diff --git a/genomics/4-Variation/updates/illumina_artic_accessions.tsv b/genomics/4-Variation/updates/illumina_artic_accessions.tsv
new file mode 100644
index 00000000..03e844ae
--- /dev/null
+++ b/genomics/4-Variation/updates/illumina_artic_accessions.tsv
@@ -0,0 +1,20 @@
+run_accession	study_accession
+ERR4238187	PRJEB38723
+ERR4238188	PRJEB38723
+ERR4238189	PRJEB38723
+ERR4238190	PRJEB38723
+ERR4238191	PRJEB38723
+ERR4238193	PRJEB38723
+ERR4238194	PRJEB38723
+ERR4238196	PRJEB38723
+ERR4238197	PRJEB38723
+ERR4238198	PRJEB38723
+ERR4238199	PRJEB38723
+ERR4238200	PRJEB38723
+ERR4238201	PRJEB38723
+ERR4238202	PRJEB38723
+ERR4238203	PRJEB38723
+ERR4238205	PRJEB38723
+ERR4238207	PRJEB38723
+ERR4238208	PRJEB38723
+ERR4238209	PRJEB38723
diff --git a/genomics/4-Variation/updates/illumina_metagenomic_accessions.tsv b/genomics/4-Variation/updates/illumina_metagenomic_accessions.tsv
new file mode 100644
index 00000000..654e2c23
--- /dev/null
+++ b/genomics/4-Variation/updates/illumina_metagenomic_accessions.tsv
@@ -0,0 +1,94 @@
+run_accession	study_accession
+ERR4450774	PRJEB39761
+ERR4452719	PRJEB39761
+ERR4452734	PRJEB39761
+ERR4452736	PRJEB39761
+ERR4452737	PRJEB39761
+ERR4452738	PRJEB39761
+ERR4452739	PRJEB39761
+ERR4452740	PRJEB39761
+ERR4452741	PRJEB39761
+ERR4452742	PRJEB39761
+ERR4452743	PRJEB39761
+ERR4452744	PRJEB39761
+ERR4452745	PRJEB39761
+ERR4452746	PRJEB39761
+ERR4452747	PRJEB39761
+ERR4452748	PRJEB39761
+ERR4452749	PRJEB39761
+ERR4452751	PRJEB39761
+ERR4452752	PRJEB39761
+ERR4452753	PRJEB39761
+ERR4452754	PRJEB39761
+ERR4452755	PRJEB39761
+ERR4452756	PRJEB39761
+ERR4452757	PRJEB39761
+ERR4452758	PRJEB39761
+ERR4452759	PRJEB39761
+ERR4452760	PRJEB39761
+ERR4452762	PRJEB39761
+ERR4452763	PRJEB39761
+ERR4452764	PRJEB39761
+ERR4452765	PRJEB39761
+ERR4452766	PRJEB39761
+ERR4452767	PRJEB39761
+ERR4452768	PRJEB39761
+ERR4452769	PRJEB39761
+ERR4452770	PRJEB39761
+ERR4452771	PRJEB39761
+ERR4452772	PRJEB39761
+ERR4452773	PRJEB39761
+ERR4452774	PRJEB39761
+ERR4452775	PRJEB39761
+ERR4452776	PRJEB39761
+ERR4452779	PRJEB39761
+ERR4452780	PRJEB39761
+ERR4452781	PRJEB39761
+ERR4452783	PRJEB39761
+ERR4452784	PRJEB39761
+ERR4452785	PRJEB39761
+SRR11961362	PRJNA638211
+SRR11961363	PRJNA638211
+SRR11961364	PRJNA638211
+SRR11961365	PRJNA638211
+SRR11961366	PRJNA638211
+SRR11961367	PRJNA638211
+SRR11961368	PRJNA638211
+SRR11961369	PRJNA638211
+SRR11961370	PRJNA638211
+SRR11961371	PRJNA638211
+SRR12008186	PRJNA631061
+SRR12008187	PRJNA631061
+SRR12008188	PRJNA631061
+SRR12133951	PRJNA643574
+SRR12133952	PRJNA643574
+SRR12192415	PRJNA631061
+SRR12192416	PRJNA631061
+SRR12192417	PRJNA631061
+SRR12192418	PRJNA631061
+SRR12192419	PRJNA631061
+SRR12192420	PRJNA631061
+SRR12192421	PRJNA631061
+SRR12192422	PRJNA631061
+SRR12192423	PRJNA631061
+SRR12192424	PRJNA631061
+SRR12192425	PRJNA631061
+SRR12192426	PRJNA631061
+SRR12192427	PRJNA631061
+SRR12192429	PRJNA631061
+SRR12192430	PRJNA631061
+SRR12192431	PRJNA631061
+SRR12192432	PRJNA631061
+SRR12192433	PRJNA631061
+SRR12192434	PRJNA631061
+SRR12192435	PRJNA631061
+SRR12192436	PRJNA631061
+SRR12192437	PRJNA631061
+SRR12192438	PRJNA631061
+SRR12192439	PRJNA631061
+SRR12192440	PRJNA631061
+SRR12192441	PRJNA631061
+SRR12192442	PRJNA631061
+SRR12192444	PRJNA631061
+SRR12192445	PRJNA631061
+SRR12192446	PRJNA631061
diff --git a/genomics/4-Variation/updates/metadata_stats_with_benchmark_accessions.ipynb b/genomics/4-Variation/updates/metadata_stats_with_benchmark_accessions.ipynb
new file mode 100644
index 00000000..498b7e2f
--- /dev/null
+++ b/genomics/4-Variation/updates/metadata_stats_with_benchmark_accessions.ipynb
@@ -0,0 +1,6917 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "metadata": {
+    "papermill": {
+     "duration": 1.504273,
+     "end_time": "2020-09-09T00:37:37.050878",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:35.546605",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "%matplotlib inline\n",
+    "\n",
+    "import matplotlib.pyplot as plt\n",
+    "import pandas as pd\n",
+    "import seaborn as sns"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {
+    "papermill": {
+     "duration": 1.438001,
+     "end_time": "2020-09-09T00:37:38.499488",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:37.061487",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/mvandenb/miniconda3/envs/sars_cov2/lib/python3.6/site-packages/IPython/core/interactiveshell.py:3063: DtypeWarning: Columns (2,5,9,21,27,31,35,53,59,60) have mixed types.Specify dtype option on import or set low_memory=False.\n",
+      "  interactivity=interactivity, compiler=compiler, result=result)\n"
+     ]
+    }
+   ],
+   "source": [
+    "df = pd.read_csv('../current_metadata_ena.tsv', sep='\\t')\n",
+    "df.index = df.run_accession"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "metadata": {
+    "papermill": {
+     "duration": 0.055639,
+     "end_time": "2020-09-09T00:37:38.566107",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:38.510468",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "date = pd.read_csv('../accession_and_date.tsv', sep='\\t', header=None)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "metadata": {
+    "papermill": {
+     "duration": 0.020077,
+     "end_time": "2020-09-09T00:37:38.598942",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:38.578865",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "date.columns = ['accession', 'date']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "metadata": {
+    "papermill": {
+     "duration": 0.023394,
+     "end_time": "2020-09-09T00:37:38.632529",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:38.609135",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "by_date = date.date.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "metadata": {
+    "papermill": {
+     "duration": 0.70284,
+     "end_time": "2020-09-09T00:37:39.345616",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:38.642776",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'All published SRA/ENA accessions by date')"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABIoAAAISCAYAAACj9CThAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzde7zd5V0n+s9XYim9oNQGShPa4BgvgLbaFHHq9WAHWlrBOUMHtSVqPfFgvU7naOjoqFWcqOd4Oqj0HMZWwBvGegFL0TJo1ZmhxVCrCJRDLBEiFNKbpfWIBb/zx3rSrm72TvZOsrKz4P1+vdZrrfX8fr/v71mXnZ188jzPr7o7AAAAAPAZq90BAAAAAI4MgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEgiKAKAVVNVV1TVT47HX1tVu2d0nndU1XcssW1DVXVVrRnPr6+qzcuo2VX1ebPuH6uvqm6rqq89jOf71qr6bzOq/WNV9auzqA0AjxeCIgCYsRGEfLiqjl7tvuxPd7+ku69c7X7sVVWfXVVvrqr3V9VDVfX/VdUPTW3vqvp4VX2sqv6uqn6uqo5aUOPkqvrnqrpsiXP8y6r6H4vU23v7wbHtx8b286eOXTPaNiyouXff0w/du7E6uvvU7n7HavfjcJsOcgHgiURQBAAzNAKEr0rSSb5hVTszn/7vJE9L8kVJPiuT9/BvFuzzvO5+WpKvSfJvk3z7gu0XJvlwkguWCOtemuRtC+tN3X5matuHkrx+YRg1raoqyavGvvsdnQUAcCQRFAHAbF2Y5J1JrshBhAZjdMr3VtX7quoDVfWzVfUZY9unTadZOJ1s+BdVdXNV/X1VXVNVz1jiPJ+cBlZVn1dVfzKO+UBV/eaC3b++qu4ao6V+cQQke+t8e1XdMbb9YVU9d2rbi6vqvaPuLySpLO2FSX69uz/c3f/c3e/t7rcstmN370zy35M8f8GmC5P8cJJPJHn5IocuDIr25Q+S/FOSV+5jn69K8uwk35dJOPWkpXasqtOr6qaq+khV3V9VvzC9f1WdWlU3VNWHquqBqnrdaD+qql5XVX8zRlrdUlUnjW1fOHXMnVX1iql6L62q28cxf1dV/360P7Oq3jr68aGq+rOp79euqvr68fjoqnpDVd03bm/YG77VmD5ZVa+tqgfH6/m2/Z176bemfn58R95bVWeOxvOr6pYFO762qn5viSInj+/wQ1V1Q5JnLtj+WzUZrfb3VfWnVXXqaN+S5FuS/GBNRpX9/mh/dlX9dlXtqaq7q+p79/EaAGAuCYoAYLYuTPJr43ZWVZ1wELW+McmmJF+W5Nw8duTM/vrx7ZkEGI8kuXQZx/xEkrcnOS7J+iQ/v2D7yzIJcp6X5BVJzkqSqjovyeuS/Oska5P8WZLfGNuemeS3MwlunpnJ6KAX7aMP70xySVV9W1Vt3Fdnq+oLMwlpdk61fdXo+9VJtmfyPkwfc2KSE5L8xb5qT+kkP5LkR6vqM5fYZ3OS30+yN1h72T7qPZrkBzJ5L74iyZlJvmv07elJ/msm4dSzk3xekhvHcf8uyTdlEnIdm8ln+w9V9dQkNyT59STHj30u2xuAJHlTku/s7qcnOS3JH4321ybZncnndUImn18v0t//kOSMTMK45yU5PZPPcq9nZTLya12SVyf5xao6bj/nXsyXJ3nfeF9+NMnvjHDz2iQnV9UXTe37yiS/skSdX09yy6jzE3lsWHt9ko2ZvFfvzuTnNN19+Xj8M2NU2ctHcPb7Sf5yvL4zk3x/VZ21j9cBAHNHUAQAM1JVX5nkuUm2d/ctmYQi33wQJX+6uz/U3fckeUMmIcBy/Up3/3V3fzyToOMVtY/pU8MnMun/s7v7H7t74QLD27r7I6M/f5xPjeT5ziT/qbvv6O5HkvxUkuePUUUvTXJ7d7+luz8xXsf799GH78nkH+zfneT2qtpZVS9ZsM+7q+rjSe5I8o4k02sRbU5yfXd/OJPQ4CVVdfzU9pcm+YPung5F3j1G1uy9fVoQ0N3XJtmT5DELcFfVU5Kcn8koqE8keUv2MZKsu2/p7nd29yPdvSvJ/5vJFLpkEjC9v7v/r/H+P9Td7xrbviPJD3f3nT3xl939wXHMru7+5VHz3ZkEc/9mHPeJJKdU1bFjlNa7p9pPTPLc7v5Ed//Zgvdkr29J8vrufrC79yT58Uym2WWqzutHjbcl+ViSL9jPuRfzYJI3jDq/meTOJOd098OZBHCvHO/3qUk2JHnrwgJV9ZxMgswf6e6Hu/tPMwl6Pqm73zze14eT/FiS51XVZy3RpxcmWdvdr+/uf+ru9yX5L0ku2MfrAIC5IygCgNnZnOTt3f2B8fzXc3Br1tw79fhvMxllcqDHfmYWTMNZxA9mMi3s5ppc+WrhCKbpgOcfMllLKJmES/95b9CSyVo9lckojGdP92WEEdN9+zTd/f9390919wuSfE4mo4J+qz596tyXjXP/20xGojw1SarqmExCm72jRG5Kck8+PaxbbNrZl3X3Z0/d/nCRrv1wJqNrnryg/RszGbG1t+avZRJOrV3s9VXV548pX++vqo9mEqrt/VxOymPXY8p+tj03yZdPB12ZhDvPGtv/1/Ga/3ZMyfqK0f6zmYzEentNpjduXeK8z87k+7PXwu/hB0c4uNf092Kpcy/m7xYEVdPnuTLJN1d9ci2o7SPoWayvHx7h6HSdJJ+cvretJtP3Pppk19i01M/Fc5M8e8F7+7pMRmABwOOGoAgAZmCEFK9I8jUjBHh/JlOMnldVzzvAsidNPX5OkvvG448necrUtmflsRYe+4kkH1hkv0/q7vd39//W3c/OZJTQZVX1ecvo572ZTDGaDluO6e7/keT+6b6Mf+yftFShBf3ZG6Q8NcnJC7Z1d29PclOS/ziavzGTaVmXTX0G6zKmn42pY1+TyVStFenuGzIJVr5rwabNmQQj94zz/VYmodxSo7/emOS9STZ297GZBA9712y6N8m/WOK4pbbdm+RPFrz3T+vui0a//7y7z81kqtXvZRK8ZYyqeW13f24m6zj9u73rAi1wXyaByV7T38N9WurcS1g3vhuPOU93vzOTdaK+KpPQb6lpZ/cnOW5Mx5uus9c3ZzKF8+szmS63YbTvPe/CEVX3Jrl7wXv79O5+6T5eBwDMHUERAMzGeZmsP3NKJlOynp/Jlbv+LAvWyVmB/6OqjqvJosXfl0+tgfOeJF9dVc8Z02YuXuTYV1bVKWNq1OuTvKW7H93XycbCwevH0w9n8g/nfR4z/D9JLp5aGPiz6lOXlL8uyalV9a9rstj292bxYGtvH36kql5YVU+qqieP1/2RTKYiLWZbki1V9axMQps3J/nifOozeFEm0+C+OJOg4a9GAHUg/kMmo6729nXvujUvmzrf85L8dJYeSfb0JB9N8rGxxtJFU9vemuRZVfX9NVlE+ulV9eVj2y8l+Ymq2lgTX1JVnzOO+fyqelVVfea4vbCqvmi8h99SVZ81psV9NOPzrKqX1WTx8ppqX+yz/o0kP1xVa8d6U/8xya8ust+n2de5l3B8ku8d/T8/k5+d6ZFfVyX5hSSPLDIlMknS3X+bZEeSHx/n/8p8+mLmT0/ycJIPZhK0/tSCEg8k+dyp5zcn+WhV/VBVHTNGJJ1WVS/cz8sHgLkiKAKA2dic5Je7+54xMuf93f3+TP5x+y316VckW65rMlmY9z2ZBC5vSj45uuU3k/zV2P6Y9VoyGXVxRSbTxZ6cSUCzPy9M8q6q+lgmiwh/X3ffvb+Duvt3MwlHrh5Tev46yUvGtg9kMh1sWyb/QN+YyZXKliyX5JczGf10X5IXZ7JWzceWOPetSf4kyX/KJLR5w/T735O1ov4gk89nqaud/WVNrnS19/aGJc713zMJD/Z6VZL3dPfbF3zmlyb5kqo6bZEy/z6TkS0PZbLezSevLNfdD43X+/JMPre7knzd2PxzmYzIeXsmocubkhwzjvlXmaybc9847qeTHD3Vx13jc/nf86mrt23MZOHsj2UyKuuy7n7HIv39yUzCl79KcmsmC0D/5GLvzyKWOvdi3jX69IEklyT5N2MNpr1+JZMFsZcaTbTXN2cyHfFDmSyKfdXUtqsymYr2d0luz2Th9GlvymRNpY9U1e+NYPXlmQSAd4++/VImo5EA4HGjFl+nEAA4klRVZzI9aed+d2ZZqur2TAKI21e7L6zMmNr5YCbrSd212v0BgMcTI4oAgCecqnpSkquERHProiR/LiQCgEPvQIa9AwDMte7+p0ymvzFnqmpXJgtOn7fKXQGAxyVTzwAAAABIYuoZAAAAAIOgCAAAAIAkc7BG0TOf+czesGHDancDAAAA4HHjlltu+UB3r13YfsQHRRs2bMiOHTtWuxsAAAAAjxtV9beLtZt6BgAAAEASQREAAAAAg6AIAAAAgCSCIgAAAAAGQREAAAAASQRFAAAAAAyCIgAAAACSCIoAAAAAGARFAAAAACQRFAEAAAAwCIoAAAAASCIoAgAAAGAQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAADDmtXuAAAAHKk2bL1u2fvu2nbODHsCAIeHEUUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAABkERAAAAAEkERQAAAAAMgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEiyzKCoqn6gqm6rqr+uqt+oqidX1TOq6oaqumvcHze1/8VVtbOq7qyqs6baX1BVt45tl1ZVzeJFAQAAALBy+w2Kqmpdku9Nsqm7T0tyVJILkmxNcmN3b0xy43ieqjplbD81ydlJLquqo0a5NybZkmTjuJ19SF8NAAAAAAdsuVPP1iQ5pqrWJHlKkvuSnJvkyrH9yiTnjcfnJrm6ux/u7ruT7ExyelWdmOTY7r6puzvJVVPHAAAAALDK9hsUdfffJfk/k9yT5P4kf9/db09yQnffP/a5P8nx45B1Se6dKrF7tK0bjxe2AwAAAHAEWM7Us+MyGSV0cpJnJ3lqVb1yX4cs0tb7aF/snFuqakdV7dizZ8/+uggAAADAIbCcqWdfn+Tu7t7T3Z9I8jtJ/mWSB8Z0soz7B8f+u5OcNHX8+kymqu0ejxe2P0Z3X97dm7p709q1a1fyegAAAAA4QMsJiu5JckZVPWVcpezMJHckuTbJ5rHP5iTXjMfXJrmgqo6uqpMzWbT65jE97aGqOmPUuXDqGAAAAABW2Zr97dDd76qqtyR5d5JHkvxFksuTPC3J9qp6dSZh0vlj/9uqanuS28f+r+nuR0e5i5JckeSYJNePGwAAAABHgP0GRUnS3T+a5EcXND+cyeiixfa/JMkli7TvSHLaCvsIAAAAwGGwnKlnAAAAADwBCIoAAAAASCIoAgAAAGAQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAACDoAgAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAABkERAAAAAEkERQAAAAAMgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEgiKAIAAABgEBQBAAAAkERQBAAAAMAgKAIAAAAgiaAIAAAAgEFQBAAAAECSZQRFVfUFVfWeqdtHq+r7q+oZVXVDVd017o+bOubiqtpZVXdW1VlT7S+oqlvHtkurqmb1wgAAAABYmf0GRd19Z3c/v7ufn+QFSf4hye8m2Zrkxu7emOTG8TxVdUqSC5KcmuTsJJdV1VGj3BuTbEmycdzOPrQvBwAAAIADtdKpZ2cm+Zvu/tsk5ya5crRfmeS88fjcJFd398PdfXeSnUlOr6oTkxzb3Td1dye5auoYAAAAAFbZSoOiC5L8xnh8QnffnyTj/vjRvi7JvVPH7B5t68bjhe0AAAAAHAGWHRRV1ZOSfEOS39rfrou09T7aFzvXlqraUVU79uzZs9wuAgAAAHAQVjKi6CVJ3t3dD4znD4zpZBn3D4723UlOmjpufZL7Rvv6Rdofo7sv7+5N3b1p7dq1K+giAAAAAAdqJUHRN+VT086S5Nokm8fjzUmumWq/oKqOrqqTM1m0+uYxPe2hqjpjXO3swqljAAAAAFhla5azU1U9JcmLk3znVPO2JNur6tVJ7klyfpJ0921VtT3J7UkeSfKa7n50HHNRkiuSHJPk+nEDAAAA4AiwrKCou/8hyecsaPtgJldBW2z/S5Jcskj7jiSnrbybAAAAAMzaSq96BgAAAMDjlKAIAAAAgCSCIgAAAAAGQREAAAAASQRFAAAAAAyCIgAAAACSCIoAAAAAGARFAAAAACQRFAEAAAAwCIoAAAAASCIoAgAAAGAQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAADDmtXuAAAAAMy7DVuvW/a+u7adM8OewMExoggAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAAhjWr3QEAAJ4YNmy9btn77tp2zgx7AgAsxYgiAAAAAJIIigAAAAAYBEUAAAAAJFlmUFRVn11Vb6mq91bVHVX1FVX1jKq6oaruGvfHTe1/cVXtrKo7q+qsqfYXVNWtY9ulVVWzeFEAAAAArNxyRxT95yR/0N1fmOR5Se5IsjXJjd29McmN43mq6pQkFyQ5NcnZSS6rqqNGnTcm2ZJk47idfYheBwAAAAAHab9BUVUdm+Srk7wpSbr7n7r7I0nOTXLl2O3KJOeNx+cmubq7H+7uu5PsTHJ6VZ2Y5Njuvqm7O8lVU8cAAAAAsMqWM6Loc5PsSfLLVfUXVfVLVfXUJCd09/1JMu6PH/uvS3Lv1PG7R9u68Xhh+2NU1Zaq2lFVO/bs2bOiFwQAAADAgVlOULQmyZcleWN3f2mSj2dMM1vCYusO9T7aH9vYfXl3b+ruTWvXrl1GFwEAAAA4WMsJinYn2d3d7xrP35JJcPTAmE6Wcf/g1P4nTR2/Psl9o339Iu0AAAAAHAH2GxR19/uT3FtVXzCazkxye5Jrk2webZuTXDMeX5vkgqo6uqpOzmTR6pvH9LSHquqMcbWzC6eOAQAAAGCVrVnmft+T5Neq6klJ3pfk2zIJmbZX1auT3JPk/CTp7tuqansmYdIjSV7T3Y+OOhcluSLJMUmuHzcAAAAAjgDLCoq6+z1JNi2y6cwl9r8kySWLtO9IctpKOggAAADA4bGcNYoAAAAAeAIQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAACDoAgAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAABkERAAAAAEkERQAAAAAMgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEgiKAIAAABgEBQBAAAAkERQBAAAAMAgKAIAAAAgiaAIAAAAgGHNancAAAA4dDZsvW7Z++7ads4MewLAPDKiCAAAAIAkgiIAAAAAhmUFRVW1q6purar3VNWO0faMqrqhqu4a98dN7X9xVe2sqjur6qyp9heMOjur6tKqqkP/kgAAAAA4ECsZUfR13f387t40nm9NcmN3b0xy43ieqjolyQVJTk1ydpLLquqoccwbk2xJsnHczj74lwAAAADAoXAwU8/OTXLleHxlkvOm2q/u7oe7++4kO5OcXlUnJjm2u2/q7k5y1dQxAAAAAKyy5QZFneTtVXVLVW0ZbSd09/1JMu6PH+3rktw7dezu0bZuPF7Y/hhVtaWqdlTVjj179iyziwAAAAAcjDXL3O9F3X1fVR2f5Iaqeu8+9l1s3aHeR/tjG7svT3J5kmzatGnRfQAAAAA4tJY1oqi77xv3Dyb53SSnJ3lgTCfLuH9w7L47yUlTh69Pct9oX79IOwAAAABHgP0GRVX11Kp6+t7HSf5Vkr9Ocm2SzWO3zUmuGY+vTXJBVR1dVSdnsmj1zWN62kNVdca42tmFU8cAAAAAsMqWM/XshCS/O65kvybJr3f3H1TVnyfZXlWvTnJPkvOTpLtvq6rtSW5P8kiS13T3o6PWRUmuSHJMkuvHDQAAAIAjwH6Dou5+X5LnLdL+wSRnLnHMJUkuWaR9R5LTVt5NAAAAAGZtuVc9AwAAAOBxTlAEAAAAQBJBEQAAAACDoAgAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAABkERAAAAAEkERQAAAAAMa1a7AwAAAAD7s2Hrdcved9e2c2bYk8c3I4oAAAAASCIoAgAAAGAQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQJJkzWp3AAAAYJ5s2Hrdsvfdte2cGfYE4NAzoggAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAsOyiqqqOq6i+q6q3j+TOq6oaqumvcHze178VVtbOq7qyqs6baX1BVt45tl1ZVHdqXAwAAAMCBWsmIou9LcsfU861JbuzujUluHM9TVackuSDJqUnOTnJZVR01jnljki1JNo7b2QfVewAAAAAOmWUFRVW1Psk5SX5pqvncJFeOx1cmOW+q/erufri7706yM8npVXVikmO7+6bu7iRXTR0DAAAAwCpb7oiiNyT5wST/PNV2QnffnyTj/vjRvi7JvVP77R5t68bjhe2PUVVbqmpHVe3Ys2fPMrsIAAAAwMHYb1BUVS9L8mB337LMmoutO9T7aH9sY/fl3b2puzetXbt2macFAAAA4GCsWcY+L0ryDVX10iRPTnJsVf1qkgeq6sTuvn9MK3tw7L87yUlTx69Pct9oX79IOwAAAABHgP2OKOrui7t7fXdvyGSR6j/q7lcmuTbJ5rHb5iTXjMfXJrmgqo6uqpMzWbT65jE97aGqOmNc7ezCqWMAAAAAWGXLGVG0lG1JtlfVq5Pck+T8JOnu26pqe5LbkzyS5DXd/eg45qIkVyQ5Jsn14wYAAADAEWBFQVF3vyPJO8bjDyY5c4n9LklyySLtO5KcttJOAgAAADB7y73qGQAAAACPc4IiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYFiz2h0AAACAaRu2XrfsfXdtO2eGPYEnHiOKAAAAAEgiKAIAAABgEBQBAAAAkERQBAAAAMAgKAIAAAAgiaAIAAAAgEFQBAAAAEASQREAAAAAg6AIAAAAgCSCIgAAAAAGQREAAAAASQRFAAAAAAyCIgAAAACSCIoAAAAAGARFAAAAACQRFAEAAAAwCIoAAAAASJKsWe0OAAAAMJ82bL1u2fvu2nbODHsCHCpGFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAACDoAgAAACAJMma1e4AAAA80WzYet2y99217ZwZ9gQAPp0RRQAAAAAkERQBAAAAMAiKAAAAAEgiKAIAAABgEBQBAAAAkERQBAAAAMCw36Coqp5cVTdX1V9W1W1V9eOj/RlVdUNV3TXuj5s65uKq2llVd1bVWVPtL6iqW8e2S6uqZvOyAAAAAFip5YwoejjJ/9Ldz0vy/CRnV9UZSbYmubG7Nya5cTxPVZ2S5IIkpyY5O8llVXXUqPXGJFuSbBy3sw/hawEAAADgIOw3KOqJj42nnzluneTcJFeO9iuTnDcen5vk6u5+uLvvTrIzyelVdWKSY7v7pu7uJFdNHQMAAADAKlvWGkVVdVRVvSfJg0lu6O53JTmhu+9PknF//Nh9XZJ7pw7fPdrWjccL2xc735aq2lFVO/bs2bOS1wMAAADAAVpWUNTdj3b385Osz2R00Gn72H2xdYd6H+2Lne/y7t7U3ZvWrl27nC4CAAAAcJBWdNWz7v5IkndksrbQA2M6Wcb9g2O33UlOmjpsfZL7Rvv6RdoBAAAAOAIs56pna6vqs8fjY5J8fZL3Jrk2yeax2+Yk14zH1ya5oKqOrqqTM1m0+uYxPe2hqjpjXO3swqljAAAAAFhla5axz4lJrhxXLvuMJNu7+61VdVOS7VX16iT3JDk/Sbr7tqranuT2JI8keU13PzpqXZTkiiTHJLl+3AAAAAA4Auw3KOruv0rypYu0fzDJmUscc0mSSxZp35FkX+sbAQAAALBKVrRGEQAAAACPX4IiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAABkERAAAAAEkERQAAAAAMgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEgiKAIAAABgEBQBAAAAkERQBAAAAMAgKAIAAAAgiaAIAAAAgEFQBAAAAEASQREAAAAAg6AIAAAAgCSCIgAAAAAGQREAAAAASQRFAAAAAAyCIgAAAACSCIoAAAAAGARFAAAAACRJ1qx2BwAAAJidDe/OQaIAAB91SURBVFuvW9H+u7adM6OeAPPAiCIAAAAAkgiKAAAAABj2GxRV1UlV9cdVdUdV3VZV3zfan1FVN1TVXeP+uKljLq6qnVV1Z1WdNdX+gqq6dWy7tKpqNi8LAAAAgJVazhpFjyR5bXe/u6qenuSWqrohybcmubG7t1XV1iRbk/xQVZ2S5IIkpyZ5dpL/WlWf392PJnljki1J3pnkbUnOTnL9oX5RALAarAEBAMC82++Iou6+v7vfPR4/lOSOJOuSnJvkyrHblUnOG4/PTXJ1dz/c3Xcn2Znk9Ko6Mcmx3X1Td3eSq6aOAQAAAGCVrWiNoqrakORLk7wryQndfX8yCZOSHD92W5fk3qnDdo+2dePxwnYAAAAAjgDLDoqq6mlJfjvJ93f3R/e16yJtvY/2xc61pap2VNWOPXv2LLeLAAAAAByEZQVFVfWZmYREv9bdvzOaHxjTyTLuHxztu5OcNHX4+iT3jfb1i7Q/Rndf3t2bunvT2rVrl/taAAAAADgIy7nqWSV5U5I7uvvnpjZdm2TzeLw5yTVT7RdU1dFVdXKSjUluHtPTHqqqM0bNC6eOAQAAAGCVLeeqZy9K8qokt1bVe0bb65JsS7K9ql6d5J4k5ydJd99WVduT3J7JFdNeM654liQXJbkiyTGZXO3MFc8AAAAAjhD7DYq6+79l8fWFkuTMJY65JMkli7TvSHLaSjoIAAAAwOGxoqueAQAAAPD4JSgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAMN+r3oGAAAAjwcbtl63ov13bTtnRj2BI5cRRQAAAAAkERQBAAAAMAiKAAAAAEhijSIAAGAVrWTNGOvFAMyeEUUAAAAAJBEUAQAAADAIigAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkyZrV7gAAHG4btl637H13bTtnhj0BAIAjixFFAAAAACQRFAEAAAAwCIoAAAAASCIoAgAAAGAQFAEAAACQRFAEAAAAwCAoAgAAACCJoAgAAACAQVAEAAAAQBJBEQAAAACDoAgAAACAJIIiAAAAAAZBEQAAAABJBEUAAAAADIIiAAAAAJIIigAAAAAYBEUAAAAAJBEUAQAAADDsNyiqqjdX1YNV9ddTbc+oqhuq6q5xf9zUtouramdV3VlVZ021v6Cqbh3bLq2qOvQvBwAAAIADtZwRRVckOXtB29YkN3b3xiQ3juepqlOSXJDk1HHMZVV11DjmjUm2JNk4bgtrAgAAALCK1uxvh+7+06rasKD53CRfOx5fmeQdSX5otF/d3Q8nubuqdiY5vap2JTm2u29Kkqq6Ksl5Sa4/6FcAAADM3Iat1y17313bzplhTwCYpQNdo+iE7r4/Scb98aN9XZJ7p/bbPdrWjccL2wEAAAA4Qux3RNEKLbbuUO+jffEiVVsymaaW5zznOYemZwAwx/xPPgAAh8OBjih6oKpOTJJx/+Bo353kpKn91ie5b7SvX6R9Ud19eXdv6u5Na9euPcAuAgAAALASBxoUXZtk83i8Ock1U+0XVNXRVXVyJotW3zympz1UVWeMq51dOHUMAAAAAEeA/U49q6rfyGTh6mdW1e4kP5pkW5LtVfXqJPckOT9Juvu2qtqe5PYkjyR5TXc/OkpdlMkV1I7JZBFrC1kDAAAAHEGWc9Wzb1pi05lL7H9JkksWad+R5LQV9Q4AAACAw+ZAp54BAAAA8DgjKAIAAAAgiaAIAAAAgGG/axQBwL5s2Hrdivbfte2cGfUEAAA4WEYUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAElc9AwDgcWAlV2B09UUAWJqgCAAAAJ5gVhKwJ0L2JxJTzwAAAABIIigCAAAAYBAUAQAAAJBEUAQAAADAICgCAAAAIImgCAAAAIBBUAQAAABAEkERAAAAAIOgCAAAAIAkgiIAAAAAhjWr3QEAgJXYsPW6Ze+7a9s5M+wJAMDjjxFFAAAAACQRFAEAAAAwmHoGHBFMJQE4cvgzGYCDMW+/R+atv7MmKAIAAACYI7MMt0w9AwAAACCJEUUAAEnmc9j5PPYZADiyGVEEAAAAQBJBEQAAAACDqWcAADNkehgAME8ERRx2/sIMAMCsreTvnIm/dwLsZeoZAAAAAEkERQAAAAAMgiIAAAAAkgiKAAAAABgERQAAAAAkERQBAAAAMAiKAAAAAEiSrFntDgBweGzYet2y99217ZwZ9oQnAt83gJXzZydwJDjsI4qq6uyqurOqdlbV1sN9fgAAAAAWd1hHFFXVUUl+McmLk+xO8udVdW133344+wEr5X93AAAAeCI43COKTk+ys7vf193/lOTqJOce5j4AAAAAsIjDvUbRuiT3Tj3fneTLV1pklqM7ZlV73urOuvYszFt/k/n7Xqyk7kprz8o8vhfz+F1mfvm+AcCRze/q+TaPn1919+E7WdX5Sc7q7u8Yz1+V5PTu/p4F+21JsmU8/YIkdy7zFM9M8oFD1N15rjvL2vNWd5a1563uLGvPW91Z1p63urOsPW91Z1l73urOsva81Z1l7XmrO8va6s6+9rzVnWXteas7y9rzVneWteet7ixrz1vdWdaet7orrf3c7l67sPFwjyjaneSkqefrk9y3cKfuvjzJ5SstXlU7unvTgXfv8VF3lrXnre4sa89b3VnWnre6s6w9b3VnWXve6s6y9rzVnWXteas7y9rzVneWtdWdfe15qzvL2vNWd5a1563uLGvPW91Z1p63urOsPW91D1Xtw71G0Z8n2VhVJ1fVk5JckOTaw9wHAAAAABZxWEcUdfcjVfXdSf4wyVFJ3tzdtx3OPgAAAACwuMM99Szd/bYkb5tR+RVPV3uc1p1l7XmrO8va81Z3lrXnre4sa89b3VnWnre6s6w9b3VnWXve6s6y9rzVnWVtdWdfe97qzrL2vNWdZe15qzvL2vNWd5a1563uLGvPW91DUvuwLmYNAAAAwJHrcK9RBAAAAMARSlAEAAAAQBJBEQAAAADDYV/M+lCqqmclSXe/v6rWJvmqJHceyiupVdXJSb40ye3d/d4jsW5VPSfJg939j1VVSb41yZcluT3Jf+nuR46kuqP2ZyU5O8m6JJ3kviR/2N0fOdCa+zjXT3X36w6yxuPivRjne3F333CQNWbyszer96Kqjk2ytrv/ZkH7l3T3Xx1M7UXOdaR/32b252ZVfXWSB7r7zqr6yiRnJLmju687yLpz972oqqdl0ueTkjyS5K4kb+/ufz6Imt8wavzjwfRtidoz+exG7Zn/GXeIf6ce8s9uqvbcfJdn+X0b9Wf2nVtwnoP+M3k/9Q/6d+qCejP5e+eofaT/fprlz97c/pthwTmO2O/brH6nzvDvnHP5d62pcxzS79sM/w43s5/rJc53xP47Z8E5jvi/t8ztiKKq+s4kNyV5Z1VdlOStSV6W5Heq6tUHUff3ph6fm+SPkrw8yTVV9a1HWt3hbfnUZ7ktyTlJ3pXkhTm4Fc9nUreqLkzy7iRfm+QpSZ6a5OuS3DK2HbCqunTB7eeTfNfe5wdReu7ei31408EcPMOfvZm8F1X1iiTvTfLbVXVbVb1wavMVB1p31J6379tMPrtR+w2jr79SVT+R5GeSHJPkB6rqZw+i7jx+L16R5I8z+aX93UlOT/KqJO+pqi8+iNK/mWR3Vf1KVb20qo46mH7uNavPbtSe1ec3q9/Vs/rs5vG7PJPvWzLTPy9m9Wfyvhzs79RZfZfn7ffTLH/25urfDPtxpH7fZvLn0P9s7/5jJbvrMo6/P6VbGmmxpaussi01LZXaKG2RSmMIhaIIEQQE1NjwSxuUEBENIGgiBjVYCdYqYIAY2pSILSYFbWj5XYoV+bG7/aUsRVrapVQoLLSl1FT78Y9zrjt7s7uGe+6zM8+d50kmnTuT+7qfPvM9Z2bOzg/l4xbMHmsp15twnyzbrg+QRX2eY/e4he62PAHXMzzQOga4B9gyXn40sGOCu33m/DXAj4znNwPXLpo7Gv82c/5zwCEzP0+ZWeXuBI7ax+VHA1+Y2MUu4GLgBcALx9PXV84vSxfA+/dz+kfgOxM7Vm17qi52AD80nj+D4YHMc8aft6/VNV1vkttuNG4EavR3A983Xr4JuGHJ1sV1M///mxleMQLwE8A1E9zt4//3ucBHgP8E/gZ44iLeduLbT3VfLbntxF1I1rJqvSnXHLp9svI+VbWW3e6flNue23MGx/Wm2g8pH7dYPdZS3Xajodonqx4POT7PsXvc4vzWs/u7+17g3qr6j+6+A6C7d1dVT3Bnf/fQ7r55dO+sqikv31K5ALdV1ZO7+6PALQwvO/tyVR2zoG6xdx8reWC8bkpOBt7AcFT1Vd39lar6w+6+cKLr1sUTgHMYdnCr/94ZE1zQbXuqLh7U3V8F6O5PV9WTgH+qqq37+XvfS9zWm+q2G5numf3ZivcA01696rguCvjueP47wA+Of+e6Gl6av9Z0d+8G3gG8o4aXRj8feGNVbe3uYye4itsOdLef6j5Vddut2E5rWbXeVmzFmlPtk5X3qaq17Hb/pNz23J4zOK431X5I+bjF7bGW8rmk8jGcYrt2fJ5j97jF+UDRA1W1qbvvZ3ipIABVdTjTFvRjquouhtIfXFVbenh/4mHAlJddq1yAXwcuqqrXA99meKnZyr8E/s4Cun8CbKuqDwK3jZcdB/wMw4OaNae77wZ+u6oeC1xcVZezPm+xdOviU8C93X3V6iuqaucEF3TbnqqLu6vqhB7fM9/dX62qs4DLgFMmuI7rTXXbAVxeVVcDhwPvBC6pqk8BTwQ+McG1WxcML2e/oqquAp4GXApQVQ9j2gGBvX53fPByAXBBVT1ygqu67UB3+6nuU1W3HfitZdV6A9GaE+6TlfepkrVseP+k3PbcnjPYrTd0+yHl4xa3x1rK55KqxwGq7drxeY7d45bqnnowdj6p4QPIbu9VHzRWVY8ATu7uD6/z3ztqdP9lUd2qOhk4ieEA4C7gM70+HwC47m5VHQ08leEDPWt0rxz/9XJdUlUFvAw4s7vPWSfTsov1zLjtfXXcgc5ePnnbU3RRVY9heBnqF1ddvgl4fne/e632Km/h15vythudMxn+VepTVXUC8GzgVuC9E+dWrYt7u/umVZevy7qoqqcDP8bwcuIPjZcdAmzq7v9ao3lWd398ylwHsCW33WgftH3cetynKm67GdtmLSvX2+jL1tzor/s++WBmnR8fLvz902hKtj31fd8+/p7kOYMyU2dWPdY6GM/33B5r7ePvrct6Ez6Gk92nKuJ4+8n2na4HipwzHuFr0YNkmZ0kq5P1lmyEZJ+cbJSo1lu2Ee84rotkSLa9JJlf3Pad6+3afuvZgVJV10/43WOr6j1VdXVVvW48Er5y3WUH+t3/xz1udL/O8In6n6mqr42XHb9WV20f4G8uXMdKW+g+uqo+UFWXV9UJVfWuqvpWVX16/BeOhXJH22q9zcNV2ku47am2kYOxT/7aetsH+JsLt97G33fbJyu3Eau1nG1kr9913HfarYsD/M1l2w/lOcMc3am223pznFl1fzraVvtO5f2p7WcUVdVz9ncVsGUC/bfAPzC89/HXgKuq6hnd/Q1gynvy/x44H/jV7v4fgBq+avZ5wHuAxy+abdix0la5bwf+HDiC4WsSXwO8mOFrGP8aOHvBXDBbb8J17Diz47anWsvZJ4vdMW77ZOU24raWs43sieO+02pdZD+0V7LtiV2x7bbeHGe2e55j6Pq+9ayq7gfezb4/Sf+53X3kGt0d3X3qzM/nAK8Fnglc2t2nr9G9qbsf9b1eN0/brWOlLXS3d/dp4/kvdveJM9dtWzR3/H239SZxlXa2vb1c1TaSfbLYHW23fbJyG7Fay9lG9nId951W6yL7ob3cbHtiV2m7rTfHmU2f51i5YPyKIuA64E3dfcPqK6rqKRPcTVV1eHffB9DdF1fVHcCVwEMmuJ+rqrcCF7Ln206OBV4IbJ/gKm23jpW2yp39lPs3r7rusAV0wW+9qVylnW1vT1RrOftkvQt++2TlNuK2lrON7InjvtNtXWQ/tCfZ9vSu0nZbb44zOz7PcXOhuy1PwBOA4/Zz3U9OcF8JPHEfl58GfGiCexjwm8AVwPXADeP5lwEPntiFxHbrWHz7qdyXAkfs4/ITgfMXzTVdbxLXcWbTbU+1jWSfLHbF68LKHQ2rtZxt5KCtC6vHnW63nbhjq9vO8fYTrwur/YXpfsjqseFouO07ZfsL27eeJUmSJEmSJEmSJEmSJOubDfWtZ1W1La7WdnOVdly97eYqbTdXabu5StvNVdpurtJ2c5W2m6u04+ptN1dpu7lK281V2m6u0l50d0MdKAIqrtx2c5V2XL3t5iptN1dpu7lK281V2m6u0nZzlbabq7Tj6m03V2m7uUrbzVXabq7SXmh3ox0oujyu3HZzlXZcve3mKm03V2m7uUrbzVXabq7SdnOVtpurtOPqbTdXabu5StvNVdpurtJeaDefUZQkyeRU1endve4vn3Rzlbabq7SVMyeJe6rqocCjgC919+5Fd5W2m6u2E99U1ebuvtPJdnOVtpurtJ3cqjoa+O/uvnsZXdtXFFXVsVX1nqq6uqpeV1WbZq67bAHdR1fVB6rq8qo6oareVVXfqqpPV9XJa3WVtpvrOLObO9qnrzo9Fnh/VZ1WVacvi+s4c7rYy33JzPmtVfWRqtpdVddU1UlrdZW2m+s4s2kXF1fV5vH8U4EbgT8DdlTV8xbNdZzZtItvVtU7q+rsqlq3tze4uUpb6D6tqm6uqk+O93U3Av9aVbuq6uxFtN1cx5nThd4d7R+uqouq6tvAncCNVXVrVb2+Zo4LbHQXYM1flzbvE/Ah4DeAU4G/Aq4Bjhmv276A7ieAZwC/AnwZ+GWG9w8+A/jIxC4ktpvrOLObO9oPjNvFx2ZO3x3/+9FlcR1nThd7udtmzl/C8FWrhwDPXodtRGK7uY4zm3Zx/cz5a4Djx/ObgWsXzXWc2bSLncDLgX8GvgL8JfD4KbM6uo4zAzuAk4EzgW+smONl2xbRdnMdZ04XB62LjwJnjeefA/wF8BDgj4G3L4vb3dYHinas+vkchn+FOWHqwhO522fOf3HVdVMXtMR2cx1ndnPH338ucBXw9JnLbp5iOrqOM6eLvdzZJ+2r9/tr/kcBpe3mOs5s2sWNwEPH858EDpm9btFcx5lNu5hdb8cBrwa2AV8C/nRZXMeZV7m3rbpux1pdpe3mOs6cLg5aF9eu+vlzM+c/vyxud3MovtlUVYd3930A3X1xVd0BXMlwFG3R3AfNnH/zqusOm+AqbTdXaccd093vraorgDdU1YuB3wV6iunoKm03V2kLZ95aVRcwvNLuB6pqU3ffP1437aW6OtvNVdpurtL+I+BjVfUWhlc2XFpV7wOeDFyxgK7jzI5d/N9bobr7VuA84Lyq+lGGVxkvi6u0Ve63quqlwEOB3VX1SoZXIT4FuGeCq7TdXMeZ04XeBfh6VZ3D8EqdXwRuAaiqYtrH9ri51geK3gn8FMO/NAPQ3R+u4f3c5y2g+5aqOqK77+nut65cWFUnAh+e4CptN1dpx51Jd98DvLKqTgMuBI6cajq6StvNVdoi91Uz5z8LHMHwYGML8P4Ftd1cpe3myuzuvqSqtgHnAicxPLY7E/i77r5y0VzHmR27YHh77r7+3k6Gg1PL4iptlftC4A8Y/lHkZxk+RuBKho8SOHeCq7TdXKXt5iptNxfgJcCbgN9jeIvby8fLHwa8doncfOtZkiTTMh6xPrK771pmV2m7uUpbOXOSJEmSJEmSJOYHimr4dohnAY9gOKJ4O/C+7p70MmA3V2m7uUo7rt52c5W2m6u03Vyl7eYqbTdXabu5StvNVdpx9fZBdi+b+go2pe3mKm03V2m7uQew3fYX013XA0VVdT7DS3QvAnaNF28FXgDc1N2vWAbXceZ04es6zpwu9K7jzOlC7zrOnC70ruPM6cLXdZw5Xehdx5nThd51nFnZxZo/BXveJ+AL+7m8xlKWwnWcOV34uo4zp4t0kS7Sxbxdx5nTRbrYCK7jzOkiXaSLdDFvt7unfRL2nHNfVZ2xj8sfB9y3RK7SdnOVdly97eYqbTdXabu5StvNVdpurtJ2c5W2m6u04+ptN1dpu7lK281V2m6u0nZzrb/17EXA26rqSPa8zOpY4K7xumVxlbabq7Tj6m03V2m7uUrbzVXabq7SdnOVtpurtN1cpR1Xb7u5StvNVdpurtJ2c5W2m+v7GUUrqeFrZR/B8PKqXd19xzK6StvNVdpx9babq7TdXKXt5iptN1dpu7lK281V2m6u0o6rt91cpe3mKm03V2m7uUrbyp3yvrVFOwGvj+s5c7rwdR1nThfpIl2ki3m7jjOni3SxEVzHmdNFukgX6eJgu86fUbSvPDOu3HZzlXZcve3mKm03V2m7uUrbzVXabq7SdnOVtpurtOPqbTdXabu5StvNVdpurtJeaHejHSiquHLbzVXacfW2m6u03Vyl7eYqbTdXabu5StvNVdpurtKOq7fdXKXt5iptN1dpu7lKe6Fd+88omk1VHdLdDyy7q7TdXKUdV2+7uUrbzVXabq7SdnOVtpurtN1cpe3mKu24etvNVdpurtJ2c5W2m6u0F921PlBUVU8FnsXwwU0N3A68r7uvWCZXabu5Sjuu3nZzlbabq7TdXKXt5iptN1dpu7lK281V2nH1tpurtN1cpe3mKm03V2nbua4HiqrqfOAk4CL2fBXcVuAFwE3d/YplcB1nThe+ruPM6ULvOs6cLvSu48zpQu86zpwufF3HmdOF3nWcOV3oXceZlV1IPhn8YJyAL+zn8hpLWQrXceZ04es6zpwu0kW6SBfzdh1nThfpYiO4jjOni3SRLtLFvN1u7289u6+qztjH5Y8D7lsiV2m7uUo7rt52c5W2m6u03Vyl7eYqbTdXabu5StvNVdpx9babq7TdXKXt5iptN1dpu7kcOuWX55wXAW+rqiPZ8zKrY4G7xuuWxVXabq7Sjqu33Vyl7eYqbTdXabu5StvNVdpurtJ2c5V2XL3t5iptN1dpu7lK281V2m6u72cUraSqtjB8cFMBu7r7jmV0lbabq7Tj6m03V2m7uUrbzVXabq7SdnOVtpurtN1cpR1Xb7u5StvNVdpurtJ2c5W2k7sRDhRt6u77V122ubvvXCZXabu5Sjuu3nZzlbabq7TdXKXt5iptN1dpu7lK281V2nH1tpurtN1cpe3mKm03V2k7ubafUVRVT6qqXcDtVfXBqjp+5uoPLourtN1cpR1Xb7u5StvNVdpurtJ2c5W2m6u03Vyl7eYq7bh6281V2m6u0nZzlbabq7TdXMD6W88+A5wynn8ucBPw+PHn7cviOs6cLnxdx5nTRbpIF+li3q7jzOkiXWwE13HmdJEu0kW6mLfb3dYHiq5d9fMpwE7g2cC2ZXEdZ04Xvq7jzOkiXaSLdDFv13HmdJEuNoLrOHO6SBfpIl3M2+32PlD0WWDLqsu2AjuAu5fFdZw5Xfi6jjOni3SRLtLFvF3HmdNFutgIruPM6SJdpIt0MW+32/tA0VOAx+zj8qOA318W13HmdOHrOs6cLtJFukgX83YdZ04X6WIjuI4zp4t0kS7Sxbzd7vb/1rMkSZIkSZIkSZIkSZJkfeL8rWffX1VvrKrPV9U3xtO/j5cdtSyu48zpwtd1nDld6F3HmdOF3nWcOV3oXceZ04Wv6zhzutC7jjOnC73rOLOyC9sDRcAlwG7grO4+pruPAZ40XnbpErmOM6cLX9dx5nShdx1nThd613HmdKF3HWdOF76u48zpQu86zpwu9K7jzLouprxvbZ4nYOdarttoruPM6cLXdZw5XaSLdJEu5u06zpwu0sVGcB1nThfpIl2ki3m73W39iqIvV9Wrq+rhKxdU1cOr6jXAbUvkKm03V2nH1dturtJ2c5W2m6u03Vyl7eYqbTdXabu5Sjuu3nZzlbabq7TdXKXt5iptN9f6QNEvAccAV1XV7qr6JvBx4GHA85fIVdpurtKOq7fdXKXt5iptN1dpu7lK281V2m6u0nZzlXZcve3mKm03V2m7uUrbzVXabq7vW8/Gl1M9muEr4Y5YdfnPLZPrOHO68HUdZ04X6SJdpIt5u44zp4t0sRFcx5nTRbpIF+li7u7UIud1An4L2AlcBtwC/MLMdduWxXWcOV34uo4zp4t0kS7Sxbxdx5nTRbrYCK7jzOkiXaSLdDFvt9v7QNH1jEfNgOOBzwKvGH/eviyu48zpwtd1nDldpIt0kS7m7TrOnC7SxUZwHWdOF+kiXaSLebvdzaH45kHdfQ9Ad99SVWcB762qRwK1RK7jzOnC13WcOV3oXceZ04XedZw5Xehdx5nTha/rOHO60LuOM6cLves4s6wL5w+zvqOqTl35YSzo54HNwI8vkau03VylHVdvu7lK281V2m6u0nZzlbabq7TdXKXt5irtuHrbzVXabq7SdnOVtpurtN1c67eebQW27Oe6n14W13HmdOHrOs6cLtJFukgX83YdZ04X6WIjuI4zp4t0kS7Sxbzd7qZGJEmSJEmSJEmSJEmSJFnyOL/1LEmSJEmSJEmSJEmSJFnH5EBRkiRJkiRJkiRJkiRJAuRAUZIkSZIkSZIkSZIkSTImB4qSJEmSJEmSJEmSJEkSIAeKkiRJkiRJkiRJkiRJkjH/C1RAMK3vNiiUAAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<Figure size 1440x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "by_date.sort_index().plot(kind='bar', figsize=(20, 8)).set_title(\"All published SRA/ENA accessions by date\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "metadata": {
+    "papermill": {
+     "duration": 0.046172,
+     "end_time": "2020-09-09T00:37:39.403553",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:39.357381",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "date['is_sra'] = date.accession.str.startswith('SRR')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {
+    "papermill": {
+     "duration": 0.032785,
+     "end_time": "2020-09-09T00:37:39.447766",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:39.414981",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [],
+   "source": [
+    "by_date_by_center = date.groupby(['date', 'is_sra']).count().reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "metadata": {
+    "papermill": {
+     "duration": 1.332872,
+     "end_time": "2020-09-09T00:37:40.792346",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:39.459474",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABJgAAAIgCAYAAADJHdOSAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4yLjEsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+j8jraAAAgAElEQVR4nOzde9hdZX0n/O9PQEEQBQTFBBq0eEBoU4mKdYbaQYUeLFgvBF81oFRmHGvtvJaO2qmnV946Um11pjpD7VTimTq1eCiOSEWtRWmCOKh4YKRAJELEE6gc/c0fewW3D0+SB1d2niR8Pte1r732ve611m/vZ+e62F/u+17V3QEAAACAn9U9FrsAAAAAALZvAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAHCXVNW5VXXSYtexUFXVVfXzG9l3clX949TrG6vqwZs53xOqau1Wqu+CqvqdLXWtHVVVLRs+x51ncO4t+vcGgB2VgAkAtkFDsPCdqrrXYtcyV3f/Wneftdh1zEJ379HdX1/sOmahqk6pqi9X1Q1VdW1Vfbiq7jPse1tV3TIEbN+uqvOq6uHznGOT38uq+mpVPXTO+TY8Pj/02RAGfXjOse+oqlfOaTuoqn5cVW/eYh/EDM0NLAHg7kTABADbmKpaluRfJ+kkv7WoxbBDqKpfSfL/J3lGd98nySOSnD2n2+u6e48kS5J8I8lfzTnHsmzie1lVD0lyj+7+6vT5ph6/OOeQI6rq8ZspfWWS7yQ5cVsMWwGAnxAwAcC2Z2WSzyR5W5KfmopWVQdU1d9W1fqqur6q/uvUvudV1WXDCJUvVdWjhvYHVdX/HI65oqp+b+qYx1TV6qr6/jCq5Q1D+67DiJLrq+q7VfXPVfWAYd8d07aq6h5V9Z+q6sqquq6qVlXVfYd9G0aqnFRVV1XVt6rqjzZ37bk2TFGqqpcN5/iXqnrm1P6fmka2kVEkv15VXx+OP6Oq5v1voOnpalX168PneENVfaOq/mBO3xcP73ldVT1nqv1eVfWnw3u+tqr+W1XtNrX/tOGYa6rqufPVMcdDquqiqvpeVZ1TVXsP5/lwVb1wTk3/u6qOm+ccj05yYXd/Lkm6+9vdfVZ33zC3Y3f/KJPwafmcXRv9Xg5+I8nfL+D9bPC6JK/ZTJ+VSf5TkluTPGUB53zu8Lmuq6oXJ0lVPbCqflhV+2zoVFWHD/8edpl7gqrabRiB9Z2q+lImn930/pdU1f+Z+nf21KH9EUn+W5LHDSO2vju0b/L7AAA7CgETAGx7ViZ55/A4eirY2SnJh5JcmWRZJiNN3jPsOz7JK4dj98xkhMn1Q5DywSSfH/ofleT3q+ro4VpvTPLG7t4zyUPyk1EtJyW5b5IDkuyT5N8l+dE8tZ48PH41yYOT7JHkv87p86+SPGy49suHH+KbuvZ8Hpjk/sN7OCnJmVX1sE30n+upSVYkeVSSY5MsJNj5qyT/dhjxc2iSf5hTz32Hek5J8hdVtdew7z8neWgmAc3PD31eniRVdUySP0jypCQHJ3niAupYOdT7oCS3JXnT0H5Wkmdt6FRVvzhca76Q57OZfJdeVVWPr02MBqqq3ZM8I8nl89Rxp+/llF9P8uEs3F8keWhVzfsZVNW/TrI0k+/42cP1N+dXM/lcn5zkJVX1xO7+ZpILkjx9qt+zkrynu2+d5xyvyOT7+JAkR+fOYdr/yWQk132TvCrJO6pq/+6+LJN/JxcOI7buN/Tf6PcBAHYkAiYA2IZU1b9K8nNJzu7uNZn8mP1/ht2PySRkOK27f9DdN3X3hpE6v5PJlKR/7onLu/vKTEZf7Nvdr+7uW4b1hf4yyYnDcbcm+fmqun9339jdn5lq3yfJz3f37d29pru/P0/Jz0zyhu7+enffmOSlmUxnml5s+VXd/aPu/nwmQdeGqVIbu/bG/HF339zdn8gkyHj6ZvpP+8/DqJ2rkvx5JgHK5tya5JCq2rO7v9PdF8/Z9+ruvrW7/z7JjUkeVlWV5HlJ/sNwvRsymZq24fN+epK/7u4vdPcPMgkFN+ftU/3/OMnTh7DxnCQHV9XBQ79nJ3lvd98y9wTd/akkv51JwPbhTMLHNwzn2eAPhlE3N2QSCj57w47NfC9TVffO5Lv2ibnnm3rMXbfrpiSnZ+OjmE5Kcm53fyfJu5L8WlXtt7EPafCq4d/GpUn+Oj/5O98Rxg3v+RlJ3r6Rczw9yenD3+/q/CTQS5J099909zXd/ePufm+Sr2Xyb/NOFvB9AIAdhoAJALYtJyX5aHd/a3j9rvxkBMUBSa7s7tvmOe6ATH70z/VzSR40/UM/ycuSbBh9ckomoyu+XJNpcL85tL89yf9K8p5hytHr5ptOlEngdeXU6yuT7Dx1/iT55tT2DzMZ5bSpa8/nO0PAMn2dB22i/1xX/wzHPi2TUTlXVtUnqupxU/uun/N32PC+9k1y7yRrpj7vjwztGa47t5a7WvsuSe7f3TdnMrLnWcNItU2FJunuc7v7KUn2zmQU18mZBJMb/Okw6mZZJqPVpkeIbep7mUxGp/1Td98093xTj/mm1f1lkgdU1U9NfxumkB2fyWipdPeFSa7KVKi1ERv7O5+TSVj44ExGj32vuy/ayDk2+TeqqpVVdcnU3/fQTEbXzWdz3wcA2GFs8Vu5AgA/m+FH9dOT7FRVG0KZeyW53zD96eokB1bVzvOETFdnMqVnrquTXNHdB8+zL939tSTPGAKK307yvqraZwhzXpXkVTVZ3Pnvk3wlcxZ+TnJNJiHWBgdmMo3r2kymN23UZq49115VtfvUvgOTfGHY/kEmP+I3eOA8xx+Q5ItTx16zqdqG+v45ybFDsPa7mYQ5B2zmsG9lEs48sru/Mc/+dXPOceDm6pin/63DdZLJyJy3J/nHJD8cgphN6u4fJzm/qv4hk3Bk7v6rqupFSc6qqg8NzRv9Xg4j0+7q9LgN17q1ql6V5P/LT/4+yWRK455J3lxV/2Vou18m0+T+fBOnPCDJl4ftO/7O3X1TVZ2dyYi7h2cTQVx+8jea/r4kSarq5zIJxY7KZCrc7VV1SZLa8JbmnGtz3wcA2GEYwQQA247jktye5JBM1mtZnsndvj6VyQ/rizL58fvaqtq9Jgtxb7gL11szmZJ0eE38/PBj+KIk36+q/zgsXrxTVR1aVY9Okqp6VlXtO4QO3x3OdXtV/WpVHTZMJ/p+JqHG7fPU/O4k/6Emt5PfI5PpP+/dyCirn7Kxa2/ikFdV1T2HtXl+M8nfDO2XJPntqrp3TRboPmWeY0+rqr2q6oAkL0ry3s3Uds+qemZV3XdYp+f7m6ktyR3hzV8m+bMN07mqasnUmldnJzm5qg4ZppW9YnPnzGSE0ob+r07yvu6+fbjehUl+nOT12URoUlXHVtWJw2dQVfWYJL+SyaLd872P8zIJZ07N5r+XSfJruWsLfE97eyaB1TFTbScl+R9JDpu65uOTLK+qwzZxrj8evgePTPKc/PTfeVUmo7Z+K8k7NnGOs5O8dPisliaZXkh990xCpPVJUpPF3adDumuTLK2qeyYL+j4AwA5DwAQA246TMlmf56ru/uaGRyaLZj8zk1EST8lkoeCrkqxNckIyWRcmk/Vs3pXJGjp/l2TvIYh4SiY/0K/IZETFWzNZoDiZ/Kj/YlXdmMmi2ycO05wemOR9mQQrl2Wyts58P8r/RyYBwSeH89+Un/5Bvikbu/Z8vpnJ7eqvyWTa1L/r7g0jVf4syS2Z/Lg/a9g/1zlJ1mQSRn04dx6JNZ9nJ/mXqvp+Jos3P2sz/Tf4j5kskP2Z4diPZZhu1t3nZjIC5x+GPv+wsZNMeXsmd277ZpJdk/zenP2rMgliNhWafCeTtYC+lsnf9B1Jzuju+T6rDc5I8oeZhEwb/V5W1aFJbhzWt5r2hzW5m9qGx7cyj+E7+opMpu6lqjYsRv/n09cb1n76SOa/g90Gn8jkcz0/kyl6H526zqczCeMu7u5/2cQ5XpXJtLgrknw0U8Fdd38pkzDvwky+b4cl+fTUsf+Qycinb069341+HwBgR1Ldc0fyAgBsO6rqCUne0d2bnHJ3d1VVK5Oc2t3/apGu/4eZrAn1h4tx/btimBb4ru5+62LXAgA7GmswAQBsp4Zpc/8+yZsXsYx/SfLBRbz+ggzTQh+VyQLnAMAWZoocAMB2aFjHZ30mU7XetVh1dPfZ3X3ZYl1/IarqrEympv1+d9+w2PUAwI7IFDkAAAAARjGCCQAAAIBRBEwAAAAAjLLDLvJ9//vfv5ctW7bYZQAAAADsMNasWfOt7t53bvsOGzAtW7Ysq1evXuwyAAAAAHYYVXXlfO2myAEAAAAwioAJAAAAgFEETAAAAACMssOuwQQAcFfceuutWbt2bW666abFLmWr2HXXXbN06dLssssui10KALADEDABACRZu3Zt7nOf+2TZsmWpqsUuZ6a6O9dff33Wrl2bgw46aLHLAQB2AKbIAQAkuemmm7LPPvvs8OFSklRV9tlnn7vNaC0AYPYETAAAg7tDuLTB3em9AgCzJ2ACAAAAYBQBEwDAFvLLv/zLi10CAMCiEDABAGwh//RP/7TFz3nbbbdt8XMCAGxpAiYAgC1kjz32SJKsW7cuRx55ZJYvX55DDz00n/rUp+btf/vtt+fkk0/OoYcemsMOOyx/9md/liR5whOekJe97GX5lV/5lbzxjW/MBz/4wTz2sY/NL/3SL+WJT3xirr322q32ngAAFmLnxS4AAGBH8653vStHH310/uiP/ii33357fvjDH87b75JLLsk3vvGNfOELX0iSfPe7371j33e/+9184hOfSJJ85zvfyWc+85lUVd761rfmda97XV7/+tfP/o0AACyQgAkAYAt79KMfnec+97m59dZbc9xxx2X58uXz9nvwgx+cr3/963nhC1+Y3/iN38iTn/zkO/adcMIJd2yvXbs2J5xwQtatW5dbbrklBx100MzfAwDAXWGKHADAFnbkkUfmk5/8ZJYsWZJnP/vZWbVq1bz99tprr3z+85/PE57whPzFX/xFfud3fueOfbvvvvsd2y984Qvzu7/7u7n00kvz3//7f89NN9008/cAAHBXGMEEALCFXXnllVmyZEme97zn5Qc/+EEuvvjirFy58k79vvWtb+We97xnnva0p+UhD3lITj755HnP973vfS9LlixJkpx11lmzLB0A4GciYAIA2MIuuOCCnHHGGdlll12yxx57bHQE0ze+8Y085znPyY9//OMkyZ/8yZ/M2++Vr3xljj/++CxZsiRHHHFErrjiipnVDgDws6juXuwaZmLFihW9evXqxS4DANhOXHbZZXnEIx6x2GVsVXfH9wwAjFNVa7p7xdx2azABAAAAMIopcgAAW8FjH/vY3HzzzT/V9va3vz2HHXbYIlXElnb4afNPhdxgzRl3XocLAHYUAiYAgK3gs5/97GKXAAAwM6bIAQAAADCKgAkAAACAUQRMAAAAAIxiDSYAgG3ETjvt9FOLfv/d3/1dli1bNm/fPfbYIzfeeONWqgwAYNMETAAA89jcHcHuqoXcQWy33XbLJZdcskWvCwCwNZgiBwCwjbrxxhtz1FFH5VGPelQOO+ywnHPOOXfqs27duhx55JFZvnx5Dj300HzqU59Kknz0ox/N4x73uDzqUY/K8ccfb7QTADBTAiYAgG3Ej370oyxfvjzLly/PU5/61Oy66655//vfn4svvjgf//jH8+IXvzjd/VPHvOtd78rRRx+dSy65JJ///OezfPnyfOtb38prXvOafOxjH8vFF1+cFStW5A1veMMivSsA4O7AFDkAgG3E3Clyt956a172spflk5/8ZO5xj3vkG9/4Rq699to88IEPvKPPox/96Dz3uc/NrbfemuOOOy7Lly/PJz7xiXzpS1/K4x//+CTJLbfcksc97nFb/f0AAHcfAiYAgG3UO9/5zqxfvz5r1qzJLrvskmXLluWmm276qT5HHnlkPvnJT+bDH/5wnv3sZ+e0007LXnvtlSc96Ul597vfvUiVAwB3N6bIAQBso773ve9lv/32yy677JKPf/zjufLKK+/U58orr8x+++2X5z3veTnllFNy8cUX54gjjsinP/3pXH755UmSH/7wh/nqV7+6tcsHAO5GjGACANhGPfOZz8xTnvKUrFixIsuXL8/DH/7wO/W54IILcsYZZ2SXXXbJHnvskVWrVmXffffN2972tjzjGc/IzTffnCR5zWtek4c+9KFb+y0AAHcTNXehyB3FihUrevXq1YtdBgCwnbjsssvyiEc8YrHL2Kruju95lg4/bdUm9685Y+VWqgQAZqeq1nT3irntpsgBAAAAMMpMA6aq+g9V9cWq+kJVvbuqdq2qvavqvKr62vC811T/l1bV5VX1lao6eqr98Kq6dNj3pqqqWdYNAAAAwMLNLGCqqiVJfi/Jiu4+NMlOSU5M8pIk53f3wUnOH16nqg4Z9j8yyTFJ3lxVOw2ne0uSU5McPDyOmVXdAAAAANw1s54it3OS3apq5yT3TnJNkmOTnDXsPyvJccP2sUne0903d/cVSS5P8piq2j/Jnt19YU8WjFo1dQwAAAAAi2xmAVN3fyPJnya5Ksm6JN/r7o8meUB3rxv6rEuy33DIkiRXT51i7dC2ZNie234nVXVqVa2uqtXr16/fkm8HAAAAgI2Y5RS5vTIZlXRQkgcl2b2qnrWpQ+Zp602037mx+8zuXtHdK/bdd9+7WjIAAAAAP4OdZ3juJya5orvXJ0lV/W2SX05ybVXt393rhulv1w391yY5YOr4pZlMqVs7bM9tBwDYYVx//fU56qijkiTf/OY3s9NOO2XD/zC76KKLcs973nMxywMA2KRZBkxXJTmiqu6d5EdJjkqyOskPkpyU5LXD8zlD/w8keVdVvSGTEU8HJ7mou2+vqhuq6ogkn02yMsl/mWHdAAC56tWHbdHzHfjySze5f5999skll1ySJHnlK1+ZPfbYI3/wB39wx/7bbrstO+88y/90AwD42c3sv1K6+7NV9b4kFye5LcnnkpyZZI8kZ1fVKZmEUMcP/b9YVWcn+dLQ/wXdfftwuucneVuS3ZKcOzwAAHZoJ598cvbee+987nOfy6Me9ajc5z73+ang6dBDD82HPvShLFu2LO94xzvypje9Kbfcckse+9jH5s1vfnN22mmnzVwBAGDLmOld5Lr7Fd398O4+tLufPdwh7vruPqq7Dx6evz3V//Tufkh3P6y7z51qXz2c4yHd/bvD3eQAAHZ4X/3qV/Oxj30sr3/96zfa57LLLst73/vefPrTn84ll1ySnXbaKe985zu3YpUAwN2dcdYAANuw448/frMjkc4///ysWbMmj370o5MkP/rRj7Lffvtt8hgAgC1JwAQAsA3bfffd79jeeeed8+Mf//iO1zfddFOSpLtz0kkn5U/+5E+2en0AAMmMp8gBALDlLFu2LBdffHGS5OKLL84VV1yRJDnqqKPyvve9L9ddN7k577e//e1ceeWVi1YnAHD3I2ACANhOPO1pT8u3v/3tLF++PG95y1vy0Ic+NElyyCGH5DWveU2e/OQn5xd+4RfypCc9KevWrVvkagGAuxNT5AAA5nHgyy9dtGu/8pWvnLd9t912y0c/+tF5951wwgk54YQTZlgVAMDGGcEEAAAAwCgCJgAAAABGETABAAAAMIqACQBg0N2LXcJWc3d6rwDA7AmYAACS7Lrrrrn++uvvFsFLd+f666/PrrvuutilAAA7CHeRAwBIsnTp0qxduzbr169f7FK2il133TVLly5d7DIAgB2EgAkAIMkuu+ySgw46aLHLAADYLpkiBwAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUWYWMFXVw6rqkqnH96vq96tq76o6r6q+NjzvNXXMS6vq8qr6SlUdPdV+eFVdOux7U1XVrOoGAAAA4K6ZWcDU3V/p7uXdvTzJ4Ul+mOT9SV6S5PzuPjjJ+cPrVNUhSU5M8sgkxyR5c1XtNJzuLUlOTXLw8DhmVnUDAAAAcNdsrSlyRyX5P919ZZJjk5w1tJ+V5Lhh+9gk7+num7v7iiSXJ3lMVe2fZM/uvrC7O8mqqWMAAAAAWGRbK2A6Mcm7h+0HdPe6JBme9xvalyS5euqYtUPbkmF7bjsAAAAA24CZB0xVdc8kv5XkbzbXdZ623kT7fNc6tapWV9Xq9evX37VCAQAAAPiZbI0RTL+W5OLuvnZ4fe0w7S3D83VD+9okB0wdtzTJNUP70nna76S7z+zuFd29Yt99992CbwEAAACAjdkaAdMz8pPpcUnygSQnDdsnJTlnqv3EqrpXVR2UyWLeFw3T6G6oqiOGu8etnDoGAAAAgEW28yxPXlX3TvKkJP92qvm1Sc6uqlOSXJXk+CTp7i9W1dlJvpTktiQv6O7bh2Oen+RtSXZLcu7wAAAAAGAbMNOAqbt/mGSfOW3XZ3JXufn6n57k9HnaVyc5dBY1AgAAADDO1rqLHAAAAAA7KAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYJSZBkxVdb+qel9VfbmqLquqx1XV3lV1XlV9bXjea6r/S6vq8qr6SlUdPdV+eFVdOux7U1XVLOsGAAAAYOFmPYLpjUk+0t0PT/KLSS5L8pIk53f3wUnOH16nqg5JcmKSRyY5Jsmbq2qn4TxvSXJqkoOHxzEzrhsAAACABZpZwFRVeyY5MslfJUl339Ld301ybJKzhm5nJTlu2D42yXu6++buviLJ5UkeU1X7J9mzuy/s7k6yauoYAAAAABbZLEcwPTjJ+iR/XVWfq6q3VtXuSR7Q3euSZHjeb+i/JMnVU8evHdqWDNtz2++kqk6tqtVVtXr9+vVb9t0AAAAAMK+dZ3zuRyV5YXd/tqremGE63EbMt65Sb6L9zo3dZyY5M0lWrFgxbx8AALZ9h5+2arN91pyxcitUAgAsxCxHMK1Nsra7Pzu8fl8mgdO1w7S3DM/XTfU/YOr4pUmuGdqXztMOAAAAwDZgZgFTd38zydVV9bCh6agkX0rygSQnDW0nJTln2P5AkhOr6l5VdVAmi3lfNEyju6GqjhjuHrdy6hgAAAAAFtksp8glyQuTvLOq7pnk60mek0modXZVnZLkqiTHJ0l3f7Gqzs4khLotyQu6+/bhPM9P8rYkuyU5d3gAAAAAsA2YacDU3ZckWTHPrqM20v/0JKfP0746yaFbtjoAAAAAtoRZrsEEAAAAwN2AgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABglJ0XuwAAAAC4uzj8tFWb7bPmjJVboRLYsoxgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoMw2YqupfqurSqrqkqlYPbXtX1XlV9bXhea+p/i+tqsur6itVdfRU++HDeS6vqjdVVc2ybgAAAAAWbmuMYPrV7l7e3SuG1y9Jcn53H5zk/OF1quqQJCcmeWSSY5K8uap2Go55S5JTkxw8PI7ZCnUDAAAAsACLMUXu2CRnDdtnJTluqv093X1zd1+R5PIkj6mq/ZPs2d0XdncnWTV1DAAAAACLbNYBUyf5aFWtqapTh7YHdPe6JBme9xvalyS5eurYtUPbkmF7bvudVNWpVbW6qlavX79+C74NAAAAADZm5xmf//HdfU1V7ZfkvKr68ib6zreuUm+i/c6N3WcmOTNJVqxYMW8fAAAAALasmY5g6u5rhufrkrw/yWOSXDtMe8vwfN3QfW2SA6YOX5rkmqF96TztAAAAAGwDZhYwVdXuVXWfDdtJnpzkC0k+kOSkodtJSc4Ztj+Q5MSquldVHZTJYt4XDdPobqiqI4a7x62cOgYAAACARTbLKXIPSPL+SSaUnZO8q7s/UlX/nOTsqjolyVVJjk+S7v5iVZ2d5EtJbkvygu6+fTjX85O8LcluSc4dHgAAAABsA2YWMHX315P84jzt1yc5aiPHnJ7k9HnaVyc5dEvXCAAAAMB4s76LHAAAAAA7OAETAAAAAKMseIpcVe2UybpKdxzT3VfNoigAAAAAth8LCpiq6oVJXpHk2iQ/Hpo7yS/MqC4AAAAAthMLHcH0oiQPGxboBgAAAIA7LHQNpquTfG+WhQAAAACwfVroCKavJ7mgqj6c5OYNjd39hplUBQAAzNThp63abJ81Z6zcCpUAsCNYaMB01fC45/AAAAAAgCQLDJi6+3BSqkQAACAASURBVFVJUlX3mbzsG2daFQAAAADbjQWtwVRVh1bV55J8IckXq2pNVT1ytqUBAAAAsD1Y6CLfZyb5f7v757r755K8OMlfzq4sAAAAALYXCw2Ydu/uj2940d0XJNl9JhUBAAAAsF1Z8F3kquqPk7x9eP2sJFfMpiQAAAAAticLHcH03CT7JvnbJO8ftp8zq6IAAAAA2H4s9C5y30nyezOuBQAAAIDt0CYDpqr68+7+/ar6YJKeu7+7f2tmlQEAAACwXdjcCKYNay796awLAQAAAGD7tMmAqbvXDM+f2NBWVXslOaC7//eMawMAAABgO7CgRb6r6oKq2rOq9k7y+SR/XVVvmG1pAAAAAGwPFnoXuft29/eT/HaSv+7uw5M8cXZlAQAAALC9WGjAtHNV7Z/k6Uk+NMN6AAAAANjOLDRgenWS/5Xk8u7+56p6cJKvza4sAAAAALYXm7uLXJKku/8myd9Mvf56kqfNqigAAAAAth8LCpiq6nVJXpPkR0k+kuQXk/x+d79jhrUBAAAAzMRVrz5ss30OfPmlW6GSHcNCp8g9eVjk+zeTrE3y0CSnzawqAAAAALYbCw2Ydhmefz3Ju7v72zOqBwAAAIDtzIKmyCX5YFV9OZMpcv++qvZNctPsygIAAABge7GgEUzd/ZIkj0uyortvTfLDJMfOsjAAAAAAtg8LCpiq6t5JXpDkLUPTg5KsmFVRAAAAAGw/FroG018nuSXJLw+v12ZyVzkAAAAA7uYWGjA9pLtfl+TWJOnuHyWpmVUFAAAAwHZjoQHTLVW1W5JOkqp6SJKbZ1YVAAAAANuNhd5F7hVJPpLkgKp6Z5LHJzl5VkUBAAAAsP1YUMDU3edV1cVJjshkatyLuvtbM60MAAAAgO3CQu8i99Qkt3X3h7v7Q0luq6rjZlsaAAAAANuDha7B9Iru/t6GF9393UymzQEAAABwN7fQgGm+fgtdvwkAAACAHdhCA6bVVfWGqnpIVT24qv4syZpZFgYAAADA9mGhAdMLk9yS5L1Jzk7yoyQvmFVRAAAAAGw/FnoXuR8kecmMawEAAABgO7TQu8idV1X3m3q9V1X9rwUeu1NVfa6qPjS83ns439eG572m+r60qi6vqq9U1dFT7YdX1aXDvjdVVS38LQIAAAAwSwudInf/4c5xSZLu/k6S/RZ47IuSXDb1+iVJzu/ug5OcP7xOVR2S5MQkj0xyTJI3V9VOwzFvSXJqkoOHxzELvDYAAAAAM7bQgOnHVXXghhdVtSxJb+6gqlqa5DeSvHWq+dgkZw3bZyU5bqr9Pd19c3dfkeTyJI+pqv2T7NndF3Z3J1k1dQwAAAAAi2xBazAl+aMk/1hVnxheH5nJiKLN+fMkf5jkPlNtD+judUnS3euqasNIqCVJPjPVb+3QduuwPbcdAAAAgG3AQhf5/khVrcgkVLokyTmZ3Eluo6rqN5Nc191rquoJC7jMfOsq9Sba57vmqUONOfDAA+frAgAAsFUcftqqzfZZc8bKrVAJwOwtKGCqqt/JZC2lpZkETEckuTDJv9nEYY9P8ltV9etJdk2yZ1W9I8m1VbX/MHpp/yTXDf3XJjlg6vilSa4Z2pfO034n3X1mkjOTZMWKFZudwgcAAADAeAtdg+lFSR6d5Mru/tUkv5Rk/aYO6O6XdvfS7l6WyeLd/9Ddz0rygSQnDd1OymQ0VIb2E6vqXlV1UCaLeV80TKe7oaqOGO4et3LqGAAAAAAW2ULXYLqpu2+qqlTVvbr7y1X1sJ/xmq9NcnZVnZLkqiTHJ0l3f7Gqzk7ypSS3JXlBd98+HPP8JG9LsluSc4cHAAAAANuAhQZMa6vqfkn+Lsl5VfWdbGSa2ny6+4IkFwzb1yc5aiP9Tk9y+jztq5McutDrAQAAALD1LHSR76cOm6+sqo8nuW+Sj8ysKgAAAAC2GwsdwXSH7v7ELAoBAAAAYPu00EW+AQAAAGBeAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABglJ0XuwAAAAD4WR1+2qrN9llzxsqtUAncvRnBBAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADDKzotdAAAAADu2w09btdk+a85YuRUqAWbFCCYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwys4Cpqnatqouq6vNV9cWqetXQvndVnVdVXxue95o65qVVdXlVfaWqjp5qP7yqLh32vamqalZ1AwAAAHDXzHIE081J/k13/2KS5UmOqaojkrwkyfndfXCS84fXqapDkpyY5JFJjkny5qraaTjXW5KcmuTg4XHMDOsGAAAA4C6YWcDUEzcOL3cZHp3k2CRnDe1nJTlu2D42yXu6++buviLJ5UkeU1X7J9mzuy/s7k6yauoYAAAAABbZTNdgqqqdquqSJNclOa+7P5vkAd29LkmG5/2G7kuSXD11+NqhbcmwPbd9vuudWlWrq2r1+vXrt+ybAQAAAGBeMw2Yuvv27l6eZGkmo5EO3UT3+dZV6k20z3e9M7t7RXev2Hfffe96wQAAAADcZVvlLnLd/d0kF2SydtK1w7S3DM/XDd3WJjlg6rClSa4Z2pfO0w4AAADANmCWd5Hbt6ruN2zvluSJSb6c5ANJThq6nZTknGH7A0lOrKp7VdVBmSzmfdEwje6GqjpiuHvcyqljAAAAAFhkO8/w3PsnOWu4E9w9kpzd3R+qqguTnF1VpyS5KsnxSdLdX6yqs5N8KcltSV7Q3bcP53p+krcl2S3JucMDAAB2eIeftmqzfdacsXIrVAIAGzezgKm7/3eSX5qn/fokR23kmNOTnD5P++okm1q/CQAAAIBFslXWYAIAAABgxyVgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACjCJgAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUWYWMFXVAVX18aq6rKq+WFUvGtr3rqrzquprw/NeU8e8tKour6qvVNXRU+2HV9Wlw743VVXNqm4AAAAA7ppZjmC6LcmLu/sRSY5I8oKqOiTJS5Kc390HJzl/eJ1h34lJHpnkmCRvrqqdhnO9JcmpSQ4eHsfMsG4AAAAA7oKZBUzdva67Lx62b0hyWZIlSY5NctbQ7awkxw3bxyZ5T3ff3N1XJLk8yWOqav8ke3b3hd3dSVZNHQMAAADAItsqazBV1bIkv5Tks0ke0N3rkkkIlWS/oduSJFdPHbZ2aFsybM9tBwAAAGAbsPOsL1BVeyT5n0l+v7u/v4nlk+bb0Zton+9ap2YylS4HHnjgXS8WALaSw09btdk+a85YuRUqAQCA8WYaMFXVLpmES+/s7r8dmq+tqv27e90w/e26oX1tkgOmDl+a5Jqhfek87XfS3WcmOTNJVqxYMW8IBQAAwM/uqlcfttk+B7780q1QCbAtmeVd5CrJXyW5rLvfMLXrA0lOGrZPSnLOVPuJVXWvqjook8W8Lxqm0d1QVUcM51w5dQwAAAAAi2yWI5gen+TZSS6tqkuGtpcleW2Ss6vqlCRXJTk+Sbr7i1V1dpIvZXIHuhd09+3Dcc9P8rYkuyU5d3gAAAAAsA2YWcDU3f+Y+ddPSpKjNnLM6UlOn6d9dZJDt1x1AAAAAGwpW+UucgAAAADsuARMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABG2XmxCwAAAIDt0VWvPmyzfQ58+aVboRJYfEYwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABgFAETAAAAAKMImAAAAAAYRcAEAAAAwCgCJgAAAABGETABAAAAMIqACQAAAIBRBEwAAAAAjCJgAgAAAGAUARMAAAAAowiYAAAAABhFwAQAAADAKAImAAAAAEYRMAEAAAAwioAJAAAAgFEETAAAAACMImACAAAAYBQBEwAAAACj7LzYBQAAAGwpV736sM32OfDll26FSgDuXoxgAgAAAGAUARMAAAAAowiYAAAAABjFGkwAAACwDbGWGNsjI5gAAAAAGEXABAAAAMAoAiYAAAAARhEwAQAAADCKgAkAAACAUQRMAAAAAIwiYAIAAABglJkFTFX1P6rquqr6wlTb3lV1XlV9bXjea2rfS6vq8qr6SlUdPdV+eFVdOux7U1XVrGoGAAAA4K7beYbnfluS/5pk1VTbS5Kc392vraqXDK//Y1UdkuTEJI9M8qAkH6uqh3b37UnekuTUJJ9J8vdJjkly7gzrBgAAfkaHn7Zqs33WnLFyK1QCwNY0sxFM3f3JJN+e03xskrOG7bOSHDfV/p7uvrm7r0hyeZLHVNX+Sfbs7gu7uzMJq44LAAAAANuMrb0G0wO6e12SDM/7De1Lklw91W/t0LZk2J7bPq+qOrWqVlfV6vXr12/RwgEAAACY37ayyPd86yr1Jtrn1d1ndveK7l6x7777brHiAAAAANi4rR0wXTtMe8vwfN3QvjbJAVP9lia5ZmhfOk87AAAAANuIrR0wfSDJScP2SUnOmWo/saruVVUHJTk4yUXDNLobquqI4e5xK6eOAQAAAGAbMLO7yFXVu5M8Icn9q2ptklckeW2Ss6vqlCRXJTk+Sfr/tnfv0bLW5WHHvw9wUCMYFGhIuagLNRJj5BJRm1rxVo0JikZpsoJILmq0tta2msZ0pVZjaiUrJRpjltoUCVklYBqkYsBr0JQYuYsQjhBvnCAqBgQkZEF5+se8p2efvc4F9jvPnnn2+/2stRd7z5zz3T+eeeedmffMJfOaiDgbuBa4F/iXwyfIAbyG2SfSPYTZp8f5CXKSJEmSJElLpOwAU2b+7E7OevZO/vzbgbfv4PRLgR+Z49IkSZIkSZI0R8vyJt+SJEmSJElqygNMkiRJkiRJGqXsJXKSJK3F19/6xN3+mcN+/ep1WIkkSZKk+8tnMEmSJEmSJGkUDzBJkiRJkiRpFA8wSZIkSZIkaRTfg0mSpF045o1n7PbPXHbqyeuwEkmSJGl5+QwmSZIkSZIkjeIzmCRJGslPvpMkSdLUeYBJkqSJ8YCYtGteRyRJeuA8wCRJkiRJknbK96TU/eF7MEmSJEmSJGkUDzBJkiRJkiRpFA8wSZIkSZIkaRQPMEmSJEmSJGkUDzBJkiRJkiRpFA8wSZIkSZIkaRQPMEmSJEmSJGkUDzBJkiRJkiRpFA8wSZIkSZIkaRQPMEmSJEmSJGkUDzBJkiRJkiRpFA8wSZIkSZIkaRQPMEmSJEmSJGmUvRa9AEmat6+/9Ym7/TOH/frV67ASSZI0T8e88Yzd/pk/3XcdFiJp3Xjffrz7s++87NSTR/8eDzBJkiSp1O4eHPjAQJKk/jzAJEmSJGmHfOaAJOn+8gCTJEnSBrdeT42XJGmj8zZ153yTb0mSJEmSJI3iM5gkSdpAfANcaZp8KZskadF8BpMkSZIkSZJG8RlMas1/rZMk7YzvkSBpnqrud3p/VtJG4QEmSZKkArt70OgDRkmStJF4gEmSJKkRn+0gSZKWkQeYJEnSZHmwRpKWh/tkqTcPMEmSJEmSAD+NVNLaeYBJkiRJLflsB0mSlscei16AJEmSJEmSevMZTJIkSQ+QLyHRWviMK603tzlJ68kDTJKkNfFOq+bl/hysuezUk9dhJZIkSVqrNgeYIuL5wO8AewIfyMx3LHhJkiSV8iDe9PjMKEmS+pvqfbgWB5giYk/gPcBzgS3AJRFxXmZeu9iVSQ/cVHc2kiRJUice9JcemBYHmIBjgRsy88sAEXEW8CLAA0ySJEkL5AMwSZIEfQ4wHQzcuOLnLcBT5hWvekZJ5TNVdteu6q613fFZO93WvMjtba3tbjOGfrNYa9cHjNoR3ytJ0rx0vA+g3tzmtnEWfS37MYbIzDX98vUUES8DnpeZvzT8/HLg2Mz8V6v+3KuAVw0//hCw+X7+igOAW+a03PXoVrbt1re7dSvb3bqV7W7dyna3bmW7W7ey3a1b2e7WrWzbrW9361a2u3Ur2926le1u3cp2t25lu1v3gbYfmZkHrj6xyzOYtgCHrvj5EOCm1X8oM98HvO+BxiPi0sz8sbUvb327lW279e1u3cp2t25lu1u3st2tW9nu1q1sd+tWtrt1K9t269vdupXtbt3KdrduZbtbt7LdrVvZ7tadV3uPeS2m2CXAYyPi0RGxN/AzwHkLXpMkSZIkSZJo8gymzLw3Il4HXAjsCfxBZl6z4GVJkiRJkiSJJgeYADLzo8BHi/IP+GV1C+5Wtu3Wt7t1K9vdupXtbt3KdrduZbtbt7LdrVvZ7tatbNutb3frVra7dSvb3bqV7W7dyna3bmW7W3cu7RZv8i1JkiRJkqTl1eU9mCRJkiRJkrSkPMAkSZIkSZKkUTzAJEmSJEmSpFHavMn3PEXEQQCZeXNEHAg8Hdg8z0+mi4hHA0cB12bmdcvYjYjDgG9l5t0REcApwNHAtcD7M/PeZeoO7e8Hng8cDCRwE3BhZt621uYuftdvZuabRzY2xCyG3/fczPz4yEbJda9qFhHxMODAzPybVaf/aGZ+YUx7B79r2be3sv1mRPwz4JuZuTki/inwVOCvM/P8kd1220VE7MNszYcC9wLXAx/LzPtGNF84NO4es7adtEsuu6Fdvo+b823q3C+7Fe0223Ll9jb0y7a5Vb9n9D55N/3Rt6mreiX3O4f2st8+VV732j5mWPU7lnZ7q7pNLbzP2fK+1orfMdftrfA+XNn1eie/b2kf56z6HUt/v2Vyz2CKiFcDfwl8LiJeA3wE+Cngf0XEL47onrvi+xcBnwKOBz4cEacsW3fwUbZtA+8AfhL4K+DJjHsH+ZJuRJwMXA4cB3wf8FDgmcBlw3lrFhHvWvX1buC1W38ekW43i13472P+cuF1r2QWEXEicB3wJxFxTUQ8ecXZp6+1O7S7bW8ll93QPm1Y6x9GxNuAdwIPAd4QEaeO6HbcLk4EPs3sxv51wLHAy4ErI+KJI9J/DGyJiD+MiBdExJ5j1rlV1WU3tKsuv6rb6qrLruO2XLK9Qen+omqfvCtjb1OrtuVut0+V171Wjxl2Y1m3t5L9UOX9Fprd16rc3gr3yWXX611Y1sc57e63kJmT+gKuZnYHbX/gTuCg4fSHA1eO6F6x4vuLgUcP3x8AXLVs3aFx7YrvLwP2WPHzmDVXdTcD++3g9IcDXxo5iy3AmcDJwCuGr29v/X4qswDO28nX/wa+N3LGVde9qllcCfzg8P2xzO4AvWT4+Yq1dptubyWX3dC4BoihfyvwfcPpm4AvTmy7+MKK//8DmD1DBeBHgYtHdK8Y/r9fCXwS+Cbw+8AzlvGyK778qm6rSy674lmUbMtV21vlNkfdPrnyNrVqW+52+1R53ev2mKHj9la1H6q839LqvlbVZTc0qvbJVfeHOj7OaXe/ZYovkbsnM+8C7oqIv8nMmwEy89aIyBHdlX93r8z8ytC9JSLGPM2sqgtwY0Q8KzM/BXyV2dPjvhYR+y9pN9h+HlvdN5w3xhHA25gdxX1jZv5tRPynzPzgyG63WTwdOInZjnH17zt2RBfqrntVs9gzM78BkJmfj4hnAh+JiEN28vseiG7bW9VlN2QyV+zPtvbuY9yzbDtuFwH8/fD994B/NPyeL8TsJQRrlZl5K/B+4P0xewr3icA7IuKQzDx0RLfisoO6y6/qNrXqstva7rQtV21vW9sV21zVPrnyNrVqW+52+1R53ev2mKHj9la1H6q839LtvlblY8nK+3AV1+uOj3Pa3W+Z4gGm+yJiU2bew+wpjQBExIMZd0V4UkTczuzCelBEHJSz11/uDYx5enhVF+CXgDMi4i3Ad5k9JW7rvzz+2yXsvh24PCI+Btw4nHYY8Fxmd4bWLDPvAP5NRBwDnBkR5zOfl5B2m8XngLsy86LVZ0TE5hFdqLvuVc3ijog4PIf3BMjMb0TEccC5wBNGdDtub1WXHcD5EfFZ4MHAB4CzI+JzwDOAz4zottsumD3t/oKIuAj4CeAcgIh4BOMOJGz3d4c7Pe8C3hURjxzRrbrsoO7yq7pNrbrsoN+2XLW9QdE2V7hPrrxNLdmWG94+VV73uj1maLe9Ubcfqrzf0u2+VuVjyar7AVXX646Pc9rdb4nMsQdxe4nZG7PdlKvegC0iDgaOyMxPzPn37Td0/3JZuxFxBPA4ZgcctwCX5HzeGHHu3Yh4OPA8Zm90GkP3wuFfS+ciIgJ4LfC0zDxpTs2Ws5in4br3jWHHu/L00de9illExJOYPV32hlWnbwJOzMw/Wmt7VW/pt7fKy27oPI3Zv4J9LiIOB14MfB340Mh1V20Xd2Xm9atOn8t2EREvAH6Y2dOePz6ctgewKTP/YY3N4zLzz8esaxftkstuaK/bPm4et6kVl92KdpttuXJ7G/pl29zQn/s+eT3N+f7h0t8+Dc2S6171bd8Ofl/JY4ZKY9dcdV9rPR7vdbuvtYPfN5ftrfA+XNltaoWOl1/ZvnNqB5g6G44oZtGd67K2tJrbmzYC98naKKq2N68jvXXcLjTjdU9anG77znl3J/cpcrsSEVeP+LuHRsRZEfHZiHjzcOR963nn7urv7qZ72ND9NrNPKLgkIr41nPaotXar27v4nUs348p2YffxEfFnEXF+RBweEadHxG0R8fnhX1SWqju0W21vi+hWtid43au6jqzHPvlb827v4ncu3fY2/P1u++TK60irbdnryHZ/t+O+s912sYvfObX9kI8ZFtgd2+62vXVcc9Xt6dBute+svD2d3HswRcRLdnYWcNCI9B8Af8LstZ2/CFwUEcdn5neAMe858MfAacDPZeb/BYjZR/6+DDgLeOqytRvOuLJd1X0fcCqwD7OPq/wV4OeZfRzm7wLPXrIuNNveCrfjjmvueN2r2pbdJxd3B932yZXXkW7bsteRbTruO1ttF+6HtuN1r7hb3O62vXVcc7vHOQ2703uJXETcA/wRO/5kgpdm5r5r7F6ZmUeu+Pkk4FeBFwLnZObRa+xen5mPfaDnLbLdbcaV7cLuFZl51PD9DZn5mBXnXb5s3eHvd9veSrqVba9723WrriPuk4u7Q7vbPrnyOtJqW/Y6sl23476z1Xbhfmi7rte94m5lu9v21nHNTR/ntOrCBJ/BBHwB+K3M/OLqMyLiOSO6myLiwZl5N0BmnhkRNwMXAg8d0b0sIn4P+CDbPj3mUOAVwBUjupXtbjOubFd1V35qwG+vOm/vJexCv+2tqlvZ9rq3TdW27D65vgv99smV15Fu27LXkW067ju7bRfuh7bxulffrWx32946rrnj45xuXcjMSX0BTwcO28l5Pzai+wbgGTs4/Sjg4yO6ewOvAS4Arga+OHz/WuBBI2dR0u424+LLr6r7amCfHZz+GOC0Zes23d5Kuh3X3PS6V3UdcZ9c3C3eLlp1h0arbdnryLptF63ud3a77Ipn3Oqy63j5FW8XrfYXTfdDre4bDo1u+86y/cXkXiInSZIkSZKk+fJT5Ji95tJubbtbt7Jtt77drVvZ7tatbHfrVra7dSvb3bqV7W7dyna3bmXbbn27W7ey3a1b2e7WrWx361a2l73rAaaZsFve7tatbNutb3frVra7dSvb3bqV7W7dyna3bmW7W7ey3a1b2bZb3+7WrWx361a2u3Ur2926le2l7nqAaeZ8u+Xtbt3Ktt36drduZbtbt7LdrVvZ7tatbHfrVra7dSvb3bqVbbv17W7dyna3bmW7W7ey3a1b2V7qru/BJGlhIuLozJz70zy7dSvb3bqV7co1S91FxMOAxwJfzsxbl71b2e7WrW6rr4g4IDNv6dTu1q1sd+tWtjt1I+LhwL2ZeccUu5N7BlNEHBoRZ0XEZyPizRGxacV55y5h9/ER8WcRcX5EHB4Rp0fEbRHx+Yg4Yq3dyna3bsc1d+sO7aNXfR0DnBcRR0XE0VPpdlyzs9iu+wsrvj8kIj4ZEbdGxMUR8bi1divb3bod19x0FmdGxAHD988DrgH+K3BlRLxs2bod19x0Fn8XER+IiGdHxNxehtGtW9ku7P5ERHwlIv5iuK27BviriNgSEc9exna3bsc1O4v67tD+xxFxRkR8F7gFuCYivh4Rb4kVxwU2ehdgzR8/1/UL+Djwy8CRwLuBi4H9h/OuWMLuZ4DjgZ8Fvgb8DLPXRx4PfHLkLEra3bod19ytO7TvG64Xn17x9ffDfz81lW7HNTuL7bqXr/j+bGYfebsH8OI5XEdK2t26HdfcdBZXr/j+YuBRw/cHAFctW7fjmpvOYjPwOuD/AH8L/A7w1DFr7djtuGbgSuAI4GnAd7Y2h9MuX8Z2t27HNTuLdZvFp4Djhu9fAvw34KHAbwDvm0o3Myd5gOnKVT+fxOxffQ4fu8EWda9Y8f0Nq84be0UoaXfrdlxzt+7w918KXAS8YMVpXxnT7NjtuGZnsV135YP9XMjb9QAADJVJREFU1fv9Nf9jQmW7W7fjmpvO4hrgYcP3fwHssfK8Zet2XHPTWazc3g4D3gRcDnwZ+M2pdDuueVX3xlXnXbnWbmW7W7fjmp3Fus3iqlU/X7bi++um0s1M9mJ6NkXEgzPzboDMPDMibgYuZHbUbtm6e674/rdXnbf3iG5lu1u3sm13kJkfiogLgLdFxM8D/w7IMc2O3cp2t25lu3DNh0TEu5g9s+/AiNiUmfcM5417SnFdu1u3st2tW9n+z8CnI+I9zJ5JcU5EfBh4FnDBEnY7rrnjLP7/S7Yy8+vAO4F3RsQPMXtW81S6le2q7m0R8WrgYcCtEfEGZs96fA5w54huZbtbt+OanUV9F+DbEXESs2cG/TTwVYCICMa9LVG37iQPMH0AeAqzf9kGIDM/EbPXq79zCbvviYh9MvPOzPy9rSdGxGOAT4zoVra7dSvbdlfIzDuBN0TEUcAHgX3HNjt2K9vdupXtou4bV3x/KbAPszspBwHnLWm7W7ey3a1b1s7MsyPicuCVwOOY3Sd8GvA/M/PCZet2XHPHWTB7GfGOft9mZge1ptKtbFd1XwH8R2b/mPLPmb3dwYXM3vLglSO6le1u3cp2t25lu1sX4BeA3wL+A7OX4r1uOP0RwK9OqOunyElajOEI+b6ZefuUu5Xtbt3KduWaJUmSJE30AFPMPm3jBOBgZkcwbwI+nJmjnq7crVvZ7tatbNutb3frVra7dSvb3bqV7W7dyna3bmW7W7ey3a1b2bZb317n7rljnzFX2e7WrWx361a2u3V30e62vxjfndoBpog4jdlTic8AtgwnHwKcDFyfma+fQrfjmp1F327HNTuL+m7HNTuL+m7HNTuL+m7HNTuLvt2Oa3YW9d2Oa3YW9d2Oa66cxZrfHbzrF/ClnZwewzAn0e24ZmfRt9txzc7CWTgLZ7Hobsc1OwtnsRG6HdfsLJyFs3AWi+5m5rh3CG/q7og4dgenPxm4e0Ldyna3bmXbbn27W7ey3a1b2e7WrWx361a2u3Ur2926le1u3cq23fp2t25lu1u3st2tW9nu1q1sd+tO8lPkTgHeGxH7su3pYIcCtw/nTaVb2e7WrWzbrW9361a2u3Ur2926le1u3cp2t25lu1u3st2tW9m2W9/u1q1sd+tWtrt1K9vdupXtbt3pvQfTVjH7eN+DmT0NbEtm3jzFbmW7W7eybbe+3a1b2e7WrWx361a2u3Ur2926le1u3cp2t25l2259u1u3st2tW9nu1q1sd+tWtlt1x7y+bqN8AW+x23PNzqJvt+OanYWzcBbOYtHdjmt2Fs5iI3Q7rtlZOAtn4SzWuzvF92DakRfaLW9361a27da3u3Ur2926le1u3cp2t25lu1u3st2tW9nu1q1s261vd+tWtrt1K9vdupXtbt3K9lJ3PcA0E3bL2926lW279e1u3cp2t25lu1u3st2tW9nu1q1sd+tWtrt1K9t269vdupXtbt3KdrduZbtbt7K91N3JvgfTShGxR2beN/VuZbtbt7Jtt77drVvZ7tatbHfrVra7dSvb3bqV7W7dyna3bmXbbn27W7ey3a1b2e7WrWx361a2l707yQNMEfE84ARmb2iVwE3AhzPzgil1K9vdupVtu/Xtbt3KdrduZbtbt7LdrVvZ7tatbHfrVra7dSvbduvb3bqV7W7dyna3bmW7W7ey3a47tQNMEXEa8DjgDLZ9JN8hwMnA9Zn5+il0O67ZWfTtdlyzs6jvdlyzs6jvdlyzs6jvdlyzs+jb7bhmZ1Hf7bhmZ1Hf7bjmylmUvGP6Mn8BX9rJ6TEMcxLdjmt2Fn27HdfsLJyFs3AWi+52XLOzcBYbodtxzc7CWTgLZ7HobuY0P0Xu7og4dgenPxm4e0Ldyna3bmXbbn27W7ey3a1b2e7WrWx361a2u3Ur2926le1u3cq23fp2t25lu1u3st2tW9nu1q1sd+uy15i/3NQpwHsjYl+2PR3sUOD24bypdCvb3bqVbbv17W7dyna3bmW7W7ey3a1b2e7WrWx361a2u3Ur23br2926le1u3cp2t25lu1u3st2tO733YNoqIg5i9oZWAWzJzJun2K1sd+tWtu3Wt7t1K9vdupXtbt3KdrduZbtbt7LdrVvZ7tatbNutb3frVra7dSvb3bqV7W7dynan7pQPMG3KzHtWnXZAZt4ypW5lu1u3sm23vt2tW9nu1q1sd+tWtrt1K9vdupXtbt3KdrduZdtufbtbt7LdrVvZ7tatbHfrVrY7dSf3HkwR8cyI2ALcFBEfi4hHrTj7Y1PpVra7dSvbduvb3bqV7W7dyna3bmW7W7ey3a1b2e7WrWx361a27da3u3Ur2926le1u3cp2t25lu1sXmOSnyF0CPGH4/qXA9cBTh5+vmEq345qdRd9uxzU7C2fhLJzForsd1+wsnMVG6HZcs7NwFs7CWSy6m5mTPMB01aqfnwBsBl4MXD6Vbsc1O4u+3Y5rdhbOwlk4i0V3O67ZWTiLjdDtuGZn4SychbNYdDdzmgeYLgUOWnXaIcCVwB1T6XZcs7Po2+24ZmfhLJyFs1h0t+OanYWz2Ajdjmt2Fs7CWTiLRXczp3mA6TnAk3Zw+n7Ar02l23HNzqJvt+OanYWzcBbOYtHdjmt2Fs5iI3Q7rtlZOAtn4SwW3c3M6X6KnCRJkiRJkuZjip8i9/0R8Y6IuC4ivjN8/fVw2n5T6XZcs7Po2+24ZmdR3+24ZmdR3+24ZmdR3+24ZmfRt9txzc6ivttxzc6ivttxzZWzmNwBJuBs4FbguMzcPzP3B545nHbOhLod1+ws+nY7rtlZ1Hc7rtlZ1Hc7rtlZ1Hc7rtlZ9O12XLOzqO92XLOzqO92XHPdLMa8vq7jF7B5LedttG7HNTuLvt2Oa3YWzsJZOItFdzuu2Vk4i43Q7bhmZ+EsnIWzWHQ3Myf5DKavRcSbIuIHtp4QET8QEb8C3DihbmW7W7eybbe+3a1b2e7WrWx361a2u3Ur2926le1u3cp2t25l2259u1u3st2tW9nu1q1sd+tWtrt1J3mA6V8A+wMXRcStEfF3wJ8DjwBOnFC3st2tW9m2W9/u1q1sd+tWtrt1K9vdupXtbt3KdrduZbtbt7Jtt77drVvZ7tatbHfrVra7dSvb3brTe4nc8LSvxzP7aL59Vp3+/Cl1O67ZWfTtdlyzs3AWzsJZLLrbcc3OwllshG7HNTsLZ+EsnMXCu2MH2e0L+NfAZuBc4KvAi1acd/lUuh3X7Cz6djuu2Vk4C2fhLBbd7bhmZ+EsNkK345qdhbNwFs5i0d3MaR5guprhKB3wKOBS4PXDz1dMpdtxzc6ib7fjmp2Fs3AWzmLR3Y5rdhbOYiN0O67ZWTgLZ+EsFt3NTPZievbMzDsBMvOrEXEc8KGIeCQQE+p2XLOz6NvtuGZnUd/tuGZnUd/tuGZnUd/tuGZn0bfbcc3Oor7bcc3Oor7bcc1ls5jim3zfHBFHbv1hGOxPAQcAT5xQt7LdrVvZtlvf7tatbHfrVra7dSvb3bqV7W7dyna3bmW7W7eybbe+3a1b2e7WrWx361a2u3Ur2926k3yJ3CHAQTs578en0u24ZmfRt9txzc7CWTgLZ7Hobsc1OwtnsRG6HdfsLJyFs3AWi+5mJjFEJEmSJEmSpDWZ4kvkJEmSJEmSNEceYJIkSZIkSdIoHmCSJElaBxHxloj497s4/4SI+OH1XJMkSdK8eIBJkiRpOZwAeIBJkiS15Jt8S5IkFYmIXwNOBm4Evg1cBnwXeBWwN3AD8HLgSOAjw3nfBX56SLwHOBC4C3hlZl63nuuXJEm6vzzAJEmSVCAijgFOB54C7AVcDvw+8D8y8zvDn/kN4JuZ+e6IOB34SGZ+aDjvk8AvZ+b1EfEU4L9k5rPW//9EkiRp9/Za9AIkSZI2qKcDf5qZdwFExHnD6T8yHFjaD9gHuHD1X4yIfYB/ApwTEVtPflD5iiVJktbIA0ySJEl1dvRU8dOBEzLzqog4BThuB39mD+C2zDyybmmSJEnz45t8S5Ik1fgM8OKIeEhE7AscP5y+L/CNiNgE/NyKP3/HcB6ZeTvwlYh4GUDMPGn9li5JkvTA+B5MkiRJRVa8yffXgC3AtcD3gDcNp10N7JuZp0TEjwPvB/4BeClwH/Be4AeBTcBZmfnWdf+fkCRJuh88wCRJkiRJkqRRfImcJEmSJEmSRvEAkyRJkiRJkkbxAJMkSZIkSZJG8QCTJEmSJEmSRvEAkyRJkiRJkkbxAJMkSZIkSZJG8QCTJEmSJEmSRvEAkyRJkiRJkkb5f9uArpt5Fn0FAAAAAElFTkSuQmCC\n",
+      "text/plain": [
+       "<Figure size 1440x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "fig, ax = plt.subplots(figsize=(20, 8))\n",
+    "ax = sns.barplot(x='date', y='accession', hue='is_sra', data=by_date_by_center, ax=ax)\n",
+    "ax.set_title('Accessions published by SRA/ENA by date')\n",
+    "for item in ax.get_xticklabels():\n",
+    "    item.set_rotation(90)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "metadata": {
+    "papermill": {
+     "duration": 0.202321,
+     "end_time": "2020-09-09T00:37:41.007507",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:40.805186",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "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>instrument_platform</th>\n",
+       "      <th>instrument_model</th>\n",
+       "      <th>accession</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>BGISEQ</td>\n",
+       "      <td>BGISEQ-500</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>CAPILLARY</td>\n",
+       "      <td>AB 3730xL Genetic Analyzer</td>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina Genome Analyzer</td>\n",
+       "      <td>3</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina HiSeq 1500</td>\n",
+       "      <td>13</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina HiSeq 2000</td>\n",
+       "      <td>4</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina HiSeq 2500</td>\n",
+       "      <td>2449</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina HiSeq 4000</td>\n",
+       "      <td>56</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina MiSeq</td>\n",
+       "      <td>8758</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina MiniSeq</td>\n",
+       "      <td>39</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina NovaSeq 6000</td>\n",
+       "      <td>14008</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>Illumina iSeq 100</td>\n",
+       "      <td>391</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>NextSeq 500</td>\n",
+       "      <td>4763</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>NextSeq 550</td>\n",
+       "      <td>12079</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>unspecified</td>\n",
+       "      <td>179</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>14</th>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>Ion Torrent PGM</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>15</th>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>Ion Torrent S5</td>\n",
+       "      <td>420</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>16</th>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>Ion Torrent S5 XL</td>\n",
+       "      <td>14</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>17</th>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>GridION</td>\n",
+       "      <td>10701</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>18</th>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>MinION</td>\n",
+       "      <td>2729</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>19</th>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>PromethION</td>\n",
+       "      <td>57</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "   instrument_platform            instrument_model  accession\n",
+       "0               BGISEQ                  BGISEQ-500          1\n",
+       "1            CAPILLARY  AB 3730xL Genetic Analyzer          7\n",
+       "2             ILLUMINA    Illumina Genome Analyzer          3\n",
+       "3             ILLUMINA         Illumina HiSeq 1500         13\n",
+       "4             ILLUMINA         Illumina HiSeq 2000          4\n",
+       "5             ILLUMINA         Illumina HiSeq 2500       2449\n",
+       "6             ILLUMINA         Illumina HiSeq 4000         56\n",
+       "7             ILLUMINA              Illumina MiSeq       8758\n",
+       "8             ILLUMINA            Illumina MiniSeq         39\n",
+       "9             ILLUMINA       Illumina NovaSeq 6000      14008\n",
+       "10            ILLUMINA           Illumina iSeq 100        391\n",
+       "11            ILLUMINA                 NextSeq 500       4763\n",
+       "12            ILLUMINA                 NextSeq 550      12079\n",
+       "13            ILLUMINA                 unspecified        179\n",
+       "14         ION_TORRENT             Ion Torrent PGM          1\n",
+       "15         ION_TORRENT              Ion Torrent S5        420\n",
+       "16         ION_TORRENT           Ion Torrent S5 XL         14\n",
+       "17     OXFORD_NANOPORE                     GridION      10701\n",
+       "18     OXFORD_NANOPORE                      MinION       2729\n",
+       "19     OXFORD_NANOPORE                  PromethION         57"
+      ]
+     },
+     "execution_count": 10,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "instruments = df.groupby(['instrument_platform', 'instrument_model']).count()['accession'].reset_index()\n",
+    "instruments"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "metadata": {
+    "papermill": {
+     "duration": 0.20133,
+     "end_time": "2020-09-09T00:37:41.222177",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:41.020847",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "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>library_strategy</th>\n",
+       "      <th>instrument_platform</th>\n",
+       "      <th>accession</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>0</th>\n",
+       "      <td>AMPLICON</td>\n",
+       "      <td>CAPILLARY</td>\n",
+       "      <td>7</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>1</th>\n",
+       "      <td>AMPLICON</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>36307</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>2</th>\n",
+       "      <td>AMPLICON</td>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>411</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>3</th>\n",
+       "      <td>AMPLICON</td>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>13010</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>4</th>\n",
+       "      <td>OTHER</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>75</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>5</th>\n",
+       "      <td>RNA-Seq</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>3339</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>6</th>\n",
+       "      <td>RNA-Seq</td>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>6</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>7</th>\n",
+       "      <td>RNA-Seq</td>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>5</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>8</th>\n",
+       "      <td>Targeted-Capture</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>711</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>9</th>\n",
+       "      <td>WGA</td>\n",
+       "      <td>BGISEQ</td>\n",
+       "      <td>1</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>10</th>\n",
+       "      <td>WGA</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>249</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>11</th>\n",
+       "      <td>WGS</td>\n",
+       "      <td>ILLUMINA</td>\n",
+       "      <td>2061</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>12</th>\n",
+       "      <td>WGS</td>\n",
+       "      <td>ION_TORRENT</td>\n",
+       "      <td>18</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>13</th>\n",
+       "      <td>WGS</td>\n",
+       "      <td>OXFORD_NANOPORE</td>\n",
+       "      <td>472</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "    library_strategy instrument_platform  accession\n",
+       "0           AMPLICON           CAPILLARY          7\n",
+       "1           AMPLICON            ILLUMINA      36307\n",
+       "2           AMPLICON         ION_TORRENT        411\n",
+       "3           AMPLICON     OXFORD_NANOPORE      13010\n",
+       "4              OTHER            ILLUMINA         75\n",
+       "5            RNA-Seq            ILLUMINA       3339\n",
+       "6            RNA-Seq         ION_TORRENT          6\n",
+       "7            RNA-Seq     OXFORD_NANOPORE          5\n",
+       "8   Targeted-Capture            ILLUMINA        711\n",
+       "9                WGA              BGISEQ          1\n",
+       "10               WGA            ILLUMINA        249\n",
+       "11               WGS            ILLUMINA       2061\n",
+       "12               WGS         ION_TORRENT         18\n",
+       "13               WGS     OXFORD_NANOPORE        472"
+      ]
+     },
+     "execution_count": 11,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.groupby(['library_strategy', 'instrument_platform']).count()['accession'].reset_index()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "metadata": {
+    "papermill": {
+     "duration": 0.542245,
+     "end_time": "2020-09-09T00:37:41.778131",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:41.235886",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "Text(0.5, 1.0, 'Desposited accessions by Country')"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1440x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "df.country.str.replace(':.*', '').value_counts().plot(kind='bar', figsize=(20, 8)).set_title(\"Desposited accessions by Country\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "metadata": {
+    "papermill": {
+     "duration": 0.675164,
+     "end_time": "2020-09-09T00:37:42.469023",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:41.793859",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "male      3568\n",
+       "female    3515\n",
+       "Name: sex, dtype: int64"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['sex'] = df.apply(axis=1, func=lambda row: row['host_sex'] or row['submitted_host_sex'])\n",
+    "df.sex.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "metadata": {
+    "papermill": {
+     "duration": 0.032187,
+     "end_time": "2020-09-09T00:37:42.516824",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:42.484637",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "nasopharyngeal swab                                                                     4863\n",
+       "human                                                                                   1211\n",
+       "patient isolate                                                                         1106\n",
+       "not collected                                                                            584\n",
+       "nasopharyngeal swabs                                                                     584\n",
+       "nasal swab                                                                               458\n",
+       "Oro-pharyngeal swab                                                                      378\n",
+       "not provided                                                                             334\n",
+       "Nasopharyngeal/oropharyngeal swab                                                        300\n",
+       "nasopharyngeal                                                                           258\n",
+       "not collected&apos;                                                                      204\n",
+       "hospital                                                                                 173\n",
+       "sputum                                                                                    87\n",
+       "nasopharynx                                                                               65\n",
+       "Diagnostic Swab                                                                           65\n",
+       "oropharynx swab                                                                           56\n",
+       "clinical sample                                                                           43\n",
+       "oralpharyngeal                                                                            27\n",
+       "Nasal-Swab and Oro-pharyngeal swab                                                        23\n",
+       "swab                                                                                      17\n",
+       "strain BavPat1                                                                            13\n",
+       "oropharyngeal swab                                                                        10\n",
+       "Wuhan                                                                                      8\n",
+       "bronchoalveolar lavage fluid(BALF)                                                         8\n",
+       "USA, WA                                                                                    8\n",
+       "Nasopharyngeal/throat swab                                                                 7\n",
+       "passage                                                                                    6\n",
+       "Naso-pharyngeal swab                                                                       6\n",
+       "Cercopithecus aethiops                                                                     5\n",
+       "Nasopharyngeal swabs                                                                       5\n",
+       "Oropharyngeal swab                                                                         5\n",
+       "Vero E6 cells supernatant                                                                  5\n",
+       "Naso and/or oropharyngeal swab                                                             5\n",
+       "oropharynx                                                                                 4\n",
+       "culture                                                                                    4\n",
+       "Seattle, WA                                                                                4\n",
+       "throat swab                                                                                4\n",
+       "Deep throat saliva                                                                         3\n",
+       "ropharyngeal swab                                                                          3\n",
+       "bronchoalveolar lavage                                                                     2\n",
+       "Biological sample                                                                          2\n",
+       "tracheal swab                                                                              2\n",
+       "saliva                                                                                     2\n",
+       "Combined nasopharyngeal and oropharyngeal swab                                             2\n",
+       "Siena University hospital                                                                  2\n",
+       "COVID-19 symptomatic patient                                                               2\n",
+       "Jingzhou                                                                                   1\n",
+       "oropharyngeal swab from positive patient in general military hospital in Cairo-Egypt       1\n",
+       "Tianmen                                                                                    1\n",
+       "respiratory nasopharyngeal sample                                                          1\n",
+       "Biological Sample                                                                          1\n",
+       "NP/OP swab                                                                                 1\n",
+       "feca swab                                                                                  1\n",
+       "Nasopharyngeal sample                                                                      1\n",
+       "USA                                                                                        1\n",
+       "cell culure                                                                                1\n",
+       "Name: isolation_source, dtype: int64"
+      ]
+     },
+     "execution_count": 14,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.isolation_source.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "metadata": {
+    "papermill": {
+     "duration": 5.434336,
+     "end_time": "2020-09-09T00:37:47.966953",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:42.532617",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 1440x576 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "ax = df.collection_date.value_counts().sort_index().plot(kind='bar', figsize=(20, 8))\n",
+    "ax.set_title('Collection by date')\n",
+    "for label in ax.xaxis.get_ticklabels()[::2]:\n",
+    "    label.set_visible(False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "False    55660\n",
+       "True      1012\n",
+       "Name: artic, dtype: int64"
+      ]
+     },
+     "execution_count": 16,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['artic'] = df.apply(lambda x: 'artic' in x.to_string().lower(), axis=1)\n",
+    "df.artic.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "df['amplicon_in_metadata'] = df.apply(lambda x: 'amplicon' in x.to_string().lower(), axis=1)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 18,
+   "metadata": {
+    "papermill": {
+     "duration": 0.016678,
+     "end_time": "2020-09-09T00:37:48.000724",
+     "exception": false,
+     "start_time": "2020-09-09T00:37:47.984046",
+     "status": "completed"
+    },
+    "tags": []
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "55737"
+      ]
+     },
+     "execution_count": 18,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sum(~df.country.isna())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "7083"
+      ]
+     },
+     "execution_count": 19,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "sum(~df.sex.isna())"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "subset = df[(~df.sex.isna()) & (~df.country.isna())]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "RECENT_ILLUMINA_MODELS = ['NextSeq 500', 'NextSeq 550', 'Illumina NovaSeq 6000']\n",
+    "NANOPORE_MODELS = ['GridION', 'PromethION', 'MinION'] # Include MinION ?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4238187</th>\n",
+       "      <td>SAMEA6915235</td>\n",
+       "      <td>47444042.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.69982e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238188</th>\n",
+       "      <td>SAMEA6915392</td>\n",
+       "      <td>24758232.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-13</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.44243e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238189</th>\n",
+       "      <td>SAMEA6915293</td>\n",
+       "      <td>49131355.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.83486e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238190</th>\n",
+       "      <td>SAMEA6915304</td>\n",
+       "      <td>45016521.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-02</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.43407e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238191</th>\n",
+       "      <td>SAMEA6915524</td>\n",
+       "      <td>12799114.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.26565e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</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>SRR12537597</th>\n",
+       "      <td>SAMN15918077</td>\n",
+       "      <td>236250203.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537598</th>\n",
+       "      <td>SAMN15918076</td>\n",
+       "      <td>248067278.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537599</th>\n",
+       "      <td>SAMN15918075</td>\n",
+       "      <td>188068675.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537600</th>\n",
+       "      <td>SAMN15918074</td>\n",
+       "      <td>256393966.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537601</th>\n",
+       "      <td>SAMN15918073</td>\n",
+       "      <td>202958641.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5258 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession   base_count cell_line  cell_type  \\\n",
+       "run_accession                                                   \n",
+       "ERR4238187     SAMEA6915235   47444042.0       NaN        NaN   \n",
+       "ERR4238188     SAMEA6915392   24758232.0       NaN        NaN   \n",
+       "ERR4238189     SAMEA6915293   49131355.0       NaN        NaN   \n",
+       "ERR4238190     SAMEA6915304   45016521.0       NaN        NaN   \n",
+       "ERR4238191     SAMEA6915524   12799114.0       NaN        NaN   \n",
+       "...                     ...          ...       ...        ...   \n",
+       "SRR12537597    SAMN15918077  236250203.0       NaN        NaN   \n",
+       "SRR12537598    SAMN15918076  248067278.0       NaN        NaN   \n",
+       "SRR12537599    SAMN15918075  188068675.0       NaN        NaN   \n",
+       "SRR12537600    SAMN15918074  256393966.0       NaN        NaN   \n",
+       "SRR12537601    SAMN15918073  202958641.0       NaN        NaN   \n",
+       "\n",
+       "                                center_name  checklist  \\\n",
+       "run_accession                                            \n",
+       "ERR4238187     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238188     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238189     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238190     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238191     Quadram Institute Bioscience  ERC000033   \n",
+       "...                                     ...        ...   \n",
+       "SRR12537597                      SUB8055754        NaN   \n",
+       "SRR12537598                      SUB8055754        NaN   \n",
+       "SRR12537599                      SUB8055754        NaN   \n",
+       "SRR12537600                      SUB8055754        NaN   \n",
+       "SRR12537601                      SUB8055754        NaN   \n",
+       "\n",
+       "                                                    collected_by  \\\n",
+       "run_accession                                                      \n",
+       "ERR4238187                                   Justin O&apos;Grady   \n",
+       "ERR4238188                                   Justin O&apos;Grady   \n",
+       "ERR4238189                                   Justin O&apos;Grady   \n",
+       "ERR4238190                                   Justin O&apos;Grady   \n",
+       "ERR4238191                                   Justin O&apos;Grady   \n",
+       "...                                                          ...   \n",
+       "SRR12537597    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537598    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537599    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537600    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537601    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "\n",
+       "              collection_date              country cram_index_ftp  ...  \\\n",
+       "run_accession                                                      ...   \n",
+       "ERR4238187         2020-05-11       United Kingdom            NaN  ...   \n",
+       "ERR4238188         2020-05-13       United Kingdom            NaN  ...   \n",
+       "ERR4238189         2020-05-11       United Kingdom            NaN  ...   \n",
+       "ERR4238190         2020-05-02       United Kingdom            NaN  ...   \n",
+       "ERR4238191         2020-05-11       United Kingdom            NaN  ...   \n",
+       "...                       ...                  ...            ...  ...   \n",
+       "SRR12537597        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537598        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537599        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537600        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537601        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "\n",
+       "              sub_species sub_strain submitted_bytes submitted_format  \\\n",
+       "run_accession                                                           \n",
+       "ERR4238187            NaN        NaN     4.69982e+07              BAM   \n",
+       "ERR4238188            NaN        NaN     2.44243e+07              BAM   \n",
+       "ERR4238189            NaN        NaN     4.83486e+07              BAM   \n",
+       "ERR4238190            NaN        NaN     4.43407e+07              BAM   \n",
+       "ERR4238191            NaN        NaN     1.26565e+07              BAM   \n",
+       "...                   ...        ...             ...              ...   \n",
+       "SRR12537597           NaN        NaN             NaN              NaN   \n",
+       "SRR12537598           NaN        NaN             NaN              NaN   \n",
+       "SRR12537599           NaN        NaN             NaN              NaN   \n",
+       "SRR12537600           NaN        NaN             NaN              NaN   \n",
+       "SRR12537601           NaN        NaN             NaN              NaN   \n",
+       "\n",
+       "              submitted_host_sex submitted_sex   tax_id     sex  artic  \\\n",
+       "run_accession                                                            \n",
+       "ERR4238187                  male           NaN  2697049    male   True   \n",
+       "ERR4238188                female           NaN  2697049  female   True   \n",
+       "ERR4238189                  male           NaN  2697049    male   True   \n",
+       "ERR4238190                female           NaN  2697049  female   True   \n",
+       "ERR4238191                  male           NaN  2697049    male   True   \n",
+       "...                          ...           ...      ...     ...    ...   \n",
+       "SRR12537597                 male           NaN  2697049    male  False   \n",
+       "SRR12537598               female           NaN  2697049  female  False   \n",
+       "SRR12537599               female           NaN  2697049  female  False   \n",
+       "SRR12537600                 male           NaN  2697049    male  False   \n",
+       "SRR12537601                 male           NaN  2697049    male  False   \n",
+       "\n",
+       "              amplicon_in_metadata  \n",
+       "run_accession                       \n",
+       "ERR4238187                    True  \n",
+       "ERR4238188                    True  \n",
+       "ERR4238189                    True  \n",
+       "ERR4238190                    True  \n",
+       "ERR4238191                    True  \n",
+       "...                            ...  \n",
+       "SRR12537597                   True  \n",
+       "SRR12537598                   True  \n",
+       "SRR12537599                   True  \n",
+       "SRR12537600                   True  \n",
+       "SRR12537601                   True  \n",
+       "\n",
+       "[5258 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 22,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina = subset[subset.instrument_model.isin(RECENT_ILLUMINA_MODELS)]\n",
+    "illumina"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>SRR11397722</th>\n",
+       "      <td>SAMN14422707</td>\n",
+       "      <td>381016503.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7178017</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Victorian Infectious Diseases Reference Labora...</td>\n",
+       "      <td>2020-02-08</td>\n",
+       "      <td>Australia: Melbourne, Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11397723</th>\n",
+       "      <td>SAMN14422706</td>\n",
+       "      <td>187769236.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7178017</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Victorian Infectious Diseases Reference Labora...</td>\n",
+       "      <td>2020-03-06</td>\n",
+       "      <td>Australia: Melbourne, Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11397724</th>\n",
+       "      <td>SAMN14422705</td>\n",
+       "      <td>221112159.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7178017</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Victorian Infectious Diseases Reference Labora...</td>\n",
+       "      <td>2020-03-05</td>\n",
+       "      <td>Australia: Melbourne, Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11397725</th>\n",
+       "      <td>SAMN14422704</td>\n",
+       "      <td>236813764.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7178017</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Victorian Infectious Diseases Reference Labora...</td>\n",
+       "      <td>2020-03-02</td>\n",
+       "      <td>Australia: Melbourne, Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11397726</th>\n",
+       "      <td>SAMN14422703</td>\n",
+       "      <td>363340838.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7178017</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Victorian Infectious Diseases Reference Labora...</td>\n",
+       "      <td>2020-01-25</td>\n",
+       "      <td>Australia: Melbourne, Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</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>SRR12480580</th>\n",
+       "      <td>SAMN15691610</td>\n",
+       "      <td>6835912.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-24</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480581</th>\n",
+       "      <td>SAMN15691609</td>\n",
+       "      <td>7529477.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480582</th>\n",
+       "      <td>SAMN15691608</td>\n",
+       "      <td>6314669.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-28</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480583</th>\n",
+       "      <td>SAMN15691607</td>\n",
+       "      <td>7533745.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-26</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12486810</th>\n",
+       "      <td>SAMN14647199</td>\n",
+       "      <td>86575096.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7942082</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Public Health Ontario</td>\n",
+       "      <td>2020-01-23</td>\n",
+       "      <td>Canada: Ontario</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>466 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession   base_count cell_line  cell_type center_name  \\\n",
+       "run_accession                                                               \n",
+       "SRR11397722    SAMN14422707  381016503.0       NaN        NaN  SUB7178017   \n",
+       "SRR11397723    SAMN14422706  187769236.0       NaN        NaN  SUB7178017   \n",
+       "SRR11397724    SAMN14422705  221112159.0       NaN        NaN  SUB7178017   \n",
+       "SRR11397725    SAMN14422704  236813764.0       NaN        NaN  SUB7178017   \n",
+       "SRR11397726    SAMN14422703  363340838.0       NaN        NaN  SUB7178017   \n",
+       "...                     ...          ...       ...        ...         ...   \n",
+       "SRR12480580    SAMN15691610    6835912.0       NaN        NaN  SUB7938744   \n",
+       "SRR12480581    SAMN15691609    7529477.0       NaN        NaN  SUB7938744   \n",
+       "SRR12480582    SAMN15691608    6314669.0       NaN        NaN  SUB7938744   \n",
+       "SRR12480583    SAMN15691607    7533745.0       NaN        NaN  SUB7938744   \n",
+       "SRR12486810    SAMN14647199   86575096.0       NaN        NaN  SUB7942082   \n",
+       "\n",
+       "              checklist                                       collected_by  \\\n",
+       "run_accession                                                                \n",
+       "SRR11397722         NaN  Victorian Infectious Diseases Reference Labora...   \n",
+       "SRR11397723         NaN  Victorian Infectious Diseases Reference Labora...   \n",
+       "SRR11397724         NaN  Victorian Infectious Diseases Reference Labora...   \n",
+       "SRR11397725         NaN  Victorian Infectious Diseases Reference Labora...   \n",
+       "SRR11397726         NaN  Victorian Infectious Diseases Reference Labora...   \n",
+       "...                 ...                                                ...   \n",
+       "SRR12480580         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480581         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480582         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480583         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12486810         NaN                              Public Health Ontario   \n",
+       "\n",
+       "              collection_date                         country cram_index_ftp  \\\n",
+       "run_accession                                                                  \n",
+       "SRR11397722        2020-02-08  Australia: Melbourne, Victoria            NaN   \n",
+       "SRR11397723        2020-03-06  Australia: Melbourne, Victoria            NaN   \n",
+       "SRR11397724        2020-03-05  Australia: Melbourne, Victoria            NaN   \n",
+       "SRR11397725        2020-03-02  Australia: Melbourne, Victoria            NaN   \n",
+       "SRR11397726        2020-01-25  Australia: Melbourne, Victoria            NaN   \n",
+       "...                       ...                             ...            ...   \n",
+       "SRR12480580        2020-03-24                   USA: Maryland            NaN   \n",
+       "SRR12480581        2020-03-30                   USA: Maryland            NaN   \n",
+       "SRR12480582        2020-03-28                         USA: DC            NaN   \n",
+       "SRR12480583        2020-03-26                         USA: DC            NaN   \n",
+       "SRR12486810        2020-01-23                 Canada: Ontario            NaN   \n",
+       "\n",
+       "               ... sub_species sub_strain submitted_bytes submitted_format  \\\n",
+       "run_accession  ...                                                           \n",
+       "SRR11397722    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR11397723    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR11397724    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR11397725    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR11397726    ...         NaN        NaN             NaN              NaN   \n",
+       "...            ...         ...        ...             ...              ...   \n",
+       "SRR12480580    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR12480581    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR12480582    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR12480583    ...         NaN        NaN             NaN              NaN   \n",
+       "SRR12486810    ...         NaN        NaN             NaN              NaN   \n",
+       "\n",
+       "              submitted_host_sex submitted_sex   tax_id     sex  artic  \\\n",
+       "run_accession                                                            \n",
+       "SRR11397722               female           NaN  2697049  female  False   \n",
+       "SRR11397723               female           NaN  2697049  female  False   \n",
+       "SRR11397724                 male           NaN  2697049    male  False   \n",
+       "SRR11397725                 male           NaN  2697049    male  False   \n",
+       "SRR11397726                 male           NaN  2697049    male  False   \n",
+       "...                          ...           ...      ...     ...    ...   \n",
+       "SRR12480580               female           NaN  2697049  female   True   \n",
+       "SRR12480581               female           NaN  2697049  female   True   \n",
+       "SRR12480582                 male           NaN  2697049    male   True   \n",
+       "SRR12480583               female           NaN  2697049  female   True   \n",
+       "SRR12486810                 male           NaN  2697049    male  False   \n",
+       "\n",
+       "              amplicon_in_metadata  \n",
+       "run_accession                       \n",
+       "SRR11397722                   True  \n",
+       "SRR11397723                   True  \n",
+       "SRR11397724                   True  \n",
+       "SRR11397725                   True  \n",
+       "SRR11397726                   True  \n",
+       "...                            ...  \n",
+       "SRR12480580                   True  \n",
+       "SRR12480581                   True  \n",
+       "SRR12480582                   True  \n",
+       "SRR12480583                   True  \n",
+       "SRR12486810                  False  \n",
+       "\n",
+       "[466 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 23,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nanopore = subset[subset.instrument_model.isin(NANOPORE_MODELS)]\n",
+    "nanopore"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AMPLICON            49735\n",
+       "RNA-Seq              3350\n",
+       "WGS                  2551\n",
+       "Targeted-Capture      711\n",
+       "WGA                   250\n",
+       "OTHER                  75\n",
+       "Name: library_strategy, dtype: int64"
+      ]
+     },
+     "execution_count": 24,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df.library_strategy.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AMPLICON    5165\n",
+       "WGS           81\n",
+       "RNA-Seq       12\n",
+       "Name: library_strategy, dtype: int64"
+      ]
+     },
+     "execution_count": 25,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina.library_strategy.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AMPLICON    465\n",
+       "WGS           1\n",
+       "Name: library_strategy, dtype: int64"
+      ]
+     },
+     "execution_count": 26,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nanopore.library_strategy.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['PCR', 'Hybrid Selection', 'RANDOM'], dtype=object)"
+      ]
+     },
+     "execution_count": 27,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina.library_selection.unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array(['VIRAL RNA', 'GENOMIC', 'TRANSCRIPTOMIC'], dtype=object)"
+      ]
+     },
+     "execution_count": 28,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina.library_source.unique()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4080473</th>\n",
+       "      <td>SAMEA6798401</td>\n",
+       "      <td>158607300.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>136591936</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080474</th>\n",
+       "      <td>SAMEA6798402</td>\n",
+       "      <td>146257565.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>125862765</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080475</th>\n",
+       "      <td>SAMEA6798403</td>\n",
+       "      <td>122898175.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>106116129</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080476</th>\n",
+       "      <td>SAMEA6798404</td>\n",
+       "      <td>165498931.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>142761688</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080477</th>\n",
+       "      <td>SAMEA6798405</td>\n",
+       "      <td>169444073.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>146011388</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</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>SRR12480582</th>\n",
+       "      <td>SAMN15691608</td>\n",
+       "      <td>6314669.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-28</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480583</th>\n",
+       "      <td>SAMN15691607</td>\n",
+       "      <td>7533745.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-26</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12486810</th>\n",
+       "      <td>SAMN14647199</td>\n",
+       "      <td>86575096.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7942082</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Public Health Ontario</td>\n",
+       "      <td>2020-01-23</td>\n",
+       "      <td>Canada: Ontario</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12491159</th>\n",
+       "      <td>SAMN15872123</td>\n",
+       "      <td>33022230.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7920134</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-04-01</td>\n",
+       "      <td>Italy: Siena</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12491160</th>\n",
+       "      <td>SAMN15872123</td>\n",
+       "      <td>4448128.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7920134</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-04-01</td>\n",
+       "      <td>Italy: Siena</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>13487 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession   base_count cell_line  cell_type  \\\n",
+       "run_accession                                                   \n",
+       "ERR4080473     SAMEA6798401  158607300.0       NaN        NaN   \n",
+       "ERR4080474     SAMEA6798402  146257565.0       NaN        NaN   \n",
+       "ERR4080475     SAMEA6798403  122898175.0       NaN        NaN   \n",
+       "ERR4080476     SAMEA6798404  165498931.0       NaN        NaN   \n",
+       "ERR4080477     SAMEA6798405  169444073.0       NaN        NaN   \n",
+       "...                     ...          ...       ...        ...   \n",
+       "SRR12480582    SAMN15691608    6314669.0       NaN        NaN   \n",
+       "SRR12480583    SAMN15691607    7533745.0       NaN        NaN   \n",
+       "SRR12486810    SAMN14647199   86575096.0       NaN        NaN   \n",
+       "SRR12491159    SAMN15872123   33022230.0       NaN        NaN   \n",
+       "SRR12491160    SAMN15872123    4448128.0       NaN        NaN   \n",
+       "\n",
+       "                      center_name  checklist             collected_by  \\\n",
+       "run_accession                                                           \n",
+       "ERR4080473     AALBORG UNIVERSITY  ERC000033             not provided   \n",
+       "ERR4080474     AALBORG UNIVERSITY  ERC000033             not provided   \n",
+       "ERR4080475     AALBORG UNIVERSITY  ERC000033             not provided   \n",
+       "ERR4080476     AALBORG UNIVERSITY  ERC000033             not provided   \n",
+       "ERR4080477     AALBORG UNIVERSITY  ERC000033             not provided   \n",
+       "...                           ...        ...                      ...   \n",
+       "SRR12480582            SUB7938744        NaN  Johns Hopkins Pathology   \n",
+       "SRR12480583            SUB7938744        NaN  Johns Hopkins Pathology   \n",
+       "SRR12486810            SUB7942082        NaN    Public Health Ontario   \n",
+       "SRR12491159            SUB7920134        NaN                      NaN   \n",
+       "SRR12491160            SUB7920134        NaN                      NaN   \n",
+       "\n",
+       "              collection_date          country cram_index_ftp  ...  \\\n",
+       "run_accession                                                  ...   \n",
+       "ERR4080473         2020-03-10          Denmark            NaN  ...   \n",
+       "ERR4080474         2020-03-10          Denmark            NaN  ...   \n",
+       "ERR4080475         2020-03-10          Denmark            NaN  ...   \n",
+       "ERR4080476         2020-03-10          Denmark            NaN  ...   \n",
+       "ERR4080477         2020-03-10          Denmark            NaN  ...   \n",
+       "...                       ...              ...            ...  ...   \n",
+       "SRR12480582        2020-03-28          USA: DC            NaN  ...   \n",
+       "SRR12480583        2020-03-26          USA: DC            NaN  ...   \n",
+       "SRR12486810        2020-01-23  Canada: Ontario            NaN  ...   \n",
+       "SRR12491159        2020-04-01     Italy: Siena            NaN  ...   \n",
+       "SRR12491160        2020-04-01     Italy: Siena            NaN  ...   \n",
+       "\n",
+       "              sub_species sub_strain submitted_bytes submitted_format  \\\n",
+       "run_accession                                                           \n",
+       "ERR4080473            NaN        NaN       136591936            FASTQ   \n",
+       "ERR4080474            NaN        NaN       125862765            FASTQ   \n",
+       "ERR4080475            NaN        NaN       106116129            FASTQ   \n",
+       "ERR4080476            NaN        NaN       142761688            FASTQ   \n",
+       "ERR4080477            NaN        NaN       146011388            FASTQ   \n",
+       "...                   ...        ...             ...              ...   \n",
+       "SRR12480582           NaN        NaN             NaN              NaN   \n",
+       "SRR12480583           NaN        NaN             NaN              NaN   \n",
+       "SRR12486810           NaN        NaN             NaN              NaN   \n",
+       "SRR12491159           NaN        NaN             NaN              NaN   \n",
+       "SRR12491160           NaN        NaN             NaN              NaN   \n",
+       "\n",
+       "              submitted_host_sex submitted_sex   tax_id     sex  artic  \\\n",
+       "run_accession                                                            \n",
+       "ERR4080473          not provided           NaN  2697049     NaN  False   \n",
+       "ERR4080474          not provided           NaN  2697049     NaN  False   \n",
+       "ERR4080475          not provided           NaN  2697049     NaN  False   \n",
+       "ERR4080476          not provided           NaN  2697049     NaN  False   \n",
+       "ERR4080477          not provided           NaN  2697049     NaN  False   \n",
+       "...                          ...           ...      ...     ...    ...   \n",
+       "SRR12480582                 male           NaN  2697049    male   True   \n",
+       "SRR12480583               female           NaN  2697049  female   True   \n",
+       "SRR12486810                 male           NaN  2697049    male  False   \n",
+       "SRR12491159                  NaN           NaN  2697049     NaN  False   \n",
+       "SRR12491160                  NaN           NaN  2697049     NaN  False   \n",
+       "\n",
+       "              amplicon_in_metadata  \n",
+       "run_accession                       \n",
+       "ERR4080473                    True  \n",
+       "ERR4080474                    True  \n",
+       "ERR4080475                    True  \n",
+       "ERR4080476                    True  \n",
+       "ERR4080477                    True  \n",
+       "...                            ...  \n",
+       "SRR12480582                   True  \n",
+       "SRR12480583                   True  \n",
+       "SRR12486810                  False  \n",
+       "SRR12491159                   True  \n",
+       "SRR12491160                  False  \n",
+       "\n",
+       "[13487 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 29,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nanopore_no_metadata_filter = df[df.instrument_model.isin(NANOPORE_MODELS)]\n",
+    "nanopore_no_metadata_filter"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "AMPLICON    13010\n",
+       "WGS           472\n",
+       "RNA-Seq         5\n",
+       "Name: library_strategy, dtype: int64"
+      ]
+     },
+     "execution_count": 30,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "nanopore_no_metadata_filter.library_strategy.value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>SRR11140745</th>\n",
+       "      <td>SAMN14154204</td>\n",
+       "      <td>2.609568e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB6993965</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Wisconsin State Lab of Hygiene</td>\n",
+       "      <td>2020-02-14</td>\n",
+       "      <td>USA:WI,Madison</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11140747</th>\n",
+       "      <td>SAMN14154202</td>\n",
+       "      <td>3.590010e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB6993965</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Wisconsin State Lab of Hygiene</td>\n",
+       "      <td>2020-02-14</td>\n",
+       "      <td>USA:WI,Madison</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11140749</th>\n",
+       "      <td>SAMN14154200</td>\n",
+       "      <td>3.041134e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB6993965</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Wisconsin State Lab of Hygiene</td>\n",
+       "      <td>2020-02-14</td>\n",
+       "      <td>USA:WI,Madison</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11140751</th>\n",
+       "      <td>SAMN14154198</td>\n",
+       "      <td>2.369616e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB6993965</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Wisconsin State Lab of Hygiene</td>\n",
+       "      <td>2020-02-14</td>\n",
+       "      <td>USA:WI,Madison</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178050</th>\n",
+       "      <td>SAMN14168020</td>\n",
+       "      <td>1.569519e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-29</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178051</th>\n",
+       "      <td>SAMN14168019</td>\n",
+       "      <td>4.216227e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-27</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178052</th>\n",
+       "      <td>SAMN14168018</td>\n",
+       "      <td>1.000052e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-29</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178053</th>\n",
+       "      <td>SAMN14168017</td>\n",
+       "      <td>3.636258e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-27</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178054</th>\n",
+       "      <td>SAMN14168016</td>\n",
+       "      <td>3.163351e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-27</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178055</th>\n",
+       "      <td>SAMN14168015</td>\n",
+       "      <td>6.003789e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-24</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178056</th>\n",
+       "      <td>SAMN14168014</td>\n",
+       "      <td>4.437900e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-24</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11178057</th>\n",
+       "      <td>SAMN14168013</td>\n",
+       "      <td>5.188641e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7021260</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-23</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11393271</th>\n",
+       "      <td>SAMN14428244</td>\n",
+       "      <td>1.581263e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7181455</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>UWHC</td>\n",
+       "      <td>2020-03-15</td>\n",
+       "      <td>USA:Wisconsin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11393272</th>\n",
+       "      <td>SAMN14428243</td>\n",
+       "      <td>8.912930e+05</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7181455</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>UWHC</td>\n",
+       "      <td>2020-03-15</td>\n",
+       "      <td>USA:Wisconsin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11393273</th>\n",
+       "      <td>SAMN14428242</td>\n",
+       "      <td>2.889738e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7181455</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>UWHC</td>\n",
+       "      <td>2020-03-14</td>\n",
+       "      <td>USA:Wisconsin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11393274</th>\n",
+       "      <td>SAMN14428241</td>\n",
+       "      <td>1.570473e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7181455</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>UWHC</td>\n",
+       "      <td>2020-03-15</td>\n",
+       "      <td>USA:Wisconsin</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11586701</th>\n",
+       "      <td>SAMN14657842</td>\n",
+       "      <td>5.575642e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7296356</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-30</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11586702</th>\n",
+       "      <td>SAMN14657841</td>\n",
+       "      <td>7.373448e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7296356</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-02-02</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11586703</th>\n",
+       "      <td>SAMN14657840</td>\n",
+       "      <td>2.529579e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7296356</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-31</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11586704</th>\n",
+       "      <td>SAMN14657839</td>\n",
+       "      <td>5.382173e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7296356</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-30</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11586705</th>\n",
+       "      <td>SAMN14657838</td>\n",
+       "      <td>1.828475e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7296356</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2020-01-24</td>\n",
+       "      <td>Hong Kong</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR11593367</th>\n",
+       "      <td>SAMN14652938</td>\n",
+       "      <td>5.574520e+05</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7314882</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Center of Medical Microbiology, Virology, and ...</td>\n",
+       "      <td>2020-03-17</td>\n",
+       "      <td>Germany: Dusseldorf</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109250</th>\n",
+       "      <td>SAMN15399820</td>\n",
+       "      <td>5.842415e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-04-01</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109251</th>\n",
+       "      <td>SAMN15399819</td>\n",
+       "      <td>3.217345e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109252</th>\n",
+       "      <td>SAMN15399818</td>\n",
+       "      <td>5.150105e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109253</th>\n",
+       "      <td>SAMN15399817</td>\n",
+       "      <td>4.025458e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-04-03</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109254</th>\n",
+       "      <td>SAMN15399816</td>\n",
+       "      <td>8.447856e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12109255</th>\n",
+       "      <td>SAMN15399815</td>\n",
+       "      <td>3.268144e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7685154</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>LNR National Reference Laboratory, Mohammed VI...</td>\n",
+       "      <td>2020-04-13</td>\n",
+       "      <td>Morocco: casablanca</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12277390</th>\n",
+       "      <td>SAMN15578213</td>\n",
+       "      <td>9.756664e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7789344</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>BEI Resources/American Type and Culture Collec...</td>\n",
+       "      <td>2020-01-19</td>\n",
+       "      <td>USA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12277391</th>\n",
+       "      <td>SAMN15546737</td>\n",
+       "      <td>2.165307e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7789344</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Center for Molecular Diagnostics, UAMS</td>\n",
+       "      <td>2020-07-02</td>\n",
+       "      <td>USA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12277392</th>\n",
+       "      <td>SAMN15546736</td>\n",
+       "      <td>1.900171e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7789344</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Center for Molecular Diagnostics, UAMS</td>\n",
+       "      <td>2020-07-02</td>\n",
+       "      <td>USA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12486810</th>\n",
+       "      <td>SAMN14647199</td>\n",
+       "      <td>8.657510e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7942082</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Public Health Ontario</td>\n",
+       "      <td>2020-01-23</td>\n",
+       "      <td>Canada: Ontario</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>32 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession    base_count cell_line  cell_type center_name  \\\n",
+       "run_accession                                                                \n",
+       "SRR11140745    SAMN14154204  2.609568e+08       NaN        NaN  SUB6993965   \n",
+       "SRR11140747    SAMN14154202  3.590010e+08       NaN        NaN  SUB6993965   \n",
+       "SRR11140749    SAMN14154200  3.041134e+08       NaN        NaN  SUB6993965   \n",
+       "SRR11140751    SAMN14154198  2.369616e+07       NaN        NaN  SUB6993965   \n",
+       "SRR11178050    SAMN14168020  1.569519e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178051    SAMN14168019  4.216227e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178052    SAMN14168018  1.000052e+09       NaN        NaN  SUB7021260   \n",
+       "SRR11178053    SAMN14168017  3.636258e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178054    SAMN14168016  3.163351e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178055    SAMN14168015  6.003789e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178056    SAMN14168014  4.437900e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11178057    SAMN14168013  5.188641e+08       NaN        NaN  SUB7021260   \n",
+       "SRR11393271    SAMN14428244  1.581263e+06       NaN        NaN  SUB7181455   \n",
+       "SRR11393272    SAMN14428243  8.912930e+05       NaN        NaN  SUB7181455   \n",
+       "SRR11393273    SAMN14428242  2.889738e+08       NaN        NaN  SUB7181455   \n",
+       "SRR11393274    SAMN14428241  1.570473e+07       NaN        NaN  SUB7181455   \n",
+       "SRR11586701    SAMN14657842  5.575642e+08       NaN        NaN  SUB7296356   \n",
+       "SRR11586702    SAMN14657841  7.373448e+07       NaN        NaN  SUB7296356   \n",
+       "SRR11586703    SAMN14657840  2.529579e+08       NaN        NaN  SUB7296356   \n",
+       "SRR11586704    SAMN14657839  5.382173e+08       NaN        NaN  SUB7296356   \n",
+       "SRR11586705    SAMN14657838  1.828475e+08       NaN        NaN  SUB7296356   \n",
+       "SRR11593367    SAMN14652938  5.574520e+05       NaN        NaN  SUB7314882   \n",
+       "SRR12109250    SAMN15399820  5.842415e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12109251    SAMN15399819  3.217345e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12109252    SAMN15399818  5.150105e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12109253    SAMN15399817  4.025458e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12109254    SAMN15399816  8.447856e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12109255    SAMN15399815  3.268144e+07       NaN        NaN  SUB7685154   \n",
+       "SRR12277390    SAMN15578213  9.756664e+08       NaN        NaN  SUB7789344   \n",
+       "SRR12277391    SAMN15546737  2.165307e+09       NaN        NaN  SUB7789344   \n",
+       "SRR12277392    SAMN15546736  1.900171e+09       NaN        NaN  SUB7789344   \n",
+       "SRR12486810    SAMN14647199  8.657510e+07       NaN        NaN  SUB7942082   \n",
+       "\n",
+       "              checklist                                       collected_by  \\\n",
+       "run_accession                                                                \n",
+       "SRR11140745         NaN                     Wisconsin State Lab of Hygiene   \n",
+       "SRR11140747         NaN                     Wisconsin State Lab of Hygiene   \n",
+       "SRR11140749         NaN                     Wisconsin State Lab of Hygiene   \n",
+       "SRR11140751         NaN                     Wisconsin State Lab of Hygiene   \n",
+       "SRR11178050         NaN                                                NaN   \n",
+       "SRR11178051         NaN                                                NaN   \n",
+       "SRR11178052         NaN                                                NaN   \n",
+       "SRR11178053         NaN                                                NaN   \n",
+       "SRR11178054         NaN                                                NaN   \n",
+       "SRR11178055         NaN                                                NaN   \n",
+       "SRR11178056         NaN                                                NaN   \n",
+       "SRR11178057         NaN                                                NaN   \n",
+       "SRR11393271         NaN                                               UWHC   \n",
+       "SRR11393272         NaN                                               UWHC   \n",
+       "SRR11393273         NaN                                               UWHC   \n",
+       "SRR11393274         NaN                                               UWHC   \n",
+       "SRR11586701         NaN                                                NaN   \n",
+       "SRR11586702         NaN                                                NaN   \n",
+       "SRR11586703         NaN                                                NaN   \n",
+       "SRR11586704         NaN                                                NaN   \n",
+       "SRR11586705         NaN                                                NaN   \n",
+       "SRR11593367         NaN  Center of Medical Microbiology, Virology, and ...   \n",
+       "SRR12109250         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12109251         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12109252         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12109253         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12109254         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12109255         NaN  LNR National Reference Laboratory, Mohammed VI...   \n",
+       "SRR12277390         NaN  BEI Resources/American Type and Culture Collec...   \n",
+       "SRR12277391         NaN             Center for Molecular Diagnostics, UAMS   \n",
+       "SRR12277392         NaN             Center for Molecular Diagnostics, UAMS   \n",
+       "SRR12486810         NaN                              Public Health Ontario   \n",
+       "\n",
+       "              collection_date              country cram_index_ftp  ...  \\\n",
+       "run_accession                                                      ...   \n",
+       "SRR11140745        2020-02-14       USA:WI,Madison            NaN  ...   \n",
+       "SRR11140747        2020-02-14       USA:WI,Madison            NaN  ...   \n",
+       "SRR11140749        2020-02-14       USA:WI,Madison            NaN  ...   \n",
+       "SRR11140751        2020-02-14       USA:WI,Madison            NaN  ...   \n",
+       "SRR11178050        2020-01-29            Hong Kong            NaN  ...   \n",
+       "SRR11178051        2020-01-27            Hong Kong            NaN  ...   \n",
+       "SRR11178052        2020-01-29            Hong Kong            NaN  ...   \n",
+       "SRR11178053        2020-01-27            Hong Kong            NaN  ...   \n",
+       "SRR11178054        2020-01-27            Hong Kong            NaN  ...   \n",
+       "SRR11178055        2020-01-24            Hong Kong            NaN  ...   \n",
+       "SRR11178056        2020-01-24            Hong Kong            NaN  ...   \n",
+       "SRR11178057        2020-01-23            Hong Kong            NaN  ...   \n",
+       "SRR11393271        2020-03-15        USA:Wisconsin            NaN  ...   \n",
+       "SRR11393272        2020-03-15        USA:Wisconsin            NaN  ...   \n",
+       "SRR11393273        2020-03-14        USA:Wisconsin            NaN  ...   \n",
+       "SRR11393274        2020-03-15        USA:Wisconsin            NaN  ...   \n",
+       "SRR11586701        2020-01-30            Hong Kong            NaN  ...   \n",
+       "SRR11586702        2020-02-02            Hong Kong            NaN  ...   \n",
+       "SRR11586703        2020-01-31            Hong Kong            NaN  ...   \n",
+       "SRR11586704        2020-01-30            Hong Kong            NaN  ...   \n",
+       "SRR11586705        2020-01-24            Hong Kong            NaN  ...   \n",
+       "SRR11593367        2020-03-17  Germany: Dusseldorf            NaN  ...   \n",
+       "SRR12109250        2020-04-01  Morocco: casablanca            NaN  ...   \n",
+       "SRR12109251        2020-03-30  Morocco: casablanca            NaN  ...   \n",
+       "SRR12109252        2020-03-30  Morocco: casablanca            NaN  ...   \n",
+       "SRR12109253        2020-04-03  Morocco: casablanca            NaN  ...   \n",
+       "SRR12109254        2020-03-30  Morocco: casablanca            NaN  ...   \n",
+       "SRR12109255        2020-04-13  Morocco: casablanca            NaN  ...   \n",
+       "SRR12277390        2020-01-19                  USA            NaN  ...   \n",
+       "SRR12277391        2020-07-02                  USA            NaN  ...   \n",
+       "SRR12277392        2020-07-02                  USA            NaN  ...   \n",
+       "SRR12486810        2020-01-23      Canada: Ontario            NaN  ...   \n",
+       "\n",
+       "              sub_species sub_strain submitted_bytes submitted_format  \\\n",
+       "run_accession                                                           \n",
+       "SRR11140745           NaN        NaN             NaN              NaN   \n",
+       "SRR11140747           NaN        NaN             NaN              NaN   \n",
+       "SRR11140749           NaN        NaN             NaN              NaN   \n",
+       "SRR11140751           NaN        NaN             NaN              NaN   \n",
+       "SRR11178050           NaN        NaN             NaN              NaN   \n",
+       "SRR11178051           NaN        NaN             NaN              NaN   \n",
+       "SRR11178052           NaN        NaN             NaN              NaN   \n",
+       "SRR11178053           NaN        NaN             NaN              NaN   \n",
+       "SRR11178054           NaN        NaN             NaN              NaN   \n",
+       "SRR11178055           NaN        NaN             NaN              NaN   \n",
+       "SRR11178056           NaN        NaN             NaN              NaN   \n",
+       "SRR11178057           NaN        NaN             NaN              NaN   \n",
+       "SRR11393271           NaN        NaN             NaN              NaN   \n",
+       "SRR11393272           NaN        NaN             NaN              NaN   \n",
+       "SRR11393273           NaN        NaN             NaN              NaN   \n",
+       "SRR11393274           NaN        NaN             NaN              NaN   \n",
+       "SRR11586701           NaN        NaN             NaN              NaN   \n",
+       "SRR11586702           NaN        NaN             NaN              NaN   \n",
+       "SRR11586703           NaN        NaN             NaN              NaN   \n",
+       "SRR11586704           NaN        NaN             NaN              NaN   \n",
+       "SRR11586705           NaN        NaN             NaN              NaN   \n",
+       "SRR11593367           NaN        NaN             NaN              NaN   \n",
+       "SRR12109250           NaN        NaN             NaN              NaN   \n",
+       "SRR12109251           NaN        NaN             NaN              NaN   \n",
+       "SRR12109252           NaN        NaN             NaN              NaN   \n",
+       "SRR12109253           NaN        NaN             NaN              NaN   \n",
+       "SRR12109254           NaN        NaN             NaN              NaN   \n",
+       "SRR12109255           NaN        NaN             NaN              NaN   \n",
+       "SRR12277390           NaN        NaN             NaN              NaN   \n",
+       "SRR12277391           NaN        NaN             NaN              NaN   \n",
+       "SRR12277392           NaN        NaN             NaN              NaN   \n",
+       "SRR12486810           NaN        NaN             NaN              NaN   \n",
+       "\n",
+       "              submitted_host_sex submitted_sex   tax_id   sex  artic  \\\n",
+       "run_accession                                                          \n",
+       "SRR11140745                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11140747                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11140749                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11140751                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178050                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178051                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178052                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178053                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178054                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178055                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178056                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11178057                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11393271                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11393272                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11393273                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11393274                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11586701                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11586702                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11586703                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11586704                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11586705                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR11593367                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109250                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109251                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109252                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109253                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109254                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12109255                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12277390                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12277391                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12277392                  NaN           NaN  2697049   NaN  False   \n",
+       "SRR12486810                 male           NaN  2697049  male  False   \n",
+       "\n",
+       "              amplicon_in_metadata  \n",
+       "run_accession                       \n",
+       "SRR11140745                  False  \n",
+       "SRR11140747                  False  \n",
+       "SRR11140749                  False  \n",
+       "SRR11140751                  False  \n",
+       "SRR11178050                  False  \n",
+       "SRR11178051                  False  \n",
+       "SRR11178052                  False  \n",
+       "SRR11178053                  False  \n",
+       "SRR11178054                  False  \n",
+       "SRR11178055                  False  \n",
+       "SRR11178056                  False  \n",
+       "SRR11178057                  False  \n",
+       "SRR11393271                  False  \n",
+       "SRR11393272                  False  \n",
+       "SRR11393273                  False  \n",
+       "SRR11393274                  False  \n",
+       "SRR11586701                  False  \n",
+       "SRR11586702                  False  \n",
+       "SRR11586703                  False  \n",
+       "SRR11586704                  False  \n",
+       "SRR11586705                  False  \n",
+       "SRR11593367                  False  \n",
+       "SRR12109250                  False  \n",
+       "SRR12109251                  False  \n",
+       "SRR12109252                  False  \n",
+       "SRR12109253                  False  \n",
+       "SRR12109254                  False  \n",
+       "SRR12109255                  False  \n",
+       "SRR12277390                  False  \n",
+       "SRR12277391                  False  \n",
+       "SRR12277392                  False  \n",
+       "SRR12486810                  False  \n",
+       "\n",
+       "[32 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "metagenomic_nanopore_maybe = nanopore_no_metadata_filter[(nanopore_no_metadata_filter.library_strategy == 'WGS') & (nanopore_no_metadata_filter.artic == False) & (nanopore_no_metadata_filter.amplicon_in_metadata == False)]\n",
+    "metagenomic_nanopore_maybe[['run_accession', 'study_accession']].to_csv('nanopore_metagenomic_accessions.tsv', sep='\\t', index=None)\n",
+    "metagenomic_nanopore_maybe"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 46,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>SRR12336747</th>\n",
+       "      <td>SAMN15659003</td>\n",
+       "      <td>1.801952e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7773855</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>CNR Virus des Infections Respiratoires - Franc...</td>\n",
+       "      <td>2020-03-19</td>\n",
+       "      <td>France:Lyon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12336758</th>\n",
+       "      <td>SAMN15659002</td>\n",
+       "      <td>1.180912e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7773855</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>CNR Virus des Infections Respiratoires - Franc...</td>\n",
+       "      <td>2020-03-17</td>\n",
+       "      <td>France:Lyon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12336769</th>\n",
+       "      <td>SAMN15659001</td>\n",
+       "      <td>1.154191e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7773855</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>CNR Virus des Infections Respiratoires - Franc...</td>\n",
+       "      <td>2020-04-09</td>\n",
+       "      <td>France:Lyon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12336780</th>\n",
+       "      <td>SAMN15659000</td>\n",
+       "      <td>1.144114e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7773855</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>CNR Virus des Infections Respiratoires - Franc...</td>\n",
+       "      <td>2020-04-09</td>\n",
+       "      <td>France:Lyon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12336791</th>\n",
+       "      <td>SAMN15658999</td>\n",
+       "      <td>2.338869e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7773855</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>CNR Virus des Infections Respiratoires - Franc...</td>\n",
+       "      <td>2020-03-08</td>\n",
+       "      <td>France:Lyon</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</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>SRR12480579</th>\n",
+       "      <td>SAMN15691611</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-23</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480580</th>\n",
+       "      <td>SAMN15691610</td>\n",
+       "      <td>6.835912e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-24</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480581</th>\n",
+       "      <td>SAMN15691609</td>\n",
+       "      <td>7.529477e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480582</th>\n",
+       "      <td>SAMN15691608</td>\n",
+       "      <td>6.314669e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-28</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480583</th>\n",
+       "      <td>SAMN15691607</td>\n",
+       "      <td>7.533745e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-26</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>234 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession    base_count cell_line  cell_type center_name  \\\n",
+       "run_accession                                                                \n",
+       "SRR12336747    SAMN15659003  1.801952e+08       NaN        NaN  SUB7773855   \n",
+       "SRR12336758    SAMN15659002  1.180912e+08       NaN        NaN  SUB7773855   \n",
+       "SRR12336769    SAMN15659001  1.154191e+09       NaN        NaN  SUB7773855   \n",
+       "SRR12336780    SAMN15659000  1.144114e+09       NaN        NaN  SUB7773855   \n",
+       "SRR12336791    SAMN15658999  2.338869e+08       NaN        NaN  SUB7773855   \n",
+       "...                     ...           ...       ...        ...         ...   \n",
+       "SRR12480579    SAMN15691611           NaN       NaN        NaN  SUB7938744   \n",
+       "SRR12480580    SAMN15691610  6.835912e+06       NaN        NaN  SUB7938744   \n",
+       "SRR12480581    SAMN15691609  7.529477e+06       NaN        NaN  SUB7938744   \n",
+       "SRR12480582    SAMN15691608  6.314669e+06       NaN        NaN  SUB7938744   \n",
+       "SRR12480583    SAMN15691607  7.533745e+06       NaN        NaN  SUB7938744   \n",
+       "\n",
+       "              checklist                                       collected_by  \\\n",
+       "run_accession                                                                \n",
+       "SRR12336747         NaN  CNR Virus des Infections Respiratoires - Franc...   \n",
+       "SRR12336758         NaN  CNR Virus des Infections Respiratoires - Franc...   \n",
+       "SRR12336769         NaN  CNR Virus des Infections Respiratoires - Franc...   \n",
+       "SRR12336780         NaN  CNR Virus des Infections Respiratoires - Franc...   \n",
+       "SRR12336791         NaN  CNR Virus des Infections Respiratoires - Franc...   \n",
+       "...                 ...                                                ...   \n",
+       "SRR12480579         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480580         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480581         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480582         NaN                            Johns Hopkins Pathology   \n",
+       "SRR12480583         NaN                            Johns Hopkins Pathology   \n",
+       "\n",
+       "              collection_date        country cram_index_ftp  ... sub_species  \\\n",
+       "run_accession                                                ...               \n",
+       "SRR12336747        2020-03-19    France:Lyon            NaN  ...         NaN   \n",
+       "SRR12336758        2020-03-17    France:Lyon            NaN  ...         NaN   \n",
+       "SRR12336769        2020-04-09    France:Lyon            NaN  ...         NaN   \n",
+       "SRR12336780        2020-04-09    France:Lyon            NaN  ...         NaN   \n",
+       "SRR12336791        2020-03-08    France:Lyon            NaN  ...         NaN   \n",
+       "...                       ...            ...            ...  ...         ...   \n",
+       "SRR12480579        2020-03-23  USA: Maryland            NaN  ...         NaN   \n",
+       "SRR12480580        2020-03-24  USA: Maryland            NaN  ...         NaN   \n",
+       "SRR12480581        2020-03-30  USA: Maryland            NaN  ...         NaN   \n",
+       "SRR12480582        2020-03-28        USA: DC            NaN  ...         NaN   \n",
+       "SRR12480583        2020-03-26        USA: DC            NaN  ...         NaN   \n",
+       "\n",
+       "              sub_strain submitted_bytes submitted_format submitted_host_sex  \\\n",
+       "run_accession                                                                  \n",
+       "SRR12336747          NaN             NaN              NaN                NaN   \n",
+       "SRR12336758          NaN             NaN              NaN                NaN   \n",
+       "SRR12336769          NaN             NaN              NaN                NaN   \n",
+       "SRR12336780          NaN             NaN              NaN                NaN   \n",
+       "SRR12336791          NaN             NaN              NaN                NaN   \n",
+       "...                  ...             ...              ...                ...   \n",
+       "SRR12480579          NaN             NaN              NaN             female   \n",
+       "SRR12480580          NaN             NaN              NaN             female   \n",
+       "SRR12480581          NaN             NaN              NaN             female   \n",
+       "SRR12480582          NaN             NaN              NaN               male   \n",
+       "SRR12480583          NaN             NaN              NaN             female   \n",
+       "\n",
+       "              submitted_sex   tax_id     sex artic amplicon_in_metadata  \n",
+       "run_accession                                                            \n",
+       "SRR12336747             NaN  2697049     NaN  True                 True  \n",
+       "SRR12336758             NaN  2697049     NaN  True                 True  \n",
+       "SRR12336769             NaN  2697049     NaN  True                 True  \n",
+       "SRR12336780             NaN  2697049     NaN  True                 True  \n",
+       "SRR12336791             NaN  2697049     NaN  True                 True  \n",
+       "...                     ...      ...     ...   ...                  ...  \n",
+       "SRR12480579             NaN  2697049  female  True                 True  \n",
+       "SRR12480580             NaN  2697049  female  True                 True  \n",
+       "SRR12480581             NaN  2697049  female  True                 True  \n",
+       "SRR12480582             NaN  2697049    male  True                 True  \n",
+       "SRR12480583             NaN  2697049  female  True                 True  \n",
+       "\n",
+       "[234 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 46,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "artic_nanopore_probably = nanopore_no_metadata_filter[(nanopore_no_metadata_filter.library_strategy == 'AMPLICON') & (nanopore_no_metadata_filter.artic == True)]\n",
+    "artic_nanopore_probably[['run_accession', 'study_accession']].to_csv('nanopore_artic_accessions.tsv', sep='\\t', index=None)\n",
+    "artic_nanopore_probably"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 45,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4450774</th>\n",
+       "      <td>SAMEA7175809</td>\n",
+       "      <td>1.643639e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>COVID-HUB-PL</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Katarzyna Lasinska</td>\n",
+       "      <td>2020-05-18</td>\n",
+       "      <td>Poland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>83728034</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4452719</th>\n",
+       "      <td>SAMEA7175809</td>\n",
+       "      <td>1.114744e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>COVID-HUB-PL</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Katarzyna Lasinska</td>\n",
+       "      <td>2020-05-18</td>\n",
+       "      <td>Poland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>56320826</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4452734</th>\n",
+       "      <td>SAMEA7175811</td>\n",
+       "      <td>6.885593e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>COVID-HUB-PL</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Katarzyna Lasinska</td>\n",
+       "      <td>2020-05-19</td>\n",
+       "      <td>Poland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3696298</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4452736</th>\n",
+       "      <td>SAMEA7175812</td>\n",
+       "      <td>1.097800e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>COVID-HUB-PL</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Katarzyna Lasinska</td>\n",
+       "      <td>2020-05-19</td>\n",
+       "      <td>Poland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>5661267</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4452737</th>\n",
+       "      <td>SAMEA7175813</td>\n",
+       "      <td>2.917065e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>COVID-HUB-PL</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Katarzyna Lasinska</td>\n",
+       "      <td>2020-05-19</td>\n",
+       "      <td>Poland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1523098</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</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>SRR12192441</th>\n",
+       "      <td>SAMN15379426</td>\n",
+       "      <td>8.335258e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7748555</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quest Diagnostics</td>\n",
+       "      <td>2020-03-12</td>\n",
+       "      <td>USA:HI</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12192442</th>\n",
+       "      <td>SAMN15379425</td>\n",
+       "      <td>2.023239e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7748555</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quest Diagnostics</td>\n",
+       "      <td>2020-03-12</td>\n",
+       "      <td>USA:CO</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12192444</th>\n",
+       "      <td>SAMN15379423</td>\n",
+       "      <td>4.033132e+06</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7748555</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quest Diagnostics</td>\n",
+       "      <td>2020-03-13</td>\n",
+       "      <td>USA:CA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12192445</th>\n",
+       "      <td>SAMN15379414</td>\n",
+       "      <td>7.659017e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7748555</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quest Diagnostics</td>\n",
+       "      <td>2020-03-13</td>\n",
+       "      <td>USA:CA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12192446</th>\n",
+       "      <td>SAMN15379413</td>\n",
+       "      <td>9.803187e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7748555</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quest Diagnostics</td>\n",
+       "      <td>2020-03-13</td>\n",
+       "      <td>USA:CA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>False</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>93 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession    base_count cell_line  cell_type   center_name  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4450774     SAMEA7175809  1.643639e+08       NaN        NaN  COVID-HUB-PL   \n",
+       "ERR4452719     SAMEA7175809  1.114744e+08       NaN        NaN  COVID-HUB-PL   \n",
+       "ERR4452734     SAMEA7175811  6.885593e+06       NaN        NaN  COVID-HUB-PL   \n",
+       "ERR4452736     SAMEA7175812  1.097800e+07       NaN        NaN  COVID-HUB-PL   \n",
+       "ERR4452737     SAMEA7175813  2.917065e+06       NaN        NaN  COVID-HUB-PL   \n",
+       "...                     ...           ...       ...        ...           ...   \n",
+       "SRR12192441    SAMN15379426  8.335258e+09       NaN        NaN    SUB7748555   \n",
+       "SRR12192442    SAMN15379425  2.023239e+09       NaN        NaN    SUB7748555   \n",
+       "SRR12192444    SAMN15379423  4.033132e+06       NaN        NaN    SUB7748555   \n",
+       "SRR12192445    SAMN15379414  7.659017e+07       NaN        NaN    SUB7748555   \n",
+       "SRR12192446    SAMN15379413  9.803187e+07       NaN        NaN    SUB7748555   \n",
+       "\n",
+       "               checklist        collected_by collection_date country  \\\n",
+       "run_accession                                                          \n",
+       "ERR4450774     ERC000033  Katarzyna Lasinska      2020-05-18  Poland   \n",
+       "ERR4452719     ERC000033  Katarzyna Lasinska      2020-05-18  Poland   \n",
+       "ERR4452734     ERC000033  Katarzyna Lasinska      2020-05-19  Poland   \n",
+       "ERR4452736     ERC000033  Katarzyna Lasinska      2020-05-19  Poland   \n",
+       "ERR4452737     ERC000033  Katarzyna Lasinska      2020-05-19  Poland   \n",
+       "...                  ...                 ...             ...     ...   \n",
+       "SRR12192441          NaN   Quest Diagnostics      2020-03-12  USA:HI   \n",
+       "SRR12192442          NaN   Quest Diagnostics      2020-03-12  USA:CO   \n",
+       "SRR12192444          NaN   Quest Diagnostics      2020-03-13  USA:CA   \n",
+       "SRR12192445          NaN   Quest Diagnostics      2020-03-13  USA:CA   \n",
+       "SRR12192446          NaN   Quest Diagnostics      2020-03-13  USA:CA   \n",
+       "\n",
+       "              cram_index_ftp  ... sub_species sub_strain submitted_bytes  \\\n",
+       "run_accession                 ...                                          \n",
+       "ERR4450774               NaN  ...         NaN        NaN        83728034   \n",
+       "ERR4452719               NaN  ...         NaN        NaN        56320826   \n",
+       "ERR4452734               NaN  ...         NaN        NaN         3696298   \n",
+       "ERR4452736               NaN  ...         NaN        NaN         5661267   \n",
+       "ERR4452737               NaN  ...         NaN        NaN         1523098   \n",
+       "...                      ...  ...         ...        ...             ...   \n",
+       "SRR12192441              NaN  ...         NaN        NaN             NaN   \n",
+       "SRR12192442              NaN  ...         NaN        NaN             NaN   \n",
+       "SRR12192444              NaN  ...         NaN        NaN             NaN   \n",
+       "SRR12192445              NaN  ...         NaN        NaN             NaN   \n",
+       "SRR12192446              NaN  ...         NaN        NaN             NaN   \n",
+       "\n",
+       "              submitted_format submitted_host_sex submitted_sex   tax_id  \\\n",
+       "run_accession                                                              \n",
+       "ERR4450774                 BAM             female           NaN  2697049   \n",
+       "ERR4452719                 BAM             female           NaN  2697049   \n",
+       "ERR4452734                 BAM               male           NaN  2697049   \n",
+       "ERR4452736                 BAM             female           NaN  2697049   \n",
+       "ERR4452737                 BAM             female           NaN  2697049   \n",
+       "...                        ...                ...           ...      ...   \n",
+       "SRR12192441                NaN             female           NaN  2697049   \n",
+       "SRR12192442                NaN             female           NaN  2697049   \n",
+       "SRR12192444                NaN             female           NaN  2697049   \n",
+       "SRR12192445                NaN             female           NaN  2697049   \n",
+       "SRR12192446                NaN               male           NaN  2697049   \n",
+       "\n",
+       "                  sex  artic amplicon_in_metadata  \n",
+       "run_accession                                      \n",
+       "ERR4450774     female  False                False  \n",
+       "ERR4452719     female  False                False  \n",
+       "ERR4452734       male  False                False  \n",
+       "ERR4452736     female  False                False  \n",
+       "ERR4452737     female  False                False  \n",
+       "...               ...    ...                  ...  \n",
+       "SRR12192441    female  False                False  \n",
+       "SRR12192442    female  False                False  \n",
+       "SRR12192444    female  False                False  \n",
+       "SRR12192445    female  False                False  \n",
+       "SRR12192446      male  False                False  \n",
+       "\n",
+       "[93 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 45,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina_metagenomic_probably = illumina[(illumina.library_strategy.isin(['WGS', 'RNA-Seq'])) & (illumina.artic == False) & (illumina.amplicon_in_metadata == False)]\n",
+    "illumina_metagenomic_probably[['run_accession', 'study_accession']].to_csv('illumina_metagenomic_accessions.tsv', sep='\\t', index=None)\n",
+    "illumina_metagenomic_probably\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 44,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4238187</th>\n",
+       "      <td>SAMEA6915235</td>\n",
+       "      <td>47444042.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.69982e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238188</th>\n",
+       "      <td>SAMEA6915392</td>\n",
+       "      <td>24758232.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-13</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.44243e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238189</th>\n",
+       "      <td>SAMEA6915293</td>\n",
+       "      <td>49131355.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.83486e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238190</th>\n",
+       "      <td>SAMEA6915304</td>\n",
+       "      <td>45016521.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-02</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.43407e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238191</th>\n",
+       "      <td>SAMEA6915524</td>\n",
+       "      <td>12799114.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.26565e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238193</th>\n",
+       "      <td>SAMEA6915234</td>\n",
+       "      <td>23694399.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.34036e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238194</th>\n",
+       "      <td>SAMEA6915400</td>\n",
+       "      <td>13675463.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.34489e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238196</th>\n",
+       "      <td>SAMEA6915362</td>\n",
+       "      <td>15539103.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.52951e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238197</th>\n",
+       "      <td>SAMEA6915466</td>\n",
+       "      <td>403743672.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.0005e+08</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238198</th>\n",
+       "      <td>SAMEA6915291</td>\n",
+       "      <td>23811158.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-10</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.34024e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238199</th>\n",
+       "      <td>SAMEA6915476</td>\n",
+       "      <td>317376376.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>3.14354e+08</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238200</th>\n",
+       "      <td>SAMEA6915322</td>\n",
+       "      <td>14970902.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.48183e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238201</th>\n",
+       "      <td>SAMEA6915232</td>\n",
+       "      <td>23569343.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-09</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.31803e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238202</th>\n",
+       "      <td>SAMEA6915280</td>\n",
+       "      <td>24950573.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.45838e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238203</th>\n",
+       "      <td>SAMEA6915445</td>\n",
+       "      <td>1594888.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.57915e+06</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238205</th>\n",
+       "      <td>SAMEA6915307</td>\n",
+       "      <td>573846.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>573444</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238207</th>\n",
+       "      <td>SAMEA6915431</td>\n",
+       "      <td>409224225.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.04756e+08</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238208</th>\n",
+       "      <td>SAMEA6915336</td>\n",
+       "      <td>48801567.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-12</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.84417e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238209</th>\n",
+       "      <td>SAMEA6915268</td>\n",
+       "      <td>93919.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>93927</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>19 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession   base_count cell_line  cell_type  \\\n",
+       "run_accession                                                   \n",
+       "ERR4238187     SAMEA6915235   47444042.0       NaN        NaN   \n",
+       "ERR4238188     SAMEA6915392   24758232.0       NaN        NaN   \n",
+       "ERR4238189     SAMEA6915293   49131355.0       NaN        NaN   \n",
+       "ERR4238190     SAMEA6915304   45016521.0       NaN        NaN   \n",
+       "ERR4238191     SAMEA6915524   12799114.0       NaN        NaN   \n",
+       "ERR4238193     SAMEA6915234   23694399.0       NaN        NaN   \n",
+       "ERR4238194     SAMEA6915400   13675463.0       NaN        NaN   \n",
+       "ERR4238196     SAMEA6915362   15539103.0       NaN        NaN   \n",
+       "ERR4238197     SAMEA6915466  403743672.0       NaN        NaN   \n",
+       "ERR4238198     SAMEA6915291   23811158.0       NaN        NaN   \n",
+       "ERR4238199     SAMEA6915476  317376376.0       NaN        NaN   \n",
+       "ERR4238200     SAMEA6915322   14970902.0       NaN        NaN   \n",
+       "ERR4238201     SAMEA6915232   23569343.0       NaN        NaN   \n",
+       "ERR4238202     SAMEA6915280   24950573.0       NaN        NaN   \n",
+       "ERR4238203     SAMEA6915445    1594888.0       NaN        NaN   \n",
+       "ERR4238205     SAMEA6915307     573846.0       NaN        NaN   \n",
+       "ERR4238207     SAMEA6915431  409224225.0       NaN        NaN   \n",
+       "ERR4238208     SAMEA6915336   48801567.0       NaN        NaN   \n",
+       "ERR4238209     SAMEA6915268      93919.0       NaN        NaN   \n",
+       "\n",
+       "                                center_name  checklist         collected_by  \\\n",
+       "run_accession                                                                 \n",
+       "ERR4238187     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238188     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238189     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238190     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238191     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238193     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238194     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238196     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238197     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238198     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238199     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238200     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238201     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238202     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238203     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238205     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238207     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238208     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "ERR4238209     Quadram Institute Bioscience  ERC000033  Justin O&apos;Grady   \n",
+       "\n",
+       "              collection_date         country cram_index_ftp  ... sub_species  \\\n",
+       "run_accession                                                 ...               \n",
+       "ERR4238187         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238188         2020-05-13  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238189         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238190         2020-05-02  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238191         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238193         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238194         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238196         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238197         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238198         2020-05-10  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238199         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238200         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238201         2020-05-09  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238202         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238203         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238205         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238207         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238208         2020-05-12  United Kingdom            NaN  ...         NaN   \n",
+       "ERR4238209         2020-05-11  United Kingdom            NaN  ...         NaN   \n",
+       "\n",
+       "              sub_strain submitted_bytes submitted_format submitted_host_sex  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4238187           NaN     4.69982e+07              BAM               male   \n",
+       "ERR4238188           NaN     2.44243e+07              BAM             female   \n",
+       "ERR4238189           NaN     4.83486e+07              BAM               male   \n",
+       "ERR4238190           NaN     4.43407e+07              BAM             female   \n",
+       "ERR4238191           NaN     1.26565e+07              BAM               male   \n",
+       "ERR4238193           NaN     2.34036e+07              BAM             female   \n",
+       "ERR4238194           NaN     1.34489e+07              BAM             female   \n",
+       "ERR4238196           NaN     1.52951e+07              BAM             female   \n",
+       "ERR4238197           NaN      4.0005e+08              BAM             female   \n",
+       "ERR4238198           NaN     2.34024e+07              BAM             female   \n",
+       "ERR4238199           NaN     3.14354e+08              BAM               male   \n",
+       "ERR4238200           NaN     1.48183e+07              BAM               male   \n",
+       "ERR4238201           NaN     2.31803e+07              BAM             female   \n",
+       "ERR4238202           NaN     2.45838e+07              BAM               male   \n",
+       "ERR4238203           NaN     1.57915e+06              BAM             female   \n",
+       "ERR4238205           NaN          573444              BAM             female   \n",
+       "ERR4238207           NaN     4.04756e+08              BAM             female   \n",
+       "ERR4238208           NaN     4.84417e+07              BAM               male   \n",
+       "ERR4238209           NaN           93927              BAM             female   \n",
+       "\n",
+       "              submitted_sex   tax_id     sex artic amplicon_in_metadata  \n",
+       "run_accession                                                            \n",
+       "ERR4238187              NaN  2697049    male  True                 True  \n",
+       "ERR4238188              NaN  2697049  female  True                 True  \n",
+       "ERR4238189              NaN  2697049    male  True                 True  \n",
+       "ERR4238190              NaN  2697049  female  True                 True  \n",
+       "ERR4238191              NaN  2697049    male  True                 True  \n",
+       "ERR4238193              NaN  2697049  female  True                 True  \n",
+       "ERR4238194              NaN  2697049  female  True                 True  \n",
+       "ERR4238196              NaN  2697049  female  True                 True  \n",
+       "ERR4238197              NaN  2697049  female  True                 True  \n",
+       "ERR4238198              NaN  2697049  female  True                 True  \n",
+       "ERR4238199              NaN  2697049    male  True                 True  \n",
+       "ERR4238200              NaN  2697049    male  True                 True  \n",
+       "ERR4238201              NaN  2697049  female  True                 True  \n",
+       "ERR4238202              NaN  2697049    male  True                 True  \n",
+       "ERR4238203              NaN  2697049  female  True                 True  \n",
+       "ERR4238205              NaN  2697049  female  True                 True  \n",
+       "ERR4238207              NaN  2697049  female  True                 True  \n",
+       "ERR4238208              NaN  2697049    male  True                 True  \n",
+       "ERR4238209              NaN  2697049  female  True                 True  \n",
+       "\n",
+       "[19 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 44,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina_ampliconic_very_probably= illumina[(illumina.library_strategy == 'AMPLICON') & (illumina.artic == True)]\n",
+    "illumina_ampliconic_very_probably[['run_accession', 'study_accession']].to_csv('illumina_artic_accessions.tsv', sep='\\t', index=None)\n",
+    "illumina_ampliconic_very_probably"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 35,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "      <th>artic</th>\n",
+       "      <th>amplicon_in_metadata</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4238187</th>\n",
+       "      <td>SAMEA6915235</td>\n",
+       "      <td>47444042.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.69982e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238188</th>\n",
+       "      <td>SAMEA6915392</td>\n",
+       "      <td>24758232.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-13</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.44243e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238189</th>\n",
+       "      <td>SAMEA6915293</td>\n",
+       "      <td>49131355.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.83486e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238190</th>\n",
+       "      <td>SAMEA6915304</td>\n",
+       "      <td>45016521.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-02</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.43407e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238191</th>\n",
+       "      <td>SAMEA6915524</td>\n",
+       "      <td>12799114.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.26565e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>True</td>\n",
+       "      <td>True</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>SRR12537597</th>\n",
+       "      <td>SAMN15918077</td>\n",
+       "      <td>236250203.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537598</th>\n",
+       "      <td>SAMN15918076</td>\n",
+       "      <td>248067278.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537599</th>\n",
+       "      <td>SAMN15918075</td>\n",
+       "      <td>188068675.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537600</th>\n",
+       "      <td>SAMN15918074</td>\n",
+       "      <td>256393966.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12537601</th>\n",
+       "      <td>SAMN15918073</td>\n",
+       "      <td>202958641.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8055754</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Microbiological Diagnostic Unit - Public Healt...</td>\n",
+       "      <td>2020-07-18</td>\n",
+       "      <td>Australia: Victoria</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "      <td>False</td>\n",
+       "      <td>True</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>5165 rows × 67 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession   base_count cell_line  cell_type  \\\n",
+       "run_accession                                                   \n",
+       "ERR4238187     SAMEA6915235   47444042.0       NaN        NaN   \n",
+       "ERR4238188     SAMEA6915392   24758232.0       NaN        NaN   \n",
+       "ERR4238189     SAMEA6915293   49131355.0       NaN        NaN   \n",
+       "ERR4238190     SAMEA6915304   45016521.0       NaN        NaN   \n",
+       "ERR4238191     SAMEA6915524   12799114.0       NaN        NaN   \n",
+       "...                     ...          ...       ...        ...   \n",
+       "SRR12537597    SAMN15918077  236250203.0       NaN        NaN   \n",
+       "SRR12537598    SAMN15918076  248067278.0       NaN        NaN   \n",
+       "SRR12537599    SAMN15918075  188068675.0       NaN        NaN   \n",
+       "SRR12537600    SAMN15918074  256393966.0       NaN        NaN   \n",
+       "SRR12537601    SAMN15918073  202958641.0       NaN        NaN   \n",
+       "\n",
+       "                                center_name  checklist  \\\n",
+       "run_accession                                            \n",
+       "ERR4238187     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238188     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238189     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238190     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238191     Quadram Institute Bioscience  ERC000033   \n",
+       "...                                     ...        ...   \n",
+       "SRR12537597                      SUB8055754        NaN   \n",
+       "SRR12537598                      SUB8055754        NaN   \n",
+       "SRR12537599                      SUB8055754        NaN   \n",
+       "SRR12537600                      SUB8055754        NaN   \n",
+       "SRR12537601                      SUB8055754        NaN   \n",
+       "\n",
+       "                                                    collected_by  \\\n",
+       "run_accession                                                      \n",
+       "ERR4238187                                   Justin O&apos;Grady   \n",
+       "ERR4238188                                   Justin O&apos;Grady   \n",
+       "ERR4238189                                   Justin O&apos;Grady   \n",
+       "ERR4238190                                   Justin O&apos;Grady   \n",
+       "ERR4238191                                   Justin O&apos;Grady   \n",
+       "...                                                          ...   \n",
+       "SRR12537597    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537598    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537599    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537600    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "SRR12537601    Microbiological Diagnostic Unit - Public Healt...   \n",
+       "\n",
+       "              collection_date              country cram_index_ftp  ...  \\\n",
+       "run_accession                                                      ...   \n",
+       "ERR4238187         2020-05-11       United Kingdom            NaN  ...   \n",
+       "ERR4238188         2020-05-13       United Kingdom            NaN  ...   \n",
+       "ERR4238189         2020-05-11       United Kingdom            NaN  ...   \n",
+       "ERR4238190         2020-05-02       United Kingdom            NaN  ...   \n",
+       "ERR4238191         2020-05-11       United Kingdom            NaN  ...   \n",
+       "...                       ...                  ...            ...  ...   \n",
+       "SRR12537597        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537598        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537599        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537600        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "SRR12537601        2020-07-18  Australia: Victoria            NaN  ...   \n",
+       "\n",
+       "              sub_species sub_strain submitted_bytes submitted_format  \\\n",
+       "run_accession                                                           \n",
+       "ERR4238187            NaN        NaN     4.69982e+07              BAM   \n",
+       "ERR4238188            NaN        NaN     2.44243e+07              BAM   \n",
+       "ERR4238189            NaN        NaN     4.83486e+07              BAM   \n",
+       "ERR4238190            NaN        NaN     4.43407e+07              BAM   \n",
+       "ERR4238191            NaN        NaN     1.26565e+07              BAM   \n",
+       "...                   ...        ...             ...              ...   \n",
+       "SRR12537597           NaN        NaN             NaN              NaN   \n",
+       "SRR12537598           NaN        NaN             NaN              NaN   \n",
+       "SRR12537599           NaN        NaN             NaN              NaN   \n",
+       "SRR12537600           NaN        NaN             NaN              NaN   \n",
+       "SRR12537601           NaN        NaN             NaN              NaN   \n",
+       "\n",
+       "              submitted_host_sex submitted_sex   tax_id     sex  artic  \\\n",
+       "run_accession                                                            \n",
+       "ERR4238187                  male           NaN  2697049    male   True   \n",
+       "ERR4238188                female           NaN  2697049  female   True   \n",
+       "ERR4238189                  male           NaN  2697049    male   True   \n",
+       "ERR4238190                female           NaN  2697049  female   True   \n",
+       "ERR4238191                  male           NaN  2697049    male   True   \n",
+       "...                          ...           ...      ...     ...    ...   \n",
+       "SRR12537597                 male           NaN  2697049    male  False   \n",
+       "SRR12537598               female           NaN  2697049  female  False   \n",
+       "SRR12537599               female           NaN  2697049  female  False   \n",
+       "SRR12537600                 male           NaN  2697049    male  False   \n",
+       "SRR12537601                 male           NaN  2697049    male  False   \n",
+       "\n",
+       "              amplicon_in_metadata  \n",
+       "run_accession                       \n",
+       "ERR4238187                    True  \n",
+       "ERR4238188                    True  \n",
+       "ERR4238189                    True  \n",
+       "ERR4238190                    True  \n",
+       "ERR4238191                    True  \n",
+       "...                            ...  \n",
+       "SRR12537597                   True  \n",
+       "SRR12537598                   True  \n",
+       "SRR12537599                   True  \n",
+       "SRR12537600                   True  \n",
+       "SRR12537601                   True  \n",
+       "\n",
+       "[5165 rows x 67 columns]"
+      ]
+     },
+     "execution_count": 35,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "illumina_ampliconic_probably = illumina[(illumina.library_strategy == 'AMPLICON')]\n",
+    "illumina_ampliconic_probably"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 104,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "SAMN14428240\t188942237\t\t\tSUB7181455\t\tUWHC\t2020-03-15\tUSA:Wisconsin\t\tGridION sequencing; swab_artic_4\tSRX7972384\tWI5_artic\tGridION sequencing; swab_artic_4\tfasp.sra.ebi.ac.uk:/vol1/fastq/SRR113/075/SRR11393275/SRR11393275_1.fastq.gz\t197659362\tftp.sra.ebi.ac.uk/vol1/fastq/SRR113/075/SRR11393275/SRR11393275_1.fastq.gz\t0f8d0fdbfc487c81494cab879eef9c1c\t2020-03-24\t2020-03-24\tHomo sapiens\t\t9606\tGridION\tOXFORD_NANOPORE\t\thomo sapien\tnasal swab\t2020-03-24\t43.0731\tSINGLE\tWI5_artic\tPCR\tVIRAL RNA\tWGS\t43.0731 N 89.4012 W\t-89.4012\t475250\tSRR11393275\thCoV-19_USA_WI-05_2020_ARTIC.fastq\tSAMN14428240\tARTIC_hCoV-19/USA/WI-05/2020\tThis sample has been submitted by pda|kmbraun2 on 2020-03-24; Severe acute respiratory syndrome coronavirus 2\t\tThis sample has been submitted by pda|kmbraun2 on 2020-03-24; Severe acute respiratory syndrome coronavirus 2\t\t\t\tSevere acute respiratory syndrome coronavirus 2\tfasp.sra.ebi.ac.uk:/vol1/srr/SRR113/075/SRR11393275\t173127508\tftp.sra.ebi.ac.uk/vol1/srr/SRR113/075/SRR11393275\ta0ba3abc4527cd7eb8172c2ce0a98299\thCoV-19/USA/WI-05/2020_ARTIC\tPRJNA614504\tPRJNA614504\tSARS-CoV-2 Deep Sequencing University of Wisconsin-Madison\t\t\t\t\t\t\t2697049\n"
+     ]
+    }
+   ],
+   "source": [
+    "!grep SRR11393275 ../current_metadata_ena.tsv"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 106,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "maybe_not_artic = df[~df.apply(lambda x: 'artic' in x.to_string().lower(), axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 107,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>study_alias</th>\n",
+       "      <th>study_title</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4080473</th>\n",
+       "      <td>SAMEA6798401</td>\n",
+       "      <td>1.586073e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>136591936</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080474</th>\n",
+       "      <td>SAMEA6798402</td>\n",
+       "      <td>1.462576e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>125862765</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080475</th>\n",
+       "      <td>SAMEA6798403</td>\n",
+       "      <td>1.228982e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>106116129</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080476</th>\n",
+       "      <td>SAMEA6798404</td>\n",
+       "      <td>1.654989e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>142761688</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080477</th>\n",
+       "      <td>SAMEA6798405</td>\n",
+       "      <td>1.694441e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>146011388</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</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>SRR12554748</th>\n",
+       "      <td>SAMN15949722</td>\n",
+       "      <td>1.199726e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8072363</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Texas Department of State Health Services</td>\n",
+       "      <td>2020-03-16</td>\n",
+       "      <td>USA:TX</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA639066</td>\n",
+       "      <td>TX SARS-CoV-2 Sequencing</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12554749</th>\n",
+       "      <td>SAMN15949721</td>\n",
+       "      <td>1.128326e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8072363</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Texas Department of State Health Services</td>\n",
+       "      <td>2020-03-11</td>\n",
+       "      <td>USA:TX</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA639066</td>\n",
+       "      <td>TX SARS-CoV-2 Sequencing</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12588591</th>\n",
+       "      <td>SAMN16058334</td>\n",
+       "      <td>2.747873e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8094684</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>University of Washington Virology Lab</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>USA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA610428</td>\n",
+       "      <td>Washington SARS-CoV-2 isolate sequences</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12598968</th>\n",
+       "      <td>SAMN16068354</td>\n",
+       "      <td>2.119223e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8102645</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Nevada State Public Health Laboratory</td>\n",
+       "      <td>2020-06-05</td>\n",
+       "      <td>USA:Nevada</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA657893</td>\n",
+       "      <td>Severe acute respiratory syndrome coronavirus ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12598969</th>\n",
+       "      <td>SAMN16068353</td>\n",
+       "      <td>1.112943e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8102645</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Nevada State Public Health Laboratory</td>\n",
+       "      <td>2020-04-18</td>\n",
+       "      <td>USA:Nevada</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA657893</td>\n",
+       "      <td>Severe acute respiratory syndrome coronavirus ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>55660 rows × 65 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession    base_count cell_line  cell_type  \\\n",
+       "run_accession                                                    \n",
+       "ERR4080473     SAMEA6798401  1.586073e+08       NaN        NaN   \n",
+       "ERR4080474     SAMEA6798402  1.462576e+08       NaN        NaN   \n",
+       "ERR4080475     SAMEA6798403  1.228982e+08       NaN        NaN   \n",
+       "ERR4080476     SAMEA6798404  1.654989e+08       NaN        NaN   \n",
+       "ERR4080477     SAMEA6798405  1.694441e+08       NaN        NaN   \n",
+       "...                     ...           ...       ...        ...   \n",
+       "SRR12554748    SAMN15949722  1.199726e+07       NaN        NaN   \n",
+       "SRR12554749    SAMN15949721  1.128326e+07       NaN        NaN   \n",
+       "SRR12588591    SAMN16058334  2.747873e+09       NaN        NaN   \n",
+       "SRR12598968    SAMN16068354  2.119223e+08       NaN        NaN   \n",
+       "SRR12598969    SAMN16068353  1.112943e+08       NaN        NaN   \n",
+       "\n",
+       "                      center_name  checklist  \\\n",
+       "run_accession                                  \n",
+       "ERR4080473     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080474     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080475     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080476     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080477     AALBORG UNIVERSITY  ERC000033   \n",
+       "...                           ...        ...   \n",
+       "SRR12554748            SUB8072363        NaN   \n",
+       "SRR12554749            SUB8072363        NaN   \n",
+       "SRR12588591            SUB8094684        NaN   \n",
+       "SRR12598968            SUB8102645        NaN   \n",
+       "SRR12598969            SUB8102645        NaN   \n",
+       "\n",
+       "                                            collected_by collection_date  \\\n",
+       "run_accession                                                              \n",
+       "ERR4080473                                  not provided      2020-03-10   \n",
+       "ERR4080474                                  not provided      2020-03-10   \n",
+       "ERR4080475                                  not provided      2020-03-10   \n",
+       "ERR4080476                                  not provided      2020-03-10   \n",
+       "ERR4080477                                  not provided      2020-03-10   \n",
+       "...                                                  ...             ...   \n",
+       "SRR12554748    Texas Department of State Health Services      2020-03-16   \n",
+       "SRR12554749    Texas Department of State Health Services      2020-03-11   \n",
+       "SRR12588591        University of Washington Virology Lab             NaN   \n",
+       "SRR12598968        Nevada State Public Health Laboratory      2020-06-05   \n",
+       "SRR12598969        Nevada State Public Health Laboratory      2020-04-18   \n",
+       "\n",
+       "                  country cram_index_ftp  ...  \\\n",
+       "run_accession                             ...   \n",
+       "ERR4080473        Denmark            NaN  ...   \n",
+       "ERR4080474        Denmark            NaN  ...   \n",
+       "ERR4080475        Denmark            NaN  ...   \n",
+       "ERR4080476        Denmark            NaN  ...   \n",
+       "ERR4080477        Denmark            NaN  ...   \n",
+       "...                   ...            ...  ...   \n",
+       "SRR12554748        USA:TX            NaN  ...   \n",
+       "SRR12554749        USA:TX            NaN  ...   \n",
+       "SRR12588591           USA            NaN  ...   \n",
+       "SRR12598968    USA:Nevada            NaN  ...   \n",
+       "SRR12598969    USA:Nevada            NaN  ...   \n",
+       "\n",
+       "                                                     study_alias  \\\n",
+       "run_accession                                                      \n",
+       "ERR4080473     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080474     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080475     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080476     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080477     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "...                                                          ...   \n",
+       "SRR12554748                                          PRJNA639066   \n",
+       "SRR12554749                                          PRJNA639066   \n",
+       "SRR12588591                                          PRJNA610428   \n",
+       "SRR12598968                                          PRJNA657893   \n",
+       "SRR12598969                                          PRJNA657893   \n",
+       "\n",
+       "                                                     study_title sub_species  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4080473                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080474                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080475                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080476                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080477                    Corona virus sequencing in Denmark         NaN   \n",
+       "...                                                          ...         ...   \n",
+       "SRR12554748                             TX SARS-CoV-2 Sequencing         NaN   \n",
+       "SRR12554749                             TX SARS-CoV-2 Sequencing         NaN   \n",
+       "SRR12588591              Washington SARS-CoV-2 isolate sequences         NaN   \n",
+       "SRR12598968    Severe acute respiratory syndrome coronavirus ...         NaN   \n",
+       "SRR12598969    Severe acute respiratory syndrome coronavirus ...         NaN   \n",
+       "\n",
+       "              sub_strain submitted_bytes submitted_format submitted_host_sex  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4080473           NaN       136591936            FASTQ       not provided   \n",
+       "ERR4080474           NaN       125862765            FASTQ       not provided   \n",
+       "ERR4080475           NaN       106116129            FASTQ       not provided   \n",
+       "ERR4080476           NaN       142761688            FASTQ       not provided   \n",
+       "ERR4080477           NaN       146011388            FASTQ       not provided   \n",
+       "...                  ...             ...              ...                ...   \n",
+       "SRR12554748          NaN             NaN              NaN                NaN   \n",
+       "SRR12554749          NaN             NaN              NaN                NaN   \n",
+       "SRR12588591          NaN             NaN              NaN                NaN   \n",
+       "SRR12598968          NaN             NaN              NaN                NaN   \n",
+       "SRR12598969          NaN             NaN              NaN                NaN   \n",
+       "\n",
+       "              submitted_sex   tax_id  sex  \n",
+       "run_accession                              \n",
+       "ERR4080473              NaN  2697049  NaN  \n",
+       "ERR4080474              NaN  2697049  NaN  \n",
+       "ERR4080475              NaN  2697049  NaN  \n",
+       "ERR4080476              NaN  2697049  NaN  \n",
+       "ERR4080477              NaN  2697049  NaN  \n",
+       "...                     ...      ...  ...  \n",
+       "SRR12554748             NaN  2697049  NaN  \n",
+       "SRR12554749             NaN  2697049  NaN  \n",
+       "SRR12588591             NaN  2697049  NaN  \n",
+       "SRR12598968             NaN  2697049  NaN  \n",
+       "SRR12598969             NaN  2697049  NaN  \n",
+       "\n",
+       "[55660 rows x 65 columns]"
+      ]
+     },
+     "execution_count": 107,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "maybe_not_artic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 108,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>study_alias</th>\n",
+       "      <th>study_title</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4080473</th>\n",
+       "      <td>SAMEA6798401</td>\n",
+       "      <td>1.586073e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>136591936</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080474</th>\n",
+       "      <td>SAMEA6798402</td>\n",
+       "      <td>1.462576e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>125862765</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080475</th>\n",
+       "      <td>SAMEA6798403</td>\n",
+       "      <td>1.228982e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>106116129</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080476</th>\n",
+       "      <td>SAMEA6798404</td>\n",
+       "      <td>1.654989e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>142761688</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4080477</th>\n",
+       "      <td>SAMEA6798405</td>\n",
+       "      <td>1.694441e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>AALBORG UNIVERSITY</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>2020-03-10</td>\n",
+       "      <td>Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...</td>\n",
+       "      <td>Corona virus sequencing in Denmark</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>146011388</td>\n",
+       "      <td>FASTQ</td>\n",
+       "      <td>not provided</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</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>SRR12554748</th>\n",
+       "      <td>SAMN15949722</td>\n",
+       "      <td>1.199726e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8072363</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Texas Department of State Health Services</td>\n",
+       "      <td>2020-03-16</td>\n",
+       "      <td>USA:TX</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA639066</td>\n",
+       "      <td>TX SARS-CoV-2 Sequencing</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12554749</th>\n",
+       "      <td>SAMN15949721</td>\n",
+       "      <td>1.128326e+07</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8072363</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Texas Department of State Health Services</td>\n",
+       "      <td>2020-03-11</td>\n",
+       "      <td>USA:TX</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA639066</td>\n",
+       "      <td>TX SARS-CoV-2 Sequencing</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12588591</th>\n",
+       "      <td>SAMN16058334</td>\n",
+       "      <td>2.747873e+09</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8094684</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>University of Washington Virology Lab</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>USA</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA610428</td>\n",
+       "      <td>Washington SARS-CoV-2 isolate sequences</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12598968</th>\n",
+       "      <td>SAMN16068354</td>\n",
+       "      <td>2.119223e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8102645</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Nevada State Public Health Laboratory</td>\n",
+       "      <td>2020-06-05</td>\n",
+       "      <td>USA:Nevada</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA657893</td>\n",
+       "      <td>Severe acute respiratory syndrome coronavirus ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12598969</th>\n",
+       "      <td>SAMN16068353</td>\n",
+       "      <td>1.112943e+08</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB8102645</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Nevada State Public Health Laboratory</td>\n",
+       "      <td>2020-04-18</td>\n",
+       "      <td>USA:Nevada</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA657893</td>\n",
+       "      <td>Severe acute respiratory syndrome coronavirus ...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>NaN</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>56672 rows × 65 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession    base_count cell_line  cell_type  \\\n",
+       "run_accession                                                    \n",
+       "ERR4080473     SAMEA6798401  1.586073e+08       NaN        NaN   \n",
+       "ERR4080474     SAMEA6798402  1.462576e+08       NaN        NaN   \n",
+       "ERR4080475     SAMEA6798403  1.228982e+08       NaN        NaN   \n",
+       "ERR4080476     SAMEA6798404  1.654989e+08       NaN        NaN   \n",
+       "ERR4080477     SAMEA6798405  1.694441e+08       NaN        NaN   \n",
+       "...                     ...           ...       ...        ...   \n",
+       "SRR12554748    SAMN15949722  1.199726e+07       NaN        NaN   \n",
+       "SRR12554749    SAMN15949721  1.128326e+07       NaN        NaN   \n",
+       "SRR12588591    SAMN16058334  2.747873e+09       NaN        NaN   \n",
+       "SRR12598968    SAMN16068354  2.119223e+08       NaN        NaN   \n",
+       "SRR12598969    SAMN16068353  1.112943e+08       NaN        NaN   \n",
+       "\n",
+       "                      center_name  checklist  \\\n",
+       "run_accession                                  \n",
+       "ERR4080473     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080474     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080475     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080476     AALBORG UNIVERSITY  ERC000033   \n",
+       "ERR4080477     AALBORG UNIVERSITY  ERC000033   \n",
+       "...                           ...        ...   \n",
+       "SRR12554748            SUB8072363        NaN   \n",
+       "SRR12554749            SUB8072363        NaN   \n",
+       "SRR12588591            SUB8094684        NaN   \n",
+       "SRR12598968            SUB8102645        NaN   \n",
+       "SRR12598969            SUB8102645        NaN   \n",
+       "\n",
+       "                                            collected_by collection_date  \\\n",
+       "run_accession                                                              \n",
+       "ERR4080473                                  not provided      2020-03-10   \n",
+       "ERR4080474                                  not provided      2020-03-10   \n",
+       "ERR4080475                                  not provided      2020-03-10   \n",
+       "ERR4080476                                  not provided      2020-03-10   \n",
+       "ERR4080477                                  not provided      2020-03-10   \n",
+       "...                                                  ...             ...   \n",
+       "SRR12554748    Texas Department of State Health Services      2020-03-16   \n",
+       "SRR12554749    Texas Department of State Health Services      2020-03-11   \n",
+       "SRR12588591        University of Washington Virology Lab             NaN   \n",
+       "SRR12598968        Nevada State Public Health Laboratory      2020-06-05   \n",
+       "SRR12598969        Nevada State Public Health Laboratory      2020-04-18   \n",
+       "\n",
+       "                  country cram_index_ftp  ...  \\\n",
+       "run_accession                             ...   \n",
+       "ERR4080473        Denmark            NaN  ...   \n",
+       "ERR4080474        Denmark            NaN  ...   \n",
+       "ERR4080475        Denmark            NaN  ...   \n",
+       "ERR4080476        Denmark            NaN  ...   \n",
+       "ERR4080477        Denmark            NaN  ...   \n",
+       "...                   ...            ...  ...   \n",
+       "SRR12554748        USA:TX            NaN  ...   \n",
+       "SRR12554749        USA:TX            NaN  ...   \n",
+       "SRR12588591           USA            NaN  ...   \n",
+       "SRR12598968    USA:Nevada            NaN  ...   \n",
+       "SRR12598969    USA:Nevada            NaN  ...   \n",
+       "\n",
+       "                                                     study_alias  \\\n",
+       "run_accession                                                      \n",
+       "ERR4080473     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080474     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080475     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080476     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "ERR4080477     ena-STUDY-AALBORG UNIVERSITY-23-04-2020-12:47:...   \n",
+       "...                                                          ...   \n",
+       "SRR12554748                                          PRJNA639066   \n",
+       "SRR12554749                                          PRJNA639066   \n",
+       "SRR12588591                                          PRJNA610428   \n",
+       "SRR12598968                                          PRJNA657893   \n",
+       "SRR12598969                                          PRJNA657893   \n",
+       "\n",
+       "                                                     study_title sub_species  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4080473                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080474                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080475                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080476                    Corona virus sequencing in Denmark         NaN   \n",
+       "ERR4080477                    Corona virus sequencing in Denmark         NaN   \n",
+       "...                                                          ...         ...   \n",
+       "SRR12554748                             TX SARS-CoV-2 Sequencing         NaN   \n",
+       "SRR12554749                             TX SARS-CoV-2 Sequencing         NaN   \n",
+       "SRR12588591              Washington SARS-CoV-2 isolate sequences         NaN   \n",
+       "SRR12598968    Severe acute respiratory syndrome coronavirus ...         NaN   \n",
+       "SRR12598969    Severe acute respiratory syndrome coronavirus ...         NaN   \n",
+       "\n",
+       "              sub_strain submitted_bytes submitted_format submitted_host_sex  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4080473           NaN       136591936            FASTQ       not provided   \n",
+       "ERR4080474           NaN       125862765            FASTQ       not provided   \n",
+       "ERR4080475           NaN       106116129            FASTQ       not provided   \n",
+       "ERR4080476           NaN       142761688            FASTQ       not provided   \n",
+       "ERR4080477           NaN       146011388            FASTQ       not provided   \n",
+       "...                  ...             ...              ...                ...   \n",
+       "SRR12554748          NaN             NaN              NaN                NaN   \n",
+       "SRR12554749          NaN             NaN              NaN                NaN   \n",
+       "SRR12588591          NaN             NaN              NaN                NaN   \n",
+       "SRR12598968          NaN             NaN              NaN                NaN   \n",
+       "SRR12598969          NaN             NaN              NaN                NaN   \n",
+       "\n",
+       "              submitted_sex   tax_id  sex  \n",
+       "run_accession                              \n",
+       "ERR4080473              NaN  2697049  NaN  \n",
+       "ERR4080474              NaN  2697049  NaN  \n",
+       "ERR4080475              NaN  2697049  NaN  \n",
+       "ERR4080476              NaN  2697049  NaN  \n",
+       "ERR4080477              NaN  2697049  NaN  \n",
+       "...                     ...      ...  ...  \n",
+       "SRR12554748             NaN  2697049  NaN  \n",
+       "SRR12554749             NaN  2697049  NaN  \n",
+       "SRR12588591             NaN  2697049  NaN  \n",
+       "SRR12598968             NaN  2697049  NaN  \n",
+       "SRR12598969             NaN  2697049  NaN  \n",
+       "\n",
+       "[56672 rows x 65 columns]"
+      ]
+     },
+     "execution_count": 108,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 109,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "defintiely_artic = df[df.apply(lambda x: 'artic' in x.to_string().lower(), axis=1)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 110,
+   "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>accession</th>\n",
+       "      <th>base_count</th>\n",
+       "      <th>cell_line</th>\n",
+       "      <th>cell_type</th>\n",
+       "      <th>center_name</th>\n",
+       "      <th>checklist</th>\n",
+       "      <th>collected_by</th>\n",
+       "      <th>collection_date</th>\n",
+       "      <th>country</th>\n",
+       "      <th>cram_index_ftp</th>\n",
+       "      <th>...</th>\n",
+       "      <th>study_alias</th>\n",
+       "      <th>study_title</th>\n",
+       "      <th>sub_species</th>\n",
+       "      <th>sub_strain</th>\n",
+       "      <th>submitted_bytes</th>\n",
+       "      <th>submitted_format</th>\n",
+       "      <th>submitted_host_sex</th>\n",
+       "      <th>submitted_sex</th>\n",
+       "      <th>tax_id</th>\n",
+       "      <th>sex</th>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>run_accession</th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "      <th></th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <th>ERR4238187</th>\n",
+       "      <td>SAMEA6915235</td>\n",
+       "      <td>47444042.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-Quadram Institute Bioscience-05-06-2...</td>\n",
+       "      <td>Large scale multiplexing of SARS-CoV-2 genomes...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.69982e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238188</th>\n",
+       "      <td>SAMEA6915392</td>\n",
+       "      <td>24758232.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-13</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-Quadram Institute Bioscience-05-06-2...</td>\n",
+       "      <td>Large scale multiplexing of SARS-CoV-2 genomes...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2.44243e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238189</th>\n",
+       "      <td>SAMEA6915293</td>\n",
+       "      <td>49131355.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-Quadram Institute Bioscience-05-06-2...</td>\n",
+       "      <td>Large scale multiplexing of SARS-CoV-2 genomes...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.83486e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238190</th>\n",
+       "      <td>SAMEA6915304</td>\n",
+       "      <td>45016521.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-02</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-Quadram Institute Bioscience-05-06-2...</td>\n",
+       "      <td>Large scale multiplexing of SARS-CoV-2 genomes...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>4.43407e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>ERR4238191</th>\n",
+       "      <td>SAMEA6915524</td>\n",
+       "      <td>12799114.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Quadram Institute Bioscience</td>\n",
+       "      <td>ERC000033</td>\n",
+       "      <td>Justin O&amp;apos;Grady</td>\n",
+       "      <td>2020-05-11</td>\n",
+       "      <td>United Kingdom</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>ena-STUDY-Quadram Institute Bioscience-05-06-2...</td>\n",
+       "      <td>Large scale multiplexing of SARS-CoV-2 genomes...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>1.26565e+07</td>\n",
+       "      <td>BAM</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</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>SRR12480579</th>\n",
+       "      <td>SAMN15691611</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-23</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA650037</td>\n",
+       "      <td>Johns Hopkins Viral Genomics of Severe acute r...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480580</th>\n",
+       "      <td>SAMN15691610</td>\n",
+       "      <td>6835912.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-24</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA650037</td>\n",
+       "      <td>Johns Hopkins Viral Genomics of Severe acute r...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480581</th>\n",
+       "      <td>SAMN15691609</td>\n",
+       "      <td>7529477.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-30</td>\n",
+       "      <td>USA: Maryland</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA650037</td>\n",
+       "      <td>Johns Hopkins Viral Genomics of Severe acute r...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480582</th>\n",
+       "      <td>SAMN15691608</td>\n",
+       "      <td>6314669.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-28</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA650037</td>\n",
+       "      <td>Johns Hopkins Viral Genomics of Severe acute r...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>male</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>male</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <th>SRR12480583</th>\n",
+       "      <td>SAMN15691607</td>\n",
+       "      <td>7533745.0</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>SUB7938744</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>Johns Hopkins Pathology</td>\n",
+       "      <td>2020-03-26</td>\n",
+       "      <td>USA: DC</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>...</td>\n",
+       "      <td>PRJNA650037</td>\n",
+       "      <td>Johns Hopkins Viral Genomics of Severe acute r...</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>female</td>\n",
+       "      <td>NaN</td>\n",
+       "      <td>2697049</td>\n",
+       "      <td>female</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table>\n",
+       "<p>1012 rows × 65 columns</p>\n",
+       "</div>"
+      ],
+      "text/plain": [
+       "                  accession  base_count cell_line  cell_type  \\\n",
+       "run_accession                                                  \n",
+       "ERR4238187     SAMEA6915235  47444042.0       NaN        NaN   \n",
+       "ERR4238188     SAMEA6915392  24758232.0       NaN        NaN   \n",
+       "ERR4238189     SAMEA6915293  49131355.0       NaN        NaN   \n",
+       "ERR4238190     SAMEA6915304  45016521.0       NaN        NaN   \n",
+       "ERR4238191     SAMEA6915524  12799114.0       NaN        NaN   \n",
+       "...                     ...         ...       ...        ...   \n",
+       "SRR12480579    SAMN15691611         NaN       NaN        NaN   \n",
+       "SRR12480580    SAMN15691610   6835912.0       NaN        NaN   \n",
+       "SRR12480581    SAMN15691609   7529477.0       NaN        NaN   \n",
+       "SRR12480582    SAMN15691608   6314669.0       NaN        NaN   \n",
+       "SRR12480583    SAMN15691607   7533745.0       NaN        NaN   \n",
+       "\n",
+       "                                center_name  checklist  \\\n",
+       "run_accession                                            \n",
+       "ERR4238187     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238188     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238189     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238190     Quadram Institute Bioscience  ERC000033   \n",
+       "ERR4238191     Quadram Institute Bioscience  ERC000033   \n",
+       "...                                     ...        ...   \n",
+       "SRR12480579                      SUB7938744        NaN   \n",
+       "SRR12480580                      SUB7938744        NaN   \n",
+       "SRR12480581                      SUB7938744        NaN   \n",
+       "SRR12480582                      SUB7938744        NaN   \n",
+       "SRR12480583                      SUB7938744        NaN   \n",
+       "\n",
+       "                          collected_by collection_date         country  \\\n",
+       "run_accession                                                            \n",
+       "ERR4238187         Justin O&apos;Grady      2020-05-11  United Kingdom   \n",
+       "ERR4238188         Justin O&apos;Grady      2020-05-13  United Kingdom   \n",
+       "ERR4238189         Justin O&apos;Grady      2020-05-11  United Kingdom   \n",
+       "ERR4238190         Justin O&apos;Grady      2020-05-02  United Kingdom   \n",
+       "ERR4238191         Justin O&apos;Grady      2020-05-11  United Kingdom   \n",
+       "...                                ...             ...             ...   \n",
+       "SRR12480579    Johns Hopkins Pathology      2020-03-23   USA: Maryland   \n",
+       "SRR12480580    Johns Hopkins Pathology      2020-03-24   USA: Maryland   \n",
+       "SRR12480581    Johns Hopkins Pathology      2020-03-30   USA: Maryland   \n",
+       "SRR12480582    Johns Hopkins Pathology      2020-03-28         USA: DC   \n",
+       "SRR12480583    Johns Hopkins Pathology      2020-03-26         USA: DC   \n",
+       "\n",
+       "              cram_index_ftp  ...  \\\n",
+       "run_accession                 ...   \n",
+       "ERR4238187               NaN  ...   \n",
+       "ERR4238188               NaN  ...   \n",
+       "ERR4238189               NaN  ...   \n",
+       "ERR4238190               NaN  ...   \n",
+       "ERR4238191               NaN  ...   \n",
+       "...                      ...  ...   \n",
+       "SRR12480579              NaN  ...   \n",
+       "SRR12480580              NaN  ...   \n",
+       "SRR12480581              NaN  ...   \n",
+       "SRR12480582              NaN  ...   \n",
+       "SRR12480583              NaN  ...   \n",
+       "\n",
+       "                                                     study_alias  \\\n",
+       "run_accession                                                      \n",
+       "ERR4238187     ena-STUDY-Quadram Institute Bioscience-05-06-2...   \n",
+       "ERR4238188     ena-STUDY-Quadram Institute Bioscience-05-06-2...   \n",
+       "ERR4238189     ena-STUDY-Quadram Institute Bioscience-05-06-2...   \n",
+       "ERR4238190     ena-STUDY-Quadram Institute Bioscience-05-06-2...   \n",
+       "ERR4238191     ena-STUDY-Quadram Institute Bioscience-05-06-2...   \n",
+       "...                                                          ...   \n",
+       "SRR12480579                                          PRJNA650037   \n",
+       "SRR12480580                                          PRJNA650037   \n",
+       "SRR12480581                                          PRJNA650037   \n",
+       "SRR12480582                                          PRJNA650037   \n",
+       "SRR12480583                                          PRJNA650037   \n",
+       "\n",
+       "                                                     study_title sub_species  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4238187     Large scale multiplexing of SARS-CoV-2 genomes...         NaN   \n",
+       "ERR4238188     Large scale multiplexing of SARS-CoV-2 genomes...         NaN   \n",
+       "ERR4238189     Large scale multiplexing of SARS-CoV-2 genomes...         NaN   \n",
+       "ERR4238190     Large scale multiplexing of SARS-CoV-2 genomes...         NaN   \n",
+       "ERR4238191     Large scale multiplexing of SARS-CoV-2 genomes...         NaN   \n",
+       "...                                                          ...         ...   \n",
+       "SRR12480579    Johns Hopkins Viral Genomics of Severe acute r...         NaN   \n",
+       "SRR12480580    Johns Hopkins Viral Genomics of Severe acute r...         NaN   \n",
+       "SRR12480581    Johns Hopkins Viral Genomics of Severe acute r...         NaN   \n",
+       "SRR12480582    Johns Hopkins Viral Genomics of Severe acute r...         NaN   \n",
+       "SRR12480583    Johns Hopkins Viral Genomics of Severe acute r...         NaN   \n",
+       "\n",
+       "              sub_strain submitted_bytes submitted_format submitted_host_sex  \\\n",
+       "run_accession                                                                  \n",
+       "ERR4238187           NaN     4.69982e+07              BAM               male   \n",
+       "ERR4238188           NaN     2.44243e+07              BAM             female   \n",
+       "ERR4238189           NaN     4.83486e+07              BAM               male   \n",
+       "ERR4238190           NaN     4.43407e+07              BAM             female   \n",
+       "ERR4238191           NaN     1.26565e+07              BAM               male   \n",
+       "...                  ...             ...              ...                ...   \n",
+       "SRR12480579          NaN             NaN              NaN             female   \n",
+       "SRR12480580          NaN             NaN              NaN             female   \n",
+       "SRR12480581          NaN             NaN              NaN             female   \n",
+       "SRR12480582          NaN             NaN              NaN               male   \n",
+       "SRR12480583          NaN             NaN              NaN             female   \n",
+       "\n",
+       "              submitted_sex   tax_id     sex  \n",
+       "run_accession                                 \n",
+       "ERR4238187              NaN  2697049    male  \n",
+       "ERR4238188              NaN  2697049  female  \n",
+       "ERR4238189              NaN  2697049    male  \n",
+       "ERR4238190              NaN  2697049  female  \n",
+       "ERR4238191              NaN  2697049    male  \n",
+       "...                     ...      ...     ...  \n",
+       "SRR12480579             NaN  2697049  female  \n",
+       "SRR12480580             NaN  2697049  female  \n",
+       "SRR12480581             NaN  2697049  female  \n",
+       "SRR12480582             NaN  2697049    male  \n",
+       "SRR12480583             NaN  2697049  female  \n",
+       "\n",
+       "[1012 rows x 65 columns]"
+      ]
+     },
+     "execution_count": 110,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "defintiely_artic"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 111,
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/Users/mvandenb/miniconda3/envs/sars_cov2/lib/python3.6/site-packages/ipykernel_launcher.py:1: SettingWithCopyWarning: \n",
+      "A value is trying to be set on a copy of a slice from a DataFrame.\n",
+      "Try using .loc[row_indexer,col_indexer] = value instead\n",
+      "\n",
+      "See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy\n",
+      "  \"\"\"Entry point for launching an IPython kernel.\n"
+     ]
+    }
+   ],
+   "source": [
+    "metagenomic_maybe['artic'] = False"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 120,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 122,
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "False    55660\n",
+       "True      1012\n",
+       "Name: artic, dtype: int64"
+      ]
+     },
+     "execution_count": 122,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "df['artic'].value_counts()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": []
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.6.10"
+  },
+  "papermill": {
+   "duration": 14.746701,
+   "end_time": "2020-09-09T00:37:48.528833",
+   "environment_variables": {},
+   "exception": null,
+   "input_path": "metadata_stats.ipynb",
+   "output_path": "metadata_stats_rendered.ipynb",
+   "parameters": {},
+   "start_time": "2020-09-09T00:37:33.782132",
+   "version": "2.1.1"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}
diff --git a/genomics/4-Variation/updates/nanopore_artic_accessions.tsv b/genomics/4-Variation/updates/nanopore_artic_accessions.tsv
new file mode 100644
index 00000000..cd0477fb
--- /dev/null
+++ b/genomics/4-Variation/updates/nanopore_artic_accessions.tsv
@@ -0,0 +1,235 @@
+run_accession	study_accession
+SRR12336747	PRJNA649101
+SRR12336758	PRJNA649101
+SRR12336769	PRJNA649101
+SRR12336780	PRJNA649101
+SRR12336791	PRJNA649101
+SRR12336802	PRJNA649101
+SRR12336813	PRJNA649101
+SRR12336820	PRJNA649101
+SRR12336821	PRJNA649101
+SRR12336822	PRJNA649101
+SRR12336823	PRJNA649101
+SRR12336824	PRJNA649101
+SRR12336825	PRJNA649101
+SRR12336826	PRJNA649101
+SRR12336827	PRJNA649101
+SRR12336828	PRJNA649101
+SRR12336829	PRJNA649101
+SRR12336830	PRJNA649101
+SRR12336831	PRJNA649101
+SRR12336832	PRJNA649101
+SRR12336833	PRJNA649101
+SRR12336834	PRJNA649101
+SRR12336835	PRJNA649101
+SRR12336836	PRJNA649101
+SRR12447360	PRJNA650037
+SRR12447361	PRJNA650037
+SRR12447362	PRJNA650037
+SRR12447363	PRJNA650037
+SRR12447365	PRJNA650037
+SRR12447366	PRJNA650037
+SRR12447367	PRJNA650037
+SRR12447368	PRJNA650037
+SRR12447369	PRJNA650037
+SRR12447370	PRJNA650037
+SRR12447371	PRJNA650037
+SRR12447372	PRJNA650037
+SRR12447373	PRJNA650037
+SRR12447374	PRJNA650037
+SRR12447376	PRJNA650037
+SRR12447377	PRJNA650037
+SRR12447378	PRJNA650037
+SRR12447379	PRJNA650037
+SRR12447380	PRJNA650037
+SRR12447381	PRJNA650037
+SRR12447382	PRJNA650037
+SRR12447383	PRJNA650037
+SRR12447384	PRJNA650037
+SRR12447385	PRJNA650037
+SRR12447413	PRJNA650037
+SRR12447414	PRJNA650037
+SRR12447415	PRJNA650037
+SRR12447416	PRJNA650037
+SRR12447417	PRJNA650037
+SRR12447419	PRJNA650037
+SRR12447420	PRJNA650037
+SRR12447421	PRJNA650037
+SRR12447422	PRJNA650037
+SRR12447423	PRJNA650037
+SRR12447424	PRJNA650037
+SRR12447425	PRJNA650037
+SRR12447426	PRJNA650037
+SRR12447427	PRJNA650037
+SRR12447428	PRJNA650037
+SRR12447430	PRJNA650037
+SRR12447431	PRJNA650037
+SRR12447432	PRJNA650037
+SRR12447433	PRJNA650037
+SRR12447434	PRJNA650037
+SRR12447435	PRJNA650037
+SRR12447436	PRJNA650037
+SRR12447437	PRJNA650037
+SRR12447438	PRJNA650037
+SRR12447439	PRJNA650037
+SRR12447441	PRJNA650037
+SRR12447442	PRJNA650037
+SRR12447443	PRJNA650037
+SRR12447444	PRJNA650037
+SRR12447445	PRJNA650037
+SRR12447446	PRJNA650037
+SRR12447447	PRJNA650037
+SRR12447448	PRJNA650037
+SRR12447449	PRJNA650037
+SRR12447450	PRJNA650037
+SRR12447452	PRJNA650037
+SRR12447453	PRJNA650037
+SRR12447454	PRJNA650037
+SRR12447455	PRJNA650037
+SRR12447456	PRJNA650037
+SRR12447457	PRJNA650037
+SRR12447458	PRJNA650037
+SRR12447459	PRJNA650037
+SRR12447460	PRJNA650037
+SRR12447461	PRJNA650037
+SRR12447463	PRJNA650037
+SRR12447464	PRJNA650037
+SRR12447465	PRJNA650037
+SRR12447466	PRJNA650037
+SRR12447467	PRJNA650037
+SRR12447468	PRJNA650037
+SRR12447469	PRJNA650037
+SRR12447470	PRJNA650037
+SRR12447471	PRJNA650037
+SRR12447472	PRJNA650037
+SRR12447476	PRJNA650037
+SRR12447477	PRJNA650037
+SRR12447478	PRJNA650037
+SRR12447479	PRJNA650037
+SRR12447480	PRJNA650037
+SRR12447481	PRJNA650037
+SRR12447482	PRJNA650037
+SRR12447483	PRJNA650037
+SRR12447484	PRJNA650037
+SRR12447485	PRJNA650037
+SRR12447487	PRJNA650037
+SRR12447488	PRJNA650037
+SRR12447489	PRJNA650037
+SRR12447490	PRJNA650037
+SRR12447491	PRJNA650037
+SRR12447492	PRJNA650037
+SRR12447493	PRJNA650037
+SRR12447494	PRJNA650037
+SRR12447495	PRJNA650037
+SRR12447496	PRJNA650037
+SRR12447498	PRJNA650037
+SRR12447499	PRJNA650037
+SRR12447500	PRJNA650037
+SRR12447501	PRJNA650037
+SRR12447502	PRJNA650037
+SRR12447503	PRJNA650037
+SRR12447504	PRJNA650037
+SRR12447505	PRJNA650037
+SRR12447506	PRJNA650037
+SRR12447507	PRJNA650037
+SRR12447509	PRJNA650037
+SRR12447510	PRJNA650037
+SRR12447511	PRJNA650037
+SRR12447512	PRJNA650037
+SRR12447513	PRJNA650037
+SRR12447514	PRJNA650037
+SRR12480469	PRJNA650037
+SRR12480471	PRJNA650037
+SRR12480473	PRJNA650037
+SRR12480474	PRJNA650037
+SRR12480475	PRJNA650037
+SRR12480476	PRJNA650037
+SRR12480477	PRJNA650037
+SRR12480478	PRJNA650037
+SRR12480479	PRJNA650037
+SRR12480480	PRJNA650037
+SRR12480481	PRJNA650037
+SRR12480482	PRJNA650037
+SRR12480484	PRJNA650037
+SRR12480485	PRJNA650037
+SRR12480486	PRJNA650037
+SRR12480487	PRJNA650037
+SRR12480488	PRJNA650037
+SRR12480489	PRJNA650037
+SRR12480490	PRJNA650037
+SRR12480491	PRJNA650037
+SRR12480492	PRJNA650037
+SRR12480493	PRJNA650037
+SRR12480494	PRJNA650037
+SRR12480495	PRJNA650037
+SRR12480496	PRJNA650037
+SRR12480497	PRJNA650037
+SRR12480498	PRJNA650037
+SRR12480499	PRJNA650037
+SRR12480500	PRJNA650037
+SRR12480501	PRJNA650037
+SRR12480502	PRJNA650037
+SRR12480503	PRJNA650037
+SRR12480504	PRJNA650037
+SRR12480505	PRJNA650037
+SRR12480506	PRJNA650037
+SRR12480507	PRJNA650037
+SRR12480508	PRJNA650037
+SRR12480509	PRJNA650037
+SRR12480510	PRJNA650037
+SRR12480511	PRJNA650037
+SRR12480512	PRJNA650037
+SRR12480513	PRJNA650037
+SRR12480514	PRJNA650037
+SRR12480515	PRJNA650037
+SRR12480516	PRJNA650037
+SRR12480517	PRJNA650037
+SRR12480518	PRJNA650037
+SRR12480519	PRJNA650037
+SRR12480520	PRJNA650037
+SRR12480521	PRJNA650037
+SRR12480522	PRJNA650037
+SRR12480523	PRJNA650037
+SRR12480524	PRJNA650037
+SRR12480525	PRJNA650037
+SRR12480526	PRJNA650037
+SRR12480528	PRJNA650037
+SRR12480529	PRJNA650037
+SRR12480530	PRJNA650037
+SRR12480531	PRJNA650037
+SRR12480532	PRJNA650037
+SRR12480533	PRJNA650037
+SRR12480534	PRJNA650037
+SRR12480535	PRJNA650037
+SRR12480536	PRJNA650037
+SRR12480537	PRJNA650037
+SRR12480539	PRJNA650037
+SRR12480540	PRJNA650037
+SRR12480541	PRJNA650037
+SRR12480542	PRJNA650037
+SRR12480543	PRJNA650037
+SRR12480544	PRJNA650037
+SRR12480545	PRJNA650037
+SRR12480546	PRJNA650037
+SRR12480547	PRJNA650037
+SRR12480548	PRJNA650037
+SRR12480550	PRJNA650037
+SRR12480551	PRJNA650037
+SRR12480552	PRJNA650037
+SRR12480553	PRJNA650037
+SRR12480554	PRJNA650037
+SRR12480555	PRJNA650037
+SRR12480569	PRJNA650037
+SRR12480570	PRJNA650037
+SRR12480571	PRJNA650037
+SRR12480572	PRJNA650037
+SRR12480573	PRJNA650037
+SRR12480575	PRJNA650037
+SRR12480576	PRJNA650037
+SRR12480577	PRJNA650037
+SRR12480578	PRJNA650037
+SRR12480579	PRJNA650037
+SRR12480580	PRJNA650037
+SRR12480581	PRJNA650037
+SRR12480582	PRJNA650037
+SRR12480583	PRJNA650037
diff --git a/genomics/4-Variation/updates/nanopore_metagenomic_accessions.tsv b/genomics/4-Variation/updates/nanopore_metagenomic_accessions.tsv
new file mode 100644
index 00000000..3e056760
--- /dev/null
+++ b/genomics/4-Variation/updates/nanopore_metagenomic_accessions.tsv
@@ -0,0 +1,33 @@
+run_accession	study_accession
+SRR11140745	PRJNA607948
+SRR11140747	PRJNA607948
+SRR11140749	PRJNA607948
+SRR11140751	PRJNA607948
+SRR11178050	PRJNA608242
+SRR11178051	PRJNA608242
+SRR11178052	PRJNA608242
+SRR11178053	PRJNA608242
+SRR11178054	PRJNA608242
+SRR11178055	PRJNA608242
+SRR11178056	PRJNA608242
+SRR11178057	PRJNA608242
+SRR11393271	PRJNA614504
+SRR11393272	PRJNA614504
+SRR11393273	PRJNA614504
+SRR11393274	PRJNA614504
+SRR11586701	PRJNA627286
+SRR11586702	PRJNA627286
+SRR11586703	PRJNA627286
+SRR11586704	PRJNA627286
+SRR11586705	PRJNA627286
+SRR11593367	PRJNA627229
+SRR12109250	PRJNA642869
+SRR12109251	PRJNA642869
+SRR12109252	PRJNA642869
+SRR12109253	PRJNA642869
+SRR12109254	PRJNA642869
+SRR12109255	PRJNA642869
+SRR12277390	PRJNA643530
+SRR12277391	PRJNA643530
+SRR12277392	PRJNA643530
+SRR12486810	PRJNA623797