{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/cellar/users/btsui/anaconda3/lib/python3.6/site-packages/IPython/core/interactiveshell.py:2785: DtypeWarning: Columns (0) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  interactivity=interactivity, compiler=compiler, result=result)\n"
     ]
    }
   ],
   "source": [
    "specie='Homo_sapiens'\n",
    "snpBed='/cellar/users/btsui/Data/dbsnp/snp_beds/'+specie+'.bed'\n",
    "import pandas as pd\n",
    "tmpDf=pd.read_csv(snpBed,sep='\\t',header=None)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "tmpDf[0]='chr'+tmpDf[0].astype(str)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'/cellar/users/btsui/Data/dbsnp/snp_beds/Homo_sapiens.bed'"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "tmpDf.to_csv(snpBed+'.with_chr',sep='\\t',header=None,index=None)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "chr1\t14727\t14727\r\n",
      "chr1\t630825\t630825\r\n",
      "chr1\t630833\t630833\r\n",
      "chr1\t817186\t817186\r\n",
      "chr1\t833068\t833068\r\n",
      "chr1\t842133\t842133\r\n",
      "chr1\t843942\t843942\r\n",
      "chr1\t850609\t850609\r\n",
      "chr1\t948136\t948136\r\n",
      "chr1\t955964\t955964\r\n"
     ]
    }
   ],
   "source": [
    "!head /cellar/users/btsui/Data/dbsnp/snp_beds/Homo_sapiens.bed.with_chr"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## the dbsnp contains all the reference bases "
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.6.5"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}