8bU/+gPvjFMSPrH9QHB47YvaXlAzy+cUvL62iloUMGxy+zW+ZmZiXgYG5mVgbliOUO5mbW2dwyNzMrAQdzM7MSGAzzrhRR913k1vrs3i5M6QskPaXc15qk70ranJ4fImlLyvMTST+U1NphHmZmjeqg+cy3pNWmq/klcDzwYFr7rnI82OruvJI+BlwMnNWbEzUza4WydLP09e+LOfx22ts/BW6rceyewC/6WJ+ZWVN10nzmwyu6WT6Q23c/8MdpHdDpwLcr8o5NeVYD5wNfbc5pm5k1R7OCuaQ9JD2cupVXSPpiSt9H0nxJT6THvXN5LpK0StLjkk7KpU+UtCztu1IFTqBIMN+SW8NzQkTkA/Z24EHgA8DwiFhbkXd1yjMW+DRpabgqH8Jv1wC9zmuAmln/UZcKbQVsBd4REX8ITACmSDoOuBC4PyLGkTWAu687HkHWCD4SmAJcnRrGANcAM4FxaZtSr/JmjGaZA8wDZtU57g7gX6vtyK8B+vI2rwFqZv2nWV0oERHA5vRyt7QFcBowOaXfRLZgz2dT+pyI2AqskbQKOFbSWmDPiFiUzu9mYCpwd636mzEmZyFwKXBLnePeBqxuQn1mZk1TtJsl34OQtplVyhoiaSnwHDA/Ih4CDoyIDQDp8YB0+Cjg6Vz2dSltVHpemV5TkZb58HRy3e6JiAu7X6Rvo8t7yDs25RXwCvAXBeozM+s3RVvm+R6EGsdsByak0X3zJI2vVXW1Imqk11Q3mEfEkB7SJ/eQPiI9rgWG1yvfzGxAtWCgSkT8UtICsr7uZyWNjIgNkkaStdoha3Hnpw8dDaxP6aOrpNdUjlufzMx6qYmjWfZPLXIkDQfeBfyU7Hph9/01ZwG3p+d3ANMlDZN0KNmFzodTV8wmScelUSxn5vL0yLfzm1lH62re4hQjgZvSiJQuYG5E3ClpETBX0tnAU8D7ACJihaS5wGPANuDc1E0DcA5wI1nvxt3UufgJDuZm1uGaOJrlUeDoKukvAO/sIc9sYHaV9MVArf72XTiYm1lHGwQ3dxbiYG5mHW0w3KpfhIP5ILTn8N0G+hT67PQ3j65/UB9Ei28964/f/63bdrS+khbSYJhqELfMzcxKoYkXQAeUg7mZdTQHczOzEnA3i5lZCZTlAmjhO0D12+Xjlkv6jqTXSZpWMdf5Ukk7JJ2cy3eepJcl7dWat2Bm1nudtDhFt+55zceTTZr18YiYl5/rHLiabBbF7+XyzQB+DExr1kmbmTWLVGxrd72dm2Uh8Hv5BEmHAV8APhwRO1LaWGAE8HmyoG5m1la6ulRoa3cNB3NJQ4GTgWW5tN2AbwEXRMRTucNnkM1zvhA4XNIBmJm1kU7sZume13wx2WQx1+f2fQlYERFzKvJMJ1tJYwfZYs/v68O5mpk1XVm6WRoZzbIl9YvvRNJk4M+AYyrSjyKb0nF++lbbHXgS+KcqZcwkW++Oq67+F87+6C4LeJiZtcRgaHUX0aehiWmV6X8FPhgRmyp2zwBmRcSluePXSDo4In6eP9BrgJrZQClJLO/zOPOPk61nd03Ft9ulZF0sJ1ccPy+l/30f6zUza4qOa5l3LwdXkXYpWeCu5ttVjj+/+KmZmbXeYBipUoTvADWzjlaShrmDuZl1to7rZjEzK6OSxPJe3wFqZlYKzbppSNIYSQ9IWilphaRPpfRZkp7JzV91Si7PRZJWSXpc0km59ImSlqV9V6rACbhlbmYdrYndLNuAz0TEf0t6A/CIpPlp3xURcXlFvUeQje47EjgIuE/SYRGxHbiG7N6bHwF3AVOAu2tV3nbBfPuO1g4zX7vxNy0tH+C2lRtaWv6xB7V2Asq3H7Z/S8sHmHXvz1pa/pI1L7a0/BOPaP3MFP9y27L6B7WxRy9/b8vrGL5b30NYs0azRMQGYEN6vknSSmBUjSynkd0hvxVYI2kVcKyktcCeEbEIQNLNwFTqBHN3s5hZRyt6O7+kmZIW57Yeb1WXdAhwNPBQSvqkpEcl3ZButoQs0D+dy7YupY1KzyvTa3IwN7OOVrTPPCKujYhJue3aHsobAdwKfDoifkXWZTIWmEDWcv9K96FVskeN9JrarpvFzKw/NXM0S5pB9lbgmxFxG0BEPJvbfx1wZ3q5DhiTyz4aWJ/SR1dJr8ktczPraF1Soa2eNOLkemBlRHw1lz4yd9g0YHl6fgcwXdIwSYeSTUz4cOp73yTpuFTmmcDt9ep3y9zMOloTb+c/HvgwsCxNFw5wMTBD0gSyrpK1wMcAImKFpLnAY2QjYc5NI1kAzgFuBIaTXfisefETGgjmkj4HfBDYDuwAfgHsTbaS0P7AmnToJ4BLgDcBB0dEpPzfBd5VbY4XM7OB0qxYHhEPUr2/+64aeWYDs6ukLwbGN1J/oWAu6Y+AU4FjImKrpP2A3SNifZrP/IKIODV3PMAvyb6pHpT0RmAkZmZtpiy38xftMx8JPJ/GQxIRz0dEvQ75OWQD4gH+lGylITOztlKWlYaKBvN7gTGSfibpaklvL5DnfuCPJQ0hC+q7TIlrZjbQVPBfuysUzCNiMzCR7PbSjcC3JX2kTrbtwIPAB4DhEbG2pwPzg/Fv+HrVoZtmZi3RpWJbu2tkcYrtwAJggaRlwFlkV1trmUO2utCsOmW/tmzcr18JLxtnZv2moxankHQ4sCMinkhJE4Cf95zjNQvJViK6pVdnZ2bWYkXGkA8GRVvmI4B/TKNStgGryLpcakrDEi+vd5yZ2UApSSwvFswj4hHgrT3sW0DW/ZJPm9zDsR5jbmZtpSxDE30HqJl1tJLEcgdzM+tsQ0oSzR3MzayjuZvFzKwESjIy0cHczDqbW+YtMqTFX5NjD3x9S8sH+OsDf6+l5bd6ndT+cMkpvz/Qp9D2Ru21+0CfQp+8fljbhZeqShLL2y+Ym5n1J7fMzcxKoNW9Af3FwdzMOlo5QrmDuZl1uLLMzeIFnc2sozVrcQpJYyQ9IGmlpBWSPpXS95E0X9IT6XHvXJ6LJK2S9Likk3LpEyUtS/uuVIGO/V4Fc0nTJIWk30+vD0mvv5Q7Zj9Jr0q6Kr2eJemC3tRnZtYqkgptBWwDPhMRfwAcB5wr6QjgQuD+iBhHtmjPhaneI8gW7jkSmAJcnRbzAbiGbDLDcWmbUq/y3rbMZ5AtPDE9l/Yk2Tqh3d4HrOhl+WZm/aJZLfOI2BAR/52ebwJWAqOA04Cb0mE3AVPT89OAORGxNSLWkM1Ge6ykkcCeEbEozTx7cy5PjxoO5pJGkC3UfDY7B/MtwEpJk9LrDwBzGy3fzKw/DelSoS2/IlraepwGXNIhwNHAQ8CBEbEBsoAPHJAOGwU8ncu2LqWNSs8r02vqzQXQqcA9EfEzSS9KOgZ4Me2bA0yX9P/Ilo1bDxzUizrMzPpF0XHm+RXR6pQ3ArgV+HRE/KpG+dV2RI30mnrTzTKDLGiTHmfk9t0DvDulFV7AOf+Nd/11XgPUzPpPV8GtCEm7kQXyb0bEbSn52dR1Qnp8LqWvA8bkso8mawCvS88r02tqqGUuaV/gHcB4SQEMIfvGuBogIl6R9AjwGbJO/fcWKTf/jffytvrfQGZmzdKsO0DTiJPrgZUR8dXcrjvI1ky+LD3enkv/lqSvkvVgjAMejojtkjZJOo6sm+ZM4B/r1d9oN8vpwM0R8bHcG/gvdv4W+QrwXxHxQllukzWz8mriDaDHAx8GlklamtIuJgvicyWdDTxFNjiEiFghaS7wGNlImHMjYnvKdw5wIzAcuDttNTUazGekE8u7NZ0w3SeIR7GY2SDRrNv5I+JBer6h9J095JkNzK6SvhgY30j9DQXzamt7RsSVwJU9HH8j2bcLETGrkbrMzPpDSaZm8e38ZtbZytIb7GBuZh2tLHOzOJibWUcrywRVDuZm1tFK0jB3MDezzubFKWzAvLp9R0vLH9I1pP5B1nKPrNs80KfQJ2ccM9BnUExJYrmDuZl1Nl8ANTMrgZLEcgdzM+ts7mYxMysBlWRJZwdzM+toQ0sy0LzQ25C0Off8lLQw6e+m10MlPS/p0oo8CyQtzr2eJGlBk87bzKwpmrgG6IBq6DtJ0jvJ5tWdEhFPpeQ/AR4H3l9lBekDJJ3c99M0M2uNLhXb2l3hYC7pBOA64D0RsTq3awbwNbJ5eo+ryPZl4PN9PUkzs1Zp1oLOA61oMB9GtjrG1Ij4aXeipOFk8/TeCdzCzkvIASwCtko6sQnnambWdF1Soa3dFQ3mrwI/BM6uSD8VeCAifkO2SMU0SZW3D/4ddVrnXgPUzAbKkK5iW7srOpplB/B+4D5JF0fEJSl9BnC8pLXp9b7AicB93Rkj4vuSvsSuXTDkjvEaoGY2ILo6bWhiRPxG0qnAQknPAt8B3gaMiYitAJL+nCzA31eRfTbwz8CTTTlrM7MmGQQ9KIU09MdDRLwITCHrNvlz4PvdgTy5HfifkoZV5LsL2NjHczUza7pmjmaRdIOk5yQtz6XNkvSMpKVpOyW37yJJqyQ9LumkXPpEScvSviurjBTcRaGWeUSMyD1/Gjg0vfxaxXEvAvunl5Mr9k0sUpeZWX9q8sXNG4GrgJsr0q+IiMvzCZKOAKYDRwIHkXVjHxYR24FrgJnAj4C7yBrRd9eqeBB065uZtU4zhyZGxA+AFwtWfRowJyK2RsQaYBVwrKSRwJ4RsSgiguyLYWq9whzMzayjDelSoS0/6i5tMxuo5pOSHk3dMHuntFHA07lj1qW0Uel5ZXpNDuZm1tG6Cm4RcW1ETMptRcdRXwOMBSYAG4CvpPRq7f2okV6TJ9oys47W6nlXIuLZXF3Xkd1kCVmLe0zu0NHA+pQ+ukp6TW6Zm1lHU8Gt1+VnfeDdpgHdI13uAKZLGibpUGAc8HBEbAA2SToujWI5k2ykYE1umQ9Cuw+G29Gsz44/eM+BPoWO0MzRLJJuIRvJt5+kdcDfAJMlTSDrKlkLfAwgIlZImgs8BmwDzk0jWQDOIRsZM5xsFEvNkSzgYG5mHa6ZnSwRUTk/FcD1NY6fTXZTZWX6YmB8I3U7mJtZR+saDPPbFuBgbmYdrSydlg7mZtbRBsMqQkU0utLQ70iaI2m1pMck3SXpsLTvPEkvS9ord/xkSS9JWiJppaS/afYbMDPri1aPZukvjaw0JGAesCAixkbEEcDFwIHpkBnAj8mG3uQtjIijgUnAhyR5jhYzaxuduAboicCrEfHP3QkRsTQiFkoaC4wgm02x2tVcIuLXwCNkd0KZmbWFIVKhrd01EszHkwXjamaQLRu3EDhc0gGVB0jal2yBihWNnqSZWat0XDdLHdPJZv/aAdwGvC+37wRJS4B7gcsiwsHczNpGpy3oDFmLepf+bklHkd2GOj8tHzednbtaFkbE0RExMd9FU1GG1wA1swHRhQpt7a6RoYnfBy6R9NGIuA5A0luAfwBmRcSl3QdKWiPp4KIFew1QMxsog6HVXUThlnmaJH0a8O40NHEFMItsHoJ5FYfPI2uhm5m1NRX81+4aumkoItYD7y9w3Pm5lwsaPCczs34zGEaqFOE7QM2so5UkljuYm1lnczA3MyuBwdAfXoSDuZl1tJLMgOtgbmadrZkrDQ0kB/NBqAyT6W9+edtAn0Lb+7M/HF3/IOuzsnSzlGVedjOzXulSsa0ISTdIek7S8lzaPpLmS3oiPe6d23eRpFWSHpd0Ui59oqRlad+VKjBto4O5mXW0Jt80dCMwpSLtQuD+iBgH3J9eI+kIspsrj0x5rpY0JOW5BphJNlXKuCpl7sLB3Mw6WjMn2oqIHwAvViSfBtyUnt8ETM2lz4mIrRGxBlgFHCtpJLBnRCxKd97fnMvTI/eZm1lH64ce8wMjYgNARGzITRE+CvhR7rh1Ke3V9LwyvSYHczPraEVv55c0k6zro9u1aZLA3qpWcdRIr6lQN4ukkPSN3OuhkjZKujO9Pl/S9bn9Z0j6z/R8lqRnJC1N22VF6jQz6xcFV6eIiGsjYlJuKxrIn01dJ6TH51L6OmBM7rjRwPqUPrpKek1F+8x/DYyXNDy9fjfwTG7/lcBEScdLeiPwd8Bf5vZfERET0nZhwTrNzFquH2ZNvAM4Kz0/C7g9lz5d0jBJh5Jd6Hw4dclsknRcGsVyZi5Pjxq5AHo38J70vHuZOAAiYhvwCeCfyOY3vyEinmygbDOzAdHMC6CSbgEWkS2fuU7S2cBlZFOHP0HWEL4MIK26Nhd4DLgHODcitqeizgG+TnZRdDVZ/K1dd3axtO4JbgbeCnwB+BBZp/2ngQsi4tSKN/I/gD+IiK0pbRbwUWBjOuyzEfG9nury4hSdwTcN1TdiD1/SqmePoX2/fvnjJ18qFHPe8qa92vruokYWp3gUOISsVX5X5X5JI4BJwG7A/hW7890suwRyLxtnZgOmJCs6N/rVfwdwOdnqQvtW7Psi8G/As8AV7Lyoc01eNs7MBkqnzs1yA/BSRCyTNLk7UdKbyfrTJwCvAP9L0rsjYn6TztPMrCXKEcobvAM0ItZFxNfyaelq6zXAeRHxckTsILsY+jVJuzfvVM3MWqAk3SyFLoD2J3ezdAZfAK3PF0Dra8YF0CU/31Qo5hx98BvaOqT7f4uZdbSSdJk7mJtZZ3MwNzMrgbIsTuFgbmYdzS1zM7MSKEksdzA3sw5XkmjuYG5mHc195mZmJVB0seZ252BuZp3NwdzMbPBzN4uZWQmUZWhiQxNtpUUqKtMq1/hcKmmUpBck7VVx7Hclvb+vJ21m1iwlmWersWBeQ37xiQkR8QxwLzC1+4AU2N8G3NmkOs3M+q4k0bxZwbyaW4DpudfTgHsi4jctrNPMrCFdUqGt3TUrmJ+X62J5IKXdA0yU1L0i0XRyi0CbmbWDZjbMJa2VtCzFwsUpbR9J8yU9kR73zh1/kaRVkh6XdFJf3kcrullOBIiIV8iWmTtd0n5kqxDdWy2z1wA1swHT/G6WE1MsnJReXwjcHxHjgPvTayQdQdbIPRKYAlwtaUhv30arR7PcAnye7KO4PSJerXaQ1wA1s4HSD0MTTyNbNxngJmAB8NmUPicitgJrJK0CjgUW9aaSVvaZAzwAjAPOxV0sZtaGpKLbb3sQ0jazSnEB3Cvpkdz+AyNiA0B6PCCljwKezuVdl9J6pdGW+eskrcu9/mp6PE/Sh3LpUyNibUTskHQr8D7gB709STOzVil6bTPfg1DD8RGxXtIBwHxJP61VdbVqip3NrhoK5hHRU0t+Vo08nwI+1Ug9Zmb9pZndLBGxPj0+J2keWbfJs5JGRsQGSSOB59Lh64AxueyjgfW9rbvV3SxmZm2taDdL/XL0eklv6H4O/AmwnGwgyFnpsLOA29PzO4DpkoZJOpSsS/rh3r4P385vZh2tiZc/DwTmKYv8Q4FvRcQ9kn4MzJV0NvAUWbczEbFC0lzgMWAbcG5EbO9t5Ypor8EjHs3SGTa/vG2gT6HtjdjDba169hja91i87hdbC8Wc0XsPa+s7h/y/xcw6XFvH6MIczM2so3lxikGqP3qVtm3f0dryd7T2TQzfvdc3oRW2cdPWlpbf6p9zf8zV8fQLW1peRyv9wag3DPQpFDIIpl0ppOOCuZlZnhenMDMrg3LEcgdzM+tsJYnlDuZm1tncZ25mVgIqSTQvfDu/pO0V63xeKGleer5K0ku5fW+VtEDSpFz+QyQtb83bMDPrnZKsGtdQy3xLREyotkPSZOCCiDg1l9anEzMz6w9lCVXuZjGzjtaJQxOHS1qae31pRHy7Tp5vSuq+82F3oLV305iZNagsLfNGpsDdklvnc0KBQA5wRvfxwCk9HeQ1QM1soDRrCtyB1hbdLF4D1MwGSid2s5iZlc5gaHUX0Zc+83si4sImn4+ZWb8qSSzvvMUpPGtiff0xa+Kajb9uafllmDVxyyu9XnSmLfTHrInNWJxi09Ziv1BvGNbek+W6m8XMOpr7zM3MSqC929vFNTI00cysfJp4P7+kKZIeT1Oc9Os1RQdzM+toKvivbjnSEOCfgJOBI4AZko5o8em/xsHczDpaE28aOhZYFRFPRsQrwBzgtFae+04iYlBvwMzBXL7fQ2eUX4b3UIbPqK/nBizObTMr9p8OfD33+sPAVf11fmVomc8c5OX3Rx1+DwNffn/UMdjL7686eiUiro2ISbmtcu6Rau33fhv7XYZgbmbWDtYBY3KvRwPr+6tyB3Mzs+b4MTBO0qGSdgemA3f0V+VlGGfe6mkW+2MaR7+H8pffH3UM9vL7q46WiIhtkj4JfA8YAtwQESv6q/62u53fzMwa524WM7MScDA3MyuBtg/mkjanx0MkhaS/zO27StJH0vMbJZ1eLW/BerZLWippuaT/kPTGXL3L0/PJkl5Kxy2VdF/BMru3C1P6AklPKbfqtaTvVrzXLSnPTyT9UNLhBc77O5JeJ2laRb1LJe2QdHIu33mSXpa0V4HP5nOSVkh6NJX1QHpcVfF5vLXee6tTz7T0M/793OcQkr6UO2Y/Sa9Kuiq9niXpgjrlbs49P0XSE5J+N70eKul5SZdW5FkgaXHu9SRJC2rU8TuS5khaLekxSXdJOizt2+Wzzv1fWiJppaS/qVF2SPpG7vVQSRsl3Zleny/p+tz+MyT9Z+7zeSb3M7qsyOeUS6vMv1TSKEkvVP7fST/n99cof5ffB0nz6vxfmpTL/9rvolUx0APxCwzU35weDwGeBVYBu6e0q4CPpOc3AqdXy9tIPen5TcDncvUuT88nA3f2psyK9AXAo8Db0us3Ag9VvNflueM/BtxU4Ly/CZxf5ZiZwH8BXbm0h4GF3Z9fjffwR8AiYFh6vR9wUE+fR733VqeuuemcZuU+h9XAktwx5wBLSTdjALOACwr+H3pnKm9sbt8pwP9N6ap4H08BJ6fXk4AFPZSv9Bl9PJc2ATihp886/9kBrweeACb2dP7AEmB4en1y+gy68w9Nr49Pn/ca4E1FP59a/197yg/cApyVe70X8DzwukZ/H+r8X5qUe30Iud8Lbztvbd8yr7ARuB84q8X1LAJGtbiOOWRDlwD+FLitxrF7Ar8oUOZC4PfyCal1+AXgwxGxI6WNBUYAnwdm1ClzJPB8RGwFiIjnI6Le2NlG3lv3eY4gC0Zn5/ICbAFW5lpoHyAL+g2RdAJwHfCeiFid2zUD+BpZ4D6uItuXyT6jek4EXo2If+5OiIilEbGwyGcdEb8GHgHG1qjjbuA9uXO+JZd/G/AJsnlB/oFsFMWTBc67L25h55/TNLIFa37T4nqtB4MtmANcBnxG2aQ2lb6c/zOuN4Wnct9Jz+NDT8jV8bk6xQ2v+LPyA7l99wN/nOqbDlQukD025VkNnA98tc55DyVrsS3Lpe0GfIusZfVU7vDuYLAQOFzSATWKvhcYI+lnkq6W9Paa77jYe6tmKlkw+BnwoqRjcvvmANMljQa20/iNGMOA24GpEfHT7kRJw8l+1neSfR6VwXYRsFXSiXXKH08WjKup+1lL2pfsi6TWMLbuz2AP4Ciyv3ZeExE/BFYC7yIL6Hnn5f4PnlTnvVSTz/9ASrsHmJjOHbKf8y3Vs7+m1u9DT76Z+32+qxfn3jEGXTCPiDVkf7Z+sMruv46ICd1bg0V3L4v3ArAPML+H4xbm6phdp8wt+fOJiHxQ2w48SNbSHB4Rayvyrk55xgKfpufxt93nvZisdXl9bt+XgBURMaciz3RgTmqp3wa8r6c3EBGbgYlkXTUbgW8rXaeood57q2YGWcAiPeYD6z3Au1NakS+GSq8CPyRr9eedCjyQWpO3AtOqNBL+jmKt857U+qxPkLSE7AvzsqgxJjkiHiXrZphBlaCW/rKZBOwG7F+x+4rc/8Hv9eI95POfmM7nFbIGz+mS9iPrVrq3Tjm1fh96ckbu9/mUXpx7xxisNw1dAvw78IMmlrklIiakizp3AucCVzax/GrmAPPI+iVruQP41x72ban2xSVpMvBnwDEV6UcB44D5yq5R7g48SfYnelURsZ2s/3KBpGVk3Vw31jnnou+tu2X6DmC8pCC74SKAq1P9r0h6BPgMcCTw3nplVtgBvB+4T9LFEXFJSp8BHC9pbXq9L1mXyWsXtiPi+8ouwFZ2weStIJtkqfJ91fusF0bEqQ28jzuAy8n6l/et2PdF4N/IritdQY0v6Ca6heyLTsDtEfFqP9RpPRh0LXOA9KfyY2Qtq2aX/RLwV8AFqZuilRYCl1L/z9O3kV2gK0TS3mTB/8yI2FSxewbZBcZD0nYQMErSwT2UdbikcbmkCcDPC5xG0fcGWSC8OSIOTuc0huwi3ujcMV8BPhsRLxQobxep9X0qcIaksyXtSfa5/m73Z0H2BV6tX3s28L9rFP99YJikj3YnSHoLWV984c+6gBuAv42IZflESW8m60//e7K/4A6W9O5e1tGIB8i+rM6l2M/ZWmiwtswh+wVb0oqCI2KJpJ+Q/Ym8sA9FdXeBdLsnIl5bfSQigqylVc3YlFfAK8BfNFDvx4EDgGu080TMl5K9p5Mrjp+X0v++SlkjgH9UNlRzG9looroz29V5b5VmkF0LybsVuDhX3gpq9ynXFREvSppC9hfdCOD73Rd2k9uBf5A0rCLfXZI21ig3JE0D/o+y4acvA2vJWtDnVBze/Vk/RIMiYh3ZF8RrlP2ArwHOi4iXU9ongJslTWiwitdJWpd73X2d5jxJH8qlT42ItRGxQ9KtZH8FFPkruebvg/WNb+c3MyuBQdnNYmZmO3MwNzMrAQdzM7MScDA3MysBB3MzsxJwMDczKwEHczOzEvj/23mZCBUPIWMAAAAASUVORK5CYII=\n",
      "text/plain": [
       "<Figure size 432x288 with 2 Axes>"
      ]
     },
     "metadata": {
      "needs_background": "light"
     },
     "output_type": "display_data"
    }
   ],
   "source": [
    "import ast\n",
    "\n",
    "number_of_links = np.zeros((len(drug_list), len(drug_list)))\n",
    "drug_to_idx = {drug:i for i, drug in enumerate(drug_list)}\n",
    "                            \n",
    "for drug in drug_list: \n",
    "    between_hits = pd.read_csv(f\"output/05.antibiotic/{drug}_between_antibiotic_hits.csv\", index_col=0).drop_duplicates()\n",
    "\n",
    "    between_hits = between_hits.dropna(subset=[\"known_drug_i\", \"known_drug_j\", \"pval_beta_i_on_j_BH_sig_sequential\"])\n",
    "    between_hits = between_hits.query(\"pval_beta_i_on_j_BH_sig_sequential\")\n",
    "    print(drug, len(between_hits))\n",
    "    \n",
    "    for idx, row in between_hits.iterrows():\n",
    "        for first_drug in ast.literal_eval(row.known_drug_j):\n",
    "            for second_drug in ast.literal_eval(row.known_drug_i):\n",
    "                \n",
    "                number_of_links[drug_to_idx[first_drug], drug_to_idx[second_drug]] += int(row.n_muts_i_on_branch_j) \n",
    "\n",
    "sns.heatmap(number_of_links[0:-3,:][:,0:-3],\n",
    "            xticklabels = drug_list[0:-3], \n",
    "            yticklabels = drug_list[0:-3], \n",
    "            cmap=\"Blues\")\n",
    "plt.savefig(\"figures/sequential_mutations_ABR_heatmap.pdf\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "id": "48d021f8-9a5b-4a2a-b3f9-60d8ade15c09",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(4310.0, 40054.0)"
      ]
     },
     "execution_count": 46,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "second_on_first = np.sum(number_of_links[0:4,:][:,4::])\n",
    "first_on_second = np.sum(number_of_links[4::,:][:,0:4])\n",
    "first_on_second, second_on_first"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 47,
   "id": "05e1a92a-5509-418e-9330-642d35986e98",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[   0., 2210., 2875., 2078.,    0., 3316., 3937., 3109., 3526.,\n",
       "        3526.,  198.,    0.,    0.,    0.],\n",
       "       [  29.,    0., 1868., 1694.,    6., 2517., 3072., 2380., 2568.,\n",
       "        2568.,  135.,    0.,    0.,    0.],\n",
       "       [  15.,   10.,    0.,  288.,    6., 1491., 1653., 1426., 1812.,\n",
       "        1812.,   35.,    0.,    0.,    0.],\n",
       "       [   0.,    6.,   10.,    0.,   10.,  132.,  141.,  136.,  261.,\n",
       "         261.,   20.,    0.,    0.,    0.],\n",
       "       [  71.,  696., 1746., 1166.,    0., 1917., 2481., 1761., 3076.,\n",
       "        3076.,  221.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,   66.,    0.,    0.,    0.,    0., 1499.,\n",
       "        1499.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,  162.,    0.,    0.,    0.,    0., 1995.,\n",
       "        1995.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,   60.,    0.,    0.,    0.,    0., 1407.,\n",
       "        1407.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,   12.,    0.,  231.,  231.,  231.,    0.,\n",
       "           0.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,   12.,    0.,  231.,  231.,  231.,    0.,\n",
       "           0.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,   20.,  121.,  178.,    0.,  661.,  685.,  633.,  817.,\n",
       "         817.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,\n",
       "           0.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,\n",
       "           0.,    0.,    0.,    0.,    0.],\n",
       "       [   0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,    0.,\n",
       "           0.,    0.,    0.,    0.,    0.]])"
      ]
     },
     "execution_count": 47,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "number_of_links"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "09a70208-2113-4165-8103-877e4c458c83",
   "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": "3.9.13"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}