5_6_gene_annot.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 37,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'\\n\\njupyter nbconvert 5_association.ipynb --to script\\npython 5_association.py albumin 2 0\\n\\nfor i in {00..101};do python 5_association.py $i 2 1;done\\n\\n\\nfor i in {00..10};do python 5_association.py $i 2 0;done\\nfor i in {11..20};do python 5_association.py $i 2 0;done\\nfor i in {21..30};do python 5_association.py $i 2 0;done\\nfor i in {31..40};do python 5_association.py $i 2 0;done\\nfor i in {41..50};do python 5_association.py $i 2 0;done\\nfor i in {51..60};do python 5_association.py $i 2 0;done\\nfor i in {61..70};do python 5_association.py $i 2 0;done\\nfor i in {71..80};do python 5_association.py $i 2 0;done\\nfor i in {91..90};do python 5_association.py $i 2 0;done\\nfor i in {91..101};do python 5_association.py $i 2 0;done\\nfor i in {51..60};do python 5_association.py $i 2 0;done\\nfor i in {51..60};do python 5_association.py $i 2 0;done\\nfor i in {51..60};do python 5_association.py $i 2 0;done\\n\\nfor i in {00..101};do python 5_association.py $i 1 0,2;done\\nfor i in {00..101};do python 5_association.py $i 1 1;done\\n\\nfor i in {00..20};do python 5_association.py $i 1 1;done\\nfor i in {21..40};do python 5_association.py $i 1 1;done\\nfor i in {41..60};do python 5_association.py $i 1 1;done\\nfor i in {61..80};do python 5_association.py $i 1 1;done\\nfor i in {81..101};do python 5_association.py $i 1 1;done\\n\\n'"
      ]
     },
     "execution_count": 37,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "import os\n",
    "import sys\n",
    "\n",
    "import logging\n",
    "import re\n",
    "import pathlib\n",
    "\n",
    "import datetime\n",
    "\n",
    "import numpy as np\n",
    "import pandas as pd\n",
    "from scipy.stats import pearsonr\n",
    "\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "from pyplink import PyPlink\n",
    "import seaborn as sns\n",
    "\n",
    "import statsmodels.api as sm\n",
    "\n",
    "import matplotlib.patches as patches\n",
    "import matplotlib\n",
    "\n",
    "from basic_tools import *\n",
    "\n",
    "\"\"\"\n",
    "\n",
    "jupyter nbconvert 5_association.ipynb --to script\n",
    "python 5_association.py albumin 2 0\n",
    "\n",
    "for i in {00..101};do python 5_association.py $i 2 1;done\n",
    "\n",
    "\n",
    "for i in {00..10};do python 5_association.py $i 2 0;done\n",
    "for i in {11..20};do python 5_association.py $i 2 0;done\n",
    "for i in {21..30};do python 5_association.py $i 2 0;done\n",
    "for i in {31..40};do python 5_association.py $i 2 0;done\n",
    "for i in {41..50};do python 5_association.py $i 2 0;done\n",
    "for i in {51..60};do python 5_association.py $i 2 0;done\n",
    "for i in {61..70};do python 5_association.py $i 2 0;done\n",
    "for i in {71..80};do python 5_association.py $i 2 0;done\n",
    "for i in {91..90};do python 5_association.py $i 2 0;done\n",
    "for i in {91..101};do python 5_association.py $i 2 0;done\n",
    "for i in {51..60};do python 5_association.py $i 2 0;done\n",
    "for i in {51..60};do python 5_association.py $i 2 0;done\n",
    "for i in {51..60};do python 5_association.py $i 2 0;done\n",
    "\n",
    "for i in {00..101};do python 5_association.py $i 1 0,2;done\n",
    "for i in {00..101};do python 5_association.py $i 1 1;done\n",
    "\n",
    "for i in {00..20};do python 5_association.py $i 1 1;done\n",
    "for i in {21..40};do python 5_association.py $i 1 1;done\n",
    "for i in {41..60};do python 5_association.py $i 1 1;done\n",
    "for i in {61..80};do python 5_association.py $i 1 1;done\n",
    "for i in {81..101};do python 5_association.py $i 1 1;done\n",
    "\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "plink_KCHIP_HLA_AA_SNP_1000G=PyPlink(plink_KCHIP_HLA_AA_SNP_1000G_path)\n",
    "plink_KCHIP_HLA_AA_SNP_1000G_fam=plink_KCHIP_HLA_AA_SNP_1000G.get_fam().astype({'fid':str,'iid':str}).rename(columns={'fid':'FID','iid':'IID'})\n",
    "plink_KCHIP_HLA_AA_SNP_1000G_bim=plink_KCHIP_HLA_AA_SNP_1000G.get_bim()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "phenotypes=pd.read_csv(pheno_all_file_path,sep='\\t')\n",
    "phenotypes=phenotypes.set_index('ID').loc[plink_KCHIP_HLA_AA_SNP_1000G_fam['IID']]\n",
    "\n",
    "binary_continuous_traits=sorted(phenotypes.columns[~phenotypes.columns.str.contains('x_ray')])    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "(209, 30)\n",
      "(207, 30)\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ch6845/tools/miniconda3/lib/python3.7/site-packages/ipykernel_launcher.py:14: 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: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  \n"
     ]
    }
   ],
   "source": [
    "gene_bed_path='data/mart_export_grch37.txt'\n",
    "gene_bed=pd.read_csv(gene_bed_path,sep='\\t')\n",
    "gene_bed=gene_bed.drop(columns='Exon stable ID')\n",
    "gene_bed=gene_bed[(gene_bed['Gene start (bp)']>=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.min())&(gene_bed['Gene end (bp)']<=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.max())]\n",
    "gene_bed=gene_bed[(gene_bed['Transcript type']=='protein_coding')]\n",
    "gene_bed=gene_bed[~gene_bed.duplicated(['Gene name','Gene start (bp)','Gene end (bp)'])]\n",
    "print(gene_bed.shape)\n",
    "gene_bed=gene_bed[~gene_bed.duplicated(['Gene name'])]\n",
    "print(gene_bed.shape)\n",
    "\n",
    "gene_assign=plink_KCHIP_HLA_AA_SNP_1000G_bim[['pos']]\n",
    "\n",
    "for idx,row in gene_bed.iterrows():\n",
    "    gene_assign[row['Gene name']]=0\n",
    "    \n",
    "for idx,row in gene_bed.iterrows():    \n",
    "    gene_assign[row['Gene name']][(gene_assign['pos']>=row['Gene start (bp)'])&(gene_assign['pos']<=row['Gene end (bp)'])]=1\n",
    "\n",
    "#gene_assign.columns=gene_assign.columns.str.replace('HLA-','HLA_')        \n",
    "    \n",
    "HLA_names=np.unique([i[0].split('_')[1] for i in plink_KCHIP_HLA_AA_SNP_1000G_bim[plink_KCHIP_HLA_AA_SNP_1000G_bim.index.str.contains('HLA_')].index.str.split('*')])\n",
    "\n",
    "for HLA_name in HLA_names:\n",
    "    gene_select=gene_assign[gene_assign.index.str.contains('HLA_'+HLA_name)|gene_assign.index.str.contains('SNPS_'+HLA_name)|gene_assign.index.str.contains('AA_'+HLA_name)]#print(gene_select.sort_values('pos').iloc[0],gene_select.sort_values('pos').iloc[-1])\n",
    "    HLA_name='HLA-{}'.format(HLA_name)\n",
    "    gene_assign[HLA_name][(gene_assign['pos']>=gene_select['pos'].min())&(gene_assign['pos']<=gene_select['pos'].max())]=1 "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(array(['protein_coding'], dtype=object),\n",
       " array(['protein_coding'], dtype=object))"
      ]
     },
     "execution_count": 42,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_bed['Gene type'].unique(),gene_bed['Transcript type'].unique()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 43,
   "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>Gene stable ID</th>\n",
       "      <th>Gene stable ID version</th>\n",
       "      <th>Transcript stable ID</th>\n",
       "      <th>Transcript stable ID version</th>\n",
       "      <th>Gene start (bp)</th>\n",
       "      <th>Gene end (bp)</th>\n",
       "      <th>Transcript start (bp)</th>\n",
       "      <th>Transcript end (bp)</th>\n",
       "      <th>Protein stable ID</th>\n",
       "      <th>Protein stable ID version</th>\n",
       "      <th>...</th>\n",
       "      <th>Transcript type</th>\n",
       "      <th>Gene type</th>\n",
       "      <th>Gene % GC content</th>\n",
       "      <th>Transcript count</th>\n",
       "      <th>Source of transcript name</th>\n",
       "      <th>Transcript name</th>\n",
       "      <th>Source of gene name</th>\n",
       "      <th>Gene name</th>\n",
       "      <th>GENCODE basic annotation</th>\n",
       "      <th>Transcript length (including UTRs and CDS)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1367</th>\n",
       "      <td>ENSG00000197279</td>\n",
       "      <td>ENSG00000197279.3</td>\n",
       "      <td>ENST00000377325</td>\n",
       "      <td>ENST00000377325.1</td>\n",
       "      <td>28048753</td>\n",
       "      <td>28057341</td>\n",
       "      <td>28048753</td>\n",
       "      <td>28057341</td>\n",
       "      <td>ENSP00000366542</td>\n",
       "      <td>ENSP00000366542.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.73</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZNF165-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZNF165</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2107</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1380</th>\n",
       "      <td>ENSG00000196812</td>\n",
       "      <td>ENSG00000196812.4</td>\n",
       "      <td>ENST00000340487</td>\n",
       "      <td>ENST00000340487.4</td>\n",
       "      <td>28092338</td>\n",
       "      <td>28097860</td>\n",
       "      <td>28092338</td>\n",
       "      <td>28097860</td>\n",
       "      <td>ENSP00000366527</td>\n",
       "      <td>ENSP00000366527.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.50</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZSCAN16-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZSCAN16</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1328</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1391</th>\n",
       "      <td>ENSG00000198315</td>\n",
       "      <td>ENSG00000198315.6</td>\n",
       "      <td>ENST00000457389</td>\n",
       "      <td>ENST00000457389.2</td>\n",
       "      <td>28109688</td>\n",
       "      <td>28127250</td>\n",
       "      <td>28109716</td>\n",
       "      <td>28121851</td>\n",
       "      <td>ENSP00000402948</td>\n",
       "      <td>ENSP00000402948.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>38.60</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZKSCAN8-003</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZKSCAN8</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2071</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1430</th>\n",
       "      <td>ENSG00000137185</td>\n",
       "      <td>ENSG00000137185.7</td>\n",
       "      <td>ENST00000531941</td>\n",
       "      <td>ENST00000531941.1</td>\n",
       "      <td>28192664</td>\n",
       "      <td>28201260</td>\n",
       "      <td>28192664</td>\n",
       "      <td>28194985</td>\n",
       "      <td>ENSP00000433307</td>\n",
       "      <td>ENSP00000433307.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>43.42</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZSCAN9-005</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZSCAN9</td>\n",
       "      <td>NaN</td>\n",
       "      <td>579</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1458</th>\n",
       "      <td>ENSG00000187626</td>\n",
       "      <td>ENSG00000187626.7</td>\n",
       "      <td>ENST00000377294</td>\n",
       "      <td>ENST00000377294.2</td>\n",
       "      <td>28212401</td>\n",
       "      <td>28227011</td>\n",
       "      <td>28212401</td>\n",
       "      <td>28220002</td>\n",
       "      <td>ENSP00000366509</td>\n",
       "      <td>ENSP00000366509.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>43.01</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZKSCAN4-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZKSCAN4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2375</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1468</th>\n",
       "      <td>ENSG00000189134</td>\n",
       "      <td>ENSG00000189134.3</td>\n",
       "      <td>ENST00000343684</td>\n",
       "      <td>ENST00000343684.3</td>\n",
       "      <td>28227098</td>\n",
       "      <td>28228736</td>\n",
       "      <td>28227098</td>\n",
       "      <td>28228736</td>\n",
       "      <td>ENSP00000345716</td>\n",
       "      <td>ENSP00000345716.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>44.66</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>NKAPL-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>NKAPL</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1639</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1481</th>\n",
       "      <td>ENSG00000137338</td>\n",
       "      <td>ENSG00000137338.4</td>\n",
       "      <td>ENST00000259883</td>\n",
       "      <td>ENST00000259883.3</td>\n",
       "      <td>28249314</td>\n",
       "      <td>28270326</td>\n",
       "      <td>28249349</td>\n",
       "      <td>28270326</td>\n",
       "      <td>ENSP00000259883</td>\n",
       "      <td>ENSP00000259883.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>39.92</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>PGBD1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>PGBD1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3100</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1498</th>\n",
       "      <td>ENSG00000235109</td>\n",
       "      <td>ENSG00000235109.3</td>\n",
       "      <td>ENST00000439158</td>\n",
       "      <td>ENST00000439158.1</td>\n",
       "      <td>28292470</td>\n",
       "      <td>28324048</td>\n",
       "      <td>28292514</td>\n",
       "      <td>28303911</td>\n",
       "      <td>ENSP00000413705</td>\n",
       "      <td>ENSP00000413705.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.29</td>\n",
       "      <td>18</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZSCAN31-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZSCAN31</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3050</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1566</th>\n",
       "      <td>ENSG00000189298</td>\n",
       "      <td>ENSG00000189298.9</td>\n",
       "      <td>ENST00000341464</td>\n",
       "      <td>ENST00000341464.5</td>\n",
       "      <td>28317691</td>\n",
       "      <td>28336947</td>\n",
       "      <td>28317727</td>\n",
       "      <td>28334523</td>\n",
       "      <td>ENSP00000341883</td>\n",
       "      <td>ENSP00000341883.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.03</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZKSCAN3-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZKSCAN3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1794</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1584</th>\n",
       "      <td>ENSG00000158691</td>\n",
       "      <td>ENSG00000158691.10</td>\n",
       "      <td>ENST00000361028</td>\n",
       "      <td>ENST00000361028.1</td>\n",
       "      <td>28346732</td>\n",
       "      <td>28367511</td>\n",
       "      <td>28346732</td>\n",
       "      <td>28367511</td>\n",
       "      <td>ENSP00000354305</td>\n",
       "      <td>ENSP00000354305.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.13</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZSCAN12-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZSCAN12</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5495</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1600</th>\n",
       "      <td>ENSG00000187987</td>\n",
       "      <td>ENSG00000187987.5</td>\n",
       "      <td>ENST00000289788</td>\n",
       "      <td>ENST00000289788.4</td>\n",
       "      <td>28399707</td>\n",
       "      <td>28411279</td>\n",
       "      <td>28400432</td>\n",
       "      <td>28411244</td>\n",
       "      <td>ENSP00000289788</td>\n",
       "      <td>ENSP00000289788.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>39.86</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZSCAN23-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZSCAN23</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3126</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1610</th>\n",
       "      <td>ENSG00000198704</td>\n",
       "      <td>ENSG00000198704.5</td>\n",
       "      <td>ENST00000361902</td>\n",
       "      <td>ENST00000361902.1</td>\n",
       "      <td>28471073</td>\n",
       "      <td>28495992</td>\n",
       "      <td>28471073</td>\n",
       "      <td>28483570</td>\n",
       "      <td>ENSP00000354581</td>\n",
       "      <td>ENSP00000354581.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.59</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>GPX6-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>GPX6</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1712</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1624</th>\n",
       "      <td>ENSG00000224586</td>\n",
       "      <td>ENSG00000224586.2</td>\n",
       "      <td>ENST00000412168</td>\n",
       "      <td>ENST00000412168.2</td>\n",
       "      <td>28493702</td>\n",
       "      <td>28502729</td>\n",
       "      <td>28493702</td>\n",
       "      <td>28502729</td>\n",
       "      <td>ENSP00000392398</td>\n",
       "      <td>ENSP00000392398.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>40.97</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>GPX5-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>GPX5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1540</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1643</th>\n",
       "      <td>ENSG00000232040</td>\n",
       "      <td>ENSG00000232040.2</td>\n",
       "      <td>ENST00000452236</td>\n",
       "      <td>ENST00000452236.2</td>\n",
       "      <td>28539407</td>\n",
       "      <td>28583989</td>\n",
       "      <td>28539407</td>\n",
       "      <td>28555112</td>\n",
       "      <td>ENSP00000395259</td>\n",
       "      <td>ENSP00000395259.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>39.71</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>SCAND3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>SCAND3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4877</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1678</th>\n",
       "      <td>ENSG00000204713</td>\n",
       "      <td>ENSG00000204713.6</td>\n",
       "      <td>ENST00000414543</td>\n",
       "      <td>ENST00000414543.1</td>\n",
       "      <td>28870779</td>\n",
       "      <td>28891766</td>\n",
       "      <td>28870779</td>\n",
       "      <td>28876766</td>\n",
       "      <td>ENSP00000400058</td>\n",
       "      <td>ENSP00000400058.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>44.66</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>TRIM27-003</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>TRIM27</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1813</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1714</th>\n",
       "      <td>ENSG00000204709</td>\n",
       "      <td>ENSG00000204709.4</td>\n",
       "      <td>ENST00000377186</td>\n",
       "      <td>ENST00000377186.3</td>\n",
       "      <td>28911654</td>\n",
       "      <td>28912314</td>\n",
       "      <td>28911654</td>\n",
       "      <td>28912314</td>\n",
       "      <td>ENSP00000366391</td>\n",
       "      <td>ENSP00000366391.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>48.26</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>C6orf100-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>C6orf100</td>\n",
       "      <td>1.0</td>\n",
       "      <td>466</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1723</th>\n",
       "      <td>ENSG00000197935</td>\n",
       "      <td>ENSG00000197935.6</td>\n",
       "      <td>ENST00000377179</td>\n",
       "      <td>ENST00000377179.3</td>\n",
       "      <td>28962562</td>\n",
       "      <td>28973093</td>\n",
       "      <td>28962562</td>\n",
       "      <td>28973037</td>\n",
       "      <td>ENSP00000366384</td>\n",
       "      <td>ENSP00000366384.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.01</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZNF311-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZNF311</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2730</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1737</th>\n",
       "      <td>ENSG00000204704</td>\n",
       "      <td>ENSG00000204704.2</td>\n",
       "      <td>ENST00000377175</td>\n",
       "      <td>ENST00000377175.1</td>\n",
       "      <td>29011990</td>\n",
       "      <td>29013017</td>\n",
       "      <td>29011990</td>\n",
       "      <td>29013017</td>\n",
       "      <td>ENSP00000366380</td>\n",
       "      <td>ENSP00000366380.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.15</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2W1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2W1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1028</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1740</th>\n",
       "      <td>ENSG00000204703</td>\n",
       "      <td>ENSG00000204703.3</td>\n",
       "      <td>ENST00000377173</td>\n",
       "      <td>ENST00000377173.2</td>\n",
       "      <td>29053985</td>\n",
       "      <td>29055090</td>\n",
       "      <td>29053985</td>\n",
       "      <td>29055090</td>\n",
       "      <td>ENSP00000366378</td>\n",
       "      <td>ENSP00000366378.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.50</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2B3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2B3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1106</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1741</th>\n",
       "      <td>ENSG00000204702</td>\n",
       "      <td>ENSG00000204702.4</td>\n",
       "      <td>ENST00000377171</td>\n",
       "      <td>ENST00000377171.3</td>\n",
       "      <td>29068386</td>\n",
       "      <td>29069658</td>\n",
       "      <td>29068386</td>\n",
       "      <td>29069658</td>\n",
       "      <td>ENSP00000366376</td>\n",
       "      <td>ENSP00000366376.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.56</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2J1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2J1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1273</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1742</th>\n",
       "      <td>ENSG00000204701</td>\n",
       "      <td>ENSG00000204701.1</td>\n",
       "      <td>ENST00000377169</td>\n",
       "      <td>ENST00000377169.1</td>\n",
       "      <td>29079668</td>\n",
       "      <td>29080603</td>\n",
       "      <td>29079668</td>\n",
       "      <td>29080603</td>\n",
       "      <td>ENSP00000366374</td>\n",
       "      <td>ENSP00000366374.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.62</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2J3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2J3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>936</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1746</th>\n",
       "      <td>ENSG00000204700</td>\n",
       "      <td>ENSG00000204700.3</td>\n",
       "      <td>ENST00000377167</td>\n",
       "      <td>ENST00000377167.2</td>\n",
       "      <td>29141311</td>\n",
       "      <td>29142351</td>\n",
       "      <td>29141311</td>\n",
       "      <td>29142351</td>\n",
       "      <td>ENSP00000366372</td>\n",
       "      <td>ENSP00000366372.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>44.48</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2J2-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2J2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1041</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1759</th>\n",
       "      <td>ENSG00000204695</td>\n",
       "      <td>ENSG00000204695.2</td>\n",
       "      <td>ENST00000377160</td>\n",
       "      <td>ENST00000377160.2</td>\n",
       "      <td>29274403</td>\n",
       "      <td>29275519</td>\n",
       "      <td>29274403</td>\n",
       "      <td>29275519</td>\n",
       "      <td>ENSP00000366365</td>\n",
       "      <td>ENSP00000366365.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>44.58</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR14J1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR14J1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1117</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1761</th>\n",
       "      <td>ENSG00000243729</td>\n",
       "      <td>ENSG00000243729.3</td>\n",
       "      <td>ENST00000377154</td>\n",
       "      <td>ENST00000377154.1</td>\n",
       "      <td>29323007</td>\n",
       "      <td>29399744</td>\n",
       "      <td>29323007</td>\n",
       "      <td>29399744</td>\n",
       "      <td>ENSP00000366359</td>\n",
       "      <td>ENSP00000366359.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>36.71</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR5V1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR5V1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1266</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1766</th>\n",
       "      <td>ENSG00000112462</td>\n",
       "      <td>ENSG00000112462.8</td>\n",
       "      <td>ENST00000396806</td>\n",
       "      <td>ENST00000396806.3</td>\n",
       "      <td>29341200</td>\n",
       "      <td>29343068</td>\n",
       "      <td>29341200</td>\n",
       "      <td>29343068</td>\n",
       "      <td>ENSP00000380023</td>\n",
       "      <td>ENSP00000380023.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>38.15</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR12D3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR12D3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1869</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1767</th>\n",
       "      <td>ENSG00000168787</td>\n",
       "      <td>ENSG00000168787.4</td>\n",
       "      <td>ENST00000383555</td>\n",
       "      <td>ENST00000383555.2</td>\n",
       "      <td>29364416</td>\n",
       "      <td>29365448</td>\n",
       "      <td>29364416</td>\n",
       "      <td>29365448</td>\n",
       "      <td>ENSP00000373047</td>\n",
       "      <td>ENSP00000373047.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.79</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR12D2-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR12D2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1033</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1769</th>\n",
       "      <td>ENSG00000204694</td>\n",
       "      <td>ENSG00000204694.6</td>\n",
       "      <td>ENST00000377148</td>\n",
       "      <td>ENST00000377148.1</td>\n",
       "      <td>29393281</td>\n",
       "      <td>29424848</td>\n",
       "      <td>29393281</td>\n",
       "      <td>29396243</td>\n",
       "      <td>ENSP00000366353</td>\n",
       "      <td>ENSP00000366353.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>39.08</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR11A1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR11A1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2482</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1777</th>\n",
       "      <td>ENSG00000206474</td>\n",
       "      <td>ENSG00000206474.6</td>\n",
       "      <td>ENST00000444197</td>\n",
       "      <td>ENST00000444197.2</td>\n",
       "      <td>29407083</td>\n",
       "      <td>29408731</td>\n",
       "      <td>29407083</td>\n",
       "      <td>29408731</td>\n",
       "      <td>ENSP00000419119</td>\n",
       "      <td>ENSP00000419119.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>49.97</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR10C1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR10C1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1649</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1778</th>\n",
       "      <td>ENSG00000204688</td>\n",
       "      <td>ENSG00000204688.5</td>\n",
       "      <td>ENST00000377136</td>\n",
       "      <td>ENST00000377136.1</td>\n",
       "      <td>29424958</td>\n",
       "      <td>29432105</td>\n",
       "      <td>29424958</td>\n",
       "      <td>29432105</td>\n",
       "      <td>ENSP00000366340</td>\n",
       "      <td>ENSP00000366340.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.35</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>OR2H1-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>OR2H1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3024</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1803</th>\n",
       "      <td>ENSG00000204687</td>\n",
       "      <td>ENSG00000204687.3</td>\n",
       "      <td>ENST00000377127</td>\n",
       "      <td>ENST00000377127.3</td>\n",
       "      <td>29454474</td>\n",
       "      <td>29455738</td>\n",
       "      <td>29454474</td>\n",
       "      <td>29455738</td>\n",
       "      <td>ENSP00000366331</td>\n",
       "      <td>ENSP00000366331.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>50.20</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>MAS1L-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>MAS1L</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1265</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>10782</th>\n",
       "      <td>ENSG00000204220</td>\n",
       "      <td>ENSG00000204220.5</td>\n",
       "      <td>ENST00000395131</td>\n",
       "      <td>ENST00000395131.1</td>\n",
       "      <td>33257079</td>\n",
       "      <td>33266178</td>\n",
       "      <td>33257079</td>\n",
       "      <td>33258710</td>\n",
       "      <td>ENSP00000378563</td>\n",
       "      <td>ENSP00000378563.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>54.13</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>PFDN6-005</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>PFDN6</td>\n",
       "      <td>1.0</td>\n",
       "      <td>884</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10859</th>\n",
       "      <td>ENSG00000237441</td>\n",
       "      <td>ENSG00000237441.5</td>\n",
       "      <td>ENST00000497454</td>\n",
       "      <td>ENST00000497454.1</td>\n",
       "      <td>33259431</td>\n",
       "      <td>33267101</td>\n",
       "      <td>33259431</td>\n",
       "      <td>33267101</td>\n",
       "      <td>ENSP00000420211</td>\n",
       "      <td>ENSP00000420211.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>57.12</td>\n",
       "      <td>12</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>RGL2-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>RGL2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3278</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10926</th>\n",
       "      <td>ENSG00000231925</td>\n",
       "      <td>ENSG00000231925.7</td>\n",
       "      <td>ENST00000434618</td>\n",
       "      <td>ENST00000434618.2</td>\n",
       "      <td>33267471</td>\n",
       "      <td>33282164</td>\n",
       "      <td>33267471</td>\n",
       "      <td>33282164</td>\n",
       "      <td>ENSP00000395701</td>\n",
       "      <td>ENSP00000395701.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>50.01</td>\n",
       "      <td>9</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>TAPBP-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>TAPBP</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3759</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10979</th>\n",
       "      <td>ENSG00000236104</td>\n",
       "      <td>ENSG00000236104.2</td>\n",
       "      <td>ENST00000431845</td>\n",
       "      <td>ENST00000431845.2</td>\n",
       "      <td>33282183</td>\n",
       "      <td>33285719</td>\n",
       "      <td>33282195</td>\n",
       "      <td>33285512</td>\n",
       "      <td>ENSP00000407545</td>\n",
       "      <td>ENSP00000407545.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>59.46</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZBTB22-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZBTB22</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2651</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10985</th>\n",
       "      <td>ENSG00000204209</td>\n",
       "      <td>ENSG00000204209.6</td>\n",
       "      <td>ENST00000266000</td>\n",
       "      <td>ENST00000266000.6</td>\n",
       "      <td>33286335</td>\n",
       "      <td>33297046</td>\n",
       "      <td>33286335</td>\n",
       "      <td>33290787</td>\n",
       "      <td>ENSP00000266000</td>\n",
       "      <td>ENSP00000266000.6</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>51.32</td>\n",
       "      <td>12</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>DAXX-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>DAXX</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2606</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11038</th>\n",
       "      <td>ENSG00000237649</td>\n",
       "      <td>ENSG00000237649.3</td>\n",
       "      <td>ENST00000428849</td>\n",
       "      <td>ENST00000428849.2</td>\n",
       "      <td>33359313</td>\n",
       "      <td>33377701</td>\n",
       "      <td>33359313</td>\n",
       "      <td>33377701</td>\n",
       "      <td>ENSP00000393963</td>\n",
       "      <td>ENSP00000393963.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>47.68</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>KIFC1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>KIFC1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2706</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11064</th>\n",
       "      <td>ENSG00000112511</td>\n",
       "      <td>ENSG00000112511.13</td>\n",
       "      <td>ENST00000427004</td>\n",
       "      <td>ENST00000427004.1</td>\n",
       "      <td>33378176</td>\n",
       "      <td>33384230</td>\n",
       "      <td>33378176</td>\n",
       "      <td>33381071</td>\n",
       "      <td>ENSP00000410494</td>\n",
       "      <td>ENSP00000410494.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>57.49</td>\n",
       "      <td>11</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>PHF1-005</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>PHF1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>609</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11159</th>\n",
       "      <td>ENSG00000112514</td>\n",
       "      <td>ENSG00000112514.11</td>\n",
       "      <td>ENST00000374500</td>\n",
       "      <td>ENST00000374500.5</td>\n",
       "      <td>33384219</td>\n",
       "      <td>33386094</td>\n",
       "      <td>33384219</td>\n",
       "      <td>33386094</td>\n",
       "      <td>ENSP00000363624</td>\n",
       "      <td>ENSP00000363624.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>54.90</td>\n",
       "      <td>14</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>CUTA-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>CUTA</td>\n",
       "      <td>1.0</td>\n",
       "      <td>937</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11234</th>\n",
       "      <td>ENSG00000197283</td>\n",
       "      <td>ENSG00000197283.8</td>\n",
       "      <td>ENST00000418600</td>\n",
       "      <td>ENST00000418600.2</td>\n",
       "      <td>33387847</td>\n",
       "      <td>33421466</td>\n",
       "      <td>33387941</td>\n",
       "      <td>33421466</td>\n",
       "      <td>ENSP00000403636</td>\n",
       "      <td>ENSP00000403636.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>53.94</td>\n",
       "      <td>9</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>SYNGAP1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>SYNGAP1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>5916</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11335</th>\n",
       "      <td>ENSG00000213588</td>\n",
       "      <td>ENSG00000213588.4</td>\n",
       "      <td>ENST00000395064</td>\n",
       "      <td>ENST00000395064.2</td>\n",
       "      <td>33422356</td>\n",
       "      <td>33425325</td>\n",
       "      <td>33422356</td>\n",
       "      <td>33425325</td>\n",
       "      <td>ENSP00000378503</td>\n",
       "      <td>ENSP00000378503.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>52.39</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ZBTB9-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ZBTB9</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2716</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11338</th>\n",
       "      <td>ENSG00000030110</td>\n",
       "      <td>ENSG00000030110.8</td>\n",
       "      <td>ENST00000374467</td>\n",
       "      <td>ENST00000374467.3</td>\n",
       "      <td>33540329</td>\n",
       "      <td>33548019</td>\n",
       "      <td>33540329</td>\n",
       "      <td>33548019</td>\n",
       "      <td>ENSP00000363591</td>\n",
       "      <td>ENSP00000363591.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>57.17</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>BAK1-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>BAK1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2136</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11358</th>\n",
       "      <td>ENSG00000204188</td>\n",
       "      <td>ENSG00000204188.3</td>\n",
       "      <td>ENST00000374458</td>\n",
       "      <td>ENST00000374458.1</td>\n",
       "      <td>33551515</td>\n",
       "      <td>33556803</td>\n",
       "      <td>33551515</td>\n",
       "      <td>33556803</td>\n",
       "      <td>ENSP00000363582</td>\n",
       "      <td>ENSP00000363582.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>55.97</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>GGNBP1-201</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>GGNBP1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>960</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11366</th>\n",
       "      <td>ENSG00000096433</td>\n",
       "      <td>ENSG00000096433.6</td>\n",
       "      <td>ENST00000374316</td>\n",
       "      <td>ENST00000374316.5</td>\n",
       "      <td>33588142</td>\n",
       "      <td>33664351</td>\n",
       "      <td>33588142</td>\n",
       "      <td>33664351</td>\n",
       "      <td>ENSP00000363435</td>\n",
       "      <td>ENSP00000363435.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>55.13</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>ITPR3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>ITPR3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9870</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11484</th>\n",
       "      <td>ENSG00000137288</td>\n",
       "      <td>ENSG00000137288.5</td>\n",
       "      <td>ENST00000374231</td>\n",
       "      <td>ENST00000374231.4</td>\n",
       "      <td>33662070</td>\n",
       "      <td>33679504</td>\n",
       "      <td>33663126</td>\n",
       "      <td>33679461</td>\n",
       "      <td>ENSP00000363348</td>\n",
       "      <td>ENSP00000363348.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>49.22</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>UQCC2-004</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>UQCC2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>509</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11496</th>\n",
       "      <td>ENSG00000269490</td>\n",
       "      <td>ENSG00000269490.1</td>\n",
       "      <td>ENST00000594414</td>\n",
       "      <td>ENST00000594414.1</td>\n",
       "      <td>33663196</td>\n",
       "      <td>33663474</td>\n",
       "      <td>33663196</td>\n",
       "      <td>33663474</td>\n",
       "      <td>ENSP00000469270</td>\n",
       "      <td>ENSP00000469270.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>59.14</td>\n",
       "      <td>1</td>\n",
       "      <td>UniProt transcript name</td>\n",
       "      <td>SBP1-201</td>\n",
       "      <td>UniProtKB Gene Name</td>\n",
       "      <td>SBP1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>279</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11498</th>\n",
       "      <td>ENSG00000161896</td>\n",
       "      <td>ENSG00000161896.6</td>\n",
       "      <td>ENST00000293756</td>\n",
       "      <td>ENST00000293756.4</td>\n",
       "      <td>33689444</td>\n",
       "      <td>33714762</td>\n",
       "      <td>33689447</td>\n",
       "      <td>33714682</td>\n",
       "      <td>ENSP00000293756</td>\n",
       "      <td>ENSP00000293756.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>53.41</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>IP6K3-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>IP6K3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2610</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11511</th>\n",
       "      <td>ENSG00000161904</td>\n",
       "      <td>ENSG00000161904.7</td>\n",
       "      <td>ENST00000506578</td>\n",
       "      <td>ENST00000506578.1</td>\n",
       "      <td>33738979</td>\n",
       "      <td>33756913</td>\n",
       "      <td>33738979</td>\n",
       "      <td>33744921</td>\n",
       "      <td>ENSP00000423715</td>\n",
       "      <td>ENSP00000423715.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>53.18</td>\n",
       "      <td>13</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>LEMD2-013</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>LEMD2</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1684</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11582</th>\n",
       "      <td>ENSG00000096395</td>\n",
       "      <td>ENSG00000096395.6</td>\n",
       "      <td>ENST00000430124</td>\n",
       "      <td>ENST00000430124.2</td>\n",
       "      <td>33762450</td>\n",
       "      <td>33771788</td>\n",
       "      <td>33762450</td>\n",
       "      <td>33771788</td>\n",
       "      <td>ENSP00000388825</td>\n",
       "      <td>ENSP00000388825.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>54.77</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>MLN-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>MLN</td>\n",
       "      <td>1.0</td>\n",
       "      <td>566</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11619</th>\n",
       "      <td>ENSG00000124493</td>\n",
       "      <td>ENSG00000124493.9</td>\n",
       "      <td>ENST00000538487</td>\n",
       "      <td>ENST00000538487.2</td>\n",
       "      <td>33989628</td>\n",
       "      <td>34123399</td>\n",
       "      <td>33989628</td>\n",
       "      <td>34113857</td>\n",
       "      <td>ENSP00000440556</td>\n",
       "      <td>ENSP00000440556.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>55.92</td>\n",
       "      <td>14</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>GRM4-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>GRM4</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4153</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11736</th>\n",
       "      <td>ENSG00000137309</td>\n",
       "      <td>ENSG00000137309.15</td>\n",
       "      <td>ENST00000347617</td>\n",
       "      <td>ENST00000347617.6</td>\n",
       "      <td>34204650</td>\n",
       "      <td>34214008</td>\n",
       "      <td>34204650</td>\n",
       "      <td>34214008</td>\n",
       "      <td>ENSP00000288245</td>\n",
       "      <td>ENSP00000288245.9</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>57.83</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HMGA1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1773</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11773</th>\n",
       "      <td>ENSG00000186577</td>\n",
       "      <td>ENSG00000186577.7</td>\n",
       "      <td>ENST00000476320</td>\n",
       "      <td>ENST00000476320.1</td>\n",
       "      <td>34214157</td>\n",
       "      <td>34217247</td>\n",
       "      <td>34214157</td>\n",
       "      <td>34217247</td>\n",
       "      <td>ENSP00000417604</td>\n",
       "      <td>ENSP00000417604.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>61.63</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>C6orf1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>C6orf1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1297</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11812</th>\n",
       "      <td>ENSG00000272325</td>\n",
       "      <td>ENSG00000272325.1</td>\n",
       "      <td>ENST00000607016</td>\n",
       "      <td>ENST00000607016.1</td>\n",
       "      <td>34247456</td>\n",
       "      <td>34360451</td>\n",
       "      <td>34247456</td>\n",
       "      <td>34360451</td>\n",
       "      <td>ENSP00000476119</td>\n",
       "      <td>ENSP00000476119.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.12</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>NUDT3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>NUDT3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9905</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11817</th>\n",
       "      <td>ENSG00000270800</td>\n",
       "      <td>ENSG00000270800.1</td>\n",
       "      <td>ENST00000605528</td>\n",
       "      <td>ENST00000605528.1</td>\n",
       "      <td>34256547</td>\n",
       "      <td>34393825</td>\n",
       "      <td>34256547</td>\n",
       "      <td>34393825</td>\n",
       "      <td>ENSP00000475027</td>\n",
       "      <td>ENSP00000475027.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>43.35</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>RPS10-NUDT3-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>RPS10-NUDT3</td>\n",
       "      <td>1.0</td>\n",
       "      <td>876</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11826</th>\n",
       "      <td>ENSG00000124614</td>\n",
       "      <td>ENSG00000124614.9</td>\n",
       "      <td>ENST00000344700</td>\n",
       "      <td>ENST00000344700.3</td>\n",
       "      <td>34385231</td>\n",
       "      <td>34393902</td>\n",
       "      <td>34385231</td>\n",
       "      <td>34392998</td>\n",
       "      <td>ENSP00000363169</td>\n",
       "      <td>ENSP00000363169.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>47.56</td>\n",
       "      <td>6</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>RPS10-005</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>RPS10</td>\n",
       "      <td>1.0</td>\n",
       "      <td>650</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11859</th>\n",
       "      <td>ENSG00000124507</td>\n",
       "      <td>ENSG00000124507.6</td>\n",
       "      <td>ENST00000244458</td>\n",
       "      <td>ENST00000244458.2</td>\n",
       "      <td>34433916</td>\n",
       "      <td>34503006</td>\n",
       "      <td>34433916</td>\n",
       "      <td>34503006</td>\n",
       "      <td>ENSP00000244458</td>\n",
       "      <td>ENSP00000244458.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>51.33</td>\n",
       "      <td>6</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>PACSIN1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>PACSIN1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11901</th>\n",
       "      <td>ENSG00000124664</td>\n",
       "      <td>ENSG00000124664.6</td>\n",
       "      <td>ENST00000374037</td>\n",
       "      <td>ENST00000374037.3</td>\n",
       "      <td>34505579</td>\n",
       "      <td>34524110</td>\n",
       "      <td>34505579</td>\n",
       "      <td>34524091</td>\n",
       "      <td>ENSP00000363149</td>\n",
       "      <td>ENSP00000363149.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>57.98</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>SPDEF-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>SPDEF</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1895</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11913</th>\n",
       "      <td>ENSG00000196821</td>\n",
       "      <td>ENSG00000196821.5</td>\n",
       "      <td>ENST00000374023</td>\n",
       "      <td>ENST00000374023.3</td>\n",
       "      <td>34555065</td>\n",
       "      <td>34664636</td>\n",
       "      <td>34555065</td>\n",
       "      <td>34664624</td>\n",
       "      <td>ENSP00000363135</td>\n",
       "      <td>ENSP00000363135.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.83</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>C6orf106-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>C6orf106</td>\n",
       "      <td>1.0</td>\n",
       "      <td>4418</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11939</th>\n",
       "      <td>ENSG00000124562</td>\n",
       "      <td>ENSG00000124562.5</td>\n",
       "      <td>ENST00000244520</td>\n",
       "      <td>ENST00000244520.5</td>\n",
       "      <td>34725183</td>\n",
       "      <td>34741571</td>\n",
       "      <td>34725183</td>\n",
       "      <td>34741571</td>\n",
       "      <td>ENSP00000244520</td>\n",
       "      <td>ENSP00000244520.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.71</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>SNRPC-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>SNRPC</td>\n",
       "      <td>1.0</td>\n",
       "      <td>842</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11961</th>\n",
       "      <td>ENSG00000065060</td>\n",
       "      <td>ENSG00000065060.12</td>\n",
       "      <td>ENST00000192788</td>\n",
       "      <td>ENST00000192788.5</td>\n",
       "      <td>34759857</td>\n",
       "      <td>34850915</td>\n",
       "      <td>34759857</td>\n",
       "      <td>34845291</td>\n",
       "      <td>ENSP00000192788</td>\n",
       "      <td>ENSP00000192788.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.62</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>UHRF1BP1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>UHRF1BP1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>9570</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12005</th>\n",
       "      <td>ENSG00000064995</td>\n",
       "      <td>ENSG00000064995.12</td>\n",
       "      <td>ENST00000361288</td>\n",
       "      <td>ENST00000361288.4</td>\n",
       "      <td>34845555</td>\n",
       "      <td>34855866</td>\n",
       "      <td>34845555</td>\n",
       "      <td>34855866</td>\n",
       "      <td>ENSP00000354633</td>\n",
       "      <td>ENSP00000354633.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>41.49</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>TAF11-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>TAF11</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1580</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>207 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "        Gene stable ID Gene stable ID version Transcript stable ID  \\\n",
       "1367   ENSG00000197279      ENSG00000197279.3      ENST00000377325   \n",
       "1380   ENSG00000196812      ENSG00000196812.4      ENST00000340487   \n",
       "1391   ENSG00000198315      ENSG00000198315.6      ENST00000457389   \n",
       "1430   ENSG00000137185      ENSG00000137185.7      ENST00000531941   \n",
       "1458   ENSG00000187626      ENSG00000187626.7      ENST00000377294   \n",
       "1468   ENSG00000189134      ENSG00000189134.3      ENST00000343684   \n",
       "1481   ENSG00000137338      ENSG00000137338.4      ENST00000259883   \n",
       "1498   ENSG00000235109      ENSG00000235109.3      ENST00000439158   \n",
       "1566   ENSG00000189298      ENSG00000189298.9      ENST00000341464   \n",
       "1584   ENSG00000158691     ENSG00000158691.10      ENST00000361028   \n",
       "1600   ENSG00000187987      ENSG00000187987.5      ENST00000289788   \n",
       "1610   ENSG00000198704      ENSG00000198704.5      ENST00000361902   \n",
       "1624   ENSG00000224586      ENSG00000224586.2      ENST00000412168   \n",
       "1643   ENSG00000232040      ENSG00000232040.2      ENST00000452236   \n",
       "1678   ENSG00000204713      ENSG00000204713.6      ENST00000414543   \n",
       "1714   ENSG00000204709      ENSG00000204709.4      ENST00000377186   \n",
       "1723   ENSG00000197935      ENSG00000197935.6      ENST00000377179   \n",
       "1737   ENSG00000204704      ENSG00000204704.2      ENST00000377175   \n",
       "1740   ENSG00000204703      ENSG00000204703.3      ENST00000377173   \n",
       "1741   ENSG00000204702      ENSG00000204702.4      ENST00000377171   \n",
       "1742   ENSG00000204701      ENSG00000204701.1      ENST00000377169   \n",
       "1746   ENSG00000204700      ENSG00000204700.3      ENST00000377167   \n",
       "1759   ENSG00000204695      ENSG00000204695.2      ENST00000377160   \n",
       "1761   ENSG00000243729      ENSG00000243729.3      ENST00000377154   \n",
       "1766   ENSG00000112462      ENSG00000112462.8      ENST00000396806   \n",
       "1767   ENSG00000168787      ENSG00000168787.4      ENST00000383555   \n",
       "1769   ENSG00000204694      ENSG00000204694.6      ENST00000377148   \n",
       "1777   ENSG00000206474      ENSG00000206474.6      ENST00000444197   \n",
       "1778   ENSG00000204688      ENSG00000204688.5      ENST00000377136   \n",
       "1803   ENSG00000204687      ENSG00000204687.3      ENST00000377127   \n",
       "...                ...                    ...                  ...   \n",
       "10782  ENSG00000204220      ENSG00000204220.5      ENST00000395131   \n",
       "10859  ENSG00000237441      ENSG00000237441.5      ENST00000497454   \n",
       "10926  ENSG00000231925      ENSG00000231925.7      ENST00000434618   \n",
       "10979  ENSG00000236104      ENSG00000236104.2      ENST00000431845   \n",
       "10985  ENSG00000204209      ENSG00000204209.6      ENST00000266000   \n",
       "11038  ENSG00000237649      ENSG00000237649.3      ENST00000428849   \n",
       "11064  ENSG00000112511     ENSG00000112511.13      ENST00000427004   \n",
       "11159  ENSG00000112514     ENSG00000112514.11      ENST00000374500   \n",
       "11234  ENSG00000197283      ENSG00000197283.8      ENST00000418600   \n",
       "11335  ENSG00000213588      ENSG00000213588.4      ENST00000395064   \n",
       "11338  ENSG00000030110      ENSG00000030110.8      ENST00000374467   \n",
       "11358  ENSG00000204188      ENSG00000204188.3      ENST00000374458   \n",
       "11366  ENSG00000096433      ENSG00000096433.6      ENST00000374316   \n",
       "11484  ENSG00000137288      ENSG00000137288.5      ENST00000374231   \n",
       "11496  ENSG00000269490      ENSG00000269490.1      ENST00000594414   \n",
       "11498  ENSG00000161896      ENSG00000161896.6      ENST00000293756   \n",
       "11511  ENSG00000161904      ENSG00000161904.7      ENST00000506578   \n",
       "11582  ENSG00000096395      ENSG00000096395.6      ENST00000430124   \n",
       "11619  ENSG00000124493      ENSG00000124493.9      ENST00000538487   \n",
       "11736  ENSG00000137309     ENSG00000137309.15      ENST00000347617   \n",
       "11773  ENSG00000186577      ENSG00000186577.7      ENST00000476320   \n",
       "11812  ENSG00000272325      ENSG00000272325.1      ENST00000607016   \n",
       "11817  ENSG00000270800      ENSG00000270800.1      ENST00000605528   \n",
       "11826  ENSG00000124614      ENSG00000124614.9      ENST00000344700   \n",
       "11859  ENSG00000124507      ENSG00000124507.6      ENST00000244458   \n",
       "11901  ENSG00000124664      ENSG00000124664.6      ENST00000374037   \n",
       "11913  ENSG00000196821      ENSG00000196821.5      ENST00000374023   \n",
       "11939  ENSG00000124562      ENSG00000124562.5      ENST00000244520   \n",
       "11961  ENSG00000065060     ENSG00000065060.12      ENST00000192788   \n",
       "12005  ENSG00000064995     ENSG00000064995.12      ENST00000361288   \n",
       "\n",
       "      Transcript stable ID version  Gene start (bp)  Gene end (bp)  \\\n",
       "1367             ENST00000377325.1         28048753       28057341   \n",
       "1380             ENST00000340487.4         28092338       28097860   \n",
       "1391             ENST00000457389.2         28109688       28127250   \n",
       "1430             ENST00000531941.1         28192664       28201260   \n",
       "1458             ENST00000377294.2         28212401       28227011   \n",
       "1468             ENST00000343684.3         28227098       28228736   \n",
       "1481             ENST00000259883.3         28249314       28270326   \n",
       "1498             ENST00000439158.1         28292470       28324048   \n",
       "1566             ENST00000341464.5         28317691       28336947   \n",
       "1584             ENST00000361028.1         28346732       28367511   \n",
       "1600             ENST00000289788.4         28399707       28411279   \n",
       "1610             ENST00000361902.1         28471073       28495992   \n",
       "1624             ENST00000412168.2         28493702       28502729   \n",
       "1643             ENST00000452236.2         28539407       28583989   \n",
       "1678             ENST00000414543.1         28870779       28891766   \n",
       "1714             ENST00000377186.3         28911654       28912314   \n",
       "1723             ENST00000377179.3         28962562       28973093   \n",
       "1737             ENST00000377175.1         29011990       29013017   \n",
       "1740             ENST00000377173.2         29053985       29055090   \n",
       "1741             ENST00000377171.3         29068386       29069658   \n",
       "1742             ENST00000377169.1         29079668       29080603   \n",
       "1746             ENST00000377167.2         29141311       29142351   \n",
       "1759             ENST00000377160.2         29274403       29275519   \n",
       "1761             ENST00000377154.1         29323007       29399744   \n",
       "1766             ENST00000396806.3         29341200       29343068   \n",
       "1767             ENST00000383555.2         29364416       29365448   \n",
       "1769             ENST00000377148.1         29393281       29424848   \n",
       "1777             ENST00000444197.2         29407083       29408731   \n",
       "1778             ENST00000377136.1         29424958       29432105   \n",
       "1803             ENST00000377127.3         29454474       29455738   \n",
       "...                            ...              ...            ...   \n",
       "10782            ENST00000395131.1         33257079       33266178   \n",
       "10859            ENST00000497454.1         33259431       33267101   \n",
       "10926            ENST00000434618.2         33267471       33282164   \n",
       "10979            ENST00000431845.2         33282183       33285719   \n",
       "10985            ENST00000266000.6         33286335       33297046   \n",
       "11038            ENST00000428849.2         33359313       33377701   \n",
       "11064            ENST00000427004.1         33378176       33384230   \n",
       "11159            ENST00000374500.5         33384219       33386094   \n",
       "11234            ENST00000418600.2         33387847       33421466   \n",
       "11335            ENST00000395064.2         33422356       33425325   \n",
       "11338            ENST00000374467.3         33540329       33548019   \n",
       "11358            ENST00000374458.1         33551515       33556803   \n",
       "11366            ENST00000374316.5         33588142       33664351   \n",
       "11484            ENST00000374231.4         33662070       33679504   \n",
       "11496            ENST00000594414.1         33663196       33663474   \n",
       "11498            ENST00000293756.4         33689444       33714762   \n",
       "11511            ENST00000506578.1         33738979       33756913   \n",
       "11582            ENST00000430124.2         33762450       33771788   \n",
       "11619            ENST00000538487.2         33989628       34123399   \n",
       "11736            ENST00000347617.6         34204650       34214008   \n",
       "11773            ENST00000476320.1         34214157       34217247   \n",
       "11812            ENST00000607016.1         34247456       34360451   \n",
       "11817            ENST00000605528.1         34256547       34393825   \n",
       "11826            ENST00000344700.3         34385231       34393902   \n",
       "11859            ENST00000244458.2         34433916       34503006   \n",
       "11901            ENST00000374037.3         34505579       34524110   \n",
       "11913            ENST00000374023.3         34555065       34664636   \n",
       "11939            ENST00000244520.5         34725183       34741571   \n",
       "11961            ENST00000192788.5         34759857       34850915   \n",
       "12005            ENST00000361288.4         34845555       34855866   \n",
       "\n",
       "       Transcript start (bp)  Transcript end (bp) Protein stable ID  \\\n",
       "1367                28048753             28057341   ENSP00000366542   \n",
       "1380                28092338             28097860   ENSP00000366527   \n",
       "1391                28109716             28121851   ENSP00000402948   \n",
       "1430                28192664             28194985   ENSP00000433307   \n",
       "1458                28212401             28220002   ENSP00000366509   \n",
       "1468                28227098             28228736   ENSP00000345716   \n",
       "1481                28249349             28270326   ENSP00000259883   \n",
       "1498                28292514             28303911   ENSP00000413705   \n",
       "1566                28317727             28334523   ENSP00000341883   \n",
       "1584                28346732             28367511   ENSP00000354305   \n",
       "1600                28400432             28411244   ENSP00000289788   \n",
       "1610                28471073             28483570   ENSP00000354581   \n",
       "1624                28493702             28502729   ENSP00000392398   \n",
       "1643                28539407             28555112   ENSP00000395259   \n",
       "1678                28870779             28876766   ENSP00000400058   \n",
       "1714                28911654             28912314   ENSP00000366391   \n",
       "1723                28962562             28973037   ENSP00000366384   \n",
       "1737                29011990             29013017   ENSP00000366380   \n",
       "1740                29053985             29055090   ENSP00000366378   \n",
       "1741                29068386             29069658   ENSP00000366376   \n",
       "1742                29079668             29080603   ENSP00000366374   \n",
       "1746                29141311             29142351   ENSP00000366372   \n",
       "1759                29274403             29275519   ENSP00000366365   \n",
       "1761                29323007             29399744   ENSP00000366359   \n",
       "1766                29341200             29343068   ENSP00000380023   \n",
       "1767                29364416             29365448   ENSP00000373047   \n",
       "1769                29393281             29396243   ENSP00000366353   \n",
       "1777                29407083             29408731   ENSP00000419119   \n",
       "1778                29424958             29432105   ENSP00000366340   \n",
       "1803                29454474             29455738   ENSP00000366331   \n",
       "...                      ...                  ...               ...   \n",
       "10782               33257079             33258710   ENSP00000378563   \n",
       "10859               33259431             33267101   ENSP00000420211   \n",
       "10926               33267471             33282164   ENSP00000395701   \n",
       "10979               33282195             33285512   ENSP00000407545   \n",
       "10985               33286335             33290787   ENSP00000266000   \n",
       "11038               33359313             33377701   ENSP00000393963   \n",
       "11064               33378176             33381071   ENSP00000410494   \n",
       "11159               33384219             33386094   ENSP00000363624   \n",
       "11234               33387941             33421466   ENSP00000403636   \n",
       "11335               33422356             33425325   ENSP00000378503   \n",
       "11338               33540329             33548019   ENSP00000363591   \n",
       "11358               33551515             33556803   ENSP00000363582   \n",
       "11366               33588142             33664351   ENSP00000363435   \n",
       "11484               33663126             33679461   ENSP00000363348   \n",
       "11496               33663196             33663474   ENSP00000469270   \n",
       "11498               33689447             33714682   ENSP00000293756   \n",
       "11511               33738979             33744921   ENSP00000423715   \n",
       "11582               33762450             33771788   ENSP00000388825   \n",
       "11619               33989628             34113857   ENSP00000440556   \n",
       "11736               34204650             34214008   ENSP00000288245   \n",
       "11773               34214157             34217247   ENSP00000417604   \n",
       "11812               34247456             34360451   ENSP00000476119   \n",
       "11817               34256547             34393825   ENSP00000475027   \n",
       "11826               34385231             34392998   ENSP00000363169   \n",
       "11859               34433916             34503006   ENSP00000244458   \n",
       "11901               34505579             34524091   ENSP00000363149   \n",
       "11913               34555065             34664624   ENSP00000363135   \n",
       "11939               34725183             34741571   ENSP00000244520   \n",
       "11961               34759857             34845291   ENSP00000192788   \n",
       "12005               34845555             34855866   ENSP00000354633   \n",
       "\n",
       "      Protein stable ID version  ... Transcript type       Gene type  \\\n",
       "1367          ENSP00000366542.1  ...  protein_coding  protein_coding   \n",
       "1380          ENSP00000366527.3  ...  protein_coding  protein_coding   \n",
       "1391          ENSP00000402948.2  ...  protein_coding  protein_coding   \n",
       "1430          ENSP00000433307.1  ...  protein_coding  protein_coding   \n",
       "1458          ENSP00000366509.2  ...  protein_coding  protein_coding   \n",
       "1468          ENSP00000345716.3  ...  protein_coding  protein_coding   \n",
       "1481          ENSP00000259883.3  ...  protein_coding  protein_coding   \n",
       "1498          ENSP00000413705.1  ...  protein_coding  protein_coding   \n",
       "1566          ENSP00000341883.5  ...  protein_coding  protein_coding   \n",
       "1584          ENSP00000354305.1  ...  protein_coding  protein_coding   \n",
       "1600          ENSP00000289788.4  ...  protein_coding  protein_coding   \n",
       "1610          ENSP00000354581.1  ...  protein_coding  protein_coding   \n",
       "1624          ENSP00000392398.2  ...  protein_coding  protein_coding   \n",
       "1643          ENSP00000395259.2  ...  protein_coding  protein_coding   \n",
       "1678          ENSP00000400058.1  ...  protein_coding  protein_coding   \n",
       "1714          ENSP00000366391.3  ...  protein_coding  protein_coding   \n",
       "1723          ENSP00000366384.3  ...  protein_coding  protein_coding   \n",
       "1737          ENSP00000366380.1  ...  protein_coding  protein_coding   \n",
       "1740          ENSP00000366378.2  ...  protein_coding  protein_coding   \n",
       "1741          ENSP00000366376.3  ...  protein_coding  protein_coding   \n",
       "1742          ENSP00000366374.1  ...  protein_coding  protein_coding   \n",
       "1746          ENSP00000366372.2  ...  protein_coding  protein_coding   \n",
       "1759          ENSP00000366365.2  ...  protein_coding  protein_coding   \n",
       "1761          ENSP00000366359.1  ...  protein_coding  protein_coding   \n",
       "1766          ENSP00000380023.3  ...  protein_coding  protein_coding   \n",
       "1767          ENSP00000373047.2  ...  protein_coding  protein_coding   \n",
       "1769          ENSP00000366353.1  ...  protein_coding  protein_coding   \n",
       "1777          ENSP00000419119.1  ...  protein_coding  protein_coding   \n",
       "1778          ENSP00000366340.1  ...  protein_coding  protein_coding   \n",
       "1803          ENSP00000366331.3  ...  protein_coding  protein_coding   \n",
       "...                         ...  ...             ...             ...   \n",
       "10782         ENSP00000378563.1  ...  protein_coding  protein_coding   \n",
       "10859         ENSP00000420211.1  ...  protein_coding  protein_coding   \n",
       "10926         ENSP00000395701.2  ...  protein_coding  protein_coding   \n",
       "10979         ENSP00000407545.2  ...  protein_coding  protein_coding   \n",
       "10985         ENSP00000266000.6  ...  protein_coding  protein_coding   \n",
       "11038         ENSP00000393963.2  ...  protein_coding  protein_coding   \n",
       "11064         ENSP00000410494.1  ...  protein_coding  protein_coding   \n",
       "11159         ENSP00000363624.5  ...  protein_coding  protein_coding   \n",
       "11234         ENSP00000403636.2  ...  protein_coding  protein_coding   \n",
       "11335         ENSP00000378503.2  ...  protein_coding  protein_coding   \n",
       "11338         ENSP00000363591.3  ...  protein_coding  protein_coding   \n",
       "11358         ENSP00000363582.1  ...  protein_coding  protein_coding   \n",
       "11366         ENSP00000363435.4  ...  protein_coding  protein_coding   \n",
       "11484         ENSP00000363348.4  ...  protein_coding  protein_coding   \n",
       "11496         ENSP00000469270.1  ...  protein_coding  protein_coding   \n",
       "11498         ENSP00000293756.4  ...  protein_coding  protein_coding   \n",
       "11511         ENSP00000423715.1  ...  protein_coding  protein_coding   \n",
       "11582         ENSP00000388825.2  ...  protein_coding  protein_coding   \n",
       "11619         ENSP00000440556.1  ...  protein_coding  protein_coding   \n",
       "11736         ENSP00000288245.9  ...  protein_coding  protein_coding   \n",
       "11773         ENSP00000417604.1  ...  protein_coding  protein_coding   \n",
       "11812         ENSP00000476119.1  ...  protein_coding  protein_coding   \n",
       "11817         ENSP00000475027.1  ...  protein_coding  protein_coding   \n",
       "11826         ENSP00000363169.1  ...  protein_coding  protein_coding   \n",
       "11859         ENSP00000244458.2  ...  protein_coding  protein_coding   \n",
       "11901         ENSP00000363149.3  ...  protein_coding  protein_coding   \n",
       "11913         ENSP00000363135.3  ...  protein_coding  protein_coding   \n",
       "11939         ENSP00000244520.5  ...  protein_coding  protein_coding   \n",
       "11961         ENSP00000192788.5  ...  protein_coding  protein_coding   \n",
       "12005         ENSP00000354633.4  ...  protein_coding  protein_coding   \n",
       "\n",
       "       Gene % GC content Transcript count  Source of transcript name  \\\n",
       "1367               41.73                1       HGNC transcript name   \n",
       "1380               41.50                1       HGNC transcript name   \n",
       "1391               38.60                4       HGNC transcript name   \n",
       "1430               43.42                8       HGNC transcript name   \n",
       "1458               43.01                2       HGNC transcript name   \n",
       "1468               44.66                1       HGNC transcript name   \n",
       "1481               39.92                2       HGNC transcript name   \n",
       "1498               41.29               18       HGNC transcript name   \n",
       "1566               45.03                3       HGNC transcript name   \n",
       "1584               41.13                2       HGNC transcript name   \n",
       "1600               39.86                3       HGNC transcript name   \n",
       "1610               42.59                3       HGNC transcript name   \n",
       "1624               40.97                4       HGNC transcript name   \n",
       "1643               39.71                4       HGNC transcript name   \n",
       "1678               44.66                7       HGNC transcript name   \n",
       "1714               48.26                1       HGNC transcript name   \n",
       "1723               41.01                2       HGNC transcript name   \n",
       "1737               41.15                1       HGNC transcript name   \n",
       "1740               42.50                1       HGNC transcript name   \n",
       "1741               41.56                1       HGNC transcript name   \n",
       "1742               45.62                1       HGNC transcript name   \n",
       "1746               44.48                1       HGNC transcript name   \n",
       "1759               44.58                1       HGNC transcript name   \n",
       "1761               36.71                2       HGNC transcript name   \n",
       "1766               38.15                1       HGNC transcript name   \n",
       "1767               45.79                1       HGNC transcript name   \n",
       "1769               39.08                3       HGNC transcript name   \n",
       "1777               49.97                1       HGNC transcript name   \n",
       "1778               41.35                8       HGNC transcript name   \n",
       "1803               50.20                1       HGNC transcript name   \n",
       "...                  ...              ...                        ...   \n",
       "10782              54.13                7       HGNC transcript name   \n",
       "10859              57.12               12       HGNC transcript name   \n",
       "10926              50.01                9       HGNC transcript name   \n",
       "10979              59.46                3       HGNC transcript name   \n",
       "10985              51.32               12       HGNC transcript name   \n",
       "11038              47.68                4       HGNC transcript name   \n",
       "11064              57.49               11       HGNC transcript name   \n",
       "11159              54.90               14       HGNC transcript name   \n",
       "11234              53.94                9       HGNC transcript name   \n",
       "11335              52.39                1       HGNC transcript name   \n",
       "11338              57.17                3       HGNC transcript name   \n",
       "11358              55.97                1       HGNC transcript name   \n",
       "11366              55.13                2       HGNC transcript name   \n",
       "11484              49.22                4       HGNC transcript name   \n",
       "11496              59.14                1    UniProt transcript name   \n",
       "11498              53.41                2       HGNC transcript name   \n",
       "11511              53.18               13       HGNC transcript name   \n",
       "11582              54.77                3       HGNC transcript name   \n",
       "11619              55.92               14       HGNC transcript name   \n",
       "11736              57.83                7       HGNC transcript name   \n",
       "11773              61.63                8       HGNC transcript name   \n",
       "11812              42.12                1       HGNC transcript name   \n",
       "11817              43.35                1       HGNC transcript name   \n",
       "11826              47.56                6       HGNC transcript name   \n",
       "11859              51.33                6       HGNC transcript name   \n",
       "11901              57.98                2       HGNC transcript name   \n",
       "11913              41.83                3       HGNC transcript name   \n",
       "11939              42.71                4       HGNC transcript name   \n",
       "11961              42.62                2       HGNC transcript name   \n",
       "12005              41.49                2       HGNC transcript name   \n",
       "\n",
       "       Transcript name  Source of gene name    Gene name  \\\n",
       "1367        ZNF165-001          HGNC Symbol       ZNF165   \n",
       "1380       ZSCAN16-001          HGNC Symbol      ZSCAN16   \n",
       "1391       ZKSCAN8-003          HGNC Symbol      ZKSCAN8   \n",
       "1430        ZSCAN9-005          HGNC Symbol       ZSCAN9   \n",
       "1458       ZKSCAN4-001          HGNC Symbol      ZKSCAN4   \n",
       "1468         NKAPL-001          HGNC Symbol        NKAPL   \n",
       "1481         PGBD1-001          HGNC Symbol        PGBD1   \n",
       "1498       ZSCAN31-001          HGNC Symbol      ZSCAN31   \n",
       "1566       ZKSCAN3-002          HGNC Symbol      ZKSCAN3   \n",
       "1584       ZSCAN12-001          HGNC Symbol      ZSCAN12   \n",
       "1600       ZSCAN23-001          HGNC Symbol      ZSCAN23   \n",
       "1610          GPX6-001          HGNC Symbol         GPX6   \n",
       "1624          GPX5-001          HGNC Symbol         GPX5   \n",
       "1643        SCAND3-001          HGNC Symbol       SCAND3   \n",
       "1678        TRIM27-003          HGNC Symbol       TRIM27   \n",
       "1714      C6orf100-001          HGNC Symbol     C6orf100   \n",
       "1723        ZNF311-001          HGNC Symbol       ZNF311   \n",
       "1737         OR2W1-001          HGNC Symbol        OR2W1   \n",
       "1740         OR2B3-001          HGNC Symbol        OR2B3   \n",
       "1741         OR2J1-001          HGNC Symbol        OR2J1   \n",
       "1742         OR2J3-001          HGNC Symbol        OR2J3   \n",
       "1746         OR2J2-001          HGNC Symbol        OR2J2   \n",
       "1759        OR14J1-001          HGNC Symbol       OR14J1   \n",
       "1761         OR5V1-001          HGNC Symbol        OR5V1   \n",
       "1766        OR12D3-001          HGNC Symbol       OR12D3   \n",
       "1767        OR12D2-001          HGNC Symbol       OR12D2   \n",
       "1769        OR11A1-001          HGNC Symbol       OR11A1   \n",
       "1777        OR10C1-001          HGNC Symbol       OR10C1   \n",
       "1778         OR2H1-002          HGNC Symbol        OR2H1   \n",
       "1803         MAS1L-001          HGNC Symbol        MAS1L   \n",
       "...                ...                  ...          ...   \n",
       "10782        PFDN6-005          HGNC Symbol        PFDN6   \n",
       "10859         RGL2-001          HGNC Symbol         RGL2   \n",
       "10926        TAPBP-001          HGNC Symbol        TAPBP   \n",
       "10979       ZBTB22-001          HGNC Symbol       ZBTB22   \n",
       "10985         DAXX-002          HGNC Symbol         DAXX   \n",
       "11038        KIFC1-001          HGNC Symbol        KIFC1   \n",
       "11064         PHF1-005          HGNC Symbol         PHF1   \n",
       "11159         CUTA-001          HGNC Symbol         CUTA   \n",
       "11234      SYNGAP1-001          HGNC Symbol      SYNGAP1   \n",
       "11335        ZBTB9-001          HGNC Symbol        ZBTB9   \n",
       "11338         BAK1-002          HGNC Symbol         BAK1   \n",
       "11358       GGNBP1-201          HGNC Symbol       GGNBP1   \n",
       "11366        ITPR3-001          HGNC Symbol        ITPR3   \n",
       "11484        UQCC2-004          HGNC Symbol        UQCC2   \n",
       "11496         SBP1-201  UniProtKB Gene Name         SBP1   \n",
       "11498        IP6K3-002          HGNC Symbol        IP6K3   \n",
       "11511        LEMD2-013          HGNC Symbol        LEMD2   \n",
       "11582          MLN-001          HGNC Symbol          MLN   \n",
       "11619         GRM4-001          HGNC Symbol         GRM4   \n",
       "11736        HMGA1-001          HGNC Symbol        HMGA1   \n",
       "11773       C6orf1-001          HGNC Symbol       C6orf1   \n",
       "11812        NUDT3-001          HGNC Symbol        NUDT3   \n",
       "11817  RPS10-NUDT3-001          HGNC Symbol  RPS10-NUDT3   \n",
       "11826        RPS10-005          HGNC Symbol        RPS10   \n",
       "11859      PACSIN1-001          HGNC Symbol      PACSIN1   \n",
       "11901        SPDEF-001          HGNC Symbol        SPDEF   \n",
       "11913     C6orf106-001          HGNC Symbol     C6orf106   \n",
       "11939        SNRPC-001          HGNC Symbol        SNRPC   \n",
       "11961     UHRF1BP1-001          HGNC Symbol     UHRF1BP1   \n",
       "12005        TAF11-001          HGNC Symbol        TAF11   \n",
       "\n",
       "      GENCODE basic annotation Transcript length (including UTRs and CDS)  \n",
       "1367                       1.0                                       2107  \n",
       "1380                       1.0                                       1328  \n",
       "1391                       1.0                                       2071  \n",
       "1430                       NaN                                        579  \n",
       "1458                       1.0                                       2375  \n",
       "1468                       1.0                                       1639  \n",
       "1481                       1.0                                       3100  \n",
       "1498                       1.0                                       3050  \n",
       "1566                       1.0                                       1794  \n",
       "1584                       1.0                                       5495  \n",
       "1600                       1.0                                       3126  \n",
       "1610                       1.0                                       1712  \n",
       "1624                       1.0                                       1540  \n",
       "1643                       1.0                                       4877  \n",
       "1678                       NaN                                       1813  \n",
       "1714                       1.0                                        466  \n",
       "1723                       1.0                                       2730  \n",
       "1737                       1.0                                       1028  \n",
       "1740                       1.0                                       1106  \n",
       "1741                       1.0                                       1273  \n",
       "1742                       1.0                                        936  \n",
       "1746                       1.0                                       1041  \n",
       "1759                       1.0                                       1117  \n",
       "1761                       1.0                                       1266  \n",
       "1766                       1.0                                       1869  \n",
       "1767                       1.0                                       1033  \n",
       "1769                       1.0                                       2482  \n",
       "1777                       1.0                                       1649  \n",
       "1778                       1.0                                       3024  \n",
       "1803                       1.0                                       1265  \n",
       "...                        ...                                        ...  \n",
       "10782                      1.0                                        884  \n",
       "10859                      1.0                                       3278  \n",
       "10926                      1.0                                       3759  \n",
       "10979                      1.0                                       2651  \n",
       "10985                      1.0                                       2606  \n",
       "11038                      1.0                                       2706  \n",
       "11064                      NaN                                        609  \n",
       "11159                      1.0                                        937  \n",
       "11234                      1.0                                       5916  \n",
       "11335                      1.0                                       2716  \n",
       "11338                      1.0                                       2136  \n",
       "11358                      1.0                                        960  \n",
       "11366                      1.0                                       9870  \n",
       "11484                      NaN                                        509  \n",
       "11496                      1.0                                        279  \n",
       "11498                      1.0                                       2610  \n",
       "11511                      NaN                                       1684  \n",
       "11582                      1.0                                        566  \n",
       "11619                      1.0                                       4153  \n",
       "11736                      1.0                                       1773  \n",
       "11773                      1.0                                       1297  \n",
       "11812                      1.0                                       9905  \n",
       "11817                      1.0                                        876  \n",
       "11826                      1.0                                        650  \n",
       "11859                      1.0                                       4229  \n",
       "11901                      1.0                                       1895  \n",
       "11913                      1.0                                       4418  \n",
       "11939                      1.0                                        842  \n",
       "11961                      1.0                                       9570  \n",
       "12005                      1.0                                       1580  \n",
       "\n",
       "[207 rows x 30 columns]"
      ]
     },
     "execution_count": 43,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_bed"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 41,
   "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>Gene stable ID</th>\n",
       "      <th>Gene stable ID version</th>\n",
       "      <th>Transcript stable ID</th>\n",
       "      <th>Transcript stable ID version</th>\n",
       "      <th>Gene start (bp)</th>\n",
       "      <th>Gene end (bp)</th>\n",
       "      <th>Transcript start (bp)</th>\n",
       "      <th>Transcript end (bp)</th>\n",
       "      <th>Protein stable ID</th>\n",
       "      <th>Protein stable ID version</th>\n",
       "      <th>...</th>\n",
       "      <th>Transcript type</th>\n",
       "      <th>Gene type</th>\n",
       "      <th>Gene % GC content</th>\n",
       "      <th>Transcript count</th>\n",
       "      <th>Source of transcript name</th>\n",
       "      <th>Transcript name</th>\n",
       "      <th>Source of gene name</th>\n",
       "      <th>Gene name</th>\n",
       "      <th>GENCODE basic annotation</th>\n",
       "      <th>Transcript length (including UTRs and CDS)</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>2188</th>\n",
       "      <td>ENSG00000204642</td>\n",
       "      <td>ENSG00000204642.9</td>\n",
       "      <td>ENST00000376861</td>\n",
       "      <td>ENST00000376861.1</td>\n",
       "      <td>29690552</td>\n",
       "      <td>29706305</td>\n",
       "      <td>29690552</td>\n",
       "      <td>29694303</td>\n",
       "      <td>ENSP00000366057</td>\n",
       "      <td>ENSP00000366057.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.02</td>\n",
       "      <td>17</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-F-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-F</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1544</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2317</th>\n",
       "      <td>ENSG00000204632</td>\n",
       "      <td>ENSG00000204632.7</td>\n",
       "      <td>ENST00000376828</td>\n",
       "      <td>ENST00000376828.2</td>\n",
       "      <td>29794744</td>\n",
       "      <td>29798902</td>\n",
       "      <td>29794744</td>\n",
       "      <td>29798902</td>\n",
       "      <td>ENSP00000366024</td>\n",
       "      <td>ENSP00000366024.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>56.38</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-G-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-G</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1490</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2393</th>\n",
       "      <td>ENSG00000206503</td>\n",
       "      <td>ENSG00000206503.7</td>\n",
       "      <td>ENST00000396634</td>\n",
       "      <td>ENST00000396634.1</td>\n",
       "      <td>29909037</td>\n",
       "      <td>29913661</td>\n",
       "      <td>29909037</td>\n",
       "      <td>29913661</td>\n",
       "      <td>ENSP00000379873</td>\n",
       "      <td>ENSP00000379873.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>55.18</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-A-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1868</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2953</th>\n",
       "      <td>ENSG00000204592</td>\n",
       "      <td>ENSG00000204592.5</td>\n",
       "      <td>ENST00000376630</td>\n",
       "      <td>ENST00000376630.4</td>\n",
       "      <td>30457244</td>\n",
       "      <td>30461982</td>\n",
       "      <td>30457244</td>\n",
       "      <td>30461982</td>\n",
       "      <td>ENSP00000365817</td>\n",
       "      <td>ENSP00000365817.4</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>55.48</td>\n",
       "      <td>3</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-E-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-E</td>\n",
       "      <td>1.0</td>\n",
       "      <td>2601</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4716</th>\n",
       "      <td>ENSG00000204525</td>\n",
       "      <td>ENSG00000204525.10</td>\n",
       "      <td>ENST00000376228</td>\n",
       "      <td>ENST00000376228.5</td>\n",
       "      <td>31236526</td>\n",
       "      <td>31239907</td>\n",
       "      <td>31236526</td>\n",
       "      <td>31239863</td>\n",
       "      <td>ENSP00000365402</td>\n",
       "      <td>ENSP00000365402.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>59.28</td>\n",
       "      <td>9</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-C-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1536</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4764</th>\n",
       "      <td>ENSG00000234745</td>\n",
       "      <td>ENSG00000234745.5</td>\n",
       "      <td>ENST00000412585</td>\n",
       "      <td>ENST00000412585.2</td>\n",
       "      <td>31321649</td>\n",
       "      <td>31324965</td>\n",
       "      <td>31321649</td>\n",
       "      <td>31324964</td>\n",
       "      <td>ENSP00000399168</td>\n",
       "      <td>ENSP00000399168.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>59.00</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-B-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1547</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9245</th>\n",
       "      <td>ENSG00000204287</td>\n",
       "      <td>ENSG00000204287.9</td>\n",
       "      <td>ENST00000395388</td>\n",
       "      <td>ENST00000395388.2</td>\n",
       "      <td>32407619</td>\n",
       "      <td>32412823</td>\n",
       "      <td>32407619</td>\n",
       "      <td>32412823</td>\n",
       "      <td>ENSP00000378786</td>\n",
       "      <td>ENSP00000378786.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.88</td>\n",
       "      <td>2</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DRA-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DRA</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1280</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9257</th>\n",
       "      <td>ENSG00000198502</td>\n",
       "      <td>ENSG00000198502.5</td>\n",
       "      <td>ENST00000374975</td>\n",
       "      <td>ENST00000374975.3</td>\n",
       "      <td>32485120</td>\n",
       "      <td>32498064</td>\n",
       "      <td>32485120</td>\n",
       "      <td>32498064</td>\n",
       "      <td>ENSP00000364114</td>\n",
       "      <td>ENSP00000364114.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.84</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DRB5-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DRB5</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1260</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9284</th>\n",
       "      <td>ENSG00000196126</td>\n",
       "      <td>ENSG00000196126.6</td>\n",
       "      <td>ENST00000360004</td>\n",
       "      <td>ENST00000360004.5</td>\n",
       "      <td>32546546</td>\n",
       "      <td>32557625</td>\n",
       "      <td>32546546</td>\n",
       "      <td>32557625</td>\n",
       "      <td>ENSP00000353099</td>\n",
       "      <td>ENSP00000353099.5</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>44.36</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DRB1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1229</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9290</th>\n",
       "      <td>ENSG00000196735</td>\n",
       "      <td>ENSG00000196735.7</td>\n",
       "      <td>ENST00000422863</td>\n",
       "      <td>ENST00000422863.1</td>\n",
       "      <td>32595956</td>\n",
       "      <td>32614839</td>\n",
       "      <td>32595956</td>\n",
       "      <td>32605308</td>\n",
       "      <td>ENSP00000405797</td>\n",
       "      <td>ENSP00000405797.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>40.06</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DQA1-010</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>520</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9324</th>\n",
       "      <td>ENSG00000179344</td>\n",
       "      <td>ENSG00000179344.12</td>\n",
       "      <td>ENST00000399082</td>\n",
       "      <td>ENST00000399082.3</td>\n",
       "      <td>32627244</td>\n",
       "      <td>32636160</td>\n",
       "      <td>32627244</td>\n",
       "      <td>32634429</td>\n",
       "      <td>ENSP00000382032</td>\n",
       "      <td>ENSP00000382032.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.39</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DQB1-007</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DQB1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1219</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9367</th>\n",
       "      <td>ENSG00000237541</td>\n",
       "      <td>ENSG00000237541.3</td>\n",
       "      <td>ENST00000374940</td>\n",
       "      <td>ENST00000374940.3</td>\n",
       "      <td>32709119</td>\n",
       "      <td>32714992</td>\n",
       "      <td>32709119</td>\n",
       "      <td>32714992</td>\n",
       "      <td>ENSP00000364076</td>\n",
       "      <td>ENSP00000364076.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>43.14</td>\n",
       "      <td>1</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DQA2-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DQA2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1524</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9373</th>\n",
       "      <td>ENSG00000232629</td>\n",
       "      <td>ENSG00000232629.4</td>\n",
       "      <td>ENST00000411527</td>\n",
       "      <td>ENST00000411527.1</td>\n",
       "      <td>32723875</td>\n",
       "      <td>32731311</td>\n",
       "      <td>32723875</td>\n",
       "      <td>32731267</td>\n",
       "      <td>ENSP00000390431</td>\n",
       "      <td>ENSP00000390431.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>47.38</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DQB2-002</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DQB2</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1059</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9399</th>\n",
       "      <td>ENSG00000241106</td>\n",
       "      <td>ENSG00000241106.2</td>\n",
       "      <td>ENST00000438763</td>\n",
       "      <td>ENST00000438763.2</td>\n",
       "      <td>32780540</td>\n",
       "      <td>32784825</td>\n",
       "      <td>32780540</td>\n",
       "      <td>32784825</td>\n",
       "      <td>ENSP00000390020</td>\n",
       "      <td>ENSP00000390020.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.19</td>\n",
       "      <td>4</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DOB-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DOB</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1372</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9564</th>\n",
       "      <td>ENSG00000242574</td>\n",
       "      <td>ENSG00000242574.4</td>\n",
       "      <td>ENST00000438510</td>\n",
       "      <td>ENST00000438510.1</td>\n",
       "      <td>32902406</td>\n",
       "      <td>32908847</td>\n",
       "      <td>32902406</td>\n",
       "      <td>32905216</td>\n",
       "      <td>ENSP00000390848</td>\n",
       "      <td>ENSP00000390848.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>45.17</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DMB-007</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DMB</td>\n",
       "      <td>NaN</td>\n",
       "      <td>663</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9589</th>\n",
       "      <td>ENSG00000204257</td>\n",
       "      <td>ENSG00000204257.10</td>\n",
       "      <td>ENST00000395305</td>\n",
       "      <td>ENST00000395305.3</td>\n",
       "      <td>32916390</td>\n",
       "      <td>32936871</td>\n",
       "      <td>32916390</td>\n",
       "      <td>32920838</td>\n",
       "      <td>ENSP00000378716</td>\n",
       "      <td>ENSP00000378716.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>43.69</td>\n",
       "      <td>9</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DMA-004</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DMA</td>\n",
       "      <td>1.0</td>\n",
       "      <td>777</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9781</th>\n",
       "      <td>ENSG00000204252</td>\n",
       "      <td>ENSG00000204252.8</td>\n",
       "      <td>ENST00000229829</td>\n",
       "      <td>ENST00000229829.5</td>\n",
       "      <td>32971955</td>\n",
       "      <td>32977389</td>\n",
       "      <td>32971955</td>\n",
       "      <td>32977389</td>\n",
       "      <td>ENSP00000229829</td>\n",
       "      <td>ENSP00000229829.3</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>52.53</td>\n",
       "      <td>7</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DOA-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DOA</td>\n",
       "      <td>1.0</td>\n",
       "      <td>3489</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9803</th>\n",
       "      <td>ENSG00000231389</td>\n",
       "      <td>ENSG00000231389.3</td>\n",
       "      <td>ENST00000419277</td>\n",
       "      <td>ENST00000419277.1</td>\n",
       "      <td>33032346</td>\n",
       "      <td>33048552</td>\n",
       "      <td>33032346</td>\n",
       "      <td>33048487</td>\n",
       "      <td>ENSP00000393566</td>\n",
       "      <td>ENSP00000393566.1</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>42.77</td>\n",
       "      <td>8</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DPA1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DPA1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1704</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9830</th>\n",
       "      <td>ENSG00000223865</td>\n",
       "      <td>ENSG00000223865.6</td>\n",
       "      <td>ENST00000418931</td>\n",
       "      <td>ENST00000418931.2</td>\n",
       "      <td>33043703</td>\n",
       "      <td>33054978</td>\n",
       "      <td>33043703</td>\n",
       "      <td>33054978</td>\n",
       "      <td>ENSP00000408146</td>\n",
       "      <td>ENSP00000408146.2</td>\n",
       "      <td>...</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>protein_coding</td>\n",
       "      <td>48.11</td>\n",
       "      <td>9</td>\n",
       "      <td>HGNC transcript name</td>\n",
       "      <td>HLA-DPB1-001</td>\n",
       "      <td>HGNC Symbol</td>\n",
       "      <td>HLA-DPB1</td>\n",
       "      <td>1.0</td>\n",
       "      <td>1560</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>19 rows × 30 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "       Gene stable ID Gene stable ID version Transcript stable ID  \\\n",
       "2188  ENSG00000204642      ENSG00000204642.9      ENST00000376861   \n",
       "2317  ENSG00000204632      ENSG00000204632.7      ENST00000376828   \n",
       "2393  ENSG00000206503      ENSG00000206503.7      ENST00000396634   \n",
       "2953  ENSG00000204592      ENSG00000204592.5      ENST00000376630   \n",
       "4716  ENSG00000204525     ENSG00000204525.10      ENST00000376228   \n",
       "4764  ENSG00000234745      ENSG00000234745.5      ENST00000412585   \n",
       "9245  ENSG00000204287      ENSG00000204287.9      ENST00000395388   \n",
       "9257  ENSG00000198502      ENSG00000198502.5      ENST00000374975   \n",
       "9284  ENSG00000196126      ENSG00000196126.6      ENST00000360004   \n",
       "9290  ENSG00000196735      ENSG00000196735.7      ENST00000422863   \n",
       "9324  ENSG00000179344     ENSG00000179344.12      ENST00000399082   \n",
       "9367  ENSG00000237541      ENSG00000237541.3      ENST00000374940   \n",
       "9373  ENSG00000232629      ENSG00000232629.4      ENST00000411527   \n",
       "9399  ENSG00000241106      ENSG00000241106.2      ENST00000438763   \n",
       "9564  ENSG00000242574      ENSG00000242574.4      ENST00000438510   \n",
       "9589  ENSG00000204257     ENSG00000204257.10      ENST00000395305   \n",
       "9781  ENSG00000204252      ENSG00000204252.8      ENST00000229829   \n",
       "9803  ENSG00000231389      ENSG00000231389.3      ENST00000419277   \n",
       "9830  ENSG00000223865      ENSG00000223865.6      ENST00000418931   \n",
       "\n",
       "     Transcript stable ID version  Gene start (bp)  Gene end (bp)  \\\n",
       "2188            ENST00000376861.1         29690552       29706305   \n",
       "2317            ENST00000376828.2         29794744       29798902   \n",
       "2393            ENST00000396634.1         29909037       29913661   \n",
       "2953            ENST00000376630.4         30457244       30461982   \n",
       "4716            ENST00000376228.5         31236526       31239907   \n",
       "4764            ENST00000412585.2         31321649       31324965   \n",
       "9245            ENST00000395388.2         32407619       32412823   \n",
       "9257            ENST00000374975.3         32485120       32498064   \n",
       "9284            ENST00000360004.5         32546546       32557625   \n",
       "9290            ENST00000422863.1         32595956       32614839   \n",
       "9324            ENST00000399082.3         32627244       32636160   \n",
       "9367            ENST00000374940.3         32709119       32714992   \n",
       "9373            ENST00000411527.1         32723875       32731311   \n",
       "9399            ENST00000438763.2         32780540       32784825   \n",
       "9564            ENST00000438510.1         32902406       32908847   \n",
       "9589            ENST00000395305.3         32916390       32936871   \n",
       "9781            ENST00000229829.5         32971955       32977389   \n",
       "9803            ENST00000419277.1         33032346       33048552   \n",
       "9830            ENST00000418931.2         33043703       33054978   \n",
       "\n",
       "      Transcript start (bp)  Transcript end (bp) Protein stable ID  \\\n",
       "2188               29690552             29694303   ENSP00000366057   \n",
       "2317               29794744             29798902   ENSP00000366024   \n",
       "2393               29909037             29913661   ENSP00000379873   \n",
       "2953               30457244             30461982   ENSP00000365817   \n",
       "4716               31236526             31239863   ENSP00000365402   \n",
       "4764               31321649             31324964   ENSP00000399168   \n",
       "9245               32407619             32412823   ENSP00000378786   \n",
       "9257               32485120             32498064   ENSP00000364114   \n",
       "9284               32546546             32557625   ENSP00000353099   \n",
       "9290               32595956             32605308   ENSP00000405797   \n",
       "9324               32627244             32634429   ENSP00000382032   \n",
       "9367               32709119             32714992   ENSP00000364076   \n",
       "9373               32723875             32731267   ENSP00000390431   \n",
       "9399               32780540             32784825   ENSP00000390020   \n",
       "9564               32902406             32905216   ENSP00000390848   \n",
       "9589               32916390             32920838   ENSP00000378716   \n",
       "9781               32971955             32977389   ENSP00000229829   \n",
       "9803               33032346             33048487   ENSP00000393566   \n",
       "9830               33043703             33054978   ENSP00000408146   \n",
       "\n",
       "     Protein stable ID version  ... Transcript type       Gene type  \\\n",
       "2188         ENSP00000366057.1  ...  protein_coding  protein_coding   \n",
       "2317         ENSP00000366024.2  ...  protein_coding  protein_coding   \n",
       "2393         ENSP00000379873.1  ...  protein_coding  protein_coding   \n",
       "2953         ENSP00000365817.4  ...  protein_coding  protein_coding   \n",
       "4716         ENSP00000365402.5  ...  protein_coding  protein_coding   \n",
       "4764         ENSP00000399168.2  ...  protein_coding  protein_coding   \n",
       "9245         ENSP00000378786.2  ...  protein_coding  protein_coding   \n",
       "9257         ENSP00000364114.3  ...  protein_coding  protein_coding   \n",
       "9284         ENSP00000353099.5  ...  protein_coding  protein_coding   \n",
       "9290         ENSP00000405797.1  ...  protein_coding  protein_coding   \n",
       "9324         ENSP00000382032.3  ...  protein_coding  protein_coding   \n",
       "9367         ENSP00000364076.3  ...  protein_coding  protein_coding   \n",
       "9373         ENSP00000390431.1  ...  protein_coding  protein_coding   \n",
       "9399         ENSP00000390020.2  ...  protein_coding  protein_coding   \n",
       "9564         ENSP00000390848.1  ...  protein_coding  protein_coding   \n",
       "9589         ENSP00000378716.3  ...  protein_coding  protein_coding   \n",
       "9781         ENSP00000229829.3  ...  protein_coding  protein_coding   \n",
       "9803         ENSP00000393566.1  ...  protein_coding  protein_coding   \n",
       "9830         ENSP00000408146.2  ...  protein_coding  protein_coding   \n",
       "\n",
       "      Gene % GC content Transcript count  Source of transcript name  \\\n",
       "2188              45.02               17       HGNC transcript name   \n",
       "2317              56.38                7       HGNC transcript name   \n",
       "2393              55.18                8       HGNC transcript name   \n",
       "2953              55.48                3       HGNC transcript name   \n",
       "4716              59.28                9       HGNC transcript name   \n",
       "4764              59.00                7       HGNC transcript name   \n",
       "9245              42.88                2       HGNC transcript name   \n",
       "9257              42.84                1       HGNC transcript name   \n",
       "9284              44.36                1       HGNC transcript name   \n",
       "9290              40.06                7       HGNC transcript name   \n",
       "9324              45.39                8       HGNC transcript name   \n",
       "9367              43.14                1       HGNC transcript name   \n",
       "9373              47.38                4       HGNC transcript name   \n",
       "9399              45.19                4       HGNC transcript name   \n",
       "9564              45.17                7       HGNC transcript name   \n",
       "9589              43.69                9       HGNC transcript name   \n",
       "9781              52.53                7       HGNC transcript name   \n",
       "9803              42.77                8       HGNC transcript name   \n",
       "9830              48.11                9       HGNC transcript name   \n",
       "\n",
       "      Transcript name  Source of gene name  Gene name  \\\n",
       "2188        HLA-F-001          HGNC Symbol      HLA-F   \n",
       "2317        HLA-G-002          HGNC Symbol      HLA-G   \n",
       "2393        HLA-A-001          HGNC Symbol      HLA-A   \n",
       "2953        HLA-E-001          HGNC Symbol      HLA-E   \n",
       "4716        HLA-C-001          HGNC Symbol      HLA-C   \n",
       "4764        HLA-B-001          HGNC Symbol      HLA-B   \n",
       "9245      HLA-DRA-001          HGNC Symbol    HLA-DRA   \n",
       "9257     HLA-DRB5-001          HGNC Symbol   HLA-DRB5   \n",
       "9284     HLA-DRB1-001          HGNC Symbol   HLA-DRB1   \n",
       "9290     HLA-DQA1-010          HGNC Symbol   HLA-DQA1   \n",
       "9324     HLA-DQB1-007          HGNC Symbol   HLA-DQB1   \n",
       "9367     HLA-DQA2-001          HGNC Symbol   HLA-DQA2   \n",
       "9373     HLA-DQB2-002          HGNC Symbol   HLA-DQB2   \n",
       "9399      HLA-DOB-001          HGNC Symbol    HLA-DOB   \n",
       "9564      HLA-DMB-007          HGNC Symbol    HLA-DMB   \n",
       "9589      HLA-DMA-004          HGNC Symbol    HLA-DMA   \n",
       "9781      HLA-DOA-001          HGNC Symbol    HLA-DOA   \n",
       "9803     HLA-DPA1-001          HGNC Symbol   HLA-DPA1   \n",
       "9830     HLA-DPB1-001          HGNC Symbol   HLA-DPB1   \n",
       "\n",
       "     GENCODE basic annotation Transcript length (including UTRs and CDS)  \n",
       "2188                      1.0                                       1544  \n",
       "2317                      1.0                                       1490  \n",
       "2393                      1.0                                       1868  \n",
       "2953                      1.0                                       2601  \n",
       "4716                      1.0                                       1536  \n",
       "4764                      1.0                                       1547  \n",
       "9245                      1.0                                       1280  \n",
       "9257                      1.0                                       1260  \n",
       "9284                      1.0                                       1229  \n",
       "9290                      NaN                                        520  \n",
       "9324                      1.0                                       1219  \n",
       "9367                      1.0                                       1524  \n",
       "9373                      1.0                                       1059  \n",
       "9399                      1.0                                       1372  \n",
       "9564                      NaN                                        663  \n",
       "9589                      1.0                                        777  \n",
       "9781                      1.0                                       3489  \n",
       "9803                      1.0                                       1704  \n",
       "9830                      1.0                                       1560  \n",
       "\n",
       "[19 rows x 30 columns]"
      ]
     },
     "execution_count": 41,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_bed[gene_bed['Gene name'].str.contains('HLA')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 39,
   "metadata": {},
   "outputs": [
    {
     "ename": "KeyError",
     "evalue": "'rs2517754'",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2656\u001b[0m             \u001b[0;32mtry\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2657\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2658\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'rs2517754'",
      "\nDuring handling of the above exception, another exception occurred:\n",
      "\u001b[0;31mKeyError\u001b[0m                                  Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-39-01c16b1b7fe1>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mgene_assign\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m'rs2517754'\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m__getitem__\u001b[0;34m(self, key)\u001b[0m\n\u001b[1;32m   1498\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1499\u001b[0m             \u001b[0mmaybe_callable\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mcom\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mapply_if_callable\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1500\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_getitem_axis\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mmaybe_callable\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1501\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1502\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_is_scalar_access\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_getitem_axis\u001b[0;34m(self, key, axis)\u001b[0m\n\u001b[1;32m   1911\u001b[0m         \u001b[0;31m# fall thru to straight lookup\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1912\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_validate_key\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1913\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_get_label\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   1914\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1915\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/indexing.py\u001b[0m in \u001b[0;36m_get_label\u001b[0;34m(self, label, axis)\u001b[0m\n\u001b[1;32m    139\u001b[0m             \u001b[0;32mraise\u001b[0m \u001b[0mIndexingError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'no slices here, handle elsewhere'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    140\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 141\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_xs\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mlabel\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0maxis\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    142\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    143\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m_get_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0maxis\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mNone\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/generic.py\u001b[0m in \u001b[0;36mxs\u001b[0;34m(self, key, axis, level, drop_level)\u001b[0m\n\u001b[1;32m   3583\u001b[0m                                                       drop_level=drop_level)\n\u001b[1;32m   3584\u001b[0m         \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 3585\u001b[0;31m             \u001b[0mloc\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mindex\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   3586\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   3587\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0misinstance\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mloc\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndarray\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32m~/tools/miniconda3/lib/python3.7/site-packages/pandas/core/indexes/base.py\u001b[0m in \u001b[0;36mget_loc\u001b[0;34m(self, key, method, tolerance)\u001b[0m\n\u001b[1;32m   2657\u001b[0m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2658\u001b[0m             \u001b[0;32mexcept\u001b[0m \u001b[0mKeyError\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2659\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_engine\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_loc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_maybe_cast_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2660\u001b[0m         \u001b[0mindexer\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_indexer\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0mkey\u001b[0m\u001b[0;34m]\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mmethod\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mmethod\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtolerance\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtolerance\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2661\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mindexer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mndim\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0mindexer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0msize\u001b[0m \u001b[0;34m>\u001b[0m \u001b[0;36m1\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/index.pyx\u001b[0m in \u001b[0;36mpandas._libs.index.IndexEngine.get_loc\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;32mpandas/_libs/hashtable_class_helper.pxi\u001b[0m in \u001b[0;36mpandas._libs.hashtable.PyObjectHashTable.get_item\u001b[0;34m()\u001b[0m\n",
      "\u001b[0;31mKeyError\u001b[0m: 'rs2517754'"
     ]
    }
   ],
   "source": [
    "gene_assign.loc['rs2517754']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>pos</th>\n",
       "      <th>ZNF165</th>\n",
       "      <th>ZSCAN16</th>\n",
       "      <th>ZKSCAN8</th>\n",
       "      <th>ZSCAN9</th>\n",
       "      <th>ZKSCAN4</th>\n",
       "      <th>NKAPL</th>\n",
       "      <th>PGBD1</th>\n",
       "      <th>ZSCAN31</th>\n",
       "      <th>ZKSCAN3</th>\n",
       "      <th>...</th>\n",
       "      <th>C6orf1</th>\n",
       "      <th>NUDT3</th>\n",
       "      <th>RPS10-NUDT3</th>\n",
       "      <th>RPS10</th>\n",
       "      <th>PACSIN1</th>\n",
       "      <th>SPDEF</th>\n",
       "      <th>C6orf106</th>\n",
       "      <th>SNRPC</th>\n",
       "      <th>UHRF1BP1</th>\n",
       "      <th>TAF11</th>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>snp</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>6:28000361_T/C</th>\n",
       "      <td>28000361</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28000610_C/A</th>\n",
       "      <td>28000610</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28001003_A/C</th>\n",
       "      <td>28001003</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28001033_T/C</th>\n",
       "      <td>28001033</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28001610_T/C</th>\n",
       "      <td>28001610</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002045_G/A</th>\n",
       "      <td>28002045</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002139_G/A</th>\n",
       "      <td>28002139</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002388_G/A</th>\n",
       "      <td>28002388</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002818_C/T</th>\n",
       "      <td>28002818</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002853_T/C</th>\n",
       "      <td>28002853</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28002963_A/G</th>\n",
       "      <td>28002963</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28003195_CTG/C</th>\n",
       "      <td>28003195</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28003205_G/A</th>\n",
       "      <td>28003205</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28003222_C/T</th>\n",
       "      <td>28003222</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28003275_T/G</th>\n",
       "      <td>28003275</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004059_T/C</th>\n",
       "      <td>28004059</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004078_A/G</th>\n",
       "      <td>28004078</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004133_G/T</th>\n",
       "      <td>28004133</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004134_G/A</th>\n",
       "      <td>28004134</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004381_A/G</th>\n",
       "      <td>28004381</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28004835_A/G</th>\n",
       "      <td>28004835</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28005112_A/G</th>\n",
       "      <td>28005112</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28006042_A/G</th>\n",
       "      <td>28006042</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28006650_A/G</th>\n",
       "      <td>28006650</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007357_A/C</th>\n",
       "      <td>28007357</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007406_AG/A</th>\n",
       "      <td>28007406</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007419_C/T</th>\n",
       "      <td>28007419</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007595_CTT/C</th>\n",
       "      <td>28007595</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007911_A/C</th>\n",
       "      <td>28007911</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:28007930_C/A</th>\n",
       "      <td>28007930</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</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>6:34982237_TC/T</th>\n",
       "      <td>34982237</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34982599_C/T</th>\n",
       "      <td>34982599</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34983275_C/CA</th>\n",
       "      <td>34983275</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34984037_A/C</th>\n",
       "      <td>34984037</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34984556_A/AG</th>\n",
       "      <td>34984556</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34984558_A/G</th>\n",
       "      <td>34984558</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34984712_CTT/C</th>\n",
       "      <td>34984712</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34985133_TTCTC/T</th>\n",
       "      <td>34985133</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34985563_G/A</th>\n",
       "      <td>34985563</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34985985_G/A</th>\n",
       "      <td>34985985</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34986340_CA/C</th>\n",
       "      <td>34986340</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34986591_G/C</th>\n",
       "      <td>34986591</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34986717_A/G</th>\n",
       "      <td>34986717</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34988391_C/A</th>\n",
       "      <td>34988391</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34988951_A/C</th>\n",
       "      <td>34988951</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34989278_C/T</th>\n",
       "      <td>34989278</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34989598_A/G</th>\n",
       "      <td>34989598</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34989761_T/TA</th>\n",
       "      <td>34989761</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34990203_G/C</th>\n",
       "      <td>34990203</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34990968_C/T</th>\n",
       "      <td>34990968</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34993233_T/TCCCTTGCTGCC</th>\n",
       "      <td>34993233</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34994293_TTGA/T</th>\n",
       "      <td>34994293</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34994686_A/G</th>\n",
       "      <td>34994686</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34995973_T/C</th>\n",
       "      <td>34995973</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34996132_A/T</th>\n",
       "      <td>34996132</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34997188_C/T</th>\n",
       "      <td>34997188</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34997259_G/A</th>\n",
       "      <td>34997259</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34997606_T/A</th>\n",
       "      <td>34997606</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34998418_G/A</th>\n",
       "      <td>34998418</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6:34999077_C/T</th>\n",
       "      <td>34999077</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>...</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>70987 rows × 208 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "                                pos  ZNF165  ZSCAN16  ZKSCAN8  ZSCAN9  \\\n",
       "snp                                                                     \n",
       "6:28000361_T/C             28000361       0        0        0       0   \n",
       "6:28000610_C/A             28000610       0        0        0       0   \n",
       "6:28001003_A/C             28001003       0        0        0       0   \n",
       "6:28001033_T/C             28001033       0        0        0       0   \n",
       "6:28001610_T/C             28001610       0        0        0       0   \n",
       "6:28002045_G/A             28002045       0        0        0       0   \n",
       "6:28002139_G/A             28002139       0        0        0       0   \n",
       "6:28002388_G/A             28002388       0        0        0       0   \n",
       "6:28002818_C/T             28002818       0        0        0       0   \n",
       "6:28002853_T/C             28002853       0        0        0       0   \n",
       "6:28002963_A/G             28002963       0        0        0       0   \n",
       "6:28003195_CTG/C           28003195       0        0        0       0   \n",
       "6:28003205_G/A             28003205       0        0        0       0   \n",
       "6:28003222_C/T             28003222       0        0        0       0   \n",
       "6:28003275_T/G             28003275       0        0        0       0   \n",
       "6:28004059_T/C             28004059       0        0        0       0   \n",
       "6:28004078_A/G             28004078       0        0        0       0   \n",
       "6:28004133_G/T             28004133       0        0        0       0   \n",
       "6:28004134_G/A             28004134       0        0        0       0   \n",
       "6:28004381_A/G             28004381       0        0        0       0   \n",
       "6:28004835_A/G             28004835       0        0        0       0   \n",
       "6:28005112_A/G             28005112       0        0        0       0   \n",
       "6:28006042_A/G             28006042       0        0        0       0   \n",
       "6:28006650_A/G             28006650       0        0        0       0   \n",
       "6:28007357_A/C             28007357       0        0        0       0   \n",
       "6:28007406_AG/A            28007406       0        0        0       0   \n",
       "6:28007419_C/T             28007419       0        0        0       0   \n",
       "6:28007595_CTT/C           28007595       0        0        0       0   \n",
       "6:28007911_A/C             28007911       0        0        0       0   \n",
       "6:28007930_C/A             28007930       0        0        0       0   \n",
       "...                             ...     ...      ...      ...     ...   \n",
       "6:34982237_TC/T            34982237       0        0        0       0   \n",
       "6:34982599_C/T             34982599       0        0        0       0   \n",
       "6:34983275_C/CA            34983275       0        0        0       0   \n",
       "6:34984037_A/C             34984037       0        0        0       0   \n",
       "6:34984556_A/AG            34984556       0        0        0       0   \n",
       "6:34984558_A/G             34984558       0        0        0       0   \n",
       "6:34984712_CTT/C           34984712       0        0        0       0   \n",
       "6:34985133_TTCTC/T         34985133       0        0        0       0   \n",
       "6:34985563_G/A             34985563       0        0        0       0   \n",
       "6:34985985_G/A             34985985       0        0        0       0   \n",
       "6:34986340_CA/C            34986340       0        0        0       0   \n",
       "6:34986591_G/C             34986591       0        0        0       0   \n",
       "6:34986717_A/G             34986717       0        0        0       0   \n",
       "6:34988391_C/A             34988391       0        0        0       0   \n",
       "6:34988951_A/C             34988951       0        0        0       0   \n",
       "6:34989278_C/T             34989278       0        0        0       0   \n",
       "6:34989598_A/G             34989598       0        0        0       0   \n",
       "6:34989761_T/TA            34989761       0        0        0       0   \n",
       "6:34990203_G/C             34990203       0        0        0       0   \n",
       "6:34990968_C/T             34990968       0        0        0       0   \n",
       "6:34993233_T/TCCCTTGCTGCC  34993233       0        0        0       0   \n",
       "6:34994293_TTGA/T          34994293       0        0        0       0   \n",
       "6:34994686_A/G             34994686       0        0        0       0   \n",
       "6:34995973_T/C             34995973       0        0        0       0   \n",
       "6:34996132_A/T             34996132       0        0        0       0   \n",
       "6:34997188_C/T             34997188       0        0        0       0   \n",
       "6:34997259_G/A             34997259       0        0        0       0   \n",
       "6:34997606_T/A             34997606       0        0        0       0   \n",
       "6:34998418_G/A             34998418       0        0        0       0   \n",
       "6:34999077_C/T             34999077       0        0        0       0   \n",
       "\n",
       "                           ZKSCAN4  NKAPL  PGBD1  ZSCAN31  ZKSCAN3  ...  \\\n",
       "snp                                                                 ...   \n",
       "6:28000361_T/C                   0      0      0        0        0  ...   \n",
       "6:28000610_C/A                   0      0      0        0        0  ...   \n",
       "6:28001003_A/C                   0      0      0        0        0  ...   \n",
       "6:28001033_T/C                   0      0      0        0        0  ...   \n",
       "6:28001610_T/C                   0      0      0        0        0  ...   \n",
       "6:28002045_G/A                   0      0      0        0        0  ...   \n",
       "6:28002139_G/A                   0      0      0        0        0  ...   \n",
       "6:28002388_G/A                   0      0      0        0        0  ...   \n",
       "6:28002818_C/T                   0      0      0        0        0  ...   \n",
       "6:28002853_T/C                   0      0      0        0        0  ...   \n",
       "6:28002963_A/G                   0      0      0        0        0  ...   \n",
       "6:28003195_CTG/C                 0      0      0        0        0  ...   \n",
       "6:28003205_G/A                   0      0      0        0        0  ...   \n",
       "6:28003222_C/T                   0      0      0        0        0  ...   \n",
       "6:28003275_T/G                   0      0      0        0        0  ...   \n",
       "6:28004059_T/C                   0      0      0        0        0  ...   \n",
       "6:28004078_A/G                   0      0      0        0        0  ...   \n",
       "6:28004133_G/T                   0      0      0        0        0  ...   \n",
       "6:28004134_G/A                   0      0      0        0        0  ...   \n",
       "6:28004381_A/G                   0      0      0        0        0  ...   \n",
       "6:28004835_A/G                   0      0      0        0        0  ...   \n",
       "6:28005112_A/G                   0      0      0        0        0  ...   \n",
       "6:28006042_A/G                   0      0      0        0        0  ...   \n",
       "6:28006650_A/G                   0      0      0        0        0  ...   \n",
       "6:28007357_A/C                   0      0      0        0        0  ...   \n",
       "6:28007406_AG/A                  0      0      0        0        0  ...   \n",
       "6:28007419_C/T                   0      0      0        0        0  ...   \n",
       "6:28007595_CTT/C                 0      0      0        0        0  ...   \n",
       "6:28007911_A/C                   0      0      0        0        0  ...   \n",
       "6:28007930_C/A                   0      0      0        0        0  ...   \n",
       "...                            ...    ...    ...      ...      ...  ...   \n",
       "6:34982237_TC/T                  0      0      0        0        0  ...   \n",
       "6:34982599_C/T                   0      0      0        0        0  ...   \n",
       "6:34983275_C/CA                  0      0      0        0        0  ...   \n",
       "6:34984037_A/C                   0      0      0        0        0  ...   \n",
       "6:34984556_A/AG                  0      0      0        0        0  ...   \n",
       "6:34984558_A/G                   0      0      0        0        0  ...   \n",
       "6:34984712_CTT/C                 0      0      0        0        0  ...   \n",
       "6:34985133_TTCTC/T               0      0      0        0        0  ...   \n",
       "6:34985563_G/A                   0      0      0        0        0  ...   \n",
       "6:34985985_G/A                   0      0      0        0        0  ...   \n",
       "6:34986340_CA/C                  0      0      0        0        0  ...   \n",
       "6:34986591_G/C                   0      0      0        0        0  ...   \n",
       "6:34986717_A/G                   0      0      0        0        0  ...   \n",
       "6:34988391_C/A                   0      0      0        0        0  ...   \n",
       "6:34988951_A/C                   0      0      0        0        0  ...   \n",
       "6:34989278_C/T                   0      0      0        0        0  ...   \n",
       "6:34989598_A/G                   0      0      0        0        0  ...   \n",
       "6:34989761_T/TA                  0      0      0        0        0  ...   \n",
       "6:34990203_G/C                   0      0      0        0        0  ...   \n",
       "6:34990968_C/T                   0      0      0        0        0  ...   \n",
       "6:34993233_T/TCCCTTGCTGCC        0      0      0        0        0  ...   \n",
       "6:34994293_TTGA/T                0      0      0        0        0  ...   \n",
       "6:34994686_A/G                   0      0      0        0        0  ...   \n",
       "6:34995973_T/C                   0      0      0        0        0  ...   \n",
       "6:34996132_A/T                   0      0      0        0        0  ...   \n",
       "6:34997188_C/T                   0      0      0        0        0  ...   \n",
       "6:34997259_G/A                   0      0      0        0        0  ...   \n",
       "6:34997606_T/A                   0      0      0        0        0  ...   \n",
       "6:34998418_G/A                   0      0      0        0        0  ...   \n",
       "6:34999077_C/T                   0      0      0        0        0  ...   \n",
       "\n",
       "                           C6orf1  NUDT3  RPS10-NUDT3  RPS10  PACSIN1  SPDEF  \\\n",
       "snp                                                                            \n",
       "6:28000361_T/C                  0      0            0      0        0      0   \n",
       "6:28000610_C/A                  0      0            0      0        0      0   \n",
       "6:28001003_A/C                  0      0            0      0        0      0   \n",
       "6:28001033_T/C                  0      0            0      0        0      0   \n",
       "6:28001610_T/C                  0      0            0      0        0      0   \n",
       "6:28002045_G/A                  0      0            0      0        0      0   \n",
       "6:28002139_G/A                  0      0            0      0        0      0   \n",
       "6:28002388_G/A                  0      0            0      0        0      0   \n",
       "6:28002818_C/T                  0      0            0      0        0      0   \n",
       "6:28002853_T/C                  0      0            0      0        0      0   \n",
       "6:28002963_A/G                  0      0            0      0        0      0   \n",
       "6:28003195_CTG/C                0      0            0      0        0      0   \n",
       "6:28003205_G/A                  0      0            0      0        0      0   \n",
       "6:28003222_C/T                  0      0            0      0        0      0   \n",
       "6:28003275_T/G                  0      0            0      0        0      0   \n",
       "6:28004059_T/C                  0      0            0      0        0      0   \n",
       "6:28004078_A/G                  0      0            0      0        0      0   \n",
       "6:28004133_G/T                  0      0            0      0        0      0   \n",
       "6:28004134_G/A                  0      0            0      0        0      0   \n",
       "6:28004381_A/G                  0      0            0      0        0      0   \n",
       "6:28004835_A/G                  0      0            0      0        0      0   \n",
       "6:28005112_A/G                  0      0            0      0        0      0   \n",
       "6:28006042_A/G                  0      0            0      0        0      0   \n",
       "6:28006650_A/G                  0      0            0      0        0      0   \n",
       "6:28007357_A/C                  0      0            0      0        0      0   \n",
       "6:28007406_AG/A                 0      0            0      0        0      0   \n",
       "6:28007419_C/T                  0      0            0      0        0      0   \n",
       "6:28007595_CTT/C                0      0            0      0        0      0   \n",
       "6:28007911_A/C                  0      0            0      0        0      0   \n",
       "6:28007930_C/A                  0      0            0      0        0      0   \n",
       "...                           ...    ...          ...    ...      ...    ...   \n",
       "6:34982237_TC/T                 0      0            0      0        0      0   \n",
       "6:34982599_C/T                  0      0            0      0        0      0   \n",
       "6:34983275_C/CA                 0      0            0      0        0      0   \n",
       "6:34984037_A/C                  0      0            0      0        0      0   \n",
       "6:34984556_A/AG                 0      0            0      0        0      0   \n",
       "6:34984558_A/G                  0      0            0      0        0      0   \n",
       "6:34984712_CTT/C                0      0            0      0        0      0   \n",
       "6:34985133_TTCTC/T              0      0            0      0        0      0   \n",
       "6:34985563_G/A                  0      0            0      0        0      0   \n",
       "6:34985985_G/A                  0      0            0      0        0      0   \n",
       "6:34986340_CA/C                 0      0            0      0        0      0   \n",
       "6:34986591_G/C                  0      0            0      0        0      0   \n",
       "6:34986717_A/G                  0      0            0      0        0      0   \n",
       "6:34988391_C/A                  0      0            0      0        0      0   \n",
       "6:34988951_A/C                  0      0            0      0        0      0   \n",
       "6:34989278_C/T                  0      0            0      0        0      0   \n",
       "6:34989598_A/G                  0      0            0      0        0      0   \n",
       "6:34989761_T/TA                 0      0            0      0        0      0   \n",
       "6:34990203_G/C                  0      0            0      0        0      0   \n",
       "6:34990968_C/T                  0      0            0      0        0      0   \n",
       "6:34993233_T/TCCCTTGCTGCC       0      0            0      0        0      0   \n",
       "6:34994293_TTGA/T               0      0            0      0        0      0   \n",
       "6:34994686_A/G                  0      0            0      0        0      0   \n",
       "6:34995973_T/C                  0      0            0      0        0      0   \n",
       "6:34996132_A/T                  0      0            0      0        0      0   \n",
       "6:34997188_C/T                  0      0            0      0        0      0   \n",
       "6:34997259_G/A                  0      0            0      0        0      0   \n",
       "6:34997606_T/A                  0      0            0      0        0      0   \n",
       "6:34998418_G/A                  0      0            0      0        0      0   \n",
       "6:34999077_C/T                  0      0            0      0        0      0   \n",
       "\n",
       "                           C6orf106  SNRPC  UHRF1BP1  TAF11  \n",
       "snp                                                          \n",
       "6:28000361_T/C                    0      0         0      0  \n",
       "6:28000610_C/A                    0      0         0      0  \n",
       "6:28001003_A/C                    0      0         0      0  \n",
       "6:28001033_T/C                    0      0         0      0  \n",
       "6:28001610_T/C                    0      0         0      0  \n",
       "6:28002045_G/A                    0      0         0      0  \n",
       "6:28002139_G/A                    0      0         0      0  \n",
       "6:28002388_G/A                    0      0         0      0  \n",
       "6:28002818_C/T                    0      0         0      0  \n",
       "6:28002853_T/C                    0      0         0      0  \n",
       "6:28002963_A/G                    0      0         0      0  \n",
       "6:28003195_CTG/C                  0      0         0      0  \n",
       "6:28003205_G/A                    0      0         0      0  \n",
       "6:28003222_C/T                    0      0         0      0  \n",
       "6:28003275_T/G                    0      0         0      0  \n",
       "6:28004059_T/C                    0      0         0      0  \n",
       "6:28004078_A/G                    0      0         0      0  \n",
       "6:28004133_G/T                    0      0         0      0  \n",
       "6:28004134_G/A                    0      0         0      0  \n",
       "6:28004381_A/G                    0      0         0      0  \n",
       "6:28004835_A/G                    0      0         0      0  \n",
       "6:28005112_A/G                    0      0         0      0  \n",
       "6:28006042_A/G                    0      0         0      0  \n",
       "6:28006650_A/G                    0      0         0      0  \n",
       "6:28007357_A/C                    0      0         0      0  \n",
       "6:28007406_AG/A                   0      0         0      0  \n",
       "6:28007419_C/T                    0      0         0      0  \n",
       "6:28007595_CTT/C                  0      0         0      0  \n",
       "6:28007911_A/C                    0      0         0      0  \n",
       "6:28007930_C/A                    0      0         0      0  \n",
       "...                             ...    ...       ...    ...  \n",
       "6:34982237_TC/T                   0      0         0      0  \n",
       "6:34982599_C/T                    0      0         0      0  \n",
       "6:34983275_C/CA                   0      0         0      0  \n",
       "6:34984037_A/C                    0      0         0      0  \n",
       "6:34984556_A/AG                   0      0         0      0  \n",
       "6:34984558_A/G                    0      0         0      0  \n",
       "6:34984712_CTT/C                  0      0         0      0  \n",
       "6:34985133_TTCTC/T                0      0         0      0  \n",
       "6:34985563_G/A                    0      0         0      0  \n",
       "6:34985985_G/A                    0      0         0      0  \n",
       "6:34986340_CA/C                   0      0         0      0  \n",
       "6:34986591_G/C                    0      0         0      0  \n",
       "6:34986717_A/G                    0      0         0      0  \n",
       "6:34988391_C/A                    0      0         0      0  \n",
       "6:34988951_A/C                    0      0         0      0  \n",
       "6:34989278_C/T                    0      0         0      0  \n",
       "6:34989598_A/G                    0      0         0      0  \n",
       "6:34989761_T/TA                   0      0         0      0  \n",
       "6:34990203_G/C                    0      0         0      0  \n",
       "6:34990968_C/T                    0      0         0      0  \n",
       "6:34993233_T/TCCCTTGCTGCC         0      0         0      0  \n",
       "6:34994293_TTGA/T                 0      0         0      0  \n",
       "6:34994686_A/G                    0      0         0      0  \n",
       "6:34995973_T/C                    0      0         0      0  \n",
       "6:34996132_A/T                    0      0         0      0  \n",
       "6:34997188_C/T                    0      0         0      0  \n",
       "6:34997259_G/A                    0      0         0      0  \n",
       "6:34997606_T/A                    0      0         0      0  \n",
       "6:34998418_G/A                    0      0         0      0  \n",
       "6:34999077_C/T                    0      0         0      0  \n",
       "\n",
       "[70987 rows x 208 columns]"
      ]
     },
     "execution_count": 38,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_assign"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "#gene_assign.iloc[:,1:].sum(axis=1).sort_values()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"\\ngene_bed_path='data/known_genes_chr6.hg19.txt'\\ngene_bed=pd.read_csv(gene_bed_path,sep='\\t')\\ngene_bed=gene_bed[(gene_bed['txStart']>=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.min())&(gene_bed['txEnd']<=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.max())]\\ngene_bed=gene_bed[~gene_bed.duplicated(['name2'])]\\n\\ngene_assign=plink_KCHIP_HLA_AA_SNP_1000G_bim[['pos']]\\n\\nfor idx,row in gene_bed.iterrows():\\n    gene_assign[row['name2']]=0\\n    \\nfor idx,row in gene_bed.iterrows():    \\n    gene_assign[row['name2']][(gene_assign['pos']>=row['txStart'])&(gene_assign['pos']<=row['txEnd'])]=1\\ngene_assign=gene_assign.drop(columns='HLA-A29.1')\\n\\ngene_assign.columns=gene_assign.columns.str.replace('HLA-','HLA_')        \\n    \\nHLA_names=np.unique([i[0].split('_')[1] for i in plink_KCHIP_HLA_AA_SNP_1000G_bim[plink_KCHIP_HLA_AA_SNP_1000G_bim.index.str.contains('HLA_')].index.str.split('*')])\\n\\nfor HLA_name in HLA_names:\\n    gene_select=gene_assign[gene_assign.index.str.contains('HLA_'+HLA_name)|gene_assign.index.str.contains('SNPS_'+HLA_name)|gene_assign.index.str.contains('AA_'+HLA_name)]#print(gene_select.sort_values('pos').iloc[0],gene_select.sort_values('pos').iloc[-1])\\n    HLA_name='HLA_{}'.format(HLA_name)\\n    gene_assign[HLA_name][(gene_assign['pos']>=gene_select['pos'].min())&(gene_assign['pos']<=gene_select['pos'].max())]=1 \\n\""
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"\n",
    "gene_bed_path='data/known_genes_chr6.hg19.txt'\n",
    "gene_bed=pd.read_csv(gene_bed_path,sep='\\t')\n",
    "gene_bed=gene_bed[(gene_bed['txStart']>=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.min())&(gene_bed['txEnd']<=plink_KCHIP_HLA_AA_SNP_1000G_bim.pos.max())]\n",
    "gene_bed=gene_bed[~gene_bed.duplicated(['name2'])]\n",
    "\n",
    "gene_assign=plink_KCHIP_HLA_AA_SNP_1000G_bim[['pos']]\n",
    "\n",
    "for idx,row in gene_bed.iterrows():\n",
    "    gene_assign[row['name2']]=0\n",
    "    \n",
    "for idx,row in gene_bed.iterrows():    \n",
    "    gene_assign[row['name2']][(gene_assign['pos']>=row['txStart'])&(gene_assign['pos']<=row['txEnd'])]=1\n",
    "gene_assign=gene_assign.drop(columns='HLA-A29.1')\n",
    "\n",
    "gene_assign.columns=gene_assign.columns.str.replace('HLA-','HLA_')        \n",
    "    \n",
    "HLA_names=np.unique([i[0].split('_')[1] for i in plink_KCHIP_HLA_AA_SNP_1000G_bim[plink_KCHIP_HLA_AA_SNP_1000G_bim.index.str.contains('HLA_')].index.str.split('*')])\n",
    "\n",
    "for HLA_name in HLA_names:\n",
    "    gene_select=gene_assign[gene_assign.index.str.contains('HLA_'+HLA_name)|gene_assign.index.str.contains('SNPS_'+HLA_name)|gene_assign.index.str.contains('AA_'+HLA_name)]#print(gene_select.sort_values('pos').iloc[0],gene_select.sort_values('pos').iloc[-1])\n",
    "    HLA_name='HLA_{}'.format(HLA_name)\n",
    "    gene_assign[HLA_name][(gene_assign['pos']>=gene_select['pos'].min())&(gene_assign['pos']<=gene_select['pos'].max())]=1 \n",
    "\"\"\"    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "#gene_assign.columns[gene_assign.columns.str.contains('HLA')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "gene_assign_reduce=gene_assign.iloc[:,:1]\n",
    "\n",
    "gene_assign_reduce['gene_1']=gene_assign.iloc[:,1:].apply(lambda x: x[x!=0].index[1-1] if (x!=0).sum()>=(1) else np.nan,axis=1)\n",
    "gene_assign_reduce['gene_2']=gene_assign.iloc[:,1:].apply(lambda x: x[x!=0].index[2-1] if (x!=0).sum()>=(2) else np.nan,axis=1)\n",
    "gene_assign_reduce['gene_3']=gene_assign.iloc[:,1:].apply(lambda x: x[x!=0].index[3-1] if (x!=0).sum()>=(3) else np.nan,axis=1)\n",
    "gene_assign_reduce['gene_4']=gene_assign.iloc[:,1:].apply(lambda x: x[x!=0].index[4-1] if (x!=0).sum()>=(4) else np.nan,axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [],
   "source": [
    "#gene_assign_reduce.to_csv('data/bim_to_gene_assign.tsv',sep='\\t')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "#gene_assign_reduce\n",
    "gene_assign_reduce=pd.read_csv('data/bim_to_gene_assign.tsv',sep='\\t',index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_all=pd.read_csv('data/result_concat_1_top_all.tsv',sep='\\t')\n",
    "result_all['P_significant']=(result_all['P']<5e-8).astype(int)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>phenotype_type</th>\n",
       "      <th>phenotype_name</th>\n",
       "      <th>samples(case/control)</th>\n",
       "      <th>step</th>\n",
       "      <th>condition</th>\n",
       "      <th>marker_name</th>\n",
       "      <th>marker_name_pub</th>\n",
       "      <th>note</th>\n",
       "      <th>...</th>\n",
       "      <th>A1_freq_control</th>\n",
       "      <th>multi_allele</th>\n",
       "      <th>nobs</th>\n",
       "      <th>Z</th>\n",
       "      <th>coef</th>\n",
       "      <th>std</th>\n",
       "      <th>chisq</th>\n",
       "      <th>df</th>\n",
       "      <th>P</th>\n",
       "      <th>P_significant</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20816</td>\n",
       "      <td>144613</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_over_FVC_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:30985177_G/A</td>\n",
       "      <td>rs12204947</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7440</td>\n",
       "      <td>-5.18377</td>\n",
       "      <td>-0.060131</td>\n",
       "      <td>0.011600</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.231720e-07</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>68685</td>\n",
       "      <td>475104</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34172055_C/A</td>\n",
       "      <td>rs1187115</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7440</td>\n",
       "      <td>5.83644</td>\n",
       "      <td>0.026954</td>\n",
       "      <td>0.004618</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.556790e-09</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>21318</td>\n",
       "      <td>169288</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34172055_C/A</td>\n",
       "      <td>6:31018788_T/G</td>\n",
       "      <td>rs2517531</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7440</td>\n",
       "      <td>-4.35216</td>\n",
       "      <td>-0.015100</td>\n",
       "      <td>0.003470</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.366070e-05</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>68741</td>\n",
       "      <td>475496</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FVC_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7441</td>\n",
       "      <td>5.57356</td>\n",
       "      <td>0.036813</td>\n",
       "      <td>0.006605</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.583340e-08</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>21307</td>\n",
       "      <td>169200</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FVC_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>AX-11396301</td>\n",
       "      <td>rs2517534</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7433</td>\n",
       "      <td>4.63010</td>\n",
       "      <td>0.022921</td>\n",
       "      <td>0.004950</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.717070e-06</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "   Unnamed: 0  Unnamed: 0.1 phenotype_type          phenotype_name  \\\n",
       "0       20816        144613     continuous  FEV_over_FVC_predicted   \n",
       "1       68685        475104     continuous           FEV_predicted   \n",
       "2       21318        169288     continuous           FEV_predicted   \n",
       "3       68741        475496     continuous           FVC_predicted   \n",
       "4       21307        169200     continuous           FVC_predicted   \n",
       "\n",
       "  samples(case/control)  step             condition           marker_name  \\\n",
       "0                  7440     1                   NaN        6:30985177_G/A   \n",
       "1                  7440     1                   NaN        6:34172055_C/A   \n",
       "2                  7440     2        6:34172055_C/A        6:31018788_T/G   \n",
       "3                  7441     1                   NaN  6:34205465_G/GGAGCCC   \n",
       "4                  7441     2  6:34205465_G/GGAGCCC           AX-11396301   \n",
       "\n",
       "        marker_name_pub               note  ... A1_freq_control  multi_allele  \\\n",
       "0            rs12204947  unphased bialleic  ...             NaN           NaN   \n",
       "1             rs1187115  unphased bialleic  ...             NaN           NaN   \n",
       "2             rs2517531  unphased bialleic  ...             NaN           NaN   \n",
       "3  6:34205465_G/GGAGCCC  unphased bialleic  ...             NaN           NaN   \n",
       "4             rs2517534  unphased bialleic  ...             NaN           NaN   \n",
       "\n",
       "   nobs        Z      coef       std chisq  df             P  P_significant  \n",
       "0  7440 -5.18377 -0.060131  0.011600   NaN NaN  2.231720e-07              0  \n",
       "1  7440  5.83644  0.026954  0.004618   NaN NaN  5.556790e-09              1  \n",
       "2  7440 -4.35216 -0.015100  0.003470   NaN NaN  1.366070e-05              0  \n",
       "3  7441  5.57356  0.036813  0.006605   NaN NaN  2.583340e-08              1  \n",
       "4  7433  4.63010  0.022921  0.004950   NaN NaN  3.717070e-06              0  \n",
       "\n",
       "[5 rows x 25 columns]"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_all.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 25,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(168, 67, 67)"
      ]
     },
     "execution_count": 25,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(result_all['marker_name']),len(result_all[result_all['P_significant']==1]['marker_name'].unique()),len(result_all[result_all['P_significant']==1]['marker_name_pub'].unique())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 26,
   "metadata": {},
   "outputs": [],
   "source": [
    "#result_all[result_all['P_significant']==1]['marker_name_pub']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {},
   "outputs": [],
   "source": [
    "r2_df=pd.read_csv('data/r2.tsv',sep='\\t',index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Index(['HLA-F', 'HLA-G', 'HLA-A', 'HLA-E', 'HLA-C', 'HLA-B', 'HLA-DRA',\n",
       "       'HLA-DRB5', 'HLA-DRB1', 'HLA-DQA1', 'HLA-DQB1', 'HLA-DQA2', 'HLA-DQB2',\n",
       "       'HLA-DOB', 'HLA-DMB', 'HLA-DMA', 'HLA-DOA', 'HLA-DPA1', 'HLA-DPB1'],\n",
       "      dtype='object')"
      ]
     },
     "execution_count": 28,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "gene_assign.columns[gene_assign.columns.str.contains('HLA')]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 29,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "('HLA-DRA', 'HLA-DRB1', 'HLA-DQA1', 'HLA-DQB1', 'HLA-DPA1', 'HLA-DPB1')"
      ]
     },
     "execution_count": 29,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "'HLA-A', 'HLA-C', 'HLA-B'\n",
    "\n",
    "'HLA-DRA','HLA-DRB1', 'HLA-DQA1', 'HLA-DQB1','HLA-DPA1', 'HLA-DPB1'"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "\"\\ndef marker_name_to_gene(marker_name):\\n    if marker_name[:3]=='AA_':\\n        ret='HLA_'+marker_name.split('_')[1]\\n    elif marker_name[:5]=='SNPS_':\\n        ret='HLA_'+marker_name.split('_')[1]\\n        #conditional_list.append('HLA_'+marker_name.split('_')[1])\\n    elif marker_name[:4]=='HLA_':\\n        ret='HLA_'+marker_name.split('_')[1].split('*')[0]\\n    elif marker_name[:9]=='INS_SNPS_':\\n        ret='HLA_'+marker_name.split('_')[2]\\n    elif np.any(~gene_assign_reduce.loc[marker_name].iloc[1:].isnull()):\\n        ret=gene_assign_reduce.loc[marker_name].iloc[1:]\\n        ret=','.join(ret[~ret.isnull()])\\n    else:\\n        r2=r2_df[marker_name].sort_values(ascending=False)\\n        gene_assign_r2_moderate_HLA=gene_assign.loc[r2[r2>0.5].index][gene_assign.columns[gene_assign.columns.str.contains('HLA')]]\\n        gene_assign_r2_moderate_HLA=gene_assign_r2_moderate_HLA[gene_assign_r2_moderate_HLA.sum(axis=1)!=0]\\n        #print(gene_assign_r2_moderate_HLA.sum(axis=1)!=0)\\n        \\n        gene_assign_r2_strong=gene_assign.loc[r2[r2>0.8].index].iloc[:,1:]\\n        gene_assign_r2_strong=gene_assign_r2_strong[gene_assign_r2_strong.sum(axis=1)!=0]\\n        #gene_assign_r2_strong_sum=gene_assign_r2_strong.sum()\\n        #\\n        if len(gene_assign_r2_moderate_HLA)!=0:\\n            ret=gene_assign_r2_moderate_HLA.iloc[0].sort_values(ascending=False).index[0]\\n        elif len(gene_assign_r2_strong)!=0:\\n            ret=gene_assign_r2_strong.iloc[0].sort_values(ascending=False).index[0]#[gene_assign_r2_strong.iloc[0]==1]\\n        else:\\n            #print(marker_name)\\n            gene_assign_temp=gene_assign.copy()\\n            gene_assign_temp['dist']=(gene_assign_temp['pos']-gene_assign_temp['pos'][marker_name]).abs()\\n            #print(marker_name,gene_assign_temp.sort_values('dist'))\\n            \\n            gene_assign_temp_clip=gene_assign_temp.sort_values('dist').iloc[:,1:-1]\\n            \\n            for row_idx,row in gene_assign_temp_clip.iterrows():\\n                if np.any(row!=0):\\n                    #print(row)\\n                    ret=','.join(row[row!=0].index)\\n                    break\\n    return ret\\n\""
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "\"\"\"\n",
    "def marker_name_to_gene(marker_name):\n",
    "    if marker_name[:3]=='AA_':\n",
    "        ret='HLA_'+marker_name.split('_')[1]\n",
    "    elif marker_name[:5]=='SNPS_':\n",
    "        ret='HLA_'+marker_name.split('_')[1]\n",
    "        #conditional_list.append('HLA_'+marker_name.split('_')[1])\n",
    "    elif marker_name[:4]=='HLA_':\n",
    "        ret='HLA_'+marker_name.split('_')[1].split('*')[0]\n",
    "    elif marker_name[:9]=='INS_SNPS_':\n",
    "        ret='HLA_'+marker_name.split('_')[2]\n",
    "    elif np.any(~gene_assign_reduce.loc[marker_name].iloc[1:].isnull()):\n",
    "        ret=gene_assign_reduce.loc[marker_name].iloc[1:]\n",
    "        ret=','.join(ret[~ret.isnull()])\n",
    "    else:\n",
    "        r2=r2_df[marker_name].sort_values(ascending=False)\n",
    "        gene_assign_r2_moderate_HLA=gene_assign.loc[r2[r2>0.5].index][gene_assign.columns[gene_assign.columns.str.contains('HLA')]]\n",
    "        gene_assign_r2_moderate_HLA=gene_assign_r2_moderate_HLA[gene_assign_r2_moderate_HLA.sum(axis=1)!=0]\n",
    "        #print(gene_assign_r2_moderate_HLA.sum(axis=1)!=0)\n",
    "        \n",
    "        gene_assign_r2_strong=gene_assign.loc[r2[r2>0.8].index].iloc[:,1:]\n",
    "        gene_assign_r2_strong=gene_assign_r2_strong[gene_assign_r2_strong.sum(axis=1)!=0]\n",
    "        #gene_assign_r2_strong_sum=gene_assign_r2_strong.sum()\n",
    "        #\n",
    "        if len(gene_assign_r2_moderate_HLA)!=0:\n",
    "            ret=gene_assign_r2_moderate_HLA.iloc[0].sort_values(ascending=False).index[0]\n",
    "        elif len(gene_assign_r2_strong)!=0:\n",
    "            ret=gene_assign_r2_strong.iloc[0].sort_values(ascending=False).index[0]#[gene_assign_r2_strong.iloc[0]==1]\n",
    "        else:\n",
    "            #print(marker_name)\n",
    "            gene_assign_temp=gene_assign.copy()\n",
    "            gene_assign_temp['dist']=(gene_assign_temp['pos']-gene_assign_temp['pos'][marker_name]).abs()\n",
    "            #print(marker_name,gene_assign_temp.sort_values('dist'))\n",
    "            \n",
    "            gene_assign_temp_clip=gene_assign_temp.sort_values('dist').iloc[:,1:-1]\n",
    "            \n",
    "            for row_idx,row in gene_assign_temp_clip.iterrows():\n",
    "                if np.any(row!=0):\n",
    "                    #print(row)\n",
    "                    ret=','.join(row[row!=0].index)\n",
    "                    break\n",
    "    return ret\n",
    "\"\"\"    "
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "metadata": {},
   "outputs": [],
   "source": [
    "def marker_name_to_genehow(marker_name):\n",
    "    if marker_name[:3]=='AA_':\n",
    "        ret=('HLA-'+marker_name.split('_')[1],'on_gene')\n",
    "    elif marker_name[:5]=='SNPS_':\n",
    "        ret=('HLA-'+marker_name.split('_')[1],'on_gene')\n",
    "        #conditional_list.append('HLA_'+marker_name.split('_')[1])\n",
    "    elif marker_name[:4]=='HLA_':\n",
    "        ret=('HLA-'+marker_name.split('_')[1].split('*')[0],'on_gene')\n",
    "    elif marker_name[:9]=='INS_SNPS_':\n",
    "        ret=('HLA-'+marker_name.split('_')[2],'on_gene')\n",
    "    elif np.any(~gene_assign_reduce.loc[marker_name].iloc[1:].isnull()):\n",
    "        ret=gene_assign_reduce.loc[marker_name].iloc[1:]\n",
    "        ret=(','.join(ret[~ret.isnull()]),'on_gene')\n",
    "    else:\n",
    "        r2=r2_df[marker_name].sort_values(ascending=False)\n",
    "        gene_assign_r2_moderate_HLA=gene_assign.loc[r2[r2>0.5].index][gene_assign.columns[gene_assign.columns.str.contains('HLA')].tolist()+['MICA','MICB','TAP1','TAP2']]\n",
    "        gene_assign_r2_moderate_HLA=gene_assign_r2_moderate_HLA[gene_assign_r2_moderate_HLA.sum(axis=1)!=0]\n",
    "        #print(gene_assign_r2_moderate_HLA.sum(axis=1)!=0)\n",
    "        \n",
    "        gene_assign_r2_strong=gene_assign.loc[r2[r2>0.8].index].iloc[:,1:]\n",
    "        gene_assign_r2_strong=gene_assign_r2_strong[gene_assign_r2_strong.sum(axis=1)!=0]\n",
    "        #gene_assign_r2_strong_sum=gene_assign_r2_strong.sum()\n",
    "        #\n",
    "        if len(gene_assign_r2_moderate_HLA)!=0:\n",
    "            ret=gene_assign_r2_moderate_HLA.iloc[0].sort_values(ascending=False).index[0]\n",
    "            ret=(ret,'moderate_LD')\n",
    "            print(marker_name)\n",
    "            print(gene_assign_r2_moderate_HLA.iloc[:10])\n",
    "        elif len(gene_assign_r2_strong)!=0:\n",
    "            ret=gene_assign_r2_strong.iloc[0].sort_values(ascending=False).index[0]#[gene_assign_r2_strong.iloc[0]==1]\n",
    "            ret=(ret,'strong_LD')\n",
    "        else:\n",
    "            #print(marker_name)\n",
    "            gene_assign_temp=gene_assign.copy()\n",
    "            gene_assign_temp['dist']=(gene_assign_temp['pos']-gene_assign_temp['pos'][marker_name]).abs()\n",
    "            #print(marker_name,gene_assign_temp.sort_values('dist'))\n",
    "            \n",
    "            gene_assign_temp_clip=gene_assign_temp.sort_values('dist').iloc[:,1:-1]\n",
    "            \n",
    "            for row_idx,row in gene_assign_temp_clip.iterrows():\n",
    "                if np.any(row!=0):\n",
    "                    #print(row)\n",
    "                    ret=','.join(row[row!=0].index)\n",
    "                    ret=(ret,'nearest')\n",
    "                    break\n",
    "    return ret"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>phenotype_type</th>\n",
       "      <th>phenotype_name</th>\n",
       "      <th>samples(case/control)</th>\n",
       "      <th>step</th>\n",
       "      <th>condition</th>\n",
       "      <th>marker_name</th>\n",
       "      <th>marker_name_pub</th>\n",
       "      <th>note</th>\n",
       "      <th>...</th>\n",
       "      <th>A1_freq_control</th>\n",
       "      <th>multi_allele</th>\n",
       "      <th>nobs</th>\n",
       "      <th>Z</th>\n",
       "      <th>coef</th>\n",
       "      <th>std</th>\n",
       "      <th>chisq</th>\n",
       "      <th>df</th>\n",
       "      <th>P</th>\n",
       "      <th>P_significant</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>18966</td>\n",
       "      <td>169281</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bun</td>\n",
       "      <td>124563</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:30737591_G/C</td>\n",
       "      <td>rs3095337</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>124563</td>\n",
       "      <td>-6.93374</td>\n",
       "      <td>-0.186481</td>\n",
       "      <td>0.026895</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.118390e-12</td>\n",
       "      <td>1</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>34</th>\n",
       "      <td>13105</td>\n",
       "      <td>323700</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bun</td>\n",
       "      <td>124563</td>\n",
       "      <td>2</td>\n",
       "      <td>6:30737591_G/C,HLA_C</td>\n",
       "      <td>6:29922341_G/C</td>\n",
       "      <td>rs28780070</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>124563</td>\n",
       "      <td>4.52102</td>\n",
       "      <td>0.071743</td>\n",
       "      <td>0.015869</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.159850e-06</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>2 rows × 25 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Unnamed: 0  Unnamed: 0.1 phenotype_type phenotype_name  \\\n",
       "33       18966        169281     continuous            bun   \n",
       "34       13105        323700     continuous            bun   \n",
       "\n",
       "   samples(case/control)  step             condition     marker_name  \\\n",
       "33                124563     1                   NaN  6:30737591_G/C   \n",
       "34                124563     2  6:30737591_G/C,HLA_C  6:29922341_G/C   \n",
       "\n",
       "   marker_name_pub               note  ... A1_freq_control  multi_allele  \\\n",
       "33       rs3095337  unphased bialleic  ...             NaN           NaN   \n",
       "34      rs28780070  unphased bialleic  ...             NaN           NaN   \n",
       "\n",
       "      nobs        Z      coef       std chisq  df             P  P_significant  \n",
       "33  124563 -6.93374 -0.186481  0.026895   NaN NaN  4.118390e-12              1  \n",
       "34  124563  4.52102  0.071743  0.015869   NaN NaN  6.159850e-06              0  \n",
       "\n",
       "[2 rows x 25 columns]"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_all[result_all['phenotype_name']=='hdl_cholesterol']\n",
    "result_all[result_all['phenotype_name']=='bun']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "AX-41950637\n",
      "                             HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                     \n",
      "SNPS_C_544_31239305_intron2      0      0      0      0      1      0   \n",
      "SNPS_C_514_31239335_intron2      0      0      0      0      1      0   \n",
      "\n",
      "                             HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                 ...   \n",
      "SNPS_C_544_31239305_intron2        0         0         0         0  ...   \n",
      "SNPS_C_514_31239335_intron2        0         0         0         0  ...   \n",
      "\n",
      "                             HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                         \n",
      "SNPS_C_544_31239305_intron2        0        0        0        0         0   \n",
      "SNPS_C_514_31239335_intron2        0        0        0        0         0   \n",
      "\n",
      "                             HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                            \n",
      "SNPS_C_544_31239305_intron2         0     0     0     0     0  \n",
      "SNPS_C_514_31239335_intron2         0     0     0     0     0  \n",
      "\n",
      "[2 rows x 23 columns]\n",
      "6:31351530_T/C\n",
      "                HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  HLA-DRB5  \\\n",
      "snp                                                                           \n",
      "6:31376545_C/T      0      0      0      0      0      0        0         0   \n",
      "\n",
      "                HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  \\\n",
      "snp                                 ...                                       \n",
      "6:31376545_C/T         0         0  ...        0        0        0        0   \n",
      "\n",
      "                HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                         \n",
      "6:31376545_C/T         0         0     1     0     0     0  \n",
      "\n",
      "[1 rows x 23 columns]\n",
      "6:32202630_G/T\n",
      "                               HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                       \n",
      "HLA_DRB1*04:05                     0      0      0      0      0      0   \n",
      "HLA_DQB1*04:01                     0      0      0      0      0      0   \n",
      "AA_DQB1_23_32632783_exon2          0      0      0      0      0      0   \n",
      "SNPS_DQB1_1602_32632783_exon2      0      0      0      0      0      0   \n",
      "6:32486666_G/A                     0      0      0      0      0      0   \n",
      "6:32601594_C/T                     0      0      0      0      0      0   \n",
      "6:32597191_C/A                     0      0      0      0      0      0   \n",
      "6:32605561_C/T                     0      0      0      0      0      0   \n",
      "6:32606215_G/A                     0      0      0      0      0      0   \n",
      "6:32486543_G/T                     0      0      0      0      0      0   \n",
      "\n",
      "                               HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                   ...   \n",
      "HLA_DRB1*04:05                       0         0         1         0  ...   \n",
      "HLA_DQB1*04:01                       0         0         0         0  ...   \n",
      "AA_DQB1_23_32632783_exon2            0         0         0         0  ...   \n",
      "SNPS_DQB1_1602_32632783_exon2        0         0         0         0  ...   \n",
      "6:32486666_G/A                       0         1         0         0  ...   \n",
      "6:32601594_C/T                       0         0         0         1  ...   \n",
      "6:32597191_C/A                       0         0         0         1  ...   \n",
      "6:32605561_C/T                       0         0         0         1  ...   \n",
      "6:32606215_G/A                       0         0         0         1  ...   \n",
      "6:32486543_G/T                       0         1         0         0  ...   \n",
      "\n",
      "                               HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                           \n",
      "HLA_DRB1*04:05                       0        0        0        0         0   \n",
      "HLA_DQB1*04:01                       0        0        0        0         0   \n",
      "AA_DQB1_23_32632783_exon2            0        0        0        0         0   \n",
      "SNPS_DQB1_1602_32632783_exon2        0        0        0        0         0   \n",
      "6:32486666_G/A                       0        0        0        0         0   \n",
      "6:32601594_C/T                       0        0        0        0         0   \n",
      "6:32597191_C/A                       0        0        0        0         0   \n",
      "6:32605561_C/T                       0        0        0        0         0   \n",
      "6:32606215_G/A                       0        0        0        0         0   \n",
      "6:32486543_G/T                       0        0        0        0         0   \n",
      "\n",
      "                               HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                              \n",
      "HLA_DRB1*04:05                        0     0     0     0     0  \n",
      "HLA_DQB1*04:01                        0     0     0     0     0  \n",
      "AA_DQB1_23_32632783_exon2             0     0     0     0     0  \n",
      "SNPS_DQB1_1602_32632783_exon2         0     0     0     0     0  \n",
      "6:32486666_G/A                        0     0     0     0     0  \n",
      "6:32601594_C/T                        0     0     0     0     0  \n",
      "6:32597191_C/A                        0     0     0     0     0  \n",
      "6:32605561_C/T                        0     0     0     0     0  \n",
      "6:32606215_G/A                        0     0     0     0     0  \n",
      "6:32486543_G/T                        0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:33076268_T/C\n",
      "                                      HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  \\\n",
      "snp                                                                       \n",
      "6:33052502_G/A                            0      0      0      0      0   \n",
      "AA_DPB1_84_33048691_exon2_G               0      0      0      0      0   \n",
      "6:33052624_AAAAAGGAAGGAAGGAAGGAAGG/A      0      0      0      0      0   \n",
      "AA_DPB1_85_33048694_exon2                 0      0      0      0      0   \n",
      "AA_DPB1_84_33048691_exon2_D               0      0      0      0      0   \n",
      "AA_DPB1_87_33048700_exon2                 0      0      0      0      0   \n",
      "AA_DPB1_86_33048697_exon2                 0      0      0      0      0   \n",
      "6:33048689_G/A                            0      0      0      0      0   \n",
      "AX-38281009                               0      0      0      0      0   \n",
      "AX-11678155                               0      0      0      0      0   \n",
      "\n",
      "                                      HLA-B  HLA-DRA  HLA-DRB5  HLA-DRB1  \\\n",
      "snp                                                                        \n",
      "6:33052502_G/A                            0        0         0         0   \n",
      "AA_DPB1_84_33048691_exon2_G               0        0         0         0   \n",
      "6:33052624_AAAAAGGAAGGAAGGAAGGAAGG/A      0        0         0         0   \n",
      "AA_DPB1_85_33048694_exon2                 0        0         0         0   \n",
      "AA_DPB1_84_33048691_exon2_D               0        0         0         0   \n",
      "AA_DPB1_87_33048700_exon2                 0        0         0         0   \n",
      "AA_DPB1_86_33048697_exon2                 0        0         0         0   \n",
      "6:33048689_G/A                            0        0         0         0   \n",
      "AX-38281009                               0        0         0         0   \n",
      "AX-11678155                               0        0         0         0   \n",
      "\n",
      "                                      HLA-DQA1  ...  HLA-DOB  HLA-DMB  \\\n",
      "snp                                             ...                     \n",
      "6:33052502_G/A                               0  ...        0        0   \n",
      "AA_DPB1_84_33048691_exon2_G                  0  ...        0        0   \n",
      "6:33052624_AAAAAGGAAGGAAGGAAGGAAGG/A         0  ...        0        0   \n",
      "AA_DPB1_85_33048694_exon2                    0  ...        0        0   \n",
      "AA_DPB1_84_33048691_exon2_D                  0  ...        0        0   \n",
      "AA_DPB1_87_33048700_exon2                    0  ...        0        0   \n",
      "AA_DPB1_86_33048697_exon2                    0  ...        0        0   \n",
      "6:33048689_G/A                               0  ...        0        0   \n",
      "AX-38281009                                  0  ...        0        0   \n",
      "AX-11678155                                  0  ...        0        0   \n",
      "\n",
      "                                      HLA-DMA  HLA-DOA  HLA-DPA1  HLA-DPB1  \\\n",
      "snp                                                                          \n",
      "6:33052502_G/A                              0        0         0         1   \n",
      "AA_DPB1_84_33048691_exon2_G                 0        0         0         1   \n",
      "6:33052624_AAAAAGGAAGGAAGGAAGGAAGG/A        0        0         0         1   \n",
      "AA_DPB1_85_33048694_exon2                   0        0         0         1   \n",
      "AA_DPB1_84_33048691_exon2_D                 0        0         0         1   \n",
      "AA_DPB1_87_33048700_exon2                   0        0         0         1   \n",
      "AA_DPB1_86_33048697_exon2                   0        0         0         1   \n",
      "6:33048689_G/A                              0        0         0         1   \n",
      "AX-38281009                                 0        0         0         1   \n",
      "AX-11678155                                 0        0         0         1   \n",
      "\n",
      "                                      MICA  MICB  TAP1  TAP2  \n",
      "snp                                                           \n",
      "6:33052502_G/A                           0     0     0     0  \n",
      "AA_DPB1_84_33048691_exon2_G              0     0     0     0  \n",
      "6:33052624_AAAAAGGAAGGAAGGAAGGAAGG/A     0     0     0     0  \n",
      "AA_DPB1_85_33048694_exon2                0     0     0     0  \n",
      "AA_DPB1_84_33048691_exon2_D              0     0     0     0  \n",
      "AA_DPB1_87_33048700_exon2                0     0     0     0  \n",
      "AA_DPB1_86_33048697_exon2                0     0     0     0  \n",
      "6:33048689_G/A                           0     0     0     0  \n",
      "AX-38281009                              0     0     0     0  \n",
      "AX-11678155                              0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:29896680_A/G\n",
      "                              HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                      \n",
      "AA_A_144_29911204_exon3           0      0      1      0      0      0   \n",
      "SNPS_A_873_29911203_exon3         0      0      1      0      0      0   \n",
      "6:29912348_A/G                    0      0      1      0      0      0   \n",
      "6:29913344_G/T                    0      0      1      0      0      0   \n",
      "AA_A_246_29912089_exon4           0      0      1      0      0      0   \n",
      "AA_A_299_29912350_exon5           0      0      1      0      0      0   \n",
      "AA_A_334_29913039_exon7           0      0      1      0      0      0   \n",
      "SNPS_A_2782_29913112_intron7      0      0      1      0      0      0   \n",
      "SNPS_A_2596_29912926_intron6      0      0      1      0      0      0   \n",
      "SNPS_A_2708_29913038_exon7        0      0      1      0      0      0   \n",
      "\n",
      "                              HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                  ...   \n",
      "AA_A_144_29911204_exon3             0         0         0         0  ...   \n",
      "SNPS_A_873_29911203_exon3           0         0         0         0  ...   \n",
      "6:29912348_A/G                      0         0         0         0  ...   \n",
      "6:29913344_G/T                      0         0         0         0  ...   \n",
      "AA_A_246_29912089_exon4             0         0         0         0  ...   \n",
      "AA_A_299_29912350_exon5             0         0         0         0  ...   \n",
      "AA_A_334_29913039_exon7             0         0         0         0  ...   \n",
      "SNPS_A_2782_29913112_intron7        0         0         0         0  ...   \n",
      "SNPS_A_2596_29912926_intron6        0         0         0         0  ...   \n",
      "SNPS_A_2708_29913038_exon7          0         0         0         0  ...   \n",
      "\n",
      "                              HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                          \n",
      "AA_A_144_29911204_exon3             0        0        0        0         0   \n",
      "SNPS_A_873_29911203_exon3           0        0        0        0         0   \n",
      "6:29912348_A/G                      0        0        0        0         0   \n",
      "6:29913344_G/T                      0        0        0        0         0   \n",
      "AA_A_246_29912089_exon4             0        0        0        0         0   \n",
      "AA_A_299_29912350_exon5             0        0        0        0         0   \n",
      "AA_A_334_29913039_exon7             0        0        0        0         0   \n",
      "SNPS_A_2782_29913112_intron7        0        0        0        0         0   \n",
      "SNPS_A_2596_29912926_intron6        0        0        0        0         0   \n",
      "SNPS_A_2708_29913038_exon7          0        0        0        0         0   \n",
      "\n",
      "                              HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                             \n",
      "AA_A_144_29911204_exon3              0     0     0     0     0  \n",
      "SNPS_A_873_29911203_exon3            0     0     0     0     0  \n",
      "6:29912348_A/G                       0     0     0     0     0  \n",
      "6:29913344_G/T                       0     0     0     0     0  \n",
      "AA_A_246_29912089_exon4              0     0     0     0     0  \n",
      "AA_A_299_29912350_exon5              0     0     0     0     0  \n",
      "AA_A_334_29913039_exon7              0     0     0     0     0  \n",
      "SNPS_A_2782_29913112_intron7         0     0     0     0     0  \n",
      "SNPS_A_2596_29912926_intron6         0     0     0     0     0  \n",
      "SNPS_A_2708_29913038_exon7           0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:30737591_G/C\n",
      "                          HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  \\\n",
      "snp                                                                           \n",
      "6:30460776_A/C                0      0      0      1      0      0        0   \n",
      "6:30457283_G/T                0      0      0      1      0      0        0   \n",
      "HLA_C*03:02                   0      0      0      0      1      0        0   \n",
      "HLA_B*58:01                   0      0      0      0      0      1        0   \n",
      "6:31465047_G/T                0      0      0      0      0      0        0   \n",
      "6:31469774_A/G                0      0      0      0      0      0        0   \n",
      "AX-35736797                   0      0      0      0      0      0        0   \n",
      "AA_B_62_31324551_exon2        0      0      0      0      0      1        0   \n",
      "AA_B_65_31324542_exon2        0      0      0      0      0      1        0   \n",
      "AA_B_66_31324539_exon2_N      0      0      0      0      0      1        0   \n",
      "\n",
      "                          HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  \\\n",
      "snp                                                     ...                     \n",
      "6:30460776_A/C                   0         0         0  ...        0        0   \n",
      "6:30457283_G/T                   0         0         0  ...        0        0   \n",
      "HLA_C*03:02                      0         0         0  ...        0        0   \n",
      "HLA_B*58:01                      0         0         0  ...        0        0   \n",
      "6:31465047_G/T                   0         0         0  ...        0        0   \n",
      "6:31469774_A/G                   0         0         0  ...        0        0   \n",
      "AX-35736797                      0         0         0  ...        0        0   \n",
      "AA_B_62_31324551_exon2           0         0         0  ...        0        0   \n",
      "AA_B_65_31324542_exon2           0         0         0  ...        0        0   \n",
      "AA_B_66_31324539_exon2_N         0         0         0  ...        0        0   \n",
      "\n",
      "                          HLA-DMA  HLA-DOA  HLA-DPA1  HLA-DPB1  MICA  MICB  \\\n",
      "snp                                                                          \n",
      "6:30460776_A/C                  0        0         0         0     0     0   \n",
      "6:30457283_G/T                  0        0         0         0     0     0   \n",
      "HLA_C*03:02                     0        0         0         0     0     0   \n",
      "HLA_B*58:01                     0        0         0         0     0     0   \n",
      "6:31465047_G/T                  0        0         0         0     0     1   \n",
      "6:31469774_A/G                  0        0         0         0     0     1   \n",
      "AX-35736797                     0        0         0         0     0     1   \n",
      "AA_B_62_31324551_exon2          0        0         0         0     0     0   \n",
      "AA_B_65_31324542_exon2          0        0         0         0     0     0   \n",
      "AA_B_66_31324539_exon2_N        0        0         0         0     0     0   \n",
      "\n",
      "                          TAP1  TAP2  \n",
      "snp                                   \n",
      "6:30460776_A/C               0     0  \n",
      "6:30457283_G/T               0     0  \n",
      "HLA_C*03:02                  0     0  \n",
      "HLA_B*58:01                  0     0  \n",
      "6:31465047_G/T               0     0  \n",
      "6:31469774_A/G               0     0  \n",
      "AX-35736797                  0     0  \n",
      "AA_B_62_31324551_exon2       0     0  \n",
      "AA_B_65_31324542_exon2       0     0  \n",
      "AA_B_66_31324539_exon2_N     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:31358559_C/T\n",
      "                              HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                      \n",
      "6:31375493_G/C                    0      0      0      0      0      0   \n",
      "6:31374579_A/G                    0      0      0      0      0      0   \n",
      "6:31381611_C/T                    0      0      0      0      0      0   \n",
      "6:31324955_C/T                    0      0      0      0      0      1   \n",
      "6:31375917_T/C                    0      0      0      0      0      0   \n",
      "6:31380897_C/T                    0      0      0      0      0      0   \n",
      "6:31378335_G/C                    0      0      0      0      0      0   \n",
      "SNPS_B_1215_31323721_intron3      0      0      0      0      0      1   \n",
      "SNPS_B_1211_31323725_intron3      0      0      0      0      0      1   \n",
      "SNPS_B_2449_31322487_intron5      0      0      0      0      0      1   \n",
      "\n",
      "                              HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                  ...   \n",
      "6:31375493_G/C                      0         0         0         0  ...   \n",
      "6:31374579_A/G                      0         0         0         0  ...   \n",
      "6:31381611_C/T                      0         0         0         0  ...   \n",
      "6:31324955_C/T                      0         0         0         0  ...   \n",
      "6:31375917_T/C                      0         0         0         0  ...   \n",
      "6:31380897_C/T                      0         0         0         0  ...   \n",
      "6:31378335_G/C                      0         0         0         0  ...   \n",
      "SNPS_B_1215_31323721_intron3        0         0         0         0  ...   \n",
      "SNPS_B_1211_31323725_intron3        0         0         0         0  ...   \n",
      "SNPS_B_2449_31322487_intron5        0         0         0         0  ...   \n",
      "\n",
      "                              HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                          \n",
      "6:31375493_G/C                      0        0        0        0         0   \n",
      "6:31374579_A/G                      0        0        0        0         0   \n",
      "6:31381611_C/T                      0        0        0        0         0   \n",
      "6:31324955_C/T                      0        0        0        0         0   \n",
      "6:31375917_T/C                      0        0        0        0         0   \n",
      "6:31380897_C/T                      0        0        0        0         0   \n",
      "6:31378335_G/C                      0        0        0        0         0   \n",
      "SNPS_B_1215_31323721_intron3        0        0        0        0         0   \n",
      "SNPS_B_1211_31323725_intron3        0        0        0        0         0   \n",
      "SNPS_B_2449_31322487_intron5        0        0        0        0         0   \n",
      "\n",
      "                              HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                             \n",
      "6:31375493_G/C                       0     1     0     0     0  \n",
      "6:31374579_A/G                       0     1     0     0     0  \n",
      "6:31381611_C/T                       0     1     0     0     0  \n",
      "6:31324955_C/T                       0     0     0     0     0  \n",
      "6:31375917_T/C                       0     1     0     0     0  \n",
      "6:31380897_C/T                       0     1     0     0     0  \n",
      "6:31378335_G/C                       0     1     0     0     0  \n",
      "SNPS_B_1215_31323721_intron3         0     0     0     0     0  \n",
      "SNPS_B_1211_31323725_intron3         0     0     0     0     0  \n",
      "SNPS_B_2449_31322487_intron5         0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:29497002_G/A\n",
      "                               HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                       \n",
      "6:29699908_A/ATTT                  1      0      0      0      0      0   \n",
      "6:29705402_C/T                     1      0      0      0      0      0   \n",
      "6:29704237_G/A                     1      0      0      0      0      0   \n",
      "6:29698036_A/C                     1      0      0      0      0      0   \n",
      "6:29699235_C/CTCAA                 1      0      0      0      0      0   \n",
      "6:29705479_G/A                     1      0      0      0      0      0   \n",
      "6:29701023_C/T                     1      0      0      0      0      0   \n",
      "6:29694336_ATGTG/ATG               1      0      0      0      0      0   \n",
      "6:29690652_A/G                     1      0      0      0      0      0   \n",
      "6:29692462_TGGAATACCGATCCGC/T      1      0      0      0      0      0   \n",
      "\n",
      "                               HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                   ...   \n",
      "6:29699908_A/ATTT                    0         0         0         0  ...   \n",
      "6:29705402_C/T                       0         0         0         0  ...   \n",
      "6:29704237_G/A                       0         0         0         0  ...   \n",
      "6:29698036_A/C                       0         0         0         0  ...   \n",
      "6:29699235_C/CTCAA                   0         0         0         0  ...   \n",
      "6:29705479_G/A                       0         0         0         0  ...   \n",
      "6:29701023_C/T                       0         0         0         0  ...   \n",
      "6:29694336_ATGTG/ATG                 0         0         0         0  ...   \n",
      "6:29690652_A/G                       0         0         0         0  ...   \n",
      "6:29692462_TGGAATACCGATCCGC/T        0         0         0         0  ...   \n",
      "\n",
      "                               HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                           \n",
      "6:29699908_A/ATTT                    0        0        0        0         0   \n",
      "6:29705402_C/T                       0        0        0        0         0   \n",
      "6:29704237_G/A                       0        0        0        0         0   \n",
      "6:29698036_A/C                       0        0        0        0         0   \n",
      "6:29699235_C/CTCAA                   0        0        0        0         0   \n",
      "6:29705479_G/A                       0        0        0        0         0   \n",
      "6:29701023_C/T                       0        0        0        0         0   \n",
      "6:29694336_ATGTG/ATG                 0        0        0        0         0   \n",
      "6:29690652_A/G                       0        0        0        0         0   \n",
      "6:29692462_TGGAATACCGATCCGC/T        0        0        0        0         0   \n",
      "\n",
      "                               HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                              \n",
      "6:29699908_A/ATTT                     0     0     0     0     0  \n",
      "6:29705402_C/T                        0     0     0     0     0  \n",
      "6:29704237_G/A                        0     0     0     0     0  \n",
      "6:29698036_A/C                        0     0     0     0     0  \n",
      "6:29699235_C/CTCAA                    0     0     0     0     0  \n",
      "6:29705479_G/A                        0     0     0     0     0  \n",
      "6:29701023_C/T                        0     0     0     0     0  \n",
      "6:29694336_ATGTG/ATG                  0     0     0     0     0  \n",
      "6:29690652_A/G                        0     0     0     0     0  \n",
      "6:29692462_TGGAATACCGATCCGC/T         0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:31538497_T/A\n",
      "                HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  HLA-DRB5  \\\n",
      "snp                                                                           \n",
      "6:31472865_G/A      0      0      0      0      0      0        0         0   \n",
      "\n",
      "                HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  \\\n",
      "snp                                 ...                                       \n",
      "6:31472865_G/A         0         0  ...        0        0        0        0   \n",
      "\n",
      "                HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                         \n",
      "6:31472865_G/A         0         0     0     1     0     0  \n",
      "\n",
      "[1 rows x 23 columns]\n",
      "6:32639786_G/A\n",
      "                HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  HLA-DRB5  \\\n",
      "snp                                                                           \n",
      "HLA_DQB1*06:04      0      0      0      0      0      0        0         0   \n",
      "6:32605917_C/T      0      0      0      0      0      0        0         0   \n",
      "6:32727550_C/T      0      0      0      0      0      0        0         0   \n",
      "6:32731047_A/C      0      0      0      0      0      0        0         0   \n",
      "AX-106775062        0      0      0      0      0      0        0         0   \n",
      "HLA_C*14:03         0      0      0      0      1      0        0         0   \n",
      "6:31371397_C/T      0      0      0      0      0      0        0         0   \n",
      "6:32903086_G/A      0      0      0      0      0      0        0         0   \n",
      "6:32976147_T/A      0      0      0      0      0      0        0         0   \n",
      "6:32976185_G/A      0      0      0      0      0      0        0         0   \n",
      "\n",
      "                HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  \\\n",
      "snp                                 ...                                       \n",
      "HLA_DQB1*06:04         0         0  ...        0        0        0        0   \n",
      "6:32605917_C/T         0         1  ...        0        0        0        0   \n",
      "6:32727550_C/T         0         0  ...        0        0        0        0   \n",
      "6:32731047_A/C         0         0  ...        0        0        0        0   \n",
      "AX-106775062           0         0  ...        0        0        0        0   \n",
      "HLA_C*14:03            0         0  ...        0        0        0        0   \n",
      "6:31371397_C/T         0         0  ...        0        0        0        0   \n",
      "6:32903086_G/A         0         0  ...        0        1        0        0   \n",
      "6:32976147_T/A         0         0  ...        0        0        0        1   \n",
      "6:32976185_G/A         0         0  ...        0        0        0        1   \n",
      "\n",
      "                HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                         \n",
      "HLA_DQB1*06:04         0         0     0     0     0     0  \n",
      "6:32605917_C/T         0         0     0     0     0     0  \n",
      "6:32727550_C/T         0         0     0     0     0     0  \n",
      "6:32731047_A/C         0         0     0     0     0     0  \n",
      "AX-106775062           0         0     0     1     0     0  \n",
      "HLA_C*14:03            0         0     0     0     0     0  \n",
      "6:31371397_C/T         0         0     1     0     0     0  \n",
      "6:32903086_G/A         0         0     0     0     0     0  \n",
      "6:32976147_T/A         0         0     0     0     0     0  \n",
      "6:32976185_G/A         0         0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "AX-11396692\n",
      "                             HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                     \n",
      "AA_B_163_31324003_exon3_L        0      0      0      0      0      1   \n",
      "SNPS_B_933_31324003_exon3_A      0      0      0      0      0      1   \n",
      "SNPS_B_932_31324004_exon3_G      0      0      0      0      0      1   \n",
      "\n",
      "                             HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                 ...   \n",
      "AA_B_163_31324003_exon3_L          0         0         0         0  ...   \n",
      "SNPS_B_933_31324003_exon3_A        0         0         0         0  ...   \n",
      "SNPS_B_932_31324004_exon3_G        0         0         0         0  ...   \n",
      "\n",
      "                             HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                         \n",
      "AA_B_163_31324003_exon3_L          0        0        0        0         0   \n",
      "SNPS_B_933_31324003_exon3_A        0        0        0        0         0   \n",
      "SNPS_B_932_31324004_exon3_G        0        0        0        0         0   \n",
      "\n",
      "                             HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                            \n",
      "AA_B_163_31324003_exon3_L           0     0     0     0     0  \n",
      "SNPS_B_933_31324003_exon3_A         0     0     0     0     0  \n",
      "SNPS_B_932_31324004_exon3_G         0     0     0     0     0  \n",
      "\n",
      "[3 rows x 23 columns]\n",
      "6:29938478_A/G\n",
      "                             HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                     \n",
      "AA_A_105_29911087_exon3          0      0      1      0      0      0   \n",
      "SNPS_A_756_29911086_exon3        0      0      1      0      0      0   \n",
      "AA_A_90_29910801_exon2           0      0      1      0      0      0   \n",
      "SNPS_A_471_29910801_exon2        0      0      1      0      0      0   \n",
      "AA_A_163_29911261_exon3          0      0      1      0      0      0   \n",
      "SNPS_A_930_29911260_exon3        0      0      1      0      0      0   \n",
      "SNPS_A_931_29911261_exon3        0      0      1      0      0      0   \n",
      "AA_A_152_29911228_exon3_V        0      0      1      0      0      0   \n",
      "SNPS_A_898_29911228_exon3_T      0      0      1      0      0      0   \n",
      "\n",
      "                             HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                 ...   \n",
      "AA_A_105_29911087_exon3            0         0         0         0  ...   \n",
      "SNPS_A_756_29911086_exon3          0         0         0         0  ...   \n",
      "AA_A_90_29910801_exon2             0         0         0         0  ...   \n",
      "SNPS_A_471_29910801_exon2          0         0         0         0  ...   \n",
      "AA_A_163_29911261_exon3            0         0         0         0  ...   \n",
      "SNPS_A_930_29911260_exon3          0         0         0         0  ...   \n",
      "SNPS_A_931_29911261_exon3          0         0         0         0  ...   \n",
      "AA_A_152_29911228_exon3_V          0         0         0         0  ...   \n",
      "SNPS_A_898_29911228_exon3_T        0         0         0         0  ...   \n",
      "\n",
      "                             HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                         \n",
      "AA_A_105_29911087_exon3            0        0        0        0         0   \n",
      "SNPS_A_756_29911086_exon3          0        0        0        0         0   \n",
      "AA_A_90_29910801_exon2             0        0        0        0         0   \n",
      "SNPS_A_471_29910801_exon2          0        0        0        0         0   \n",
      "AA_A_163_29911261_exon3            0        0        0        0         0   \n",
      "SNPS_A_930_29911260_exon3          0        0        0        0         0   \n",
      "SNPS_A_931_29911261_exon3          0        0        0        0         0   \n",
      "AA_A_152_29911228_exon3_V          0        0        0        0         0   \n",
      "SNPS_A_898_29911228_exon3_T        0        0        0        0         0   \n",
      "\n",
      "                             HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                            \n",
      "AA_A_105_29911087_exon3             0     0     0     0     0  \n",
      "SNPS_A_756_29911086_exon3           0     0     0     0     0  \n",
      "AA_A_90_29910801_exon2              0     0     0     0     0  \n",
      "SNPS_A_471_29910801_exon2           0     0     0     0     0  \n",
      "AA_A_163_29911261_exon3             0     0     0     0     0  \n",
      "SNPS_A_930_29911260_exon3           0     0     0     0     0  \n",
      "SNPS_A_931_29911261_exon3           0     0     0     0     0  \n",
      "AA_A_152_29911228_exon3_V           0     0     0     0     0  \n",
      "SNPS_A_898_29911228_exon3_T         0     0     0     0     0  \n",
      "\n",
      "[9 rows x 23 columns]\n",
      "6:32641938_G/T\n",
      "                HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  HLA-DRB5  \\\n",
      "snp                                                                           \n",
      "6:32601995_G/A      0      0      0      0      0      0        0         0   \n",
      "6:32599297_T/G      0      0      0      0      0      0        0         0   \n",
      "6:32602751_C/A      0      0      0      0      0      0        0         0   \n",
      "6:32603758_T/C      0      0      0      0      0      0        0         0   \n",
      "6:32597334_C/T      0      0      0      0      0      0        0         0   \n",
      "6:32604198_G/A      0      0      0      0      0      0        0         0   \n",
      "6:32604457_G/A      0      0      0      0      0      0        0         0   \n",
      "6:32604976_C/G      0      0      0      0      0      0        0         0   \n",
      "6:32604530_A/T      0      0      0      0      0      0        0         0   \n",
      "HLA_DQB1*03:03      0      0      0      0      0      0        0         0   \n",
      "\n",
      "                HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  \\\n",
      "snp                                 ...                                       \n",
      "6:32601995_G/A         0         1  ...        0        0        0        0   \n",
      "6:32599297_T/G         0         1  ...        0        0        0        0   \n",
      "6:32602751_C/A         0         1  ...        0        0        0        0   \n",
      "6:32603758_T/C         0         1  ...        0        0        0        0   \n",
      "6:32597334_C/T         0         1  ...        0        0        0        0   \n",
      "6:32604198_G/A         0         1  ...        0        0        0        0   \n",
      "6:32604457_G/A         0         1  ...        0        0        0        0   \n",
      "6:32604976_C/G         0         1  ...        0        0        0        0   \n",
      "6:32604530_A/T         0         1  ...        0        0        0        0   \n",
      "HLA_DQB1*03:03         0         0  ...        0        0        0        0   \n",
      "\n",
      "                HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                         \n",
      "6:32601995_G/A         0         0     0     0     0     0  \n",
      "6:32599297_T/G         0         0     0     0     0     0  \n",
      "6:32602751_C/A         0         0     0     0     0     0  \n",
      "6:32603758_T/C         0         0     0     0     0     0  \n",
      "6:32597334_C/T         0         0     0     0     0     0  \n",
      "6:32604198_G/A         0         0     0     0     0     0  \n",
      "6:32604457_G/A         0         0     0     0     0     0  \n",
      "6:32604976_C/G         0         0     0     0     0     0  \n",
      "6:32604530_A/T         0         0     0     0     0     0  \n",
      "HLA_DQB1*03:03         0         0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:32453284_C/G\n",
      "                HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  HLA-DRB5  \\\n",
      "snp                                                                           \n",
      "6:32609009_T/G      0      0      0      0      0      0        0         0   \n",
      "6:32609047_C/T      0      0      0      0      0      0        0         0   \n",
      "6:32608435_T/C      0      0      0      0      0      0        0         0   \n",
      "6:32609425_C/G      0      0      0      0      0      0        0         0   \n",
      "6:32613362_G/A      0      0      0      0      0      0        0         0   \n",
      "6:32610947_A/C      0      0      0      0      0      0        0         0   \n",
      "6:32608276_A/G      0      0      0      0      0      0        0         0   \n",
      "6:32606691_T/G      0      0      0      0      0      0        0         0   \n",
      "6:32606682_C/G      0      0      0      0      0      0        0         0   \n",
      "6:32629545_T/C      0      0      0      0      0      0        0         0   \n",
      "\n",
      "                HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  \\\n",
      "snp                                 ...                                       \n",
      "6:32609009_T/G         0         1  ...        0        0        0        0   \n",
      "6:32609047_C/T         0         1  ...        0        0        0        0   \n",
      "6:32608435_T/C         0         1  ...        0        0        0        0   \n",
      "6:32609425_C/G         0         1  ...        0        0        0        0   \n",
      "6:32613362_G/A         0         1  ...        0        0        0        0   \n",
      "6:32610947_A/C         0         1  ...        0        0        0        0   \n",
      "6:32608276_A/G         0         1  ...        0        0        0        0   \n",
      "6:32606691_T/G         0         1  ...        0        0        0        0   \n",
      "6:32606682_C/G         0         1  ...        0        0        0        0   \n",
      "6:32629545_T/C         0         0  ...        0        0        0        0   \n",
      "\n",
      "                HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                         \n",
      "6:32609009_T/G         0         0     0     0     0     0  \n",
      "6:32609047_C/T         0         0     0     0     0     0  \n",
      "6:32608435_T/C         0         0     0     0     0     0  \n",
      "6:32609425_C/G         0         0     0     0     0     0  \n",
      "6:32613362_G/A         0         0     0     0     0     0  \n",
      "6:32610947_A/C         0         0     0     0     0     0  \n",
      "6:32608276_A/G         0         0     0     0     0     0  \n",
      "6:32606691_T/G         0         0     0     0     0     0  \n",
      "6:32606682_C/G         0         0     0     0     0     0  \n",
      "6:32629545_T/C         0         0     0     0     0     0  \n",
      "\n",
      "[10 rows x 23 columns]\n",
      "6:31428911_A/G\n",
      "                             HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  \\\n",
      "snp                                                                     \n",
      "6:31322047_A/G                   0      0      0      0      0      1   \n",
      "SNPS_B_912_31324024_exon3_C      0      0      0      0      0      1   \n",
      "6:31380897_C/T                   0      0      0      0      0      0   \n",
      "6:31378335_G/C                   0      0      0      0      0      0   \n",
      "6:31375917_T/C                   0      0      0      0      0      0   \n",
      "6:31373260_G/C                   0      0      0      0      0      0   \n",
      "\n",
      "                             HLA-DRA  HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  \\\n",
      "snp                                                                 ...   \n",
      "6:31322047_A/G                     0         0         0         0  ...   \n",
      "SNPS_B_912_31324024_exon3_C        0         0         0         0  ...   \n",
      "6:31380897_C/T                     0         0         0         0  ...   \n",
      "6:31378335_G/C                     0         0         0         0  ...   \n",
      "6:31375917_T/C                     0         0         0         0  ...   \n",
      "6:31373260_G/C                     0         0         0         0  ...   \n",
      "\n",
      "                             HLA-DOB  HLA-DMB  HLA-DMA  HLA-DOA  HLA-DPA1  \\\n",
      "snp                                                                         \n",
      "6:31322047_A/G                     0        0        0        0         0   \n",
      "SNPS_B_912_31324024_exon3_C        0        0        0        0         0   \n",
      "6:31380897_C/T                     0        0        0        0         0   \n",
      "6:31378335_G/C                     0        0        0        0         0   \n",
      "6:31375917_T/C                     0        0        0        0         0   \n",
      "6:31373260_G/C                     0        0        0        0         0   \n",
      "\n",
      "                             HLA-DPB1  MICA  MICB  TAP1  TAP2  \n",
      "snp                                                            \n",
      "6:31322047_A/G                      0     0     0     0     0  \n",
      "SNPS_B_912_31324024_exon3_C         0     0     0     0     0  \n",
      "6:31380897_C/T                      0     1     0     0     0  \n",
      "6:31378335_G/C                      0     1     0     0     0  \n",
      "6:31375917_T/C                      0     1     0     0     0  \n",
      "6:31373260_G/C                      0     1     0     0     0  \n",
      "\n",
      "[6 rows x 23 columns]\n",
      "6:32569297_A/G\n",
      "                   HLA-F  HLA-G  HLA-A  HLA-E  HLA-C  HLA-B  HLA-DRA  \\\n",
      "snp                                                                    \n",
      "6:32607926_T/G         0      0      0      0      0      0        0   \n",
      "6:32605027_C/CACA      0      0      0      0      0      0        0   \n",
      "6:32604124_G/A         0      0      0      0      0      0        0   \n",
      "6:32609279_C/T         0      0      0      0      0      0        0   \n",
      "6:32609278_G/C         0      0      0      0      0      0        0   \n",
      "AX-112917173           0      0      0      0      0      0        0   \n",
      "6:32607729_C/T         0      0      0      0      0      0        0   \n",
      "6:32606665_C/T         0      0      0      0      0      0        0   \n",
      "6:32607986_G/C         0      0      0      0      0      0        0   \n",
      "6:32606941_T/C         0      0      0      0      0      0        0   \n",
      "\n",
      "                   HLA-DRB5  HLA-DRB1  HLA-DQA1  ...  HLA-DOB  HLA-DMB  \\\n",
      "snp                                              ...                     \n",
      "6:32607926_T/G            0         0         1  ...        0        0   \n",
      "6:32605027_C/CACA         0         0         1  ...        0        0   \n",
      "6:32604124_G/A            0         0         1  ...        0        0   \n",
      "6:32609279_C/T            0         0         1  ...        0        0   \n",
      "6:32609278_G/C            0         0         1  ...        0        0   \n",
      "AX-112917173              0         0         1  ...        0        0   \n",
      "6:32607729_C/T            0         0         1  ...        0        0   \n",
      "6:32606665_C/T            0         0         1  ...        0        0   \n",
      "6:32607986_G/C            0         0         1  ...        0        0   \n",
      "6:32606941_T/C            0         0         1  ...        0        0   \n",
      "\n",
      "                   HLA-DMA  HLA-DOA  HLA-DPA1  HLA-DPB1  MICA  MICB  TAP1  \\\n",
      "snp                                                                         \n",
      "6:32607926_T/G           0        0         0         0     0     0     0   \n",
      "6:32605027_C/CACA        0        0         0         0     0     0     0   \n",
      "6:32604124_G/A           0        0         0         0     0     0     0   \n",
      "6:32609279_C/T           0        0         0         0     0     0     0   \n",
      "6:32609278_G/C           0        0         0         0     0     0     0   \n",
      "AX-112917173             0        0         0         0     0     0     0   \n",
      "6:32607729_C/T           0        0         0         0     0     0     0   \n",
      "6:32606665_C/T           0        0         0         0     0     0     0   \n",
      "6:32607986_G/C           0        0         0         0     0     0     0   \n",
      "6:32606941_T/C           0        0         0         0     0     0     0   \n",
      "\n",
      "                   TAP2  \n",
      "snp                      \n",
      "6:32607926_T/G        0  \n",
      "6:32605027_C/CACA     0  \n",
      "6:32604124_G/A        0  \n",
      "6:32609279_C/T        0  \n",
      "6:32609278_G/C        0  \n",
      "AX-112917173          0  \n",
      "6:32607729_C/T        0  \n",
      "6:32606665_C/T        0  \n",
      "6:32607986_G/C        0  \n",
      "6:32606941_T/C        0  \n",
      "\n",
      "[10 rows x 23 columns]\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/home/ch6845/tools/miniconda3/lib/python3.7/site-packages/ipykernel_launcher.py:6: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  \n",
      "/home/ch6845/tools/miniconda3/lib/python3.7/site-packages/ipykernel_launcher.py:8: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  \n",
      "/home/ch6845/tools/miniconda3/lib/python3.7/site-packages/ipykernel_launcher.py:9: SettingWithCopyWarning: \n",
      "A value is trying to be set on a copy of a slice from a DataFrame\n",
      "\n",
      "See the caveats in the documentation: http://pandas.pydata.org/pandas-docs/stable/indexing.html#indexing-view-versus-copy\n",
      "  if __name__ == '__main__':\n"
     ]
    }
   ],
   "source": [
    "result_all['gene_genehow']=np.nan\n",
    "result_all['gene']=np.nan\n",
    "result_all['genehow']=np.nan\n",
    "\n",
    "result_all['gene_genehow'][result_all['P_significant']==1]=\\\n",
    "result_all[result_all['P_significant']==1].apply(lambda x: marker_name_to_genehow(x['marker_name']),axis=1)\n",
    "\n",
    "result_all['gene'][result_all['P_significant']==1]=result_all[result_all['P_significant']==1].apply(lambda x: x['gene_genehow'][0],axis=1)\n",
    "result_all['genehow'][result_all['P_significant']==1]=result_all[result_all['P_significant']==1].apply(lambda x: x['gene_genehow'][1],axis=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>phenotype_type</th>\n",
       "      <th>phenotype_name</th>\n",
       "      <th>samples(case/control)</th>\n",
       "      <th>step</th>\n",
       "      <th>condition</th>\n",
       "      <th>marker_name</th>\n",
       "      <th>marker_name_pub</th>\n",
       "      <th>note</th>\n",
       "      <th>...</th>\n",
       "      <th>Z</th>\n",
       "      <th>coef</th>\n",
       "      <th>std</th>\n",
       "      <th>chisq</th>\n",
       "      <th>df</th>\n",
       "      <th>P</th>\n",
       "      <th>P_significant</th>\n",
       "      <th>gene_genehow</th>\n",
       "      <th>gene</th>\n",
       "      <th>genehow</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>23270</td>\n",
       "      <td>208017</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-41950637</td>\n",
       "      <td>rs7762933</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.55617</td>\n",
       "      <td>-0.008719</td>\n",
       "      <td>0.001019</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.179740e-17</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, moderate_LD)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>30669</td>\n",
       "      <td>272754</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31351530_T/C</td>\n",
       "      <td>rs2905715</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.52296</td>\n",
       "      <td>0.326987</td>\n",
       "      <td>0.050129</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.920490e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, moderate_LD)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>35667</td>\n",
       "      <td>317736</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32202630_G/T</td>\n",
       "      <td>rs117654833</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.60265</td>\n",
       "      <td>0.443845</td>\n",
       "      <td>0.058380</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.921930e-14</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, moderate_LD)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>63263</td>\n",
       "      <td>1498800</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>2</td>\n",
       "      <td>6:32202630_G/T,HLA_DQB1</td>\n",
       "      <td>6:33076268_T/C</td>\n",
       "      <td>rs742870</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.81671</td>\n",
       "      <td>-0.191552</td>\n",
       "      <td>0.032931</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.016610e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DPB1, moderate_LD)</td>\n",
       "      <td>HLA-DPB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>11573</td>\n",
       "      <td>92584</td>\n",
       "      <td>binary</td>\n",
       "      <td>blood_in_urine</td>\n",
       "      <td>1817/14938</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:29896680_A/G</td>\n",
       "      <td>rs2517754</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.53651</td>\n",
       "      <td>-0.201425</td>\n",
       "      <td>0.036381</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.085650e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-A, moderate_LD)</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>5 rows × 28 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "    Unnamed: 0  Unnamed: 0.1 phenotype_type  phenotype_name  \\\n",
       "7        23270        208017     continuous         albumin   \n",
       "13       30669        272754     continuous             alt   \n",
       "18       35667        317736     continuous             ast   \n",
       "19       63263       1498800     continuous             ast   \n",
       "25       11573         92584         binary  blood_in_urine   \n",
       "\n",
       "   samples(case/control)  step                condition     marker_name  \\\n",
       "7                 125069     1                      NaN     AX-41950637   \n",
       "13                120788     1                      NaN  6:31351530_T/C   \n",
       "18                121162     1                      NaN  6:32202630_G/T   \n",
       "19                121162     2  6:32202630_G/T,HLA_DQB1  6:33076268_T/C   \n",
       "25            1817/14938     1                      NaN  6:29896680_A/G   \n",
       "\n",
       "   marker_name_pub               note  ...        Z      coef       std chisq  \\\n",
       "7        rs7762933  unphased bialleic  ... -8.55617 -0.008719  0.001019   NaN   \n",
       "13       rs2905715  unphased bialleic  ...  6.52296  0.326987  0.050129   NaN   \n",
       "18     rs117654833  unphased bialleic  ...  7.60265  0.443845  0.058380   NaN   \n",
       "19        rs742870  unphased bialleic  ... -5.81671 -0.191552  0.032931   NaN   \n",
       "25       rs2517754  unphased bialleic  ... -5.53651 -0.201425  0.036381   NaN   \n",
       "\n",
       "    df             P P_significant             gene_genehow      gene  \\\n",
       "7  NaN  1.179740e-17             1     (HLA-C, moderate_LD)     HLA-C   \n",
       "13 NaN  6.920490e-11             1      (MICA, moderate_LD)      MICA   \n",
       "18 NaN  2.921930e-14             1  (HLA-DRB1, moderate_LD)  HLA-DRB1   \n",
       "19 NaN  6.016610e-09             1  (HLA-DPB1, moderate_LD)  HLA-DPB1   \n",
       "25 NaN  3.085650e-08             1     (HLA-A, moderate_LD)     HLA-A   \n",
       "\n",
       "        genehow  \n",
       "7   moderate_LD  \n",
       "13  moderate_LD  \n",
       "18  moderate_LD  \n",
       "19  moderate_LD  \n",
       "25  moderate_LD  \n",
       "\n",
       "[5 rows x 28 columns]"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_all[result_all['genehow']=='moderate_LD'].head()"
   ]
  },
  {
   "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>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>phenotype_type</th>\n",
       "      <th>phenotype_name</th>\n",
       "      <th>samples(case/control)</th>\n",
       "      <th>step</th>\n",
       "      <th>condition</th>\n",
       "      <th>marker_name</th>\n",
       "      <th>marker_name_pub</th>\n",
       "      <th>note</th>\n",
       "      <th>...</th>\n",
       "      <th>Z</th>\n",
       "      <th>coef</th>\n",
       "      <th>std</th>\n",
       "      <th>chisq</th>\n",
       "      <th>df</th>\n",
       "      <th>P</th>\n",
       "      <th>P_significant</th>\n",
       "      <th>gene_genehow</th>\n",
       "      <th>gene</th>\n",
       "      <th>genehow</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>20816</td>\n",
       "      <td>144613</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_over_FVC_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:30985177_G/A</td>\n",
       "      <td>rs12204947</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.183770</td>\n",
       "      <td>-0.060131</td>\n",
       "      <td>0.011600</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.231720e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>68685</td>\n",
       "      <td>475104</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34172055_C/A</td>\n",
       "      <td>rs1187115</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.836440</td>\n",
       "      <td>0.026954</td>\n",
       "      <td>0.004618</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.556790e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>21318</td>\n",
       "      <td>169288</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34172055_C/A</td>\n",
       "      <td>6:31018788_T/G</td>\n",
       "      <td>rs2517531</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.352160</td>\n",
       "      <td>-0.015100</td>\n",
       "      <td>0.003470</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.366070e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>68741</td>\n",
       "      <td>475496</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FVC_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.573560</td>\n",
       "      <td>0.036813</td>\n",
       "      <td>0.006605</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.583340e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>21307</td>\n",
       "      <td>169200</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FVC_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>AX-11396301</td>\n",
       "      <td>rs2517534</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.630100</td>\n",
       "      <td>0.022921</td>\n",
       "      <td>0.004950</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.717070e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>5</th>\n",
       "      <td>29549</td>\n",
       "      <td>204407</td>\n",
       "      <td>continuous</td>\n",
       "      <td>MVV_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>SNPS_B_293_31324643_exon2</td>\n",
       "      <td>rs1050517</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.290540</td>\n",
       "      <td>-0.415866</td>\n",
       "      <td>0.126382</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.004640e-03</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>6</th>\n",
       "      <td>56431</td>\n",
       "      <td>445472</td>\n",
       "      <td>binary</td>\n",
       "      <td>acute_liver_disease</td>\n",
       "      <td>669/74104</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32658375_T/G</td>\n",
       "      <td>rs28371257</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.001600</td>\n",
       "      <td>0.261618</td>\n",
       "      <td>0.065378</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.291630e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>23270</td>\n",
       "      <td>208017</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-41950637</td>\n",
       "      <td>rs7762933</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.556170</td>\n",
       "      <td>-0.008719</td>\n",
       "      <td>0.001019</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.179740e-17</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, moderate_LD)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>68761</td>\n",
       "      <td>679480</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>2</td>\n",
       "      <td>AX-41950637</td>\n",
       "      <td>6:34215221_G/A</td>\n",
       "      <td>rs928482</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.163130</td>\n",
       "      <td>-0.010955</td>\n",
       "      <td>0.001342</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.294620e-16</td>\n",
       "      <td>1</td>\n",
       "      <td>(C6orf1, on_gene)</td>\n",
       "      <td>C6orf1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>22997</td>\n",
       "      <td>251240</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>3</td>\n",
       "      <td>6:34215221_G/A,AX-41950637</td>\n",
       "      <td>AX-15354567</td>\n",
       "      <td>rs4713438</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.830450</td>\n",
       "      <td>-0.008171</td>\n",
       "      <td>0.001402</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.541470e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(POU5F1, on_gene)</td>\n",
       "      <td>POU5F1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>10</th>\n",
       "      <td>17705</td>\n",
       "      <td>210576</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>4</td>\n",
       "      <td>6:34215221_G/A,AX-15354567,AX-41950637</td>\n",
       "      <td>6:30436315_C/CAT</td>\n",
       "      <td>6:30436315_C/CAT</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.283050</td>\n",
       "      <td>0.005532</td>\n",
       "      <td>0.001047</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.272620e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>54209</td>\n",
       "      <td>481860</td>\n",
       "      <td>binary</td>\n",
       "      <td>allergic_disease</td>\n",
       "      <td>9273/78950</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32632237_C/T</td>\n",
       "      <td>rs9274326</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.603280</td>\n",
       "      <td>0.088615</td>\n",
       "      <td>0.015814</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.103290e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQB1, on_gene)</td>\n",
       "      <td>HLA-DQB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>12</th>\n",
       "      <td>12809</td>\n",
       "      <td>290996</td>\n",
       "      <td>binary</td>\n",
       "      <td>allergic_disease</td>\n",
       "      <td>9273/78950</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQB1</td>\n",
       "      <td>6:29916650_G/A</td>\n",
       "      <td>rs13215305</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.195720</td>\n",
       "      <td>-0.093244</td>\n",
       "      <td>0.017946</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.039270e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>30669</td>\n",
       "      <td>272754</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31351530_T/C</td>\n",
       "      <td>rs2905715</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.522960</td>\n",
       "      <td>0.326987</td>\n",
       "      <td>0.050129</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.920490e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, moderate_LD)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>68693</td>\n",
       "      <td>678800</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>2</td>\n",
       "      <td>6:31351530_T/C</td>\n",
       "      <td>6:34178764_A/C</td>\n",
       "      <td>rs28673163</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.475840</td>\n",
       "      <td>-0.334937</td>\n",
       "      <td>0.061166</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.362960e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>15</th>\n",
       "      <td>51373</td>\n",
       "      <td>419</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>3</td>\n",
       "      <td>6:31351530_T/C,6:34178764_A/C</td>\n",
       "      <td>AA_DQA1_75_32609303_exon2</td>\n",
       "      <td>HLA-DQA1 pos.75</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.613860</td>\n",
       "      <td>-0.356955</td>\n",
       "      <td>0.077366</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.952585e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>16</th>\n",
       "      <td>29461</td>\n",
       "      <td>198</td>\n",
       "      <td>binary</td>\n",
       "      <td>angina_pectoris_myocardial_infarction</td>\n",
       "      <td>3077/77843</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_B_80_31324497_exon2_T</td>\n",
       "      <td>HLA-B pos.80(T)</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.733281</td>\n",
       "      <td>0.149197</td>\n",
       "      <td>0.031521</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.209191e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>17</th>\n",
       "      <td>36489</td>\n",
       "      <td>325134</td>\n",
       "      <td>binary</td>\n",
       "      <td>arthritis</td>\n",
       "      <td>11348/73684</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32288790_A/G</td>\n",
       "      <td>rs117475045</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.757840</td>\n",
       "      <td>0.182630</td>\n",
       "      <td>0.038384</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.956730e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>35667</td>\n",
       "      <td>317736</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32202630_G/T</td>\n",
       "      <td>rs117654833</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.602650</td>\n",
       "      <td>0.443845</td>\n",
       "      <td>0.058380</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.921930e-14</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, moderate_LD)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>63263</td>\n",
       "      <td>1498800</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>2</td>\n",
       "      <td>6:32202630_G/T,HLA_DQB1</td>\n",
       "      <td>6:33076268_T/C</td>\n",
       "      <td>rs742870</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.816710</td>\n",
       "      <td>-0.191552</td>\n",
       "      <td>0.032931</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.016610e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DPB1, moderate_LD)</td>\n",
       "      <td>HLA-DPB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>20</th>\n",
       "      <td>68693</td>\n",
       "      <td>2307920</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>3</td>\n",
       "      <td>6:32202630_G/T,6:33076268_T/C,HLA_DPB1,HLA_DQB1</td>\n",
       "      <td>6:34178764_A/C</td>\n",
       "      <td>rs28673163</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.908920</td>\n",
       "      <td>-0.205566</td>\n",
       "      <td>0.041876</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.169740e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>21</th>\n",
       "      <td>38500</td>\n",
       "      <td>343233</td>\n",
       "      <td>binary</td>\n",
       "      <td>asthma</td>\n",
       "      <td>2115/78066</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32408907_G/A</td>\n",
       "      <td>rs3129879</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.645560</td>\n",
       "      <td>-0.157035</td>\n",
       "      <td>0.033803</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.391630e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>22</th>\n",
       "      <td>671</td>\n",
       "      <td>4697</td>\n",
       "      <td>binary</td>\n",
       "      <td>benign_prostatic_hyperplasia</td>\n",
       "      <td>168/11518</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:28177492_C/T</td>\n",
       "      <td>rs988084</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>3.758090</td>\n",
       "      <td>0.477103</td>\n",
       "      <td>0.126954</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.712120e-04</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>23</th>\n",
       "      <td>37231</td>\n",
       "      <td>258076</td>\n",
       "      <td>binary</td>\n",
       "      <td>big_baby</td>\n",
       "      <td>5057/71304</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32354723_CT/C</td>\n",
       "      <td>6:32354723_CT/C</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>3.603740</td>\n",
       "      <td>0.082041</td>\n",
       "      <td>0.022765</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.136670e-04</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>24</th>\n",
       "      <td>64351</td>\n",
       "      <td>508304</td>\n",
       "      <td>binary</td>\n",
       "      <td>bladder_cancer</td>\n",
       "      <td>47/74436</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:33200591_T/C</td>\n",
       "      <td>rs111327924</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>3.903040</td>\n",
       "      <td>1.653330</td>\n",
       "      <td>0.423601</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.499280e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>11573</td>\n",
       "      <td>92584</td>\n",
       "      <td>binary</td>\n",
       "      <td>blood_in_urine</td>\n",
       "      <td>1817/14938</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:29896680_A/G</td>\n",
       "      <td>rs2517754</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.536510</td>\n",
       "      <td>-0.201425</td>\n",
       "      <td>0.036381</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.085650e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-A, moderate_LD)</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>26</th>\n",
       "      <td>38146</td>\n",
       "      <td>340047</td>\n",
       "      <td>binary</td>\n",
       "      <td>blood_in_urine</td>\n",
       "      <td>1817/14938</td>\n",
       "      <td>2</td>\n",
       "      <td>6:29896680_A/G</td>\n",
       "      <td>6:32386619_T/C</td>\n",
       "      <td>rs4335021</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.229910</td>\n",
       "      <td>-0.202580</td>\n",
       "      <td>0.047892</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.337840e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>51369</td>\n",
       "      <td>417</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bmi</td>\n",
       "      <td>124539</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_DQA1_69_32609285_exon2_L</td>\n",
       "      <td>HLA-DQA1 pos.69(L)</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.082880</td>\n",
       "      <td>-0.070694</td>\n",
       "      <td>0.011622</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.180429e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, on_gene)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>4332</td>\n",
       "      <td>95304</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bmi</td>\n",
       "      <td>124539</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQA1</td>\n",
       "      <td>6:29190624_G/A</td>\n",
       "      <td>rs59230085</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.111320</td>\n",
       "      <td>-0.074561</td>\n",
       "      <td>0.012200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.910210e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(TRIM27, strong_LD)</td>\n",
       "      <td>TRIM27</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>29</th>\n",
       "      <td>68875</td>\n",
       "      <td>1565426</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bmi</td>\n",
       "      <td>124539</td>\n",
       "      <td>3</td>\n",
       "      <td>6:29190624_G/A,HLA_DQA1</td>\n",
       "      <td>6:34244245_C/A</td>\n",
       "      <td>rs4713766</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.068540</td>\n",
       "      <td>0.086797</td>\n",
       "      <td>0.017125</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.014480e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</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>138</th>\n",
       "      <td>41739</td>\n",
       "      <td>794</td>\n",
       "      <td>continuous</td>\n",
       "      <td>systolic_blood_pressure</td>\n",
       "      <td>124467</td>\n",
       "      <td>2</td>\n",
       "      <td>AX-11365330</td>\n",
       "      <td>HLA_DRB1*04:03</td>\n",
       "      <td>HLA-DRB1*04:03</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.580334</td>\n",
       "      <td>-0.835254</td>\n",
       "      <td>0.182357</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.642346e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139</th>\n",
       "      <td>68714</td>\n",
       "      <td>611109</td>\n",
       "      <td>binary</td>\n",
       "      <td>t2_diabetes</td>\n",
       "      <td>8662/78950</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34185749_C/T</td>\n",
       "      <td>rs2797963</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.849640</td>\n",
       "      <td>-0.164752</td>\n",
       "      <td>0.024053</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.403820e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>140</th>\n",
       "      <td>35422</td>\n",
       "      <td>350590</td>\n",
       "      <td>binary</td>\n",
       "      <td>t2_diabetes</td>\n",
       "      <td>8662/78950</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34185749_C/T</td>\n",
       "      <td>6:32181182_G/A</td>\n",
       "      <td>rs206016</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.920040</td>\n",
       "      <td>-0.092008</td>\n",
       "      <td>0.018700</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>8.652720e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>141</th>\n",
       "      <td>34182</td>\n",
       "      <td>304371</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_cancer</td>\n",
       "      <td>681/78535</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31797422_G/C</td>\n",
       "      <td>rs56280220</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>3.564350</td>\n",
       "      <td>0.433865</td>\n",
       "      <td>0.121723</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.647530e-04</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>51056</td>\n",
       "      <td>454437</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32608334_GAAA/G</td>\n",
       "      <td>6:32608334_GAAA/G</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-9.577430</td>\n",
       "      <td>-0.206240</td>\n",
       "      <td>0.021534</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.949160e-22</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, on_gene)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>143</th>\n",
       "      <td>32232</td>\n",
       "      <td>701118</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQA1</td>\n",
       "      <td>6:31430143_G/C</td>\n",
       "      <td>rs2255001</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.327290</td>\n",
       "      <td>0.243174</td>\n",
       "      <td>0.033188</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.348530e-13</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICB, nearest)</td>\n",
       "      <td>MICB</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>33689</td>\n",
       "      <td>766498</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>3</td>\n",
       "      <td>6:31430143_G/C,HLA_DQA1</td>\n",
       "      <td>6:31612576_A/T</td>\n",
       "      <td>rs12055599</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.640940</td>\n",
       "      <td>0.297620</td>\n",
       "      <td>0.044816</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.116790e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(BAG6, on_gene)</td>\n",
       "      <td>BAG6</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>55587</td>\n",
       "      <td>1316160</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>4</td>\n",
       "      <td>6:31430143_G/C,6:31612576_A/T,HLA_DQA1</td>\n",
       "      <td>6:32641938_G/T</td>\n",
       "      <td>rs28891457</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.567150</td>\n",
       "      <td>0.238481</td>\n",
       "      <td>0.036315</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.128710e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>146</th>\n",
       "      <td>30563</td>\n",
       "      <td>755000</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>5</td>\n",
       "      <td>6:31430143_G/C,6:31612576_A/T,6:32641938_G/T,H...</td>\n",
       "      <td>6:31348403_G/T</td>\n",
       "      <td>rs9266681</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.892880</td>\n",
       "      <td>-0.117203</td>\n",
       "      <td>0.023954</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.937060e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>147</th>\n",
       "      <td>39995</td>\n",
       "      <td>356688</td>\n",
       "      <td>continuous</td>\n",
       "      <td>total_bilirubin</td>\n",
       "      <td>77789</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32460867_T/C</td>\n",
       "      <td>rs78325334</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.444800</td>\n",
       "      <td>0.009289</td>\n",
       "      <td>0.001706</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.202030e-08</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>54447</td>\n",
       "      <td>494</td>\n",
       "      <td>continuous</td>\n",
       "      <td>total_cholesterol</td>\n",
       "      <td>125007</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_DQB1_57_32632681_exon2_V</td>\n",
       "      <td>HLA-DQB1 pos.57(V)</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>12.090447</td>\n",
       "      <td>2.167680</td>\n",
       "      <td>0.179289</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.186392e-33</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQB1, on_gene)</td>\n",
       "      <td>HLA-DQB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>149</th>\n",
       "      <td>61399</td>\n",
       "      <td>1394996</td>\n",
       "      <td>continuous</td>\n",
       "      <td>total_cholesterol</td>\n",
       "      <td>125007</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQB1</td>\n",
       "      <td>AX-11505577</td>\n",
       "      <td>rs443623</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-4.791750</td>\n",
       "      <td>-0.736927</td>\n",
       "      <td>0.153791</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.655190e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>150</th>\n",
       "      <td>29520</td>\n",
       "      <td>167</td>\n",
       "      <td>binary</td>\n",
       "      <td>transient_ischemic_attacks</td>\n",
       "      <td>59/74437</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_B_63_31324548_exon2</td>\n",
       "      <td>HLA-B pos.63</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.760997</td>\n",
       "      <td>-0.835879</td>\n",
       "      <td>0.222249</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.692373e-04</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151</th>\n",
       "      <td>39841</td>\n",
       "      <td>355302</td>\n",
       "      <td>continuous</td>\n",
       "      <td>triglyceride</td>\n",
       "      <td>123426</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32453284_C/G</td>\n",
       "      <td>rs111524667</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>14.355300</td>\n",
       "      <td>6.680110</td>\n",
       "      <td>0.465340</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.075790e-46</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>152</th>\n",
       "      <td>68714</td>\n",
       "      <td>1561723</td>\n",
       "      <td>continuous</td>\n",
       "      <td>triglyceride</td>\n",
       "      <td>123426</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQB1</td>\n",
       "      <td>6:34185749_C/T</td>\n",
       "      <td>rs2797963</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-7.420780</td>\n",
       "      <td>-2.760130</td>\n",
       "      <td>0.371946</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.171770e-13</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>153</th>\n",
       "      <td>34658</td>\n",
       "      <td>823080</td>\n",
       "      <td>continuous</td>\n",
       "      <td>triglyceride</td>\n",
       "      <td>123426</td>\n",
       "      <td>3</td>\n",
       "      <td>6:34185749_C/T,HLA_DQB1</td>\n",
       "      <td>AX-83121875</td>\n",
       "      <td>rs440454</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.388710</td>\n",
       "      <td>-1.881500</td>\n",
       "      <td>0.349157</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.110180e-08</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>154</th>\n",
       "      <td>69788</td>\n",
       "      <td>482825</td>\n",
       "      <td>continuous</td>\n",
       "      <td>tsh</td>\n",
       "      <td>286</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34539305_T/C</td>\n",
       "      <td>rs117748192</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>3.953750</td>\n",
       "      <td>0.618714</td>\n",
       "      <td>0.156488</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.766990e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>155</th>\n",
       "      <td>3634</td>\n",
       "      <td>25438</td>\n",
       "      <td>binary</td>\n",
       "      <td>tuberculosis</td>\n",
       "      <td>403/11344</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:28984512_T/C</td>\n",
       "      <td>rs9468464</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.366900</td>\n",
       "      <td>0.645987</td>\n",
       "      <td>0.147929</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.260240e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>156</th>\n",
       "      <td>11836</td>\n",
       "      <td>106524</td>\n",
       "      <td>binary</td>\n",
       "      <td>urinary_tract_infection</td>\n",
       "      <td>2368/77648</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:29904453_A/G</td>\n",
       "      <td>rs429762</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-3.979550</td>\n",
       "      <td>-0.449889</td>\n",
       "      <td>0.113050</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.904710e-05</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>157</th>\n",
       "      <td>68715</td>\n",
       "      <td>611118</td>\n",
       "      <td>continuous</td>\n",
       "      <td>waist_circumference</td>\n",
       "      <td>124772</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34185755_C/T</td>\n",
       "      <td>rs2797964</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.286300</td>\n",
       "      <td>0.225496</td>\n",
       "      <td>0.042657</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.250260e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>25152</td>\n",
       "      <td>224775</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31237965_G/C</td>\n",
       "      <td>rs17886232</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>15.854400</td>\n",
       "      <td>0.118848</td>\n",
       "      <td>0.007496</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.574790e-56</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, on_gene)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>159</th>\n",
       "      <td>42966</td>\n",
       "      <td>1021944</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_C</td>\n",
       "      <td>SNPS_DRB1_9776_32547744_intron5_A</td>\n",
       "      <td>SNPS_DRB1_9776_32547744_intron5_A</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>8.887500</td>\n",
       "      <td>0.070215</td>\n",
       "      <td>0.007900</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.368470e-19</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, on_gene)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>32222</td>\n",
       "      <td>1401796</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>3</td>\n",
       "      <td>HLA_C,HLA_DRB1</td>\n",
       "      <td>6:31428911_A/G</td>\n",
       "      <td>rs2596471</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.374980</td>\n",
       "      <td>-0.066856</td>\n",
       "      <td>0.010487</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.839100e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-B, moderate_LD)</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>161</th>\n",
       "      <td>68824</td>\n",
       "      <td>3060495</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>4</td>\n",
       "      <td>6:31428911_A/G,HLA_C,HLA_DRB1</td>\n",
       "      <td>6:34234974_A/G</td>\n",
       "      <td>rs117324087</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.650810</td>\n",
       "      <td>-0.062154</td>\n",
       "      <td>0.010999</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.601910e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>162</th>\n",
       "      <td>11583</td>\n",
       "      <td>532818</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>5</td>\n",
       "      <td>6:31428911_A/G,6:34234974_A/G,HLA_C,HLA_DRB1</td>\n",
       "      <td>6:29897017_C/A</td>\n",
       "      <td>rs434577</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.140090</td>\n",
       "      <td>-0.047704</td>\n",
       "      <td>0.009281</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.752090e-07</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>68741</td>\n",
       "      <td>611352</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>12.533800</td>\n",
       "      <td>0.553022</td>\n",
       "      <td>0.044123</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.129760e-36</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>47363</td>\n",
       "      <td>468200</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:32569297_A/G</td>\n",
       "      <td>rs9270797</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>8.083850</td>\n",
       "      <td>0.263069</td>\n",
       "      <td>0.032543</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.330940e-16</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165</th>\n",
       "      <td>3225</td>\n",
       "      <td>77400</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>3</td>\n",
       "      <td>6:32569297_A/G,6:34205465_G/GGAGCCC,HLA_DQA1</td>\n",
       "      <td>6:28861320_A/G</td>\n",
       "      <td>rs3135314</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.860230</td>\n",
       "      <td>0.228396</td>\n",
       "      <td>0.033293</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.906660e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(TRIM27, strong_LD)</td>\n",
       "      <td>TRIM27</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>20964</td>\n",
       "      <td>520175</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>4</td>\n",
       "      <td>6:28861320_A/G,6:32569297_A/G,6:34205465_G/GGA...</td>\n",
       "      <td>6:30990019_A/G</td>\n",
       "      <td>rs9380210</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.495360</td>\n",
       "      <td>0.189633</td>\n",
       "      <td>0.034508</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.906670e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(MUC22, on_gene)</td>\n",
       "      <td>MUC22</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>167</th>\n",
       "      <td>11868</td>\n",
       "      <td>308568</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>5</td>\n",
       "      <td>6:28861320_A/G,6:30990019_A/G,6:32569297_A/G,6...</td>\n",
       "      <td>6:29905224_A/T</td>\n",
       "      <td>rs28482016</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>4.790480</td>\n",
       "      <td>0.166417</td>\n",
       "      <td>0.034739</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.665760e-06</td>\n",
       "      <td>0</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>168 rows × 28 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unnamed: 0  Unnamed: 0.1 phenotype_type  \\\n",
       "0         20816        144613     continuous   \n",
       "1         68685        475104     continuous   \n",
       "2         21318        169288     continuous   \n",
       "3         68741        475496     continuous   \n",
       "4         21307        169200     continuous   \n",
       "5         29549        204407     continuous   \n",
       "6         56431        445472         binary   \n",
       "7         23270        208017     continuous   \n",
       "8         68761        679480     continuous   \n",
       "9         22997        251240     continuous   \n",
       "10        17705        210576     continuous   \n",
       "11        54209        481860         binary   \n",
       "12        12809        290996         binary   \n",
       "13        30669        272754     continuous   \n",
       "14        68693        678800     continuous   \n",
       "15        51373           419     continuous   \n",
       "16        29461           198         binary   \n",
       "17        36489        325134         binary   \n",
       "18        35667        317736     continuous   \n",
       "19        63263       1498800     continuous   \n",
       "20        68693       2307920     continuous   \n",
       "21        38500        343233         binary   \n",
       "22          671          4697         binary   \n",
       "23        37231        258076         binary   \n",
       "24        64351        508304         binary   \n",
       "25        11573         92584         binary   \n",
       "26        38146        340047         binary   \n",
       "27        51369           417     continuous   \n",
       "28         4332         95304     continuous   \n",
       "29        68875       1565426     continuous   \n",
       "..          ...           ...            ...   \n",
       "138       41739           794     continuous   \n",
       "139       68714        611109         binary   \n",
       "140       35422        350590         binary   \n",
       "141       34182        304371         binary   \n",
       "142       51056        454437         binary   \n",
       "143       32232        701118         binary   \n",
       "144       33689        766498         binary   \n",
       "145       55587       1316160         binary   \n",
       "146       30563        755000         binary   \n",
       "147       39995        356688     continuous   \n",
       "148       54447           494     continuous   \n",
       "149       61399       1394996     continuous   \n",
       "150       29520           167         binary   \n",
       "151       39841        355302     continuous   \n",
       "152       68714       1561723     continuous   \n",
       "153       34658        823080     continuous   \n",
       "154       69788        482825     continuous   \n",
       "155        3634         25438         binary   \n",
       "156       11836        106524         binary   \n",
       "157       68715        611118     continuous   \n",
       "158       25152        224775     continuous   \n",
       "159       42966       1021944     continuous   \n",
       "160       32222       1401796     continuous   \n",
       "161       68824       3060495     continuous   \n",
       "162       11583        532818     continuous   \n",
       "163       68741        611352     continuous   \n",
       "164       47363        468200     continuous   \n",
       "165        3225         77400     continuous   \n",
       "166       20964        520175     continuous   \n",
       "167       11868        308568     continuous   \n",
       "\n",
       "                            phenotype_name samples(case/control)  step  \\\n",
       "0                   FEV_over_FVC_predicted                  7440     1   \n",
       "1                            FEV_predicted                  7440     1   \n",
       "2                            FEV_predicted                  7440     2   \n",
       "3                            FVC_predicted                  7441     1   \n",
       "4                            FVC_predicted                  7441     2   \n",
       "5                            MVV_predicted                  7441     1   \n",
       "6                      acute_liver_disease             669/74104     1   \n",
       "7                                  albumin                125069     1   \n",
       "8                                  albumin                125069     2   \n",
       "9                                  albumin                125069     3   \n",
       "10                                 albumin                125069     4   \n",
       "11                        allergic_disease            9273/78950     1   \n",
       "12                        allergic_disease            9273/78950     2   \n",
       "13                                     alt                120788     1   \n",
       "14                                     alt                120788     2   \n",
       "15                                     alt                120788     3   \n",
       "16   angina_pectoris_myocardial_infarction            3077/77843     1   \n",
       "17                               arthritis           11348/73684     1   \n",
       "18                                     ast                121162     1   \n",
       "19                                     ast                121162     2   \n",
       "20                                     ast                121162     3   \n",
       "21                                  asthma            2115/78066     1   \n",
       "22            benign_prostatic_hyperplasia             168/11518     1   \n",
       "23                                big_baby            5057/71304     1   \n",
       "24                          bladder_cancer              47/74436     1   \n",
       "25                          blood_in_urine            1817/14938     1   \n",
       "26                          blood_in_urine            1817/14938     2   \n",
       "27                                     bmi                124539     1   \n",
       "28                                     bmi                124539     2   \n",
       "29                                     bmi                124539     3   \n",
       "..                                     ...                   ...   ...   \n",
       "138                systolic_blood_pressure                124467     2   \n",
       "139                            t2_diabetes            8662/78950     1   \n",
       "140                            t2_diabetes            8662/78950     2   \n",
       "141                         thyroid_cancer             681/78535     1   \n",
       "142                        thyroid_disease            5139/75944     1   \n",
       "143                        thyroid_disease            5139/75944     2   \n",
       "144                        thyroid_disease            5139/75944     3   \n",
       "145                        thyroid_disease            5139/75944     4   \n",
       "146                        thyroid_disease            5139/75944     5   \n",
       "147                        total_bilirubin                 77789     1   \n",
       "148                      total_cholesterol                125007     1   \n",
       "149                      total_cholesterol                125007     2   \n",
       "150             transient_ischemic_attacks              59/74437     1   \n",
       "151                           triglyceride                123426     1   \n",
       "152                           triglyceride                123426     2   \n",
       "153                           triglyceride                123426     3   \n",
       "154                                    tsh                   286     1   \n",
       "155                           tuberculosis             403/11344     1   \n",
       "156                urinary_tract_infection            2368/77648     1   \n",
       "157                    waist_circumference                124772     1   \n",
       "158                                    wbc                 86639     1   \n",
       "159                                    wbc                 86639     2   \n",
       "160                                    wbc                 86639     3   \n",
       "161                                    wbc                 86639     4   \n",
       "162                                    wbc                 86639     5   \n",
       "163                                 weight                124693     1   \n",
       "164                                 weight                124693     2   \n",
       "165                                 weight                124693     3   \n",
       "166                                 weight                124693     4   \n",
       "167                                 weight                124693     5   \n",
       "\n",
       "                                             condition  \\\n",
       "0                                                  NaN   \n",
       "1                                                  NaN   \n",
       "2                                       6:34172055_C/A   \n",
       "3                                                  NaN   \n",
       "4                                 6:34205465_G/GGAGCCC   \n",
       "5                                                  NaN   \n",
       "6                                                  NaN   \n",
       "7                                                  NaN   \n",
       "8                                          AX-41950637   \n",
       "9                           6:34215221_G/A,AX-41950637   \n",
       "10              6:34215221_G/A,AX-15354567,AX-41950637   \n",
       "11                                                 NaN   \n",
       "12                                            HLA_DQB1   \n",
       "13                                                 NaN   \n",
       "14                                      6:31351530_T/C   \n",
       "15                       6:31351530_T/C,6:34178764_A/C   \n",
       "16                                                 NaN   \n",
       "17                                                 NaN   \n",
       "18                                                 NaN   \n",
       "19                             6:32202630_G/T,HLA_DQB1   \n",
       "20     6:32202630_G/T,6:33076268_T/C,HLA_DPB1,HLA_DQB1   \n",
       "21                                                 NaN   \n",
       "22                                                 NaN   \n",
       "23                                                 NaN   \n",
       "24                                                 NaN   \n",
       "25                                                 NaN   \n",
       "26                                      6:29896680_A/G   \n",
       "27                                                 NaN   \n",
       "28                                            HLA_DQA1   \n",
       "29                             6:29190624_G/A,HLA_DQA1   \n",
       "..                                                 ...   \n",
       "138                                        AX-11365330   \n",
       "139                                                NaN   \n",
       "140                                     6:34185749_C/T   \n",
       "141                                                NaN   \n",
       "142                                                NaN   \n",
       "143                                           HLA_DQA1   \n",
       "144                            6:31430143_G/C,HLA_DQA1   \n",
       "145             6:31430143_G/C,6:31612576_A/T,HLA_DQA1   \n",
       "146  6:31430143_G/C,6:31612576_A/T,6:32641938_G/T,H...   \n",
       "147                                                NaN   \n",
       "148                                                NaN   \n",
       "149                                           HLA_DQB1   \n",
       "150                                                NaN   \n",
       "151                                                NaN   \n",
       "152                                           HLA_DQB1   \n",
       "153                            6:34185749_C/T,HLA_DQB1   \n",
       "154                                                NaN   \n",
       "155                                                NaN   \n",
       "156                                                NaN   \n",
       "157                                                NaN   \n",
       "158                                                NaN   \n",
       "159                                              HLA_C   \n",
       "160                                     HLA_C,HLA_DRB1   \n",
       "161                      6:31428911_A/G,HLA_C,HLA_DRB1   \n",
       "162       6:31428911_A/G,6:34234974_A/G,HLA_C,HLA_DRB1   \n",
       "163                                                NaN   \n",
       "164                               6:34205465_G/GGAGCCC   \n",
       "165       6:32569297_A/G,6:34205465_G/GGAGCCC,HLA_DQA1   \n",
       "166  6:28861320_A/G,6:32569297_A/G,6:34205465_G/GGA...   \n",
       "167  6:28861320_A/G,6:30990019_A/G,6:32569297_A/G,6...   \n",
       "\n",
       "                           marker_name                    marker_name_pub  \\\n",
       "0                       6:30985177_G/A                         rs12204947   \n",
       "1                       6:34172055_C/A                          rs1187115   \n",
       "2                       6:31018788_T/G                          rs2517531   \n",
       "3                 6:34205465_G/GGAGCCC               6:34205465_G/GGAGCCC   \n",
       "4                          AX-11396301                          rs2517534   \n",
       "5            SNPS_B_293_31324643_exon2                          rs1050517   \n",
       "6                       6:32658375_T/G                         rs28371257   \n",
       "7                          AX-41950637                          rs7762933   \n",
       "8                       6:34215221_G/A                           rs928482   \n",
       "9                          AX-15354567                          rs4713438   \n",
       "10                    6:30436315_C/CAT                   6:30436315_C/CAT   \n",
       "11                      6:32632237_C/T                          rs9274326   \n",
       "12                      6:29916650_G/A                         rs13215305   \n",
       "13                      6:31351530_T/C                          rs2905715   \n",
       "14                      6:34178764_A/C                         rs28673163   \n",
       "15           AA_DQA1_75_32609303_exon2                    HLA-DQA1 pos.75   \n",
       "16            AA_B_80_31324497_exon2_T                    HLA-B pos.80(T)   \n",
       "17                      6:32288790_A/G                        rs117475045   \n",
       "18                      6:32202630_G/T                        rs117654833   \n",
       "19                      6:33076268_T/C                           rs742870   \n",
       "20                      6:34178764_A/C                         rs28673163   \n",
       "21                      6:32408907_G/A                          rs3129879   \n",
       "22                      6:28177492_C/T                           rs988084   \n",
       "23                     6:32354723_CT/C                    6:32354723_CT/C   \n",
       "24                      6:33200591_T/C                        rs111327924   \n",
       "25                      6:29896680_A/G                          rs2517754   \n",
       "26                      6:32386619_T/C                          rs4335021   \n",
       "27         AA_DQA1_69_32609285_exon2_L                 HLA-DQA1 pos.69(L)   \n",
       "28                      6:29190624_G/A                         rs59230085   \n",
       "29                      6:34244245_C/A                          rs4713766   \n",
       "..                                 ...                                ...   \n",
       "138                     HLA_DRB1*04:03                     HLA-DRB1*04:03   \n",
       "139                     6:34185749_C/T                          rs2797963   \n",
       "140                     6:32181182_G/A                           rs206016   \n",
       "141                     6:31797422_G/C                         rs56280220   \n",
       "142                  6:32608334_GAAA/G                  6:32608334_GAAA/G   \n",
       "143                     6:31430143_G/C                          rs2255001   \n",
       "144                     6:31612576_A/T                         rs12055599   \n",
       "145                     6:32641938_G/T                         rs28891457   \n",
       "146                     6:31348403_G/T                          rs9266681   \n",
       "147                     6:32460867_T/C                         rs78325334   \n",
       "148        AA_DQB1_57_32632681_exon2_V                 HLA-DQB1 pos.57(V)   \n",
       "149                        AX-11505577                           rs443623   \n",
       "150             AA_B_63_31324548_exon2                       HLA-B pos.63   \n",
       "151                     6:32453284_C/G                        rs111524667   \n",
       "152                     6:34185749_C/T                          rs2797963   \n",
       "153                        AX-83121875                           rs440454   \n",
       "154                     6:34539305_T/C                        rs117748192   \n",
       "155                     6:28984512_T/C                          rs9468464   \n",
       "156                     6:29904453_A/G                           rs429762   \n",
       "157                     6:34185755_C/T                          rs2797964   \n",
       "158                     6:31237965_G/C                         rs17886232   \n",
       "159  SNPS_DRB1_9776_32547744_intron5_A  SNPS_DRB1_9776_32547744_intron5_A   \n",
       "160                     6:31428911_A/G                          rs2596471   \n",
       "161                     6:34234974_A/G                        rs117324087   \n",
       "162                     6:29897017_C/A                           rs434577   \n",
       "163               6:34205465_G/GGAGCCC               6:34205465_G/GGAGCCC   \n",
       "164                     6:32569297_A/G                          rs9270797   \n",
       "165                     6:28861320_A/G                          rs3135314   \n",
       "166                     6:30990019_A/G                          rs9380210   \n",
       "167                     6:29905224_A/T                         rs28482016   \n",
       "\n",
       "                  note  ...          Z      coef       std chisq  df  \\\n",
       "0    unphased bialleic  ...  -5.183770 -0.060131  0.011600   NaN NaN   \n",
       "1    unphased bialleic  ...   5.836440  0.026954  0.004618   NaN NaN   \n",
       "2    unphased bialleic  ...  -4.352160 -0.015100  0.003470   NaN NaN   \n",
       "3    unphased bialleic  ...   5.573560  0.036813  0.006605   NaN NaN   \n",
       "4    unphased bialleic  ...   4.630100  0.022921  0.004950   NaN NaN   \n",
       "5    unphased bialleic  ...  -3.290540 -0.415866  0.126382   NaN NaN   \n",
       "6    unphased bialleic  ...   4.001600  0.261618  0.065378   NaN NaN   \n",
       "7    unphased bialleic  ...  -8.556170 -0.008719  0.001019   NaN NaN   \n",
       "8    unphased bialleic  ...  -8.163130 -0.010955  0.001342   NaN NaN   \n",
       "9    unphased bialleic  ...  -5.830450 -0.008171  0.001402   NaN NaN   \n",
       "10   unphased bialleic  ...   5.283050  0.005532  0.001047   NaN NaN   \n",
       "11   unphased bialleic  ...   5.603280  0.088615  0.015814   NaN NaN   \n",
       "12   unphased bialleic  ...  -5.195720 -0.093244  0.017946   NaN NaN   \n",
       "13   unphased bialleic  ...   6.522960  0.326987  0.050129   NaN NaN   \n",
       "14   unphased bialleic  ...  -5.475840 -0.334937  0.061166   NaN NaN   \n",
       "15    phased biallelic  ...  -4.613860 -0.356955  0.077366   NaN NaN   \n",
       "16    phased biallelic  ...   4.733281  0.149197  0.031521   NaN NaN   \n",
       "17   unphased bialleic  ...   4.757840  0.182630  0.038384   NaN NaN   \n",
       "18   unphased bialleic  ...   7.602650  0.443845  0.058380   NaN NaN   \n",
       "19   unphased bialleic  ...  -5.816710 -0.191552  0.032931   NaN NaN   \n",
       "20   unphased bialleic  ...  -4.908920 -0.205566  0.041876   NaN NaN   \n",
       "21   unphased bialleic  ...  -4.645560 -0.157035  0.033803   NaN NaN   \n",
       "22   unphased bialleic  ...   3.758090  0.477103  0.126954   NaN NaN   \n",
       "23   unphased bialleic  ...   3.603740  0.082041  0.022765   NaN NaN   \n",
       "24   unphased bialleic  ...   3.903040  1.653330  0.423601   NaN NaN   \n",
       "25   unphased bialleic  ...  -5.536510 -0.201425  0.036381   NaN NaN   \n",
       "26   unphased bialleic  ...  -4.229910 -0.202580  0.047892   NaN NaN   \n",
       "27    phased biallelic  ...  -6.082880 -0.070694  0.011622   NaN NaN   \n",
       "28   unphased bialleic  ...  -6.111320 -0.074561  0.012200   NaN NaN   \n",
       "29   unphased bialleic  ...   5.068540  0.086797  0.017125   NaN NaN   \n",
       "..                 ...  ...        ...       ...       ...   ...  ..   \n",
       "138   phased biallelic  ...  -4.580334 -0.835254  0.182357   NaN NaN   \n",
       "139  unphased bialleic  ...  -6.849640 -0.164752  0.024053   NaN NaN   \n",
       "140  unphased bialleic  ...  -4.920040 -0.092008  0.018700   NaN NaN   \n",
       "141  unphased bialleic  ...   3.564350  0.433865  0.121723   NaN NaN   \n",
       "142  unphased bialleic  ...  -9.577430 -0.206240  0.021534   NaN NaN   \n",
       "143  unphased bialleic  ...   7.327290  0.243174  0.033188   NaN NaN   \n",
       "144  unphased bialleic  ...   6.640940  0.297620  0.044816   NaN NaN   \n",
       "145  unphased bialleic  ...   6.567150  0.238481  0.036315   NaN NaN   \n",
       "146  unphased bialleic  ...  -4.892880 -0.117203  0.023954   NaN NaN   \n",
       "147  unphased bialleic  ...   5.444800  0.009289  0.001706   NaN NaN   \n",
       "148   phased biallelic  ...  12.090447  2.167680  0.179289   NaN NaN   \n",
       "149  unphased bialleic  ...  -4.791750 -0.736927  0.153791   NaN NaN   \n",
       "150   phased biallelic  ...  -3.760997 -0.835879  0.222249   NaN NaN   \n",
       "151  unphased bialleic  ...  14.355300  6.680110  0.465340   NaN NaN   \n",
       "152  unphased bialleic  ...  -7.420780 -2.760130  0.371946   NaN NaN   \n",
       "153  unphased bialleic  ...  -5.388710 -1.881500  0.349157   NaN NaN   \n",
       "154  unphased bialleic  ...   3.953750  0.618714  0.156488   NaN NaN   \n",
       "155  unphased bialleic  ...   4.366900  0.645987  0.147929   NaN NaN   \n",
       "156  unphased bialleic  ...  -3.979550 -0.449889  0.113050   NaN NaN   \n",
       "157  unphased bialleic  ...   5.286300  0.225496  0.042657   NaN NaN   \n",
       "158  unphased bialleic  ...  15.854400  0.118848  0.007496   NaN NaN   \n",
       "159  unphased bialleic  ...   8.887500  0.070215  0.007900   NaN NaN   \n",
       "160  unphased bialleic  ...  -6.374980 -0.066856  0.010487   NaN NaN   \n",
       "161  unphased bialleic  ...  -5.650810 -0.062154  0.010999   NaN NaN   \n",
       "162  unphased bialleic  ...  -5.140090 -0.047704  0.009281   NaN NaN   \n",
       "163  unphased bialleic  ...  12.533800  0.553022  0.044123   NaN NaN   \n",
       "164  unphased bialleic  ...   8.083850  0.263069  0.032543   NaN NaN   \n",
       "165  unphased bialleic  ...   6.860230  0.228396  0.033293   NaN NaN   \n",
       "166  unphased bialleic  ...   5.495360  0.189633  0.034508   NaN NaN   \n",
       "167  unphased bialleic  ...   4.790480  0.166417  0.034739   NaN NaN   \n",
       "\n",
       "                P P_significant             gene_genehow      gene  \\\n",
       "0    2.231720e-07             0                      NaN       NaN   \n",
       "1    5.556790e-09             1       (HMGA1, strong_LD)     HMGA1   \n",
       "2    1.366070e-05             0                      NaN       NaN   \n",
       "3    2.583340e-08             1         (HMGA1, on_gene)     HMGA1   \n",
       "4    3.717070e-06             0                      NaN       NaN   \n",
       "5    1.004640e-03             0                      NaN       NaN   \n",
       "6    6.291630e-05             0                      NaN       NaN   \n",
       "7    1.179740e-17             1     (HLA-C, moderate_LD)     HLA-C   \n",
       "8    3.294620e-16             1        (C6orf1, on_gene)    C6orf1   \n",
       "9    5.541470e-09             1        (POU5F1, on_gene)    POU5F1   \n",
       "10   1.272620e-07             0                      NaN       NaN   \n",
       "11   2.103290e-08             1      (HLA-DQB1, on_gene)  HLA-DQB1   \n",
       "12   2.039270e-07             0                      NaN       NaN   \n",
       "13   6.920490e-11             1      (MICA, moderate_LD)      MICA   \n",
       "14   4.362960e-08             1       (HMGA1, strong_LD)     HMGA1   \n",
       "15   3.952585e-06             0                      NaN       NaN   \n",
       "16   2.209191e-06             0                      NaN       NaN   \n",
       "17   1.956730e-06             0                      NaN       NaN   \n",
       "18   2.921930e-14             1  (HLA-DRB1, moderate_LD)  HLA-DRB1   \n",
       "19   6.016610e-09             1  (HLA-DPB1, moderate_LD)  HLA-DPB1   \n",
       "20   9.169740e-07             0                      NaN       NaN   \n",
       "21   3.391630e-06             0                      NaN       NaN   \n",
       "22   1.712120e-04             0                      NaN       NaN   \n",
       "23   3.136670e-04             0                      NaN       NaN   \n",
       "24   9.499280e-05             0                      NaN       NaN   \n",
       "25   3.085650e-08             1     (HLA-A, moderate_LD)     HLA-A   \n",
       "26   2.337840e-05             0                      NaN       NaN   \n",
       "27   1.180429e-09             1      (HLA-DQA1, on_gene)  HLA-DQA1   \n",
       "28   9.910210e-10             1      (TRIM27, strong_LD)    TRIM27   \n",
       "29   4.014480e-07             0                      NaN       NaN   \n",
       "..            ...           ...                      ...       ...   \n",
       "138  4.642346e-06             0                      NaN       NaN   \n",
       "139  7.403820e-12             1       (HMGA1, strong_LD)     HMGA1   \n",
       "140  8.652720e-07             0                      NaN       NaN   \n",
       "141  3.647530e-04             0                      NaN       NaN   \n",
       "142  9.949160e-22             1      (HLA-DQA1, on_gene)  HLA-DQA1   \n",
       "143  2.348530e-13             1          (MICB, nearest)      MICB   \n",
       "144  3.116790e-11             1          (BAG6, on_gene)      BAG6   \n",
       "145  5.128710e-11             1  (HLA-DQA1, moderate_LD)  HLA-DQA1   \n",
       "146  9.937060e-07             0                      NaN       NaN   \n",
       "147  5.202030e-08             0                      NaN       NaN   \n",
       "148  1.186392e-33             1      (HLA-DQB1, on_gene)  HLA-DQB1   \n",
       "149  1.655190e-06             0                      NaN       NaN   \n",
       "150  1.692373e-04             0                      NaN       NaN   \n",
       "151  1.075790e-46             1  (HLA-DQA1, moderate_LD)  HLA-DQA1   \n",
       "152  1.171770e-13             1       (HMGA1, strong_LD)     HMGA1   \n",
       "153  7.110180e-08             0                      NaN       NaN   \n",
       "154  9.766990e-05             0                      NaN       NaN   \n",
       "155  1.260240e-05             0                      NaN       NaN   \n",
       "156  6.904710e-05             0                      NaN       NaN   \n",
       "157  1.250260e-07             0                      NaN       NaN   \n",
       "158  1.574790e-56             1         (HLA-C, on_gene)     HLA-C   \n",
       "159  6.368470e-19             1      (HLA-DRB1, on_gene)  HLA-DRB1   \n",
       "160  1.839100e-10             1     (HLA-B, moderate_LD)     HLA-B   \n",
       "161  1.601910e-08             1       (HMGA1, strong_LD)     HMGA1   \n",
       "162  2.752090e-07             0                      NaN       NaN   \n",
       "163  5.129760e-36             1         (HMGA1, on_gene)     HMGA1   \n",
       "164  6.330940e-16             1  (HLA-DQA1, moderate_LD)  HLA-DQA1   \n",
       "165  6.906660e-12             1      (TRIM27, strong_LD)    TRIM27   \n",
       "166  3.906670e-08             1         (MUC22, on_gene)     MUC22   \n",
       "167  1.665760e-06             0                      NaN       NaN   \n",
       "\n",
       "         genehow  \n",
       "0            NaN  \n",
       "1      strong_LD  \n",
       "2            NaN  \n",
       "3        on_gene  \n",
       "4            NaN  \n",
       "5            NaN  \n",
       "6            NaN  \n",
       "7    moderate_LD  \n",
       "8        on_gene  \n",
       "9        on_gene  \n",
       "10           NaN  \n",
       "11       on_gene  \n",
       "12           NaN  \n",
       "13   moderate_LD  \n",
       "14     strong_LD  \n",
       "15           NaN  \n",
       "16           NaN  \n",
       "17           NaN  \n",
       "18   moderate_LD  \n",
       "19   moderate_LD  \n",
       "20           NaN  \n",
       "21           NaN  \n",
       "22           NaN  \n",
       "23           NaN  \n",
       "24           NaN  \n",
       "25   moderate_LD  \n",
       "26           NaN  \n",
       "27       on_gene  \n",
       "28     strong_LD  \n",
       "29           NaN  \n",
       "..           ...  \n",
       "138          NaN  \n",
       "139    strong_LD  \n",
       "140          NaN  \n",
       "141          NaN  \n",
       "142      on_gene  \n",
       "143      nearest  \n",
       "144      on_gene  \n",
       "145  moderate_LD  \n",
       "146          NaN  \n",
       "147          NaN  \n",
       "148      on_gene  \n",
       "149          NaN  \n",
       "150          NaN  \n",
       "151  moderate_LD  \n",
       "152    strong_LD  \n",
       "153          NaN  \n",
       "154          NaN  \n",
       "155          NaN  \n",
       "156          NaN  \n",
       "157          NaN  \n",
       "158      on_gene  \n",
       "159      on_gene  \n",
       "160  moderate_LD  \n",
       "161    strong_LD  \n",
       "162          NaN  \n",
       "163      on_gene  \n",
       "164  moderate_LD  \n",
       "165    strong_LD  \n",
       "166      on_gene  \n",
       "167          NaN  \n",
       "\n",
       "[168 rows x 28 columns]"
      ]
     },
     "execution_count": 35,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_all"
   ]
  },
  {
   "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>Unnamed: 0</th>\n",
       "      <th>Unnamed: 0.1</th>\n",
       "      <th>phenotype_type</th>\n",
       "      <th>phenotype_name</th>\n",
       "      <th>samples(case/control)</th>\n",
       "      <th>step</th>\n",
       "      <th>condition</th>\n",
       "      <th>marker_name</th>\n",
       "      <th>marker_name_pub</th>\n",
       "      <th>note</th>\n",
       "      <th>...</th>\n",
       "      <th>Z</th>\n",
       "      <th>coef</th>\n",
       "      <th>std</th>\n",
       "      <th>chisq</th>\n",
       "      <th>df</th>\n",
       "      <th>P</th>\n",
       "      <th>P_significant</th>\n",
       "      <th>gene_genehow</th>\n",
       "      <th>gene</th>\n",
       "      <th>genehow</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>68677</td>\n",
       "      <td>475104</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FEV_predicted</td>\n",
       "      <td>7440</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34172055_C/A</td>\n",
       "      <td>rs1187115</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.836440</td>\n",
       "      <td>0.026954</td>\n",
       "      <td>0.004618</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.556790e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>68733</td>\n",
       "      <td>475496</td>\n",
       "      <td>continuous</td>\n",
       "      <td>FVC_predicted</td>\n",
       "      <td>7441</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.573560</td>\n",
       "      <td>0.036813</td>\n",
       "      <td>0.006605</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.583340e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>7</th>\n",
       "      <td>23267</td>\n",
       "      <td>208017</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-41950637</td>\n",
       "      <td>rs7762933</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.556170</td>\n",
       "      <td>-0.008719</td>\n",
       "      <td>0.001019</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.179740e-17</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, moderate_LD)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>8</th>\n",
       "      <td>68753</td>\n",
       "      <td>679480</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>2</td>\n",
       "      <td>AX-41950637</td>\n",
       "      <td>6:34215221_G/A</td>\n",
       "      <td>rs928482</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.163130</td>\n",
       "      <td>-0.010955</td>\n",
       "      <td>0.001342</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.294620e-16</td>\n",
       "      <td>1</td>\n",
       "      <td>(C6orf1, on_gene)</td>\n",
       "      <td>C6orf1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>9</th>\n",
       "      <td>22994</td>\n",
       "      <td>251240</td>\n",
       "      <td>continuous</td>\n",
       "      <td>albumin</td>\n",
       "      <td>125069</td>\n",
       "      <td>3</td>\n",
       "      <td>6:34215221_G/A,AX-41950637</td>\n",
       "      <td>AX-15354567</td>\n",
       "      <td>rs4713438</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.830450</td>\n",
       "      <td>-0.008171</td>\n",
       "      <td>0.001402</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.541470e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(POU5F1, on_gene)</td>\n",
       "      <td>POU5F1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>11</th>\n",
       "      <td>54203</td>\n",
       "      <td>481860</td>\n",
       "      <td>binary</td>\n",
       "      <td>allergic_disease</td>\n",
       "      <td>9273/78950</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32632237_C/T</td>\n",
       "      <td>rs9274326</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.603280</td>\n",
       "      <td>0.088615</td>\n",
       "      <td>0.015814</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.103290e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQB1, on_gene)</td>\n",
       "      <td>HLA-DQB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>13</th>\n",
       "      <td>30666</td>\n",
       "      <td>272754</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31351530_T/C</td>\n",
       "      <td>rs2905715</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.522960</td>\n",
       "      <td>0.326987</td>\n",
       "      <td>0.050129</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.920490e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, moderate_LD)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>14</th>\n",
       "      <td>68685</td>\n",
       "      <td>678800</td>\n",
       "      <td>continuous</td>\n",
       "      <td>alt</td>\n",
       "      <td>120788</td>\n",
       "      <td>2</td>\n",
       "      <td>6:31351530_T/C</td>\n",
       "      <td>6:34178764_A/C</td>\n",
       "      <td>rs28673163</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.475840</td>\n",
       "      <td>-0.334937</td>\n",
       "      <td>0.061166</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.362960e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>18</th>\n",
       "      <td>35664</td>\n",
       "      <td>317736</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32202630_G/T</td>\n",
       "      <td>rs117654833</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.602650</td>\n",
       "      <td>0.443845</td>\n",
       "      <td>0.058380</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.921930e-14</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, moderate_LD)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>19</th>\n",
       "      <td>63255</td>\n",
       "      <td>1498800</td>\n",
       "      <td>continuous</td>\n",
       "      <td>ast</td>\n",
       "      <td>121162</td>\n",
       "      <td>2</td>\n",
       "      <td>6:32202630_G/T,HLA_DQB1</td>\n",
       "      <td>6:33076268_T/C</td>\n",
       "      <td>rs742870</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.816710</td>\n",
       "      <td>-0.191552</td>\n",
       "      <td>0.032931</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.016610e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DPB1, moderate_LD)</td>\n",
       "      <td>HLA-DPB1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>25</th>\n",
       "      <td>11573</td>\n",
       "      <td>92584</td>\n",
       "      <td>binary</td>\n",
       "      <td>blood_in_urine</td>\n",
       "      <td>1817/14938</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:29896680_A/G</td>\n",
       "      <td>rs2517754</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.536510</td>\n",
       "      <td>-0.201425</td>\n",
       "      <td>0.036381</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.085650e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-A, moderate_LD)</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>27</th>\n",
       "      <td>51364</td>\n",
       "      <td>417</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bmi</td>\n",
       "      <td>124539</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_DQA1_69_32609285_exon2_L</td>\n",
       "      <td>HLA-DQA1 position 69</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.082880</td>\n",
       "      <td>-0.070694</td>\n",
       "      <td>0.011622</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.180429e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, on_gene)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>28</th>\n",
       "      <td>4332</td>\n",
       "      <td>95304</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bmi</td>\n",
       "      <td>124539</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQA1</td>\n",
       "      <td>6:29190624_G/A</td>\n",
       "      <td>rs59230085</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.111320</td>\n",
       "      <td>-0.074561</td>\n",
       "      <td>0.012200</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.910210e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(TRIM27, strong_LD)</td>\n",
       "      <td>TRIM27</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>33</th>\n",
       "      <td>18963</td>\n",
       "      <td>169281</td>\n",
       "      <td>continuous</td>\n",
       "      <td>bun</td>\n",
       "      <td>124563</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:30737591_G/C</td>\n",
       "      <td>rs3095337</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.933740</td>\n",
       "      <td>-0.186481</td>\n",
       "      <td>0.026895</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.118390e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-E, moderate_LD)</td>\n",
       "      <td>HLA-E</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>46</th>\n",
       "      <td>31181</td>\n",
       "      <td>277389</td>\n",
       "      <td>continuous</td>\n",
       "      <td>creatinine</td>\n",
       "      <td>125191</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31371397_C/T</td>\n",
       "      <td>rs2301748</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>11.720900</td>\n",
       "      <td>0.012433</td>\n",
       "      <td>0.001061</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.035490e-31</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, on_gene)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>47</th>\n",
       "      <td>25121</td>\n",
       "      <td>598824</td>\n",
       "      <td>continuous</td>\n",
       "      <td>creatinine</td>\n",
       "      <td>125191</td>\n",
       "      <td>2</td>\n",
       "      <td>6:31371397_C/T,HLA_DQB1</td>\n",
       "      <td>6:31237858_T/C</td>\n",
       "      <td>rs34794906</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.898860</td>\n",
       "      <td>-0.003895</td>\n",
       "      <td>0.000565</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.267020e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, on_gene)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>49</th>\n",
       "      <td>35371</td>\n",
       "      <td>315099</td>\n",
       "      <td>continuous</td>\n",
       "      <td>diastolic_blood_pressure</td>\n",
       "      <td>124766</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-11365330</td>\n",
       "      <td>rs2071277</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.653510</td>\n",
       "      <td>0.260993</td>\n",
       "      <td>0.039226</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.873610e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(NOTCH4, on_gene)</td>\n",
       "      <td>NOTCH4</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>58</th>\n",
       "      <td>31181</td>\n",
       "      <td>215747</td>\n",
       "      <td>continuous</td>\n",
       "      <td>grip_strength</td>\n",
       "      <td>59747</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31371397_C/T</td>\n",
       "      <td>rs2301748</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.466610</td>\n",
       "      <td>0.401340</td>\n",
       "      <td>0.073417</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>4.605620e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, on_gene)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>61</th>\n",
       "      <td>30860</td>\n",
       "      <td>274500</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hba1c</td>\n",
       "      <td>56650</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31358559_C/T</td>\n",
       "      <td>rs2923009</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.212440</td>\n",
       "      <td>-0.020605</td>\n",
       "      <td>0.003317</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.253110e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICA, moderate_LD)</td>\n",
       "      <td>MICA</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>63</th>\n",
       "      <td>38054</td>\n",
       "      <td>339246</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hdl_cholesterol</td>\n",
       "      <td>124772</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32380909_A/C</td>\n",
       "      <td>rs9380294</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.694130</td>\n",
       "      <td>0.502552</td>\n",
       "      <td>0.065316</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.434950e-14</td>\n",
       "      <td>1</td>\n",
       "      <td>(BTNL2, nearest)</td>\n",
       "      <td>BTNL2</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>64</th>\n",
       "      <td>37991</td>\n",
       "      <td>376310</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hdl_cholesterol</td>\n",
       "      <td>124772</td>\n",
       "      <td>2</td>\n",
       "      <td>6:32380909_A/C</td>\n",
       "      <td>6:32377408_T/C</td>\n",
       "      <td>rs9268505</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.409360</td>\n",
       "      <td>-0.328365</td>\n",
       "      <td>0.051232</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.466540e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(BTNL2, nearest)</td>\n",
       "      <td>BTNL2</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>65</th>\n",
       "      <td>70668</td>\n",
       "      <td>768493</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hdl_cholesterol</td>\n",
       "      <td>124772</td>\n",
       "      <td>3</td>\n",
       "      <td>6:32377408_T/C,6:32380909_A/C</td>\n",
       "      <td>6:34810172_T/C</td>\n",
       "      <td>rs13220394</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.174010</td>\n",
       "      <td>-0.294747</td>\n",
       "      <td>0.047740</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.678210e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(UHRF1BP1, on_gene)</td>\n",
       "      <td>UHRF1BP1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>68</th>\n",
       "      <td>68738</td>\n",
       "      <td>611397</td>\n",
       "      <td>continuous</td>\n",
       "      <td>height</td>\n",
       "      <td>125264</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34207474_T/TAA</td>\n",
       "      <td>6:34207474_T/TAA</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>18.513100</td>\n",
       "      <td>0.524680</td>\n",
       "      <td>0.028341</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.047770e-76</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>69</th>\n",
       "      <td>5776</td>\n",
       "      <td>57760</td>\n",
       "      <td>continuous</td>\n",
       "      <td>height</td>\n",
       "      <td>125264</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34207474_T/TAA</td>\n",
       "      <td>6:29497002_G/A</td>\n",
       "      <td>rs9501677</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>13.237700</td>\n",
       "      <td>0.345431</td>\n",
       "      <td>0.026094</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.654650e-40</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-F, moderate_LD)</td>\n",
       "      <td>HLA-F</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>70</th>\n",
       "      <td>22772</td>\n",
       "      <td>248798</td>\n",
       "      <td>continuous</td>\n",
       "      <td>height</td>\n",
       "      <td>125264</td>\n",
       "      <td>3</td>\n",
       "      <td>6:29497002_G/A,6:34207474_T/TAA</td>\n",
       "      <td>6:31128329_G/A</td>\n",
       "      <td>rs9263789</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-8.504020</td>\n",
       "      <td>-0.359084</td>\n",
       "      <td>0.042225</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.851080e-17</td>\n",
       "      <td>1</td>\n",
       "      <td>(TCF19, on_gene)</td>\n",
       "      <td>TCF19</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>71</th>\n",
       "      <td>71028</td>\n",
       "      <td>1896021</td>\n",
       "      <td>continuous</td>\n",
       "      <td>height</td>\n",
       "      <td>125264</td>\n",
       "      <td>4</td>\n",
       "      <td>6:29497002_G/A,6:31128329_G/A,6:34207474_T/TAA...</td>\n",
       "      <td>6:34967349_G/A</td>\n",
       "      <td>rs12527060</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.022430</td>\n",
       "      <td>0.270738</td>\n",
       "      <td>0.038553</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.191480e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(TAF11, nearest)</td>\n",
       "      <td>TAF11</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>72</th>\n",
       "      <td>4149</td>\n",
       "      <td>116172</td>\n",
       "      <td>continuous</td>\n",
       "      <td>height</td>\n",
       "      <td>125264</td>\n",
       "      <td>5</td>\n",
       "      <td>6:29497002_G/A,6:31128329_G/A,6:34207474_T/TAA...</td>\n",
       "      <td>AX-11435484</td>\n",
       "      <td>rs3130743</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.519490</td>\n",
       "      <td>0.147346</td>\n",
       "      <td>0.022601</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.081290e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(OR2J2, on_gene)</td>\n",
       "      <td>OR2J2</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>74</th>\n",
       "      <td>35289</td>\n",
       "      <td>314361</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hematocrit</td>\n",
       "      <td>87158</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32149801_C/T</td>\n",
       "      <td>rs9391855</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-7.143070</td>\n",
       "      <td>-0.133691</td>\n",
       "      <td>0.018716</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.197860e-13</td>\n",
       "      <td>1</td>\n",
       "      <td>(RNF5,AGER, on_gene)</td>\n",
       "      <td>RNF5,AGER</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>75</th>\n",
       "      <td>29374</td>\n",
       "      <td>291010</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hematocrit</td>\n",
       "      <td>87158</td>\n",
       "      <td>2</td>\n",
       "      <td>6:32149801_C/T</td>\n",
       "      <td>SNPS_B_836_31324100_exon3</td>\n",
       "      <td>rs1050654</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.102360</td>\n",
       "      <td>0.103592</td>\n",
       "      <td>0.016976</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.049540e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-B, on_gene)</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>76</th>\n",
       "      <td>7442</td>\n",
       "      <td>267912</td>\n",
       "      <td>continuous</td>\n",
       "      <td>hematocrit</td>\n",
       "      <td>87158</td>\n",
       "      <td>3</td>\n",
       "      <td>6:32149801_C/T,HLA_B</td>\n",
       "      <td>6:29698050_A/G</td>\n",
       "      <td>rs2743925</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.732800</td>\n",
       "      <td>-0.153786</td>\n",
       "      <td>0.026826</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.911020e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-F, on_gene)</td>\n",
       "      <td>HLA-F</td>\n",
       "      <td>on_gene</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>110</th>\n",
       "      <td>65631</td>\n",
       "      <td>583434</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-41961031</td>\n",
       "      <td>rs9296095</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>17.641200</td>\n",
       "      <td>5.566170</td>\n",
       "      <td>0.315522</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.579220e-69</td>\n",
       "      <td>1</td>\n",
       "      <td>(BAK1, on_gene)</td>\n",
       "      <td>BAK1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>111</th>\n",
       "      <td>65627</td>\n",
       "      <td>648220</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>2</td>\n",
       "      <td>AX-41961031</td>\n",
       "      <td>6:33541507_A/G</td>\n",
       "      <td>rs511515</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-12.411800</td>\n",
       "      <td>-3.938910</td>\n",
       "      <td>0.317352</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.417650e-35</td>\n",
       "      <td>1</td>\n",
       "      <td>(BAK1, on_gene)</td>\n",
       "      <td>BAK1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>112</th>\n",
       "      <td>24319</td>\n",
       "      <td>265815</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>3</td>\n",
       "      <td>6:33541507_A/G,AX-41961031</td>\n",
       "      <td>6:31217815_A/C</td>\n",
       "      <td>rs2894189</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>12.416900</td>\n",
       "      <td>3.262640</td>\n",
       "      <td>0.262759</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.270210e-35</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, nearest)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>113</th>\n",
       "      <td>45013</td>\n",
       "      <td>660</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>4</td>\n",
       "      <td>6:31217815_A/C,6:33541507_A/G,AX-41961031</td>\n",
       "      <td>AA_DRB1_71_32551949_exon2_E</td>\n",
       "      <td>HLA-DRB1 position 71</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>8.551858</td>\n",
       "      <td>3.711096</td>\n",
       "      <td>0.433952</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.211227e-17</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, on_gene)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>114</th>\n",
       "      <td>68707</td>\n",
       "      <td>2172864</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>5</td>\n",
       "      <td>6:31217815_A/C,6:33541507_A/G,AX-41961031,HLA_...</td>\n",
       "      <td>6:34185755_C/T</td>\n",
       "      <td>rs2797964</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.662370</td>\n",
       "      <td>-2.368900</td>\n",
       "      <td>0.355564</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.710710e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>115</th>\n",
       "      <td>12341</td>\n",
       "      <td>4</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>6</td>\n",
       "      <td>6:31217815_A/C,6:33541507_A/G,6:34185755_C/T,A...</td>\n",
       "      <td>AA_A_114_29911114_exon3</td>\n",
       "      <td>HLA-A position 114</td>\n",
       "      <td>phased multiallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>44.475274</td>\n",
       "      <td>3.0</td>\n",
       "      <td>1.196110e-09</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-A, on_gene)</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>116</th>\n",
       "      <td>29754</td>\n",
       "      <td>1322730</td>\n",
       "      <td>continuous</td>\n",
       "      <td>platelet</td>\n",
       "      <td>86087</td>\n",
       "      <td>7</td>\n",
       "      <td>6:31217815_A/C,6:33541507_A/G,6:34185755_C/T,A...</td>\n",
       "      <td>AX-11396692</td>\n",
       "      <td>rs2523589</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.034830</td>\n",
       "      <td>2.262390</td>\n",
       "      <td>0.321599</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.009910e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-B, moderate_LD)</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>119</th>\n",
       "      <td>36851</td>\n",
       "      <td>291928</td>\n",
       "      <td>continuous</td>\n",
       "      <td>protein_in_blood</td>\n",
       "      <td>24307</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32324081_A/AT</td>\n",
       "      <td>6:32324081_A/AT</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.567080</td>\n",
       "      <td>0.030129</td>\n",
       "      <td>0.005412</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.617760e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(C6orf10, on_gene)</td>\n",
       "      <td>C6orf10</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>122</th>\n",
       "      <td>6018</td>\n",
       "      <td>54162</td>\n",
       "      <td>continuous</td>\n",
       "      <td>pulse</td>\n",
       "      <td>121124</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-11397307</td>\n",
       "      <td>rs2534791</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.536170</td>\n",
       "      <td>0.254352</td>\n",
       "      <td>0.045944</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.098060e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(UBD, strong_LD)</td>\n",
       "      <td>UBD</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>125</th>\n",
       "      <td>29492</td>\n",
       "      <td>179</td>\n",
       "      <td>continuous</td>\n",
       "      <td>rbc</td>\n",
       "      <td>87356</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_B_69_31324530_exon2</td>\n",
       "      <td>HLA-B position 69</td>\n",
       "      <td>phased multiallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>100.521732</td>\n",
       "      <td>2.0</td>\n",
       "      <td>1.485878e-22</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-B, on_gene)</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>126</th>\n",
       "      <td>68735</td>\n",
       "      <td>2377550</td>\n",
       "      <td>continuous</td>\n",
       "      <td>rbc</td>\n",
       "      <td>87356</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_B</td>\n",
       "      <td>6:34205822_T/C</td>\n",
       "      <td>rs118012224</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.530060</td>\n",
       "      <td>-0.015963</td>\n",
       "      <td>0.002445</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.610360e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>127</th>\n",
       "      <td>35164</td>\n",
       "      <td>1252944</td>\n",
       "      <td>continuous</td>\n",
       "      <td>rbc</td>\n",
       "      <td>87356</td>\n",
       "      <td>3</td>\n",
       "      <td>6:34205822_T/C,HLA_B</td>\n",
       "      <td>6:32109294_A/G</td>\n",
       "      <td>rs9348878</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.658800</td>\n",
       "      <td>-0.014044</td>\n",
       "      <td>0.002482</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.529120e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(ATF6B, strong_LD)</td>\n",
       "      <td>ATF6B</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>128</th>\n",
       "      <td>13551</td>\n",
       "      <td>495689</td>\n",
       "      <td>continuous</td>\n",
       "      <td>rbc</td>\n",
       "      <td>87356</td>\n",
       "      <td>4</td>\n",
       "      <td>6:32109294_A/G,6:34205822_T/C,HLA_B</td>\n",
       "      <td>6:29938478_A/G</td>\n",
       "      <td>rs7754245</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.545740</td>\n",
       "      <td>-0.012154</td>\n",
       "      <td>0.002192</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.935550e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-A, moderate_LD)</td>\n",
       "      <td>HLA-A</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>137</th>\n",
       "      <td>35371</td>\n",
       "      <td>315099</td>\n",
       "      <td>continuous</td>\n",
       "      <td>systolic_blood_pressure</td>\n",
       "      <td>124467</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AX-11365330</td>\n",
       "      <td>rs2071277</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.327180</td>\n",
       "      <td>0.370073</td>\n",
       "      <td>0.058489</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.505260e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(NOTCH4, on_gene)</td>\n",
       "      <td>NOTCH4</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>139</th>\n",
       "      <td>68706</td>\n",
       "      <td>611109</td>\n",
       "      <td>binary</td>\n",
       "      <td>t2_diabetes</td>\n",
       "      <td>8662/78950</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34185749_C/T</td>\n",
       "      <td>rs2797963</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.849640</td>\n",
       "      <td>-0.164752</td>\n",
       "      <td>0.024053</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>7.403820e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>142</th>\n",
       "      <td>51051</td>\n",
       "      <td>454437</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32608334_GAAA/G</td>\n",
       "      <td>6:32608334_GAAA/G</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-9.577430</td>\n",
       "      <td>-0.206240</td>\n",
       "      <td>0.021534</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>9.949160e-22</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, on_gene)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>143</th>\n",
       "      <td>32229</td>\n",
       "      <td>701118</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQA1</td>\n",
       "      <td>6:31430143_G/C</td>\n",
       "      <td>rs2255001</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>7.327290</td>\n",
       "      <td>0.243174</td>\n",
       "      <td>0.033188</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>2.348530e-13</td>\n",
       "      <td>1</td>\n",
       "      <td>(MICB, nearest)</td>\n",
       "      <td>MICB</td>\n",
       "      <td>nearest</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>144</th>\n",
       "      <td>33685</td>\n",
       "      <td>766498</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>3</td>\n",
       "      <td>6:31430143_G/C,HLA_DQA1</td>\n",
       "      <td>6:31612576_A/T</td>\n",
       "      <td>rs12055599</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.640940</td>\n",
       "      <td>0.297620</td>\n",
       "      <td>0.044816</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.116790e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(BAG6, on_gene)</td>\n",
       "      <td>BAG6</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>145</th>\n",
       "      <td>55581</td>\n",
       "      <td>1316160</td>\n",
       "      <td>binary</td>\n",
       "      <td>thyroid_disease</td>\n",
       "      <td>5139/75944</td>\n",
       "      <td>4</td>\n",
       "      <td>6:31430143_G/C,6:31612576_A/T,HLA_DQA1</td>\n",
       "      <td>6:32641938_G/T</td>\n",
       "      <td>rs28891457</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.567150</td>\n",
       "      <td>0.238481</td>\n",
       "      <td>0.036315</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.128710e-11</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>148</th>\n",
       "      <td>54439</td>\n",
       "      <td>494</td>\n",
       "      <td>continuous</td>\n",
       "      <td>total_cholesterol</td>\n",
       "      <td>125007</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>AA_DQB1_57_32632681_exon2_V</td>\n",
       "      <td>HLA-DQB1 position 57</td>\n",
       "      <td>phased biallelic</td>\n",
       "      <td>...</td>\n",
       "      <td>12.090447</td>\n",
       "      <td>2.167680</td>\n",
       "      <td>0.179289</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.186392e-33</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQB1, on_gene)</td>\n",
       "      <td>HLA-DQB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>151</th>\n",
       "      <td>39838</td>\n",
       "      <td>355302</td>\n",
       "      <td>continuous</td>\n",
       "      <td>triglyceride</td>\n",
       "      <td>123426</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:32453284_C/G</td>\n",
       "      <td>rs111524667</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>14.355300</td>\n",
       "      <td>6.680110</td>\n",
       "      <td>0.465340</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.075790e-46</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>152</th>\n",
       "      <td>68706</td>\n",
       "      <td>1561723</td>\n",
       "      <td>continuous</td>\n",
       "      <td>triglyceride</td>\n",
       "      <td>123426</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_DQB1</td>\n",
       "      <td>6:34185749_C/T</td>\n",
       "      <td>rs2797963</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-7.420780</td>\n",
       "      <td>-2.760130</td>\n",
       "      <td>0.371946</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.171770e-13</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>158</th>\n",
       "      <td>25149</td>\n",
       "      <td>224775</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:31237965_G/C</td>\n",
       "      <td>rs17886232</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>15.854400</td>\n",
       "      <td>0.118848</td>\n",
       "      <td>0.007496</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.574790e-56</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-C, on_gene)</td>\n",
       "      <td>HLA-C</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>159</th>\n",
       "      <td>42704</td>\n",
       "      <td>1015704</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>2</td>\n",
       "      <td>HLA_C</td>\n",
       "      <td>SNPS_DRB1_9849_32547671_intron5_C</td>\n",
       "      <td>SNPS_DRB1_9849_32547671_intron5_C</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>8.887500</td>\n",
       "      <td>0.070215</td>\n",
       "      <td>0.007900</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.368470e-19</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DRB1, on_gene)</td>\n",
       "      <td>HLA-DRB1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>160</th>\n",
       "      <td>32219</td>\n",
       "      <td>1401796</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>3</td>\n",
       "      <td>HLA_C,HLA_DRB1</td>\n",
       "      <td>6:31428911_A/G</td>\n",
       "      <td>rs2596471</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-6.374980</td>\n",
       "      <td>-0.066856</td>\n",
       "      <td>0.010487</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.839100e-10</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-B, moderate_LD)</td>\n",
       "      <td>HLA-B</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>161</th>\n",
       "      <td>68816</td>\n",
       "      <td>3060495</td>\n",
       "      <td>continuous</td>\n",
       "      <td>wbc</td>\n",
       "      <td>86639</td>\n",
       "      <td>4</td>\n",
       "      <td>6:31428911_A/G,HLA_C,HLA_DRB1</td>\n",
       "      <td>6:34234974_A/G</td>\n",
       "      <td>rs117324087</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>-5.650810</td>\n",
       "      <td>-0.062154</td>\n",
       "      <td>0.010999</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>1.601910e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, strong_LD)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>163</th>\n",
       "      <td>68733</td>\n",
       "      <td>611352</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>1</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>12.533800</td>\n",
       "      <td>0.553022</td>\n",
       "      <td>0.044123</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>5.129760e-36</td>\n",
       "      <td>1</td>\n",
       "      <td>(HMGA1, on_gene)</td>\n",
       "      <td>HMGA1</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>164</th>\n",
       "      <td>47359</td>\n",
       "      <td>468200</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>2</td>\n",
       "      <td>6:34205465_G/GGAGCCC</td>\n",
       "      <td>6:32569297_A/G</td>\n",
       "      <td>rs9270797</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>8.083850</td>\n",
       "      <td>0.263069</td>\n",
       "      <td>0.032543</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.330940e-16</td>\n",
       "      <td>1</td>\n",
       "      <td>(HLA-DQA1, moderate_LD)</td>\n",
       "      <td>HLA-DQA1</td>\n",
       "      <td>moderate_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>165</th>\n",
       "      <td>3225</td>\n",
       "      <td>77400</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>3</td>\n",
       "      <td>6:32569297_A/G,6:34205465_G/GGAGCCC,HLA_DQA1</td>\n",
       "      <td>6:28861320_A/G</td>\n",
       "      <td>rs3135314</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>6.860230</td>\n",
       "      <td>0.228396</td>\n",
       "      <td>0.033293</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>6.906660e-12</td>\n",
       "      <td>1</td>\n",
       "      <td>(TRIM27, strong_LD)</td>\n",
       "      <td>TRIM27</td>\n",
       "      <td>strong_LD</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>166</th>\n",
       "      <td>20961</td>\n",
       "      <td>520175</td>\n",
       "      <td>continuous</td>\n",
       "      <td>weight</td>\n",
       "      <td>124693</td>\n",
       "      <td>4</td>\n",
       "      <td>6:28861320_A/G,6:32569297_A/G,6:34205465_G/GGA...</td>\n",
       "      <td>6:30990019_A/G</td>\n",
       "      <td>rs9380210</td>\n",
       "      <td>unphased bialleic</td>\n",
       "      <td>...</td>\n",
       "      <td>5.495360</td>\n",
       "      <td>0.189633</td>\n",
       "      <td>0.034508</td>\n",
       "      <td>NaN</td>\n",
       "      <td>NaN</td>\n",
       "      <td>3.906670e-08</td>\n",
       "      <td>1</td>\n",
       "      <td>(MUC22, on_gene)</td>\n",
       "      <td>MUC22</td>\n",
       "      <td>on_gene</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>71 rows × 28 columns</p>\n",
       "</div>"
      ],
      "text/plain": [
       "     Unnamed: 0  Unnamed: 0.1 phenotype_type            phenotype_name  \\\n",
       "1         68677        475104     continuous             FEV_predicted   \n",
       "3         68733        475496     continuous             FVC_predicted   \n",
       "7         23267        208017     continuous                   albumin   \n",
       "8         68753        679480     continuous                   albumin   \n",
       "9         22994        251240     continuous                   albumin   \n",
       "11        54203        481860         binary          allergic_disease   \n",
       "13        30666        272754     continuous                       alt   \n",
       "14        68685        678800     continuous                       alt   \n",
       "18        35664        317736     continuous                       ast   \n",
       "19        63255       1498800     continuous                       ast   \n",
       "25        11573         92584         binary            blood_in_urine   \n",
       "27        51364           417     continuous                       bmi   \n",
       "28         4332         95304     continuous                       bmi   \n",
       "33        18963        169281     continuous                       bun   \n",
       "46        31181        277389     continuous                creatinine   \n",
       "47        25121        598824     continuous                creatinine   \n",
       "49        35371        315099     continuous  diastolic_blood_pressure   \n",
       "58        31181        215747     continuous             grip_strength   \n",
       "61        30860        274500     continuous                     hba1c   \n",
       "63        38054        339246     continuous           hdl_cholesterol   \n",
       "64        37991        376310     continuous           hdl_cholesterol   \n",
       "65        70668        768493     continuous           hdl_cholesterol   \n",
       "68        68738        611397     continuous                    height   \n",
       "69         5776         57760     continuous                    height   \n",
       "70        22772        248798     continuous                    height   \n",
       "71        71028       1896021     continuous                    height   \n",
       "72         4149        116172     continuous                    height   \n",
       "74        35289        314361     continuous                hematocrit   \n",
       "75        29374        291010     continuous                hematocrit   \n",
       "76         7442        267912     continuous                hematocrit   \n",
       "..          ...           ...            ...                       ...   \n",
       "110       65631        583434     continuous                  platelet   \n",
       "111       65627        648220     continuous                  platelet   \n",
       "112       24319        265815     continuous                  platelet   \n",
       "113       45013           660     continuous                  platelet   \n",
       "114       68707       2172864     continuous                  platelet   \n",
       "115       12341             4     continuous                  platelet   \n",
       "116       29754       1322730     continuous                  platelet   \n",
       "119       36851        291928     continuous          protein_in_blood   \n",
       "122        6018         54162     continuous                     pulse   \n",
       "125       29492           179     continuous                       rbc   \n",
       "126       68735       2377550     continuous                       rbc   \n",
       "127       35164       1252944     continuous                       rbc   \n",
       "128       13551        495689     continuous                       rbc   \n",
       "137       35371        315099     continuous   systolic_blood_pressure   \n",
       "139       68706        611109         binary               t2_diabetes   \n",
       "142       51051        454437         binary           thyroid_disease   \n",
       "143       32229        701118         binary           thyroid_disease   \n",
       "144       33685        766498         binary           thyroid_disease   \n",
       "145       55581       1316160         binary           thyroid_disease   \n",
       "148       54439           494     continuous         total_cholesterol   \n",
       "151       39838        355302     continuous              triglyceride   \n",
       "152       68706       1561723     continuous              triglyceride   \n",
       "158       25149        224775     continuous                       wbc   \n",
       "159       42704       1015704     continuous                       wbc   \n",
       "160       32219       1401796     continuous                       wbc   \n",
       "161       68816       3060495     continuous                       wbc   \n",
       "163       68733        611352     continuous                    weight   \n",
       "164       47359        468200     continuous                    weight   \n",
       "165        3225         77400     continuous                    weight   \n",
       "166       20961        520175     continuous                    weight   \n",
       "\n",
       "    samples(case/control)  step  \\\n",
       "1                    7440     1   \n",
       "3                    7441     1   \n",
       "7                  125069     1   \n",
       "8                  125069     2   \n",
       "9                  125069     3   \n",
       "11             9273/78950     1   \n",
       "13                 120788     1   \n",
       "14                 120788     2   \n",
       "18                 121162     1   \n",
       "19                 121162     2   \n",
       "25             1817/14938     1   \n",
       "27                 124539     1   \n",
       "28                 124539     2   \n",
       "33                 124563     1   \n",
       "46                 125191     1   \n",
       "47                 125191     2   \n",
       "49                 124766     1   \n",
       "58                  59747     1   \n",
       "61                  56650     1   \n",
       "63                 124772     1   \n",
       "64                 124772     2   \n",
       "65                 124772     3   \n",
       "68                 125264     1   \n",
       "69                 125264     2   \n",
       "70                 125264     3   \n",
       "71                 125264     4   \n",
       "72                 125264     5   \n",
       "74                  87158     1   \n",
       "75                  87158     2   \n",
       "76                  87158     3   \n",
       "..                    ...   ...   \n",
       "110                 86087     1   \n",
       "111                 86087     2   \n",
       "112                 86087     3   \n",
       "113                 86087     4   \n",
       "114                 86087     5   \n",
       "115                 86087     6   \n",
       "116                 86087     7   \n",
       "119                 24307     1   \n",
       "122                121124     1   \n",
       "125                 87356     1   \n",
       "126                 87356     2   \n",
       "127                 87356     3   \n",
       "128                 87356     4   \n",
       "137                124467     1   \n",
       "139            8662/78950     1   \n",
       "142            5139/75944     1   \n",
       "143            5139/75944     2   \n",
       "144            5139/75944     3   \n",
       "145            5139/75944     4   \n",
       "148                125007     1   \n",
       "151                123426     1   \n",
       "152                123426     2   \n",
       "158                 86639     1   \n",
       "159                 86639     2   \n",
       "160                 86639     3   \n",
       "161                 86639     4   \n",
       "163                124693     1   \n",
       "164                124693     2   \n",
       "165                124693     3   \n",
       "166                124693     4   \n",
       "\n",
       "                                             condition  \\\n",
       "1                                                  NaN   \n",
       "3                                                  NaN   \n",
       "7                                                  NaN   \n",
       "8                                          AX-41950637   \n",
       "9                           6:34215221_G/A,AX-41950637   \n",
       "11                                                 NaN   \n",
       "13                                                 NaN   \n",
       "14                                      6:31351530_T/C   \n",
       "18                                                 NaN   \n",
       "19                             6:32202630_G/T,HLA_DQB1   \n",
       "25                                                 NaN   \n",
       "27                                                 NaN   \n",
       "28                                            HLA_DQA1   \n",
       "33                                                 NaN   \n",
       "46                                                 NaN   \n",
       "47                             6:31371397_C/T,HLA_DQB1   \n",
       "49                                                 NaN   \n",
       "58                                                 NaN   \n",
       "61                                                 NaN   \n",
       "63                                                 NaN   \n",
       "64                                      6:32380909_A/C   \n",
       "65                       6:32377408_T/C,6:32380909_A/C   \n",
       "68                                                 NaN   \n",
       "69                                    6:34207474_T/TAA   \n",
       "70                     6:29497002_G/A,6:34207474_T/TAA   \n",
       "71   6:29497002_G/A,6:31128329_G/A,6:34207474_T/TAA...   \n",
       "72   6:29497002_G/A,6:31128329_G/A,6:34207474_T/TAA...   \n",
       "74                                                 NaN   \n",
       "75                                      6:32149801_C/T   \n",
       "76                                6:32149801_C/T,HLA_B   \n",
       "..                                                 ...   \n",
       "110                                                NaN   \n",
       "111                                        AX-41961031   \n",
       "112                         6:33541507_A/G,AX-41961031   \n",
       "113          6:31217815_A/C,6:33541507_A/G,AX-41961031   \n",
       "114  6:31217815_A/C,6:33541507_A/G,AX-41961031,HLA_...   \n",
       "115  6:31217815_A/C,6:33541507_A/G,6:34185755_C/T,A...   \n",
       "116  6:31217815_A/C,6:33541507_A/G,6:34185755_C/T,A...   \n",
       "119                                                NaN   \n",
       "122                                                NaN   \n",
       "125                                                NaN   \n",
       "126                                              HLA_B   \n",
       "127                               6:34205822_T/C,HLA_B   \n",
       "128                6:32109294_A/G,6:34205822_T/C,HLA_B   \n",
       "137                                                NaN   \n",
       "139                                                NaN   \n",
       "142                                                NaN   \n",
       "143                                           HLA_DQA1   \n",
       "144                            6:31430143_G/C,HLA_DQA1   \n",
       "145             6:31430143_G/C,6:31612576_A/T,HLA_DQA1   \n",
       "148                                                NaN   \n",
       "151                                                NaN   \n",
       "152                                           HLA_DQB1   \n",
       "158                                                NaN   \n",
       "159                                              HLA_C   \n",
       "160                                     HLA_C,HLA_DRB1   \n",
       "161                      6:31428911_A/G,HLA_C,HLA_DRB1   \n",
       "163                                                NaN   \n",
       "164                               6:34205465_G/GGAGCCC   \n",
       "165       6:32569297_A/G,6:34205465_G/GGAGCCC,HLA_DQA1   \n",
       "166  6:28861320_A/G,6:32569297_A/G,6:34205465_G/GGA...   \n",
       "\n",
       "                           marker_name                    marker_name_pub  \\\n",
       "1                       6:34172055_C/A                          rs1187115   \n",
       "3                 6:34205465_G/GGAGCCC               6:34205465_G/GGAGCCC   \n",
       "7                          AX-41950637                          rs7762933   \n",
       "8                       6:34215221_G/A                           rs928482   \n",
       "9                          AX-15354567                          rs4713438   \n",
       "11                      6:32632237_C/T                          rs9274326   \n",
       "13                      6:31351530_T/C                          rs2905715   \n",
       "14                      6:34178764_A/C                         rs28673163   \n",
       "18                      6:32202630_G/T                        rs117654833   \n",
       "19                      6:33076268_T/C                           rs742870   \n",
       "25                      6:29896680_A/G                          rs2517754   \n",
       "27         AA_DQA1_69_32609285_exon2_L               HLA-DQA1 position 69   \n",
       "28                      6:29190624_G/A                         rs59230085   \n",
       "33                      6:30737591_G/C                          rs3095337   \n",
       "46                      6:31371397_C/T                          rs2301748   \n",
       "47                      6:31237858_T/C                         rs34794906   \n",
       "49                         AX-11365330                          rs2071277   \n",
       "58                      6:31371397_C/T                          rs2301748   \n",
       "61                      6:31358559_C/T                          rs2923009   \n",
       "63                      6:32380909_A/C                          rs9380294   \n",
       "64                      6:32377408_T/C                          rs9268505   \n",
       "65                      6:34810172_T/C                         rs13220394   \n",
       "68                    6:34207474_T/TAA                   6:34207474_T/TAA   \n",
       "69                      6:29497002_G/A                          rs9501677   \n",
       "70                      6:31128329_G/A                          rs9263789   \n",
       "71                      6:34967349_G/A                         rs12527060   \n",
       "72                         AX-11435484                          rs3130743   \n",
       "74                      6:32149801_C/T                          rs9391855   \n",
       "75           SNPS_B_836_31324100_exon3                          rs1050654   \n",
       "76                      6:29698050_A/G                          rs2743925   \n",
       "..                                 ...                                ...   \n",
       "110                        AX-41961031                          rs9296095   \n",
       "111                     6:33541507_A/G                           rs511515   \n",
       "112                     6:31217815_A/C                          rs2894189   \n",
       "113        AA_DRB1_71_32551949_exon2_E               HLA-DRB1 position 71   \n",
       "114                     6:34185755_C/T                          rs2797964   \n",
       "115            AA_A_114_29911114_exon3                 HLA-A position 114   \n",
       "116                        AX-11396692                          rs2523589   \n",
       "119                    6:32324081_A/AT                    6:32324081_A/AT   \n",
       "122                        AX-11397307                          rs2534791   \n",
       "125             AA_B_69_31324530_exon2                  HLA-B position 69   \n",
       "126                     6:34205822_T/C                        rs118012224   \n",
       "127                     6:32109294_A/G                          rs9348878   \n",
       "128                     6:29938478_A/G                          rs7754245   \n",
       "137                        AX-11365330                          rs2071277   \n",
       "139                     6:34185749_C/T                          rs2797963   \n",
       "142                  6:32608334_GAAA/G                  6:32608334_GAAA/G   \n",
       "143                     6:31430143_G/C                          rs2255001   \n",
       "144                     6:31612576_A/T                         rs12055599   \n",
       "145                     6:32641938_G/T                         rs28891457   \n",
       "148        AA_DQB1_57_32632681_exon2_V               HLA-DQB1 position 57   \n",
       "151                     6:32453284_C/G                        rs111524667   \n",
       "152                     6:34185749_C/T                          rs2797963   \n",
       "158                     6:31237965_G/C                         rs17886232   \n",
       "159  SNPS_DRB1_9849_32547671_intron5_C  SNPS_DRB1_9849_32547671_intron5_C   \n",
       "160                     6:31428911_A/G                          rs2596471   \n",
       "161                     6:34234974_A/G                        rs117324087   \n",
       "163               6:34205465_G/GGAGCCC               6:34205465_G/GGAGCCC   \n",
       "164                     6:32569297_A/G                          rs9270797   \n",
       "165                     6:28861320_A/G                          rs3135314   \n",
       "166                     6:30990019_A/G                          rs9380210   \n",
       "\n",
       "                    note  ...          Z      coef       std       chisq   df  \\\n",
       "1      unphased bialleic  ...   5.836440  0.026954  0.004618         NaN  NaN   \n",
       "3      unphased bialleic  ...   5.573560  0.036813  0.006605         NaN  NaN   \n",
       "7      unphased bialleic  ...  -8.556170 -0.008719  0.001019         NaN  NaN   \n",
       "8      unphased bialleic  ...  -8.163130 -0.010955  0.001342         NaN  NaN   \n",
       "9      unphased bialleic  ...  -5.830450 -0.008171  0.001402         NaN  NaN   \n",
       "11     unphased bialleic  ...   5.603280  0.088615  0.015814         NaN  NaN   \n",
       "13     unphased bialleic  ...   6.522960  0.326987  0.050129         NaN  NaN   \n",
       "14     unphased bialleic  ...  -5.475840 -0.334937  0.061166         NaN  NaN   \n",
       "18     unphased bialleic  ...   7.602650  0.443845  0.058380         NaN  NaN   \n",
       "19     unphased bialleic  ...  -5.816710 -0.191552  0.032931         NaN  NaN   \n",
       "25     unphased bialleic  ...  -5.536510 -0.201425  0.036381         NaN  NaN   \n",
       "27      phased biallelic  ...  -6.082880 -0.070694  0.011622         NaN  NaN   \n",
       "28     unphased bialleic  ...  -6.111320 -0.074561  0.012200         NaN  NaN   \n",
       "33     unphased bialleic  ...  -6.933740 -0.186481  0.026895         NaN  NaN   \n",
       "46     unphased bialleic  ...  11.720900  0.012433  0.001061         NaN  NaN   \n",
       "47     unphased bialleic  ...  -6.898860 -0.003895  0.000565         NaN  NaN   \n",
       "49     unphased bialleic  ...   6.653510  0.260993  0.039226         NaN  NaN   \n",
       "58     unphased bialleic  ...   5.466610  0.401340  0.073417         NaN  NaN   \n",
       "61     unphased bialleic  ...  -6.212440 -0.020605  0.003317         NaN  NaN   \n",
       "63     unphased bialleic  ...   7.694130  0.502552  0.065316         NaN  NaN   \n",
       "64     unphased bialleic  ...  -6.409360 -0.328365  0.051232         NaN  NaN   \n",
       "65     unphased bialleic  ...  -6.174010 -0.294747  0.047740         NaN  NaN   \n",
       "68     unphased bialleic  ...  18.513100  0.524680  0.028341         NaN  NaN   \n",
       "69     unphased bialleic  ...  13.237700  0.345431  0.026094         NaN  NaN   \n",
       "70     unphased bialleic  ...  -8.504020 -0.359084  0.042225         NaN  NaN   \n",
       "71     unphased bialleic  ...   7.022430  0.270738  0.038553         NaN  NaN   \n",
       "72     unphased bialleic  ...   6.519490  0.147346  0.022601         NaN  NaN   \n",
       "74     unphased bialleic  ...  -7.143070 -0.133691  0.018716         NaN  NaN   \n",
       "75     unphased bialleic  ...   6.102360  0.103592  0.016976         NaN  NaN   \n",
       "76     unphased bialleic  ...  -5.732800 -0.153786  0.026826         NaN  NaN   \n",
       "..                   ...  ...        ...       ...       ...         ...  ...   \n",
       "110    unphased bialleic  ...  17.641200  5.566170  0.315522         NaN  NaN   \n",
       "111    unphased bialleic  ... -12.411800 -3.938910  0.317352         NaN  NaN   \n",
       "112    unphased bialleic  ...  12.416900  3.262640  0.262759         NaN  NaN   \n",
       "113     phased biallelic  ...   8.551858  3.711096  0.433952         NaN  NaN   \n",
       "114    unphased bialleic  ...  -6.662370 -2.368900  0.355564         NaN  NaN   \n",
       "115  phased multiallelic  ...        NaN       NaN       NaN   44.475274  3.0   \n",
       "116    unphased bialleic  ...   7.034830  2.262390  0.321599         NaN  NaN   \n",
       "119    unphased bialleic  ...   5.567080  0.030129  0.005412         NaN  NaN   \n",
       "122    unphased bialleic  ...   5.536170  0.254352  0.045944         NaN  NaN   \n",
       "125  phased multiallelic  ...        NaN       NaN       NaN  100.521732  2.0   \n",
       "126    unphased bialleic  ...  -6.530060 -0.015963  0.002445         NaN  NaN   \n",
       "127    unphased bialleic  ...  -5.658800 -0.014044  0.002482         NaN  NaN   \n",
       "128    unphased bialleic  ...  -5.545740 -0.012154  0.002192         NaN  NaN   \n",
       "137    unphased bialleic  ...   6.327180  0.370073  0.058489         NaN  NaN   \n",
       "139    unphased bialleic  ...  -6.849640 -0.164752  0.024053         NaN  NaN   \n",
       "142    unphased bialleic  ...  -9.577430 -0.206240  0.021534         NaN  NaN   \n",
       "143    unphased bialleic  ...   7.327290  0.243174  0.033188         NaN  NaN   \n",
       "144    unphased bialleic  ...   6.640940  0.297620  0.044816         NaN  NaN   \n",
       "145    unphased bialleic  ...   6.567150  0.238481  0.036315         NaN  NaN   \n",
       "148     phased biallelic  ...  12.090447  2.167680  0.179289         NaN  NaN   \n",
       "151    unphased bialleic  ...  14.355300  6.680110  0.465340         NaN  NaN   \n",
       "152    unphased bialleic  ...  -7.420780 -2.760130  0.371946         NaN  NaN   \n",
       "158    unphased bialleic  ...  15.854400  0.118848  0.007496         NaN  NaN   \n",
       "159    unphased bialleic  ...   8.887500  0.070215  0.007900         NaN  NaN   \n",
       "160    unphased bialleic  ...  -6.374980 -0.066856  0.010487         NaN  NaN   \n",
       "161    unphased bialleic  ...  -5.650810 -0.062154  0.010999         NaN  NaN   \n",
       "163    unphased bialleic  ...  12.533800  0.553022  0.044123         NaN  NaN   \n",
       "164    unphased bialleic  ...   8.083850  0.263069  0.032543         NaN  NaN   \n",
       "165    unphased bialleic  ...   6.860230  0.228396  0.033293         NaN  NaN   \n",
       "166    unphased bialleic  ...   5.495360  0.189633  0.034508         NaN  NaN   \n",
       "\n",
       "                P P_significant             gene_genehow       gene  \\\n",
       "1    5.556790e-09             1       (HMGA1, strong_LD)      HMGA1   \n",
       "3    2.583340e-08             1         (HMGA1, on_gene)      HMGA1   \n",
       "7    1.179740e-17             1     (HLA-C, moderate_LD)      HLA-C   \n",
       "8    3.294620e-16             1        (C6orf1, on_gene)     C6orf1   \n",
       "9    5.541470e-09             1        (POU5F1, on_gene)     POU5F1   \n",
       "11   2.103290e-08             1      (HLA-DQB1, on_gene)   HLA-DQB1   \n",
       "13   6.920490e-11             1      (MICA, moderate_LD)       MICA   \n",
       "14   4.362960e-08             1       (HMGA1, strong_LD)      HMGA1   \n",
       "18   2.921930e-14             1  (HLA-DRB1, moderate_LD)   HLA-DRB1   \n",
       "19   6.016610e-09             1  (HLA-DPB1, moderate_LD)   HLA-DPB1   \n",
       "25   3.085650e-08             1     (HLA-A, moderate_LD)      HLA-A   \n",
       "27   1.180429e-09             1      (HLA-DQA1, on_gene)   HLA-DQA1   \n",
       "28   9.910210e-10             1      (TRIM27, strong_LD)     TRIM27   \n",
       "33   4.118390e-12             1     (HLA-E, moderate_LD)      HLA-E   \n",
       "46   1.035490e-31             1          (MICA, on_gene)       MICA   \n",
       "47   5.267020e-12             1         (HLA-C, on_gene)      HLA-C   \n",
       "49   2.873610e-11             1        (NOTCH4, on_gene)     NOTCH4   \n",
       "58   4.605620e-08             1          (MICA, on_gene)       MICA   \n",
       "61   5.253110e-10             1      (MICA, moderate_LD)       MICA   \n",
       "63   1.434950e-14             1         (BTNL2, nearest)      BTNL2   \n",
       "64   1.466540e-10             1         (BTNL2, nearest)      BTNL2   \n",
       "65   6.678210e-10             1      (UHRF1BP1, on_gene)   UHRF1BP1   \n",
       "68   2.047770e-76             1         (HMGA1, on_gene)      HMGA1   \n",
       "69   5.654650e-40             1     (HLA-F, moderate_LD)      HLA-F   \n",
       "70   1.851080e-17             1         (TCF19, on_gene)      TCF19   \n",
       "71   2.191480e-12             1         (TAF11, nearest)      TAF11   \n",
       "72   7.081290e-11             1         (OR2J2, on_gene)      OR2J2   \n",
       "74   9.197860e-13             1     (RNF5,AGER, on_gene)  RNF5,AGER   \n",
       "75   1.049540e-09             1         (HLA-B, on_gene)      HLA-B   \n",
       "76   9.911020e-09             1         (HLA-F, on_gene)      HLA-F   \n",
       "..            ...           ...                      ...        ...   \n",
       "110  1.579220e-69             1          (BAK1, on_gene)       BAK1   \n",
       "111  2.417650e-35             1          (BAK1, on_gene)       BAK1   \n",
       "112  2.270210e-35             1         (HLA-C, nearest)      HLA-C   \n",
       "113  1.211227e-17             1      (HLA-DRB1, on_gene)   HLA-DRB1   \n",
       "114  2.710710e-11             1       (HMGA1, strong_LD)      HMGA1   \n",
       "115  1.196110e-09             1         (HLA-A, on_gene)      HLA-A   \n",
       "116  2.009910e-12             1     (HLA-B, moderate_LD)      HLA-B   \n",
       "119  2.617760e-08             1       (C6orf10, on_gene)    C6orf10   \n",
       "122  3.098060e-08             1         (UBD, strong_LD)        UBD   \n",
       "125  1.485878e-22             1         (HLA-B, on_gene)      HLA-B   \n",
       "126  6.610360e-11             1         (HMGA1, on_gene)      HMGA1   \n",
       "127  1.529120e-08             1       (ATF6B, strong_LD)      ATF6B   \n",
       "128  2.935550e-08             1     (HLA-A, moderate_LD)      HLA-A   \n",
       "137  2.505260e-10             1        (NOTCH4, on_gene)     NOTCH4   \n",
       "139  7.403820e-12             1       (HMGA1, strong_LD)      HMGA1   \n",
       "142  9.949160e-22             1      (HLA-DQA1, on_gene)   HLA-DQA1   \n",
       "143  2.348530e-13             1          (MICB, nearest)       MICB   \n",
       "144  3.116790e-11             1          (BAG6, on_gene)       BAG6   \n",
       "145  5.128710e-11             1  (HLA-DQA1, moderate_LD)   HLA-DQA1   \n",
       "148  1.186392e-33             1      (HLA-DQB1, on_gene)   HLA-DQB1   \n",
       "151  1.075790e-46             1  (HLA-DQA1, moderate_LD)   HLA-DQA1   \n",
       "152  1.171770e-13             1       (HMGA1, strong_LD)      HMGA1   \n",
       "158  1.574790e-56             1         (HLA-C, on_gene)      HLA-C   \n",
       "159  6.368470e-19             1      (HLA-DRB1, on_gene)   HLA-DRB1   \n",
       "160  1.839100e-10             1     (HLA-B, moderate_LD)      HLA-B   \n",
       "161  1.601910e-08             1       (HMGA1, strong_LD)      HMGA1   \n",
       "163  5.129760e-36             1         (HMGA1, on_gene)      HMGA1   \n",
       "164  6.330940e-16             1  (HLA-DQA1, moderate_LD)   HLA-DQA1   \n",
       "165  6.906660e-12             1      (TRIM27, strong_LD)     TRIM27   \n",
       "166  3.906670e-08             1         (MUC22, on_gene)      MUC22   \n",
       "\n",
       "         genehow  \n",
       "1      strong_LD  \n",
       "3        on_gene  \n",
       "7    moderate_LD  \n",
       "8        on_gene  \n",
       "9        on_gene  \n",
       "11       on_gene  \n",
       "13   moderate_LD  \n",
       "14     strong_LD  \n",
       "18   moderate_LD  \n",
       "19   moderate_LD  \n",
       "25   moderate_LD  \n",
       "27       on_gene  \n",
       "28     strong_LD  \n",
       "33   moderate_LD  \n",
       "46       on_gene  \n",
       "47       on_gene  \n",
       "49       on_gene  \n",
       "58       on_gene  \n",
       "61   moderate_LD  \n",
       "63       nearest  \n",
       "64       nearest  \n",
       "65       on_gene  \n",
       "68       on_gene  \n",
       "69   moderate_LD  \n",
       "70       on_gene  \n",
       "71       nearest  \n",
       "72       on_gene  \n",
       "74       on_gene  \n",
       "75       on_gene  \n",
       "76       on_gene  \n",
       "..           ...  \n",
       "110      on_gene  \n",
       "111      on_gene  \n",
       "112      nearest  \n",
       "113      on_gene  \n",
       "114    strong_LD  \n",
       "115      on_gene  \n",
       "116  moderate_LD  \n",
       "119      on_gene  \n",
       "122    strong_LD  \n",
       "125      on_gene  \n",
       "126      on_gene  \n",
       "127    strong_LD  \n",
       "128  moderate_LD  \n",
       "137      on_gene  \n",
       "139    strong_LD  \n",
       "142      on_gene  \n",
       "143      nearest  \n",
       "144      on_gene  \n",
       "145  moderate_LD  \n",
       "148      on_gene  \n",
       "151  moderate_LD  \n",
       "152    strong_LD  \n",
       "158      on_gene  \n",
       "159      on_gene  \n",
       "160  moderate_LD  \n",
       "161    strong_LD  \n",
       "163      on_gene  \n",
       "164  moderate_LD  \n",
       "165    strong_LD  \n",
       "166      on_gene  \n",
       "\n",
       "[71 rows x 28 columns]"
      ]
     },
     "execution_count": 45,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "result_all[result_all['P_significant']==1]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {},
   "outputs": [],
   "source": [
    "result_all.to_csv('data/result_concat_2_top_gene_annot.tsv',sep='\\t',index=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 100,
   "metadata": {},
   "outputs": [],
   "source": [
    "#result_all[result_all['phenotype_name']=='glucose_in_blood']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 286,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "HCG22\n",
      "HCG22\n",
      "HMGA1\n",
      "HLA_E\n",
      "HLA_A\n",
      "HMGA1\n",
      "HLA_DQA1\n",
      "HLA_DPB1\n",
      "HMGA1\n",
      "HLA_A\n",
      "TRIM27\n",
      "C6orf1\n",
      "HLA_A\n",
      "NOTCH4\n",
      "HLA_DRB1\n",
      "HMGA1\n",
      "NOTCH4\n",
      "ITPR3\n",
      "HLA_B\n",
      "HMGA1\n",
      "UHRF1BP1\n",
      "HCG22\n",
      "HLA_DPB1\n",
      "HLA_C\n",
      "SCAND3\n",
      "TAF11\n",
      "IER3\n",
      "LSM2\n",
      "HLA_B\n",
      "LOC285830\n",
      "FLJ43752\n",
      "HCG9\n",
      "HLA_DRB1\n",
      "TRIM27\n",
      "RPS10\n",
      "HCG26\n",
      "HMGA1\n",
      "GRM4\n",
      "GRM4\n",
      "GRM4\n",
      "ZSCAN16\n",
      "HLA_B\n",
      "BAK1\n",
      "HLA_DRB1\n",
      "HMGA1\n",
      "HLA_A\n",
      "HLA_DPB1\n",
      "ZFP57\n",
      "HMGA1\n",
      "ATF6B\n",
      "HLA_A\n",
      "HLA_B\n",
      "HLA_DRB1\n",
      "HLA_B\n",
      "HLA_C\n",
      "HLA_DOA\n",
      "HMGA1\n",
      "SKIV2L\n",
      "HLA_DRB1\n",
      "HLA_B\n",
      "HMGA1\n",
      "HLA_A\n",
      "HLA_DQA1\n",
      "TRIM27\n",
      "HCG22\n",
      "HLA_A\n"
     ]
    }
   ],
   "source": [
    "for i in result_all['gene'][result_all['step']!=1]:\n",
    "    print(i)"
   ]
  },
  {
   "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": "3.7.3"
  },
  "toc": {
   "base_numbering": 1,
   "nav_menu": {},
   "number_sections": true,
   "sideBar": true,
   "skip_h1_title": false,
   "title_cell": "Table of Contents",
   "title_sidebar": "Contents",
   "toc_cell": false,
   "toc_position": {},
   "toc_section_display": true,
   "toc_window_display": false
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}