{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 165,
   "metadata": {},
   "outputs": [],
   "source": [
    "from Bio import Entrez\n",
    "from Bio import SeqIO\n",
    "from Bio.Seq import Seq\n",
    "from Bio.SeqRecord import SeqRecord\n",
    "import re\n",
    "import random\n",
    "import pandas as pd\n",
    "\n",
    "Entrez.email = 'sasha.grrshnova98@gmail.com'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#get B.burgdorferi genome\n",
    "\n",
    "burgdorferi_genome = id_search('NC_001318.1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [],
   "source": [
    "bavariensis_genome=id_search('NC_006156.1')\n",
    "afzelii_genome=id_search('NC_018887.1')\n",
    "garenii_genome=id_search('NC_018747.1')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "borrelia=['burgdorferi', 'bavariensis', 'afzelii', 'garenii']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "def PAM_search(seq):\n",
    "    \n",
    "    genome = str(seq)\n",
    "\n",
    "    PAM_positions = {}\n",
    "\n",
    "    PAM_pos = []\n",
    "    \n",
    "    for m in re.finditer(r\"[ACGT]GG\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SpCas9'] = PAM_pos\n",
    "        \n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"[ACGT]G[AG][AG]T\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SaCas9_1'] = PAM_pos\n",
    "\n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"G[ACGT]G[AG][AG][ACTG]\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SaCas9_2'] = PAM_pos\n",
    "    \n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"[ACGT][ACGT][ACGT][ACGT][AG][CT]AC\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['CjCas9'] = PAM_pos\n",
    "\n",
    "    \n",
    "    return PAM_positions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 430,
   "metadata": {},
   "outputs": [],
   "source": [
    "#to search start inverted pam in complement DNA\n",
    "def PAM_rev_search(seq):\n",
    "    \n",
    "    genome = str(seq.complement())\n",
    "\n",
    "    PAM_positions = {}\n",
    "\n",
    "    PAM_pos = []\n",
    "    \n",
    "    for m in re.finditer(r\"GG[ACGT]\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SpCas9'] = PAM_pos\n",
    "        \n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"T[AG][AG]G[ACGT]\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SaCas9_1'] = PAM_pos\n",
    "\n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"[ACGT][AG][AG]G[ACGT]\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['SaCas9_2'] = PAM_pos\n",
    "    \n",
    "    PAM_pos = []\n",
    "    for m in re.finditer(r\"CA[CT][AG][ACGT][ACGT][ACGT][ACGT]\", genome):\n",
    "        PAM_pos.append(m.start())\n",
    "        PAM_positions['CjCas9'] = PAM_pos\n",
    "\n",
    "    \n",
    "    return PAM_positions"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 433,
   "metadata": {},
   "outputs": [],
   "source": [
    "burgdorferi_PAM_rev_pos = PAM_rev_search(burgdorferi_genome)\n",
    "burgdorferi_PAM_pos = PAM_search(burgdorferi_genome)\n",
    "\n",
    "bavariensis_PAM_rev_pos = PAM_rev_search(bavariensis_genome)\n",
    "bavariensis_PAM_pos = PAM_search(bavariensis_genome)\n",
    "\n",
    "afzelii_PAM_rev_pos = PAM_rev_search(afzelii_genome)\n",
    "afzelii_PAM_pos = PAM_search(afzelii_genome)\n",
    "\n",
    "garenii_PAM_rev_pos = PAM_rev_search(garenii_genome)\n",
    "garenii_PAM_pos = PAM_search(garenii_genome)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 436,
   "metadata": {},
   "outputs": [],
   "source": [
    "#to chose cas proteins, len first pam and len between 2 pams (here 24 for SpCas9)\n",
    "def pam_pairs(PAM_pos, PAM_rev_pos, pos_cas, rev_cas):    \n",
    "    PAM_pos_y = []\n",
    "\n",
    "    for el in PAM_pos[pos_cas]:\n",
    "        PAM_pos_y.append(el + 24)\n",
    "    \n",
    "    PAM_pairs = {}\n",
    "    for el in PAM_pos_y:\n",
    "        if el in set(PAM_rev_pos[rev_cas]):\n",
    "            PAM_pairs[el-24] = el\n",
    "    \n",
    "    return PAM_pairs"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 437,
   "metadata": {},
   "outputs": [],
   "source": [
    "burgdorferi_pam_pairs=pam_pairs(burgdorferi_PAM_pos, burgdorferi_PAM_rev_pos, 'SpCas9', 'SpCas9')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 438,
   "metadata": {},
   "outputs": [],
   "source": [
    "bavariensis_pam_pairs=pam_pairs(bavariensis_PAM_pos, bavariensis_PAM_rev_pos, 'SpCas9', 'SpCas9')\n",
    "afzelii_pam_pairs=pam_pairs(afzelii_PAM_pos, afzelii_PAM_rev_pos, 'SpCas9', 'SpCas9')\n",
    "garenii_pam_pairs=pam_pairs(garenii_PAM_pos, garenii_PAM_rev_pos, 'SpCas9', 'SpCas9')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 276,
   "metadata": {},
   "outputs": [],
   "source": [
    "# 1 target + pam\n",
    "burgdorferi_pam_targets_pairs_seq={}\n",
    "for i in burgdorferi_pam_pairs.keys():\n",
    "    burgdorferi_pam_targets_pairs_seq.update({i:str(burgdorferi_genome[i-20:i+3])})\n",
    "    \n",
    "bavariensis_pam_targets_pairs_seq={}\n",
    "for i in bavariensis_pam_pairs.keys():\n",
    "    bavariensis_pam_targets_pairs_seq.update({i:str(bavariensis_genome[i-20:i+3])})\n",
    "    \n",
    "afzelii_pam_targets_pairs_seq={}\n",
    "for i in afzelii_pam_pairs.keys():\n",
    "    afzelii_pam_targets_pairs_seq.update({i:str(afzelii_genome[i-20:i+3])})\n",
    "    \n",
    "garenii_pam_targets_pairs_seq={}\n",
    "for i in garenii_pam_pairs.keys():\n",
    "    garenii_pam_targets_pairs_seq.update({i:str(garenii_genome[i-20:i+3])})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 305,
   "metadata": {},
   "outputs": [],
   "source": [
    "# second target + pam\n",
    "burgdorferi_pam_targets_pairs_seq_rev={}\n",
    "for i in burgdorferi_pam_pairs.values():\n",
    "    burgdorferi_pam_targets_pairs_seq_rev.update({i: str(burgdorferi_genome[i:i+23])})\n",
    "    \n",
    "bavariensis_pam_targets_pairs_seq_rev={}\n",
    "for i in bavariensis_pam_pairs.values():\n",
    "    bavariensis_pam_targets_pairs_seq_rev.update({i:str(bavariensis_genome[i:i+23])})\n",
    "    \n",
    "afzelii_pam_targets_pairs_seq_rev={}\n",
    "for i in afzelii_pam_pairs.values():\n",
    "    afzelii_pam_targets_pairs_seq_rev.update({i:str(afzelii_genome[i:i+23])})\n",
    "    \n",
    "garenii_pam_targets_pairs_seq_rev={}\n",
    "for i in garenii_pam_pairs.values():\n",
    "    garenii_pam_targets_pairs_seq_rev.update({i: str(garenii_genome[i:i+23])})\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sequence_compare(seq_a, seq_b):\n",
    "        len1= len(seq_a)\n",
    "        len2= len(seq_b)\n",
    "        matches = 0\n",
    "        for pos in range (0,min(len1,len2)) :\n",
    "              if seq_a[pos] != seq_b[pos]:\n",
    "                  matches+=0\n",
    "              else:\n",
    "                  matches+=1\n",
    "        return matches"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 408,
   "metadata": {},
   "outputs": [],
   "source": [
    "# to search condervative sequnces (target1-pam1) among 4 borrelias, \n",
    "# threshold is a number of same nucleotides in same positions\n",
    "\n",
    "thres=22\n",
    "\n",
    "common_seq_dict={}\n",
    "common_seq=[]\n",
    "n=0\n",
    "for i in set(burgdorferi_pam_targets_pairs_seq.values()):\n",
    "    for k in set(bavariensis_pam_targets_pairs_seq.values()):\n",
    "        if sequence_compare(i,k) > thres:\n",
    "            for l in set(afzelii_pam_targets_pairs_seq.values()):\n",
    "                if sequence_compare(i,l) > thres:\n",
    "                    for m in set(garenii_pam_targets_pairs_seq.values()):\n",
    "                        if sequence_compare(i,m) > thres:\n",
    "                            a= [key  for (key, value) in burgdorferi_pam_targets_pairs_seq.items() if value == i]\n",
    "                            b= [key  for (key, value) in bavariensis_pam_targets_pairs_seq.items() if value == k]\n",
    "                            c= [key  for (key, value) in afzelii_pam_targets_pairs_seq.items() if value == l]\n",
    "                            d= [key  for (key, value) in garenii_pam_targets_pairs_seq.items() if value == m]\n",
    "                            common_seq_dict.update({n: [a , b, c, d]})\n",
    "                            n=n+1\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 409,
   "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>0</th>\n",
       "      <th>1</th>\n",
       "      <th>2</th>\n",
       "      <th>3</th>\n",
       "      <th>4</th>\n",
       "      <th>5</th>\n",
       "      <th>6</th>\n",
       "      <th>7</th>\n",
       "      <th>8</th>\n",
       "      <th>9</th>\n",
       "      <th>10</th>\n",
       "      <th>11</th>\n",
       "      <th>12</th>\n",
       "      <th>13</th>\n",
       "      <th>14</th>\n",
       "      <th>15</th>\n",
       "      <th>16</th>\n",
       "      <th>17</th>\n",
       "      <th>18</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>[134376]</td>\n",
       "      <td>[378587]</td>\n",
       "      <td>[484274]</td>\n",
       "      <td>[444913]</td>\n",
       "      <td>[628385]</td>\n",
       "      <td>[443638]</td>\n",
       "      <td>[441401, 438156]</td>\n",
       "      <td>[438906, 435661]</td>\n",
       "      <td>[535898]</td>\n",
       "      <td>[445778]</td>\n",
       "      <td>[417622]</td>\n",
       "      <td>[345887]</td>\n",
       "      <td>[19925]</td>\n",
       "      <td>[481105]</td>\n",
       "      <td>[789106]</td>\n",
       "      <td>[436784, 440029]</td>\n",
       "      <td>[331095]</td>\n",
       "      <td>[871669]</td>\n",
       "      <td>[444366]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>[134197]</td>\n",
       "      <td>[377346]</td>\n",
       "      <td>[486625]</td>\n",
       "      <td>[447105]</td>\n",
       "      <td>[630325]</td>\n",
       "      <td>[444930]</td>\n",
       "      <td>[438801, 442045]</td>\n",
       "      <td>[436306, 439550]</td>\n",
       "      <td>[538085]</td>\n",
       "      <td>[447970]</td>\n",
       "      <td>[418254]</td>\n",
       "      <td>[344628]</td>\n",
       "      <td>[19773]</td>\n",
       "      <td>[483428]</td>\n",
       "      <td>[791106]</td>\n",
       "      <td>[437429, 440673]</td>\n",
       "      <td>[329902]</td>\n",
       "      <td>[873604]</td>\n",
       "      <td>[446555]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>[134240]</td>\n",
       "      <td>[377159]</td>\n",
       "      <td>[486357]</td>\n",
       "      <td>[446825]</td>\n",
       "      <td>[630240]</td>\n",
       "      <td>[444150]</td>\n",
       "      <td>[438413, 441649]</td>\n",
       "      <td>[435918, 439154]</td>\n",
       "      <td>[537885]</td>\n",
       "      <td>[447690]</td>\n",
       "      <td>[417870]</td>\n",
       "      <td>[344443]</td>\n",
       "      <td>[19926]</td>\n",
       "      <td>[483120]</td>\n",
       "      <td>[790823]</td>\n",
       "      <td>[440277, 437041]</td>\n",
       "      <td>[329753]</td>\n",
       "      <td>[873497]</td>\n",
       "      <td>[446273]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>[134244]</td>\n",
       "      <td>[377626]</td>\n",
       "      <td>[483767]</td>\n",
       "      <td>[444253]</td>\n",
       "      <td>[627939]</td>\n",
       "      <td>[441997]</td>\n",
       "      <td>[439103]</td>\n",
       "      <td>[436608]</td>\n",
       "      <td>[535613]</td>\n",
       "      <td>[445118]</td>\n",
       "      <td>[418542]</td>\n",
       "      <td>[344906]</td>\n",
       "      <td>[19810]</td>\n",
       "      <td>[480567]</td>\n",
       "      <td>[788736]</td>\n",
       "      <td>[437731]</td>\n",
       "      <td>[330186]</td>\n",
       "      <td>[870992]</td>\n",
       "      <td>[443703]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "         0         1         2         3         4         5   \\\n",
       "0  [134376]  [378587]  [484274]  [444913]  [628385]  [443638]   \n",
       "1  [134197]  [377346]  [486625]  [447105]  [630325]  [444930]   \n",
       "2  [134240]  [377159]  [486357]  [446825]  [630240]  [444150]   \n",
       "3  [134244]  [377626]  [483767]  [444253]  [627939]  [441997]   \n",
       "\n",
       "                 6                 7         8         9         10        11  \\\n",
       "0  [441401, 438156]  [438906, 435661]  [535898]  [445778]  [417622]  [345887]   \n",
       "1  [438801, 442045]  [436306, 439550]  [538085]  [447970]  [418254]  [344628]   \n",
       "2  [438413, 441649]  [435918, 439154]  [537885]  [447690]  [417870]  [344443]   \n",
       "3          [439103]          [436608]  [535613]  [445118]  [418542]  [344906]   \n",
       "\n",
       "        12        13        14                15        16        17        18  \n",
       "0  [19925]  [481105]  [789106]  [436784, 440029]  [331095]  [871669]  [444366]  \n",
       "1  [19773]  [483428]  [791106]  [437429, 440673]  [329902]  [873604]  [446555]  \n",
       "2  [19926]  [483120]  [790823]  [440277, 437041]  [329753]  [873497]  [446273]  \n",
       "3  [19810]  [480567]  [788736]          [437731]  [330186]  [870992]  [443703]  "
      ]
     },
     "execution_count": 409,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "common_seq_df=pd.DataFrame.from_dict(common_seq_dict)\n",
    "common_seq_df"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "- I chose only the first start of same positions in one borrelia"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 410,
   "metadata": {},
   "outputs": [],
   "source": [
    "for index, column in common_seq_df.iteritems():\n",
    "    common_seq_df[index][0]=common_seq_df[index][0][0]\n",
    "    common_seq_df[index][1]=common_seq_df[index][1][0]\n",
    "    common_seq_df[index][2]=common_seq_df[index][2][0]\n",
    "    common_seq_df[index][3]=common_seq_df[index][3][0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 411,
   "metadata": {},
   "outputs": [],
   "source": [
    "common_seq_rev_dict={}\n",
    "#24 is len of pam1 and len between 2 pams\n",
    "\n",
    "for index, column in common_seq_df.iteritems():\n",
    "    bur=burgdorferi_pam_targets_pairs_seq_rev[common_seq_df[index][0]+24]\n",
    "    bav=bavariensis_pam_targets_pairs_seq_rev[common_seq_df[index][1]+24]\n",
    "    afz=afzelii_pam_targets_pairs_seq_rev[common_seq_df[index][2]+24]\n",
    "    gar=garenii_pam_targets_pairs_seq_rev[common_seq_df[index][3]+24]\n",
    "    \n",
    "    thres=22\n",
    "    if sequence_compare(bur,bav) > thres:\n",
    "        if sequence_compare(bur,afz) > thres:\n",
    "            if sequence_compare(bur,gar) > thres:\n",
    "                common_seq_rev_dict.update({index: [common_seq_df[index][0]+24, common_seq_df[index][1]+24,\\\n",
    "                                                    common_seq_df[index][2]+24, common_seq_df[index][3]+24]})\n",
    "\n",
    "\n",
    "common_seq_rev_df=pd.DataFrame.from_dict(common_seq_rev_dict)\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 412,
   "metadata": {},
   "outputs": [],
   "source": [
    "common_seq_rev_df=common_seq_rev_df.T\n",
    "common_seq_df=common_seq_df.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 413,
   "metadata": {},
   "outputs": [],
   "source": [
    "common_seq_df.columns=['bur_1', 'bav_1', 'afz_1', 'gar_1']\n",
    "common_seq_rev_df.columns=['bur_2', 'bav_2', 'afz_2', 'gar_2']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 414,
   "metadata": {},
   "outputs": [],
   "source": [
    "common_seq_all=pd.merge(common_seq_df, common_seq_rev_df, how='outer', left_index=True, right_index=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 420,
   "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>bur_1</th>\n",
       "      <th>bav_1</th>\n",
       "      <th>afz_1</th>\n",
       "      <th>gar_1</th>\n",
       "      <th>bur_2</th>\n",
       "      <th>bav_2</th>\n",
       "      <th>afz_2</th>\n",
       "      <th>gar_2</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>444913</td>\n",
       "      <td>447105</td>\n",
       "      <td>446825</td>\n",
       "      <td>444253</td>\n",
       "      <td>444937.0</td>\n",
       "      <td>447129.0</td>\n",
       "      <td>446849.0</td>\n",
       "      <td>444277.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>443638</td>\n",
       "      <td>444930</td>\n",
       "      <td>444150</td>\n",
       "      <td>441997</td>\n",
       "      <td>443662.0</td>\n",
       "      <td>444954.0</td>\n",
       "      <td>444174.0</td>\n",
       "      <td>442021.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>441401</td>\n",
       "      <td>438801</td>\n",
       "      <td>438413</td>\n",
       "      <td>439103</td>\n",
       "      <td>441425.0</td>\n",
       "      <td>438825.0</td>\n",
       "      <td>438437.0</td>\n",
       "      <td>439127.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>438906</td>\n",
       "      <td>436306</td>\n",
       "      <td>435918</td>\n",
       "      <td>436608</td>\n",
       "      <td>438930.0</td>\n",
       "      <td>436330.0</td>\n",
       "      <td>435942.0</td>\n",
       "      <td>436632.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>445778</td>\n",
       "      <td>447970</td>\n",
       "      <td>447690</td>\n",
       "      <td>445118</td>\n",
       "      <td>445802.0</td>\n",
       "      <td>447994.0</td>\n",
       "      <td>447714.0</td>\n",
       "      <td>445142.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>417622</td>\n",
       "      <td>418254</td>\n",
       "      <td>417870</td>\n",
       "      <td>418542</td>\n",
       "      <td>417646.0</td>\n",
       "      <td>418278.0</td>\n",
       "      <td>417894.0</td>\n",
       "      <td>418566.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>789106</td>\n",
       "      <td>791106</td>\n",
       "      <td>790823</td>\n",
       "      <td>788736</td>\n",
       "      <td>789130.0</td>\n",
       "      <td>791130.0</td>\n",
       "      <td>790847.0</td>\n",
       "      <td>788760.0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>436784</td>\n",
       "      <td>437429</td>\n",
       "      <td>440277</td>\n",
       "      <td>437731</td>\n",
       "      <td>436808.0</td>\n",
       "      <td>437453.0</td>\n",
       "      <td>440301.0</td>\n",
       "      <td>437755.0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "     bur_1   bav_1   afz_1   gar_1     bur_2     bav_2     afz_2     gar_2\n",
       "3   444913  447105  446825  444253  444937.0  447129.0  446849.0  444277.0\n",
       "5   443638  444930  444150  441997  443662.0  444954.0  444174.0  442021.0\n",
       "6   441401  438801  438413  439103  441425.0  438825.0  438437.0  439127.0\n",
       "7   438906  436306  435918  436608  438930.0  436330.0  435942.0  436632.0\n",
       "9   445778  447970  447690  445118  445802.0  447994.0  447714.0  445142.0\n",
       "10  417622  418254  417870  418542  417646.0  418278.0  417894.0  418566.0\n",
       "14  789106  791106  790823  788736  789130.0  791130.0  790847.0  788760.0\n",
       "15  436784  437429  440277  437731  436808.0  437453.0  440301.0  437755.0"
      ]
     },
     "execution_count": 420,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "common_seq_all.loc[~common_seq_all['bur_2'].isna()]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 421,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Seq('CGTGTGTAGCCCAGGACATAAGG', SingleLetterAlphabet())"
      ]
     },
     "execution_count": 421,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "burgdorferi_genome[444913-20:444913+3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 422,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Seq('CGTGTGTAGCCCAGGACATAAGG', SingleLetterAlphabet())"
      ]
     },
     "execution_count": 422,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bavariensis_genome[447105-20:447105+3]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 424,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Seq('CCTCACCTTCCTCCGACTTATCA', SingleLetterAlphabet())"
      ]
     },
     "execution_count": 424,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "burgdorferi_genome[444937:444937+23]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 425,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Seq('CCTCACCTTCCTCCGACTTATCA', SingleLetterAlphabet())"
      ]
     },
     "execution_count": 425,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "bavariensis_genome[447129:447129+23]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# MISC"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [],
   "source": [
    "#create df_PAM; 1 - Watson, 0 - Crick\n",
    "\n",
    "import pandas as pd\n",
    "df_PAM = pd.DataFrame({\"PAM_pos\" : PAM_SpCas9_pos, \"Strand\" : 0})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [],
   "source": [
    "#create df_PAM_rev; 1 - Watson, 0 - Crick\n",
    "\n",
    "df_PAM_rev = pd.DataFrame({\"PAM_pos\" : PAM_SpCas9_rev_pos, \"Strand\" : 1})"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_all_PAMs = pd.concat([df_PAM, df_PAM_rev])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "handle = Entrez.esearch(db=\"probe\", term=\"borrelia burgdorferi\", retmode=\"text\", retmax = 220)\n",
    "\n",
    "record = Entrez.read(handle)\n",
    "#print(record[\"IdList\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "scrolled": true
   },
   "outputs": [],
   "source": [
    "records = record['IdList']\n",
    "#print(records)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[1;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[0;32m    378\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m  \u001b[1;31m# Python 2.7, use buffering of HTTP responses\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 379\u001b[1;33m                 \u001b[0mhttplib_response\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mbuffering\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    380\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m:\u001b[0m  \u001b[1;31m# Python 2.6 and older, Python 3\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mTypeError\u001b[0m: getresponse() got an unexpected keyword argument 'buffering'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-55-eaed8232975d>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      5\u001b[0m     \u001b[0mid_dbprobe\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mi\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      6\u001b[0m     \u001b[0mlink\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;34m'https://www.ncbi.nlm.nih.gov/probe/'\u001b[0m \u001b[1;33m+\u001b[0m \u001b[0mid_dbprobe\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 7\u001b[1;33m     \u001b[0mf\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mrequests\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mget\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mlink\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      8\u001b[0m     \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mf\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mtext\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      9\u001b[0m     \u001b[0mres\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mre\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfindall\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34mr'class=\"breakTxt\">[ACTG]+'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mget\u001b[1;34m(url, params, **kwargs)\u001b[0m\n\u001b[0;32m     70\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     71\u001b[0m     \u001b[0mkwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msetdefault\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'allow_redirects'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 72\u001b[1;33m     \u001b[1;32mreturn\u001b[0m \u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m'get'\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mparams\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mparams\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     73\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     74\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\api.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(method, url, **kwargs)\u001b[0m\n\u001b[0;32m     56\u001b[0m     \u001b[1;31m# cases, and look like a memory leak in others.\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     57\u001b[0m     \u001b[1;32mwith\u001b[0m \u001b[0msessions\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSession\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 58\u001b[1;33m         \u001b[1;32mreturn\u001b[0m \u001b[0msession\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0murl\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0murl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     59\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     60\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36mrequest\u001b[1;34m(self, method, url, params, data, headers, cookies, files, auth, timeout, allow_redirects, proxies, hooks, stream, verify, cert, json)\u001b[0m\n\u001b[0;32m    516\u001b[0m         }\n\u001b[0;32m    517\u001b[0m         \u001b[0msend_kwargs\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mupdate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0msettings\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 518\u001b[1;33m         \u001b[0mresp\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mprep\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0msend_kwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    519\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    520\u001b[0m         \u001b[1;32mreturn\u001b[0m \u001b[0mresp\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\sessions.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, request, **kwargs)\u001b[0m\n\u001b[0;32m    637\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    638\u001b[0m         \u001b[1;31m# Send the request\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 639\u001b[1;33m         \u001b[0mr\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0madapter\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msend\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mrequest\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    640\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    641\u001b[0m         \u001b[1;31m# Total elapsed time of the request (approximately)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\adapters.py\u001b[0m in \u001b[0;36msend\u001b[1;34m(self, request, stream, timeout, verify, cert, proxies)\u001b[0m\n\u001b[0;32m    436\u001b[0m                     \u001b[0mdecode_content\u001b[0m\u001b[1;33m=\u001b[0m\u001b[1;32mFalse\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    437\u001b[0m                     \u001b[0mretries\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mmax_retries\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 438\u001b[1;33m                     \u001b[0mtimeout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtimeout\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    439\u001b[0m                 )\n\u001b[0;32m    440\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36murlopen\u001b[1;34m(self, method, url, body, headers, retries, redirect, assert_same_host, timeout, pool_timeout, release_conn, chunked, body_pos, **response_kw)\u001b[0m\n\u001b[0;32m    598\u001b[0m                                                   \u001b[0mtimeout\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mtimeout_obj\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    599\u001b[0m                                                   \u001b[0mbody\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mbody\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mheaders\u001b[0m\u001b[1;33m=\u001b[0m\u001b[0mheaders\u001b[0m\u001b[1;33m,\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 600\u001b[1;33m                                                   chunked=chunked)\n\u001b[0m\u001b[0;32m    601\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    602\u001b[0m             \u001b[1;31m# If we're going to release the connection in ``finally:``, then\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\packages\\urllib3\\connectionpool.py\u001b[0m in \u001b[0;36m_make_request\u001b[1;34m(self, conn, method, url, timeout, chunked, **httplib_request_kw)\u001b[0m\n\u001b[0;32m    380\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mTypeError\u001b[0m\u001b[1;33m:\u001b[0m  \u001b[1;31m# Python 2.6 and older, Python 3\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    381\u001b[0m                 \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 382\u001b[1;33m                     \u001b[0mhttplib_response\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mconn\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mgetresponse\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    383\u001b[0m                 \u001b[1;32mexcept\u001b[0m \u001b[0mException\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    384\u001b[0m                     \u001b[1;31m# Remove the TypeError from the exception chain in Python 3;\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\http\\client.py\u001b[0m in \u001b[0;36mgetresponse\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m   1196\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1197\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1198\u001b[1;33m                 \u001b[0mresponse\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mbegin\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1199\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mConnectionError\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1200\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mclose\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\http\\client.py\u001b[0m in \u001b[0;36mbegin\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    295\u001b[0m         \u001b[1;31m# read until we get a non-100 response\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    296\u001b[0m         \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 297\u001b[1;33m             \u001b[0mversion\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mstatus\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mreason\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_read_status\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    298\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mstatus\u001b[0m \u001b[1;33m!=\u001b[0m \u001b[0mCONTINUE\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    299\u001b[0m                 \u001b[1;32mbreak\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\http\\client.py\u001b[0m in \u001b[0;36m_read_status\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    256\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    257\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0m_read_status\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 258\u001b[1;33m         \u001b[0mline\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0mstr\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mfp\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mreadline\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0m_MAXLINE\u001b[0m \u001b[1;33m+\u001b[0m \u001b[1;36m1\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m\"iso-8859-1\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    259\u001b[0m         \u001b[1;32mif\u001b[0m \u001b[0mlen\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mline\u001b[0m\u001b[1;33m)\u001b[0m \u001b[1;33m>\u001b[0m \u001b[0m_MAXLINE\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    260\u001b[0m             \u001b[1;32mraise\u001b[0m \u001b[0mLineTooLong\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;34m\"status line\"\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\socket.py\u001b[0m in \u001b[0;36mreadinto\u001b[1;34m(self, b)\u001b[0m\n\u001b[0;32m    574\u001b[0m         \u001b[1;32mwhile\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    575\u001b[0m             \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 576\u001b[1;33m                 \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_sock\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mb\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    577\u001b[0m             \u001b[1;32mexcept\u001b[0m \u001b[0mtimeout\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    578\u001b[0m                 \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_timeout_occurred\u001b[0m \u001b[1;33m=\u001b[0m \u001b[1;32mTrue\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\requests\\packages\\urllib3\\contrib\\pyopenssl.py\u001b[0m in \u001b[0;36mrecv_into\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m    275\u001b[0m     \u001b[1;32mdef\u001b[0m \u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    276\u001b[0m         \u001b[1;32mtry\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m--> 277\u001b[1;33m             \u001b[1;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mconnection\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrecv_into\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m*\u001b[0m\u001b[0margs\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;33m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m    278\u001b[0m         \u001b[1;32mexcept\u001b[0m \u001b[0mOpenSSL\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSSL\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSysCallError\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m    279\u001b[0m             \u001b[1;32mif\u001b[0m \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0msuppress_ragged_eofs\u001b[0m \u001b[1;32mand\u001b[0m \u001b[0me\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0margs\u001b[0m \u001b[1;33m==\u001b[0m \u001b[1;33m(\u001b[0m\u001b[1;33m-\u001b[0m\u001b[1;36m1\u001b[0m\u001b[1;33m,\u001b[0m \u001b[1;34m'Unexpected EOF'\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32m~\\Miniconda3\\lib\\site-packages\\OpenSSL\\SSL.py\u001b[0m in \u001b[0;36mrecv_into\u001b[1;34m(self, buffer, nbytes, flags)\u001b[0m\n\u001b[0;32m   1332\u001b[0m             \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_lib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSSL_peek\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_ssl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbuf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1333\u001b[0m         \u001b[1;32melse\u001b[0m\u001b[1;33m:\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m-> 1334\u001b[1;33m             \u001b[0mresult\u001b[0m \u001b[1;33m=\u001b[0m \u001b[0m_lib\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mSSL_read\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_ssl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mbuf\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mnbytes\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m   1335\u001b[0m         \u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_raise_ssl_error\u001b[0m\u001b[1;33m(\u001b[0m\u001b[0mself\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0m_ssl\u001b[0m\u001b[1;33m,\u001b[0m \u001b[0mresult\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m   1336\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "import requests\n",
    "\n",
    "probes = []\n",
    "for i in records:\n",
    "    id_dbprobe = i\n",
    "    link = 'https://www.ncbi.nlm.nih.gov/probe/' + id_dbprobe\n",
    "    f = requests.get(link)\n",
    "    result = f.text\n",
    "    res = re.findall(r'class=\"breakTxt\">[ACTG]+', result)\n",
    "    for el in res:\n",
    "        probes.append(el[17:])\n",
    "\n",
    "print(len(probes))\n",
    "#print(probes)    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "f = open(\"BB_markers.txt\", \"a\")\n",
    "for k in probes:\n",
    "    a = str(k)+'\\n'\n",
    "    f.write(a)\n",
    "f.close()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "#number of PAM for different Cas9 proteins in B.burgdorferi genome\n",
    "\n",
    "Bburgdorferi_PAM_cnt = {}\n",
    "for k in Bburgdorferi_PAM.keys():\n",
    "    Bburgdorferi_PAM_cnt[k] = len(Bburgdorferi_PAM.get(k))\n",
    "    \n",
    "print(Bburgdorferi_PAM_cnt)\n",
    "\n",
    "\n",
    "#histogram - number of PAM for different Cas9 proteins in B.burgdorferi genome\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "plt.bar(list(Bburgdorferi_PAM_cnt.keys()), Bburgdorferi_PAM_cnt.values())\n",
    "plt.show()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "burgdorferi_PAM_rev_pos = burgdorferi_PAM_rev_pos[\"SpCas9\"]\n",
    "burgdorferi_PAM_pos = burgdorferi_PAM_pos[\"SpCas9\"]\n",
    "\n",
    "bavariensis_PAM_rev_pos = bavariensis_PAM_rev_pos[\"SpCas9\"]\n",
    "bavariensis_PAM_pos = bavariensis_PAM_pos[\"SpCas9\"]\n",
    "\n",
    "afzelii_PAM_rev_pos = afzelii_PAM_rev_pos[\"SpCas9\"]\n",
    "afzelii_PAM_pos = afzelii_PAM_pos[\"SpCas9\"]\n",
    "\n",
    "garenii_PAM_rev_pos = garenii_PAM_rev_pos[\"SpCas9\"]\n",
    "garenii_PAM_pos = garenii_PAM_pos[\"SpCas9\"]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "thres=22\n",
    "\n",
    "common_seq=[]\n",
    "for i in set(burgdorferi_pam_targets_pairs_seq.values()):\n",
    "    for k in set(bavariensis_pam_targets_pairs_seq.values()):\n",
    "        if sequence_compare(i,k) > thres:\n",
    "            common_seq.append(i)\n",
    "\n",
    "common_seq_2=[]\n",
    "for i in common_seq:\n",
    "    for k in set(afzelii_pam_targets_pairs_seq.values()):\n",
    "        if sequence_compare(i,k) > thres:\n",
    "            common_seq_2.append(i)\n",
    "    \n",
    "common_seq=[]\n",
    "for i in common_seq_2:\n",
    "    for k in set(garenii_pam_targets_pairs_seq.values()):\n",
    "        if sequence_compare(i,k) > thres:\n",
    "            common_seq.append(i)"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.5.6"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}