python code for conversion hapmap to numeric (-1,0,1).ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "import rpy2"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "ename": "ModuleNotFoundError",
     "evalue": "No module named 'tzlocal'",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
      "\u001b[1;32m<ipython-input-8-61cdef9365ba>\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m      2\u001b[0m \u001b[1;32mfrom\u001b[0m \u001b[0mrpy2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrobjects\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mpackages\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mimportr\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m      3\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpandas\u001b[0m \u001b[1;32mas\u001b[0m \u001b[0mpd\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m----> 4\u001b[1;33m \u001b[1;32mfrom\u001b[0m \u001b[0mrpy2\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mrobjects\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpandas2ri\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m      5\u001b[0m \u001b[0mpandas2ri\u001b[0m\u001b[1;33m.\u001b[0m\u001b[0mactivate\u001b[0m\u001b[1;33m(\u001b[0m\u001b[1;33m)\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;32mC:\\ProgramData\\Anaconda3\\lib\\site-packages\\rpy2\\robjects\\pandas2ri.py\u001b[0m in \u001b[0;36m<module>\u001b[1;34m\u001b[0m\n\u001b[0;32m     21\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mnumpy\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     22\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mpytz\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[1;32m---> 23\u001b[1;33m \u001b[1;32mimport\u001b[0m \u001b[0mtzlocal\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0m\u001b[0;32m     24\u001b[0m \u001b[1;32mimport\u001b[0m \u001b[0mwarnings\u001b[0m\u001b[1;33m\u001b[0m\u001b[1;33m\u001b[0m\u001b[0m\n\u001b[0;32m     25\u001b[0m \u001b[1;33m\u001b[0m\u001b[0m\n",
      "\u001b[1;31mModuleNotFoundError\u001b[0m: No module named 'tzlocal'"
     ]
    }
   ],
   "source": [
    "import rpy2.robjects as robjects\n",
    "from rpy2.robjects.packages import importr\n",
    "import pandas as pd\n",
    "from rpy2.robjects import pandas2ri\n",
    "pandas2ri.activate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "## I connected the GAPIT.Numericalization and GAPIT.HapMap function. These R codes will help convert the hapmap data to (-1,0,1) data format\n",
    "rstring=\"\"\"\n",
    "GAPIT.Numericalization <-\n",
    "  function(x,bit=2,effect=\"Add\",impute=\"None\", Create.indicator = FALSE, Major.allele.zero = FALSE, byRow=TRUE){\n",
    "    #Object: To convert character SNP genotpe to numerical (-1,0,1)\n",
    "    #Output: Coresponding numerical value\n",
    "    #Authors: Feng Tian and Zhiwu Zhang\n",
    "    # Last update: May 30, 2011 \n",
    "    ##############################################################################################\n",
    "    if(bit==1)  {\n",
    "      x[x==\"X\"]=\"N\"\n",
    "      x[x==\"-\"]=\"N\"\n",
    "      x[x==\"+\"]=\"N\"\n",
    "      x[x==\"/\"]=\"N\"\n",
    "      x[x==\"K\"]=\"Z\" #K (for GT genotype)is replaced by Z to ensure heterozygose has the largest value\n",
    "    }\n",
    "    \n",
    "    if(bit==2)  {\n",
    "      x[x==\"XX\"]=\"N\"\n",
    "      x[x==\"--\"]=\"N\"\n",
    "      x[x==\"++\"]=\"N\"\n",
    "      x[x==\"//\"]=\"N\"\n",
    "      x[x==\"NN\"]=\"N\"\n",
    "    }\n",
    "    \n",
    "    n=length(x)\n",
    "    lev=levels(as.factor(x))\n",
    "    lev=setdiff(lev,\"N\")\n",
    "    #print(lev)\n",
    "    len=length(lev)\n",
    "    #print(lev)\n",
    "    \n",
    "    \n",
    "    \n",
    "    #Genotype counts\n",
    "    count=1:len\n",
    "    for(i in 1:len){\n",
    "      count[i]=length(x[(x==lev[i])])\n",
    "    }\n",
    "    \n",
    "    \n",
    "    \n",
    "    if(Major.allele.zero){\n",
    "      if(len>1 & len<=3){\n",
    "        #One bit: Make sure that the SNP with the major allele is on the top, and the SNP with the minor allele is on the second position\n",
    "        if(bit==1){ \n",
    "          count.temp = cbind(count, seq(1:len))\n",
    "          if(len==3) count.temp = count.temp[-3,]\n",
    "          count.temp <- count.temp[order(count.temp[,1], decreasing = TRUE),]\n",
    "          if(len==3)order =  c(count.temp[,2],3)else order = count.temp[,2]\n",
    "        }\n",
    "        \n",
    "        #Two bit: Make sure that the SNP with the major allele is on the top, and the SNP with the minor allele is on the third position\n",
    "        if(bit==2){ \n",
    "          count.temp = cbind(count, seq(1:len))\n",
    "          if(len==3) count.temp = count.temp[-2,]\n",
    "          count.temp <- count.temp[order(count.temp[,1], decreasing = TRUE),]\n",
    "          if(len==3) order =  c(count.temp[1,2],2,count.temp[2,2])else order = count.temp[,2]\n",
    "        }\n",
    "        \n",
    "        count = count[order]\n",
    "        lev = lev[order]\n",
    "        \n",
    "      }   #End  if(len<=1 | len> 3)\n",
    "    } #End  if(Major.allele.zero)\n",
    "    \n",
    "    \n",
    "    \n",
    "    #make two  bit order genotype as AA,AT and TT, one bit as A(AA),T(TT) and X(AT)\n",
    "    if(bit==1 & len==3){\n",
    "      temp=count[2]\n",
    "      count[2]=count[3]\n",
    "      count[3]=temp\n",
    "    }\n",
    "    position=order(count)\n",
    "    \n",
    "    \n",
    "    #1status other than 2 or 3\n",
    "    if(len<=1 | len> 3)x=-1\n",
    "    \n",
    "    #2 status\n",
    "    if(len==2)x=ifelse(x==\"N\",NA,ifelse(x==lev[1],-1,1))\n",
    "    \n",
    "    #3 status\n",
    "    if(bit==1){\n",
    "      if(len==3)x=ifelse(x==\"N\",NA,ifelse(x==lev[1],-1,ifelse(x==lev[3],0,1)))\n",
    "    }else{\n",
    "      if(len==3)x=ifelse(x==\"N\",NA,ifelse(x==lev[1],-1,ifelse(x==lev[3],1,0)))\n",
    "    }\n",
    "    \n",
    "    #print(paste(lev,len,sep=\" \"))\n",
    "    #print(position)\n",
    "    \n",
    "    #missing data imputation\n",
    "    if(impute==\"Middle\") {x[is.na(x)]=0 }\n",
    "    \n",
    "    if(len==3){\n",
    "      if(impute==\"Minor\")  {x[is.na(x)]=position[1]  -1}\n",
    "      if(impute==\"Major\")  {x[is.na(x)]=position[len]-1}\n",
    "      \n",
    "    }else{\n",
    "      if(impute==\"Minor\")  {x[is.na(x)]=2*(position[1]  -1)}\n",
    "      if(impute==\"Major\")  {x[is.na(x)]=2*(position[len]-1)}\n",
    "    }\n",
    "    \n",
    "    #alternative genetic models\n",
    "    if(effect==\"Dom\") x=ifelse(x==1,1,0)\n",
    "    if(effect==\"Left\") x[x==1]=0\n",
    "    if(effect==\"Right\") x[x==1]=2\n",
    "    \n",
    "    if(byRow) {\n",
    "      result=matrix(x,n,1)\n",
    "    }else{\n",
    "      result=matrix(x,1,n)  \n",
    "    }\n",
    "    \n",
    "    return(result)\n",
    "  }\n",
    "#end of GAPIT.Numericalization function\n",
    "\n",
    "\n",
    "\n",
    "# Beginning of GAPIT.HapMap function\n",
    "\n",
    "\n",
    "GAPIT.HapMap <-\n",
    "  function(G,SNP.effect=\"Add\",SNP.impute=\"Middle\",heading=TRUE, Create.indicator = FALSE, Major.allele.zero = FALSE){\n",
    "    #Object: To convert character SNP genotpe to numerical\n",
    "    #Output: Coresponding numerical value\n",
    "    #Authors: Feng Tian and Zhiwu Zhang\n",
    "    # Last update: May 30, 2011 \n",
    "    ##############################################################################################\n",
    "    \n",
    "    print(paste(\"Converting HapMap format to numerical under model of \", SNP.impute,sep=\"\"))\n",
    "    #gc()\n",
    "    #GAPIT.Memory.Object(name.of.trait=\"HapMap.Start\")\n",
    "    \n",
    "    #GT=data.frame(G[1,-(1:11)])\n",
    "    if(heading){\n",
    "      GT= t(G[1,-(1:11)])\n",
    "      GI= G[-1,c(1,3,4)]\n",
    "    }else{\n",
    "      GT=NULL\n",
    "      GI= G[,c(1,3,4)]\n",
    "    }\n",
    "    \n",
    "    \n",
    "    #Set column names\n",
    "    if(heading)colnames(GT)=\"taxa\"\n",
    "    colnames(GI)=c(\"SNP\",\"Chromosome\",\"Position\")\n",
    "    \n",
    "    #Initial GD\n",
    "    GD=NULL\n",
    "    bit=nchar(as.character(G[2,12])) #to determine number of bits of genotype\n",
    "    #print(paste(\"Number of bits for genotype: \", bit))\n",
    "    \n",
    "    print(\"Perform numericalization\")\n",
    "    \n",
    "    if(heading){\n",
    "      if(!Create.indicator) GD= apply(G[-1,-(1:11)],1,function(one) GAPIT.Numericalization(one,bit=bit,effect=SNP.effect,impute=SNP.impute, Major.allele.zero=Major.allele.zero))\n",
    "      if(Create.indicator) GD= t(G[-1,-(1:11)])\n",
    "    }else{\n",
    "      if(!Create.indicator) GD= apply(G[  ,-(1:11)],1,function(one) GAPIT.Numericalization(one,bit=bit,effect=SNP.effect,impute=SNP.impute, Major.allele.zero=Major.allele.zero))\n",
    "      if(Create.indicator) GD= t(G[ ,-(1:11)])\n",
    "    }\n",
    "    \n",
    "    #set GT and GI to NULL in case of null GD\n",
    "    if(is.null(GD)){\n",
    "      GT=NULL\n",
    "      GI=NULL\n",
    "    }\n",
    "    \n",
    "    \n",
    "    write.csv(GD, file =\"Numeric data_-101_aytn.csv\")\n",
    "    print(\"The dimension of GD is:\")\n",
    "    print(dim(GD))\n",
    "    print (\"Succesfuly finished converting HapMap to numeric data !\")\n",
    "    \n",
    "    if(!Create.indicator) {print(paste(\"Succesfuly finished converting HapMap which has bits of \", bit,sep=\"\")) }\n",
    "    return(list(GT=GT,GD=GD,GI=GI))\n",
    "  }\n",
    "\n",
    "\"\"\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "transfunc=robjects.r(rstring)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [],
   "source": [
    "readtable=robjects.r('read.table')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'C:\\\\Users\\\\Zixiang'"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "pwd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [],
   "source": [
    "rdata=readtable(\"AYT_hapmap_ploy.txt.hmp.txt\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "           V1      V2    V3     V4     V5       V6     V7       V8        V9\n",
      "\r\n",
      "1          rs alleles chrom    pos strand assembly center protLSID assayLSID\n",
      "\r\n",
      "2 Gm01-138835     A/G     1 138835      +     <NA>   <NA>     <NA>      <NA>\n",
      "\r\n",
      "3 Gm01-281790     T/C     1 281790      +     <NA>   <NA>     <NA>      <NA>\n",
      "\r\n",
      "4 Gm01-402061     A/C     1 402061      +     <NA>   <NA>     <NA>      <NA>\n",
      "\r\n",
      "5 Gm01-565991     A/C     1 565991      +     <NA>   <NA>     <NA>      <NA>\n",
      "\r\n",
      "6 Gm01-901691     C/T     1 901691      +     <NA>   <NA>     <NA>      <NA>\n",
      "\r\n",
      "        V10    V11 V12 V13 V14 V15 V16 V17 V18 V19 V20 V21 V22 V23 V24 V25 V26\n",
      "\r\n",
      "1 panelLSID QCcode 226 410 411 886 887 888 889 890 891 892 893 894 895 896 897\n",
      "\r\n",
      "2      <NA>   <NA>   A   A   A   G   N   R   A   A   A   A   A   A   A   A   A\n",
      "\r\n",
      "3      <NA>   <NA>   T   T   T   C   N   Y   T   C   C   C   T   C   C   C   C\n",
      "\r\n",
      "4      <NA>   <NA>   A   A   A   C   N   A   A   C   C   N   A   C   C   C   C\n",
      "\r\n",
      "5      <NA>   <NA>   A   A   A   C   N   A   A   C   C   N   A   C   C   C   C\n",
      "\r\n",
      "6      <NA>   <NA>   C   C   C   T   N   C   C   C   C   C   C   C   C   C   C\n",
      "\r\n",
      "  V27 V28 V29 V30 V31 V32 V33 V34 V35 V36 V37 V38 V39 V40 V41 V42 V43 V44 V45\n",
      "\r\n",
      "1 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916\n",
      "\r\n",
      "2   A   A   A   A   A   A   G   R   A   G   G   G   G   A   A   A   A   A   A\n",
      "\r\n",
      "3   C   T   Y   T   T   T   C   C   C   C   C   C   C   C   C   C   T   T   T\n",
      "\r\n",
      "4   C   A   M   A   C   M   C   C   C   C   C   C   C   A   A   A   A   A   A\n",
      "\r\n",
      "5   C   A   N   A   C   M   A   M   A   C   C   C   C   C   C   C   A   A   A\n",
      "\r\n",
      "6   C   C   C   C   T   N   C   Y   C   T   T   C   C   C   C   C   C   C   C\n",
      "\r\n",
      "  V46 V47 V48 V49 V50 V51 V52 V53 V54 V55 V56 V57 V58 V59 V60 V61 V62 V63 V64\n",
      "\r\n",
      "1 917 918 919 920 921 922 923 924 925 927 928 929 930 931 932 933 938 941 942\n",
      "\r\n",
      "2   A   A   A   G   A   A   N   A   A   A   A   A   R   G   A   R   A   G   A\n",
      "\r\n",
      "3   T   Y   T   C   T   T   Y   T   C   T   T   T   Y   C   T   Y   T   C   T\n",
      "\r\n",
      "4   A   A   A   C   A   A   M   C   A   A   A   A   M   C   A   M   C   C   C\n",
      "\r\n",
      "5   A   M   A   C   A   A   M   C   C   A   A   A   M   C   A   M   A   N   C\n",
      "\r\n",
      "6   C   C   C   C   C   C   C   T   C   C   C   C   Y   T   T   Y   C   N   T\n",
      "\r\n",
      "  V65 V66 V67 V68 V69 V70 V71 V72 V73 V74 V75 V76 V77 V78 V79 V80 V81 V82 V83\n",
      "\r\n",
      "1 943 944 945 946 950 951 952 953 954 955 956 957 958 959 960 962 963 964 965\n",
      "\r\n",
      "2   A   R   A   A   R   A   A   N   A   A   G   R   A   N   A   A   A   A   A\n",
      "\r\n",
      "3   N   C   T   C   C   T   Y   N   T   Y   C   C   C   C   C   C   C   N   C\n",
      "\r\n",
      "4   C   C   A   C   C   A   M   C   C   C   C   C   C   C   C   C   C   N   C\n",
      "\r\n",
      "5   A   M   A   A   M   A   A   C   C   M   M   M   A   N   A   A   A   N   A\n",
      "\r\n",
      "6   Y   Y   C   C   Y   C   C   T   T   T   Y   Y   C   C   C   C   C   C   C\n",
      "\r\n",
      "  V84 V85 V86 V87 V88 V89 V90 V91 V92 V93 V94 V95 V96 V97 V98 V99 V100 V101\n",
      "\r\n",
      "1 966 967 968 969 970 971 972 973 974 975 976 977 978 979 982 983  984  985\n",
      "\r\n",
      "2   R   A   G   G   A   G   G   R   N   G   R   R   A   G   A   A    G    A\n",
      "\r\n",
      "3   C   C   C   C   C   C   C   Y   C   C   C   C   C   C   T   T    C    T\n",
      "\r\n",
      "4   C   C   C   C   C   C   C   M   C   C   C   C   C   C   A   C    C    A\n",
      "\r\n",
      "5   M   A   C   A   A   A   A   M   N   A   N   M   A   C   A   A    C    A\n",
      "\r\n",
      "6   C   C   C   C   C   C   C   C   C   C   N   Y   C   T   C   C    C    C\n",
      "\r\n",
      "  V102 V103 V104 V105 V106 V107 V108 V109 V110 V111 V112 V113 V114 V115 V116\n",
      "\r\n",
      "1  986  987  988  989  990  991  992  993  994  995  996  997  998  999 1000\n",
      "\r\n",
      "2    G    A    G    A    A    A    G    G    R    G    A    G    A    A    A\n",
      "\r\n",
      "3    C    C    C    C    T    T    C    C    Y    C    T    C    T    T    T\n",
      "\r\n",
      "4    C    C    C    C    A    A    C    C    M    C    A    C    A    A    M\n",
      "\r\n",
      "5    C    A    C    A    A    A    C    C    M    C    A    C    A    A    M\n",
      "\r\n",
      "6    T    T    T    C    C    C    T    T    Y    T    C    T    C    C    Y\n",
      "\r\n",
      "  V117 V118 V119 V120 V121 V122 V123 V124 V125 V126 V127 V128 V129 V130 V131\n",
      "\r\n",
      "1 1001 1002 1003 1004 1005 1006 1008 1009 1011 1012 1013 1014 1015 1016 1017\n",
      "\r\n",
      "2    G    R    A    A    G    A    A    A    A    A    G    R    A    G    R\n",
      "\r\n",
      "3    C    Y    T    T    C    T    T    T    T    T    C    Y    T    C    Y\n",
      "\r\n",
      "4    C    M    A    A    C    A    A    A    A    A    C    M    A    C    C\n",
      "\r\n",
      "5    C    M    A    A    C    A    A    A    C    A    C    M    A    C    C\n",
      "\r\n",
      "6    T    Y    C    C    T    C    C    C    T    C    T    C    C    T    T\n",
      "\r\n",
      "  V132 V133 V134 V135 V136 V137 V138 V139 V140 V141 V142 V143 V144 V145 V146\n",
      "\r\n",
      "1 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1030 1031 1032 1033\n",
      "\r\n",
      "2    G    G    N    G    A    G    G    G    G    G    A    A    A    A    G\n",
      "\r\n",
      "3    C    C    Y    C    T    C    C    C    C    C    T    T    T    T    C\n",
      "\r\n",
      "4    C    C    N    C    A    C    C    C    C    C    A    A    A    A    C\n",
      "\r\n",
      "5    C    C    N    C    A    C    C    C    C    C    A    A    A    A    C\n",
      "\r\n",
      "6    T    T    Y    T    C    T    T    T    T    C    C    C    C    C    T\n",
      "\r\n",
      "  V147 V148 V149 V150 V151 V152 V153 V154 V155 V156 V157 V158 V159 V160 V161\n",
      "\r\n",
      "1 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1047 1048 1049\n",
      "\r\n",
      "2    N    G    A    A    R    G    R    A    A    A    A    A    G    G    G\n",
      "\r\n",
      "3    T    C    T    T    Y    C    Y    C    C    C    C    T    C    C    C\n",
      "\r\n",
      "4    N    C    A    A    M    A    A    C    C    C    C    A    C    C    C\n",
      "\r\n",
      "5    A    C    A    A    M    C    M    A    A    A    A    A    C    C    C\n",
      "\r\n",
      "6    N    T    Y    C    Y    T    Y    Y    C    C    C    C    T    T    T\n",
      "\r\n",
      "  V162 V163 V164 V165 V166 V167 V168 V169 V170 V171 V172 V173 V174 V175 V176\n",
      "\r\n",
      "1 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064\n",
      "\r\n",
      "2    G    G    G    G    N    A    G    A    A    A    N    A    A    A    G\n",
      "\r\n",
      "3    C    C    C    C    N    C    C    T    T    T    N    T    C    C    C\n",
      "\r\n",
      "4    C    C    C    C    N    C    C    A    A    A    N    A    C    C    C\n",
      "\r\n",
      "5    C    C    C    C    N    A    C    A    A    A    N    M    A    A    C\n",
      "\r\n",
      "6    T    T    T    T    N    C    T    C    C    Y    N    Y    C    C    T\n",
      "\r\n",
      "  V177 V178 V179 V180 V181 V182 V183 V184 V185 V186 V187 V188 V189 V190 V191\n",
      "\r\n",
      "1 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1077 1078 1079 1080\n",
      "\r\n",
      "2    R    R    R    G    A    R    A    G    A    A    A    A    A    A    A\n",
      "\r\n",
      "3    Y    Y    Y    C    T    Y    T    C    T    T    T    T    T    T    T\n",
      "\r\n",
      "4    M    M    M    C    A    M    A    C    M    A    C    A    C    A    A\n",
      "\r\n",
      "5    M    M    M    C    M    M    A    C    A    A    C    A    C    A    A\n",
      "\r\n",
      "6    Y    Y    N    T    Y    Y    C    T    C    C    T    T    T    C    C\n",
      "\r\n",
      "  V192 V193 V194 V195 V196 V197 V198 V199 V200 V201 V202 V203 V204 V205 V206\n",
      "\r\n",
      "1 1081 1082 1083 1084 1085 1086 1087 1089 1090 1091 1092 1093 1094 1095 1096\n",
      "\r\n",
      "2    A    N    A    A    A    A    A    A    A    A    A    A    A    A    A\n",
      "\r\n",
      "3    T    N    T    T    T    T    N    T    C    T    C    Y    T    C    C\n",
      "\r\n",
      "4    A    N    A    A    A    A    N    A    C    A    C    N    A    C    C\n",
      "\r\n",
      "5    A    A    A    A    A    A    A    A    A    A    A    A    A    A    A\n",
      "\r\n",
      "6    C    C    C    C    C    C    C    C    C    C    C    C    C    C    C\n",
      "\r\n",
      "  V207 V208 V209 V210 V211 V212 V213 V214 V215 V216 V217 V218 V219 V220 V221\n",
      "\r\n",
      "1 1097 1098 1099 1100 1101 1102 1103 1104 1105 1106 1107 1108 1109 1110 1111\n",
      "\r\n",
      "2    A    A    A    A    R    A    A    A    A    R    G    R    A    G    A\n",
      "\r\n",
      "3    C    T    T    T    Y    T    C    C    T    Y    C    Y    T    C    T\n",
      "\r\n",
      "4    C    A    A    A    N    A    C    C    C    N    C    C    C    C    A\n",
      "\r\n",
      "5    A    A    A    A    N    A    C    A    A    A    C    C    A    C    A\n",
      "\r\n",
      "6    C    C    C    C    Y    C    T    Y    C    C    T    T    C    T    C\n",
      "\r\n",
      "  V222 V223 V224 V225 V226 V227 V228 V229 V230 V231 V232 V233 V234 V235 V236\n",
      "\r\n",
      "1 1112 1113 1115 1116 1117 1118 1119 1120 1121 1123 1124 1125 1126 1127 1128\n",
      "\r\n",
      "2    G    A    A    A    A    A    A    A    A    A    R    G    G    G    R\n",
      "\r\n",
      "3    C    T    T    C    Y    T    T    Y    C    C    Y    C    C    C    Y\n",
      "\r\n",
      "4    C    C    A    C    M    M    A    M    C    C    M    C    C    C    M\n",
      "\r\n",
      "5    C    C    A    C    M    N    A    M    C    C    M    C    C    C    M\n",
      "\r\n",
      "6    T    T    C    T    Y    Y    C    Y    T    T    Y    T    T    T    T\n",
      "\r\n",
      "  V237 V238 V239 V240 V241 V242 V243 V244 V245 V246 V247 V248 V249 V250 V251\n",
      "\r\n",
      "1 1129 1130 1131 1132 1133 1134 1135 1136 1137 1138 1139 1140 1141 1142 1143\n",
      "\r\n",
      "2    R    R    A    R    G    R    A    G    G    G    G    G    G    R    R\n",
      "\r\n",
      "3    Y    Y    T    Y    C    Y    T    C    C    C    C    C    C    Y    Y\n",
      "\r\n",
      "4    M    M    A    M    C    M    A    C    C    C    C    C    C    M    M\n",
      "\r\n",
      "5    M    M    A    M    C    M    A    C    C    C    C    C    C    M    M\n",
      "\r\n",
      "6    Y    Y    C    Y    T    Y    C    T    T    T    T    T    T    Y    Y\n",
      "\r\n",
      "  V252 V253 V254 V255 V256 V257 V258 V259 V260 V261 V262 V263 V264 V265 V266\n",
      "\r\n",
      "1 1144 1145 1146 1147 1148 1149 1150 1151 1152 1153 1154 1155 1156 1157 1158\n",
      "\r\n",
      "2    N    A    A    R    G    A    A    A    N    A    A    A    A    A    A\n",
      "\r\n",
      "3    Y    Y    C    C    C    C    T    T    C    T    C    T    T    T    T\n",
      "\r\n",
      "4    N    M    C    C    C    C    A    A    C    A    A    A    A    A    A\n",
      "\r\n",
      "5    N    A    A    M    C    A    A    A    N    A    A    A    A    A    A\n",
      "\r\n",
      "6    N    C    C    Y    T    C    C    C    Y    C    T    C    C    C    C\n",
      "\r\n",
      "  V267 V268 V269 V270 V271 V272 V273 V274 V275 V276 V277 V278 V279 V280 V281\n",
      "\r\n",
      "1 1159 1160 1161 1162 1164 1165 1166 1167 1168 1169 1170 1171 1172 1173 1174\n",
      "\r\n",
      "2    A    A    A    A    A    A    A    A    A    A    A    A    A    G    A\n",
      "\r\n",
      "3    Y    T    T    T    T    T    T    T    T    T    T    T    T    C    C\n",
      "\r\n",
      "4    A    A    A    A    A    A    A    A    A    A    A    A    C    C    C\n",
      "\r\n",
      "5    A    A    A    A    A    A    A    A    A    A    A    A    A    C    A\n",
      "\r\n",
      "6    C    C    C    C    T    T    Y    C    T    T    C    C    T    T    C\n",
      "\r\n",
      "  V282 V283 V284 V285 V286 V287 V288 V289 V290 V291   V292    V293    V294\n",
      "\r\n",
      "1 1175 1176 1177 1178 1179 1180 1181 1182 1183 1184 2012-1 2012-10 2012-11\n",
      "\r\n",
      "2    A    A    A    A    G    A    A    A    A    A      A       A       A\n",
      "\r\n",
      "3    C    T    C    C    C    T    C    T    T    T      T       C       Y\n",
      "\r\n",
      "4    C    A    C    C    C    A    C    A    A    A      A       C       M\n",
      "\r\n",
      "5    C    A    A    A    C    A    A    A    A    A      A       A       M\n",
      "\r\n",
      "6    T    C    C    C    C    Y    C    C    Y    Y      C       C       Y\n",
      "\r\n",
      "     V295    V296    V297    V298    V299    V300    V301    V302   V303\n",
      "\r\n",
      "1 2012-12 2012-13 2012-14 2012-15 2012-16 2012-17 2012-18 2012-19 2012-2\n",
      "\r\n",
      "2       A       A       A       A       A       A       A       A      A\n",
      "\r\n",
      "3       C       C       T       C       C       T       T       T      T\n",
      "\r\n",
      "4       C       N       A       C       C       A       A       A      A\n",
      "\r\n",
      "5       A       M       A       A       C       A       A       A      A\n",
      "\r\n",
      "6       C       Y       C       C       T       C       C       C      C\n",
      "\r\n",
      "     V304    V305    V306    V307    V308    V309    V310    V311    V312\n",
      "\r\n",
      "1 2012-20 2012-21 2012-22 2012-23 2012-24 2012-25 2012-26 2012-27 2012-28\n",
      "\r\n",
      "2       A       A       A       G       G       G       G       G       G\n",
      "\r\n",
      "3       T       T       T       C       C       C       C       C       C\n",
      "\r\n",
      "4       A       A       A       C       C       C       C       C       C\n",
      "\r\n",
      "5       A       A       A       C       C       C       C       C       C\n",
      "\r\n",
      "6       C       C       C       T       T       T       T       T       T\n",
      "\r\n",
      "     V313   V314    V315    V316    V317    V318    V319    V320    V321\n",
      "\r\n",
      "1 2012-29 2012-3 2012-30 2012-31 2012-32 2012-33 2012-34 2012-35 2012-36\n",
      "\r\n",
      "2       G      A       A       G       R       G       G       G       G\n",
      "\r\n",
      "3       C      T       C       C       Y       C       C       C       C\n",
      "\r\n",
      "4       C      A       C       C       M       M       C       C       C\n",
      "\r\n",
      "5       C      A       C       C       M       M       C       C       C\n",
      "\r\n",
      "6       T      C       T       T       Y       Y       T       T       T\n",
      "\r\n",
      "     V322    V323    V324   V325    V326    V327    V328    V329    V330\n",
      "\r\n",
      "1 2012-37 2012-38 2012-39 2012-4 2012-40 2012-41 2012-42 2012-43 2012-44\n",
      "\r\n",
      "2       A       A       A      A       A       G       A       A       A\n",
      "\r\n",
      "3       T       C       T      T       T       C       T       T       T\n",
      "\r\n",
      "4       A       C       A      A       C       C       A       A       A\n",
      "\r\n",
      "5       A       C       A      A       A       A       A       A       A\n",
      "\r\n",
      "6       C       T       C      C       C       C       C       C       C\n",
      "\r\n",
      "     V331    V332    V333    V334    V335   V336    V337    V338    V339\n",
      "\r\n",
      "1 2012-45 2012-46 2012-47 2012-48 2012-49 2012-5 2012-50 2012-51 2012-52\n",
      "\r\n",
      "2       A       G       G       A       A      A       A       A       A\n",
      "\r\n",
      "3       T       C       C       T       T      T       T       T       T\n",
      "\r\n",
      "4       A       C       C       A       A      A       A       A       A\n",
      "\r\n",
      "5       A       C       C       A       A      A       A       A       A\n",
      "\r\n",
      "6       C       Y       T       C       C      C       C       C       C\n",
      "\r\n",
      "     V340    V341    V342    V343    V344    V345    V346   V347    V348\n",
      "\r\n",
      "1 2012-53 2012-54 2012-55 2012-56 2012-57 2012-58 2012-59 2012-6 2012-60\n",
      "\r\n",
      "2       A       A       A       A       G       A       A      G       A\n",
      "\r\n",
      "3       T       T       T       Y       C       T       T      C       T\n",
      "\r\n",
      "4       A       A       A       M       C       A       A      C       A\n",
      "\r\n",
      "5       A       A       A       M       C       A       A      N       A\n",
      "\r\n",
      "6       C       C       C       Y       T       C       C      N       C\n",
      "\r\n",
      "     V349    V350    V351   V352    V353    V354    V355    V356    V357\n",
      "\r\n",
      "1 2012-61 2012-62 2012-63 2013-1 2013-10 2013-12 2013-13 2013-14 2013-15\n",
      "\r\n",
      "2       A       A       A      A       A       G       G       R       G\n",
      "\r\n",
      "3       T       T       T      C       T       C       C       C       C\n",
      "\r\n",
      "4       A       A       A      C       A       C       C       C       C\n",
      "\r\n",
      "5       A       A       A      C       A       C       C       C       C\n",
      "\r\n",
      "6       C       C       C      T       C       T       T       T       T\n",
      "\r\n",
      "     V358    V359    V360    V361   V362    V363    V364    V365    V366\n",
      "\r\n",
      "1 2013-16 2013-17 2013-18 2013-19 2013-2 2013-20 2013-21 2013-22 2013-23\n",
      "\r\n",
      "2       A       A       A       N      A       A       G       G       A\n",
      "\r\n",
      "3       T       T       Y       Y      C       Y       C       C       T\n",
      "\r\n",
      "4       A       A       N       M      C       C       C       C       C\n",
      "\r\n",
      "5       A       A       N       M      A       A       C       C       C\n",
      "\r\n",
      "6       C       C       N       Y      C       C       T       T       T\n",
      "\r\n",
      "     V367    V368    V369    V370    V371    V372   V373    V374    V375\n",
      "\r\n",
      "1 2013-24 2013-25 2013-26 2013-27 2013-28 2013-29 2013-3 2013-30 2013-31\n",
      "\r\n",
      "2       A       A       A       A       A       A      G       R       A\n",
      "\r\n",
      "3       T       T       T       T       Y       T      C       C       T\n",
      "\r\n",
      "4       A       A       A       A       M       A      C       M       A\n",
      "\r\n",
      "5       A       A       A       A       M       A      C       M       A\n",
      "\r\n",
      "6       C       C       C       C       Y       C      T       T       C\n",
      "\r\n",
      "     V376    V377    V378    V379    V380    V381    V382    V383   V384\n",
      "\r\n",
      "1 2013-32 2013-33 2013-34 2013-35 2013-36 2013-37 2013-38 2013-39 2013-4\n",
      "\r\n",
      "2       A       A       A       A       R       A       A       R      A\n",
      "\r\n",
      "3       T       Y       T       T       N       T       T       N      C\n",
      "\r\n",
      "4       A       M       A       A       N       A       A       M      C\n",
      "\r\n",
      "5       A       M       A       A       N       A       A       N      C\n",
      "\r\n",
      "6       C       Y       C       C       N       T       C       T      T\n",
      "\r\n",
      "     V385    V386    V387    V388    V389    V390    V391    V392    V393\n",
      "\r\n",
      "1 2013-40 2013-41 2013-42 2013-43 2013-44 2013-45 2013-46 2013-47 2013-48\n",
      "\r\n",
      "2       G       R       A       G       G       A       A       A       A\n",
      "\r\n",
      "3       C       Y       T       C       C       T       C       C       T\n",
      "\r\n",
      "4       C       M       A       C       C       A       C       C       A\n",
      "\r\n",
      "5       C       M       A       C       C       A       C       C       A\n",
      "\r\n",
      "6       T       Y       C       T       T       C       T       T       C\n",
      "\r\n",
      "     V394   V395    V396    V397    V398    V399    V400    V401    V402\n",
      "\r\n",
      "1 2013-49 2013-5 2013-50 2013-51 2013-52 2013-53 2013-54 2013-55 2013-56\n",
      "\r\n",
      "2       A      R       G       A       A       A       G       G       A\n",
      "\r\n",
      "3       C      Y       C       Y       T       T       C       C       T\n",
      "\r\n",
      "4       C      M       C       M       A       A       C       C       A\n",
      "\r\n",
      "5       A      M       C       M       A       A       C       C       A\n",
      "\r\n",
      "6       C      Y       T       Y       C       C       T       T       C\n",
      "\r\n",
      "     V403    V404    V405   V406    V407    V408    V409    V410    V411\n",
      "\r\n",
      "1 2013-57 2013-58 2013-59 2013-6 2013-60 2013-61 2013-62 2013-63 2013-64\n",
      "\r\n",
      "2       A       A       A      A       A       A       A       A       A\n",
      "\r\n",
      "3       Y       Y       C      Y       T       C       Y       T       C\n",
      "\r\n",
      "4       M       M       C      M       M       C       M       A       C\n",
      "\r\n",
      "5       M       M       C      M       A       C       M       A       C\n",
      "\r\n",
      "6       T       Y       T      Y       C       T       T       C       T\n",
      "\r\n",
      "     V412    V413   V414   V415   V416   V417    V418     V419     V420\n",
      "\r\n",
      "1 2013-65 2013-66 2013-7 2013-8 2013-9 2014-1 2014-10 2014-100 2014-101\n",
      "\r\n",
      "2       A       A      A      R      A      A       A        G        A\n",
      "\r\n",
      "3       N       C      T      Y      T      T       Y        C        C\n",
      "\r\n",
      "4       N       C      A      M      A      A       M        C        C\n",
      "\r\n",
      "5       N       C      A      M      A      A       A        C        A\n",
      "\r\n",
      "6       N       T      C      Y      C      C       C        T        C\n",
      "\r\n",
      "      V421     V422     V423     V424     V425     V426     V427     V428\n",
      "\r\n",
      "1 2014-102 2014-103 2014-104 2014-105 2014-106 2014-107 2014-108 2014-109\n",
      "\r\n",
      "2        G        G        A        R        G        A        A        A\n",
      "\r\n",
      "3        C        C        C        C        C        N        T        T\n",
      "\r\n",
      "4        C        C        C        C        C        C        C        C\n",
      "\r\n",
      "5        C        C        N        N        C        N        C        C\n",
      "\r\n",
      "6        T        T        Y        N        T        C        T        T\n",
      "\r\n",
      "     V429     V430     V431     V432     V433     V434     V435     V436\n",
      "\r\n",
      "1 2014-11 2014-110 2014-111 2014-112 2014-113 2014-114 2014-115 2014-116\n",
      "\r\n",
      "2       A        A        A        A        R        A        A        A\n",
      "\r\n",
      "3       C        T        T        T        N        T        T        T\n",
      "\r\n",
      "4       C        C        C        C        N        A        A        A\n",
      "\r\n",
      "5       A        C        C        C        N        A        A        A\n",
      "\r\n",
      "6       C        T        T        T        N        C        Y        Y\n",
      "\r\n",
      "      V437     V438     V439    V440     V441     V442     V443     V444\n",
      "\r\n",
      "1 2014-117 2014-118 2014-119 2014-12 2014-120 2014-121 2014-122 2014-123\n",
      "\r\n",
      "2        A        A        A       A        A        A        A        G\n",
      "\r\n",
      "3        T        T        T       T        T        T        T        C\n",
      "\r\n",
      "4        A        A        A       A        A        A        A        C\n",
      "\r\n",
      "5        A        A        A       A        A        A        A        C\n",
      "\r\n",
      "6        Y        N        T       C        T        C        C        T\n",
      "\r\n",
      "      V445     V446     V447     V448     V449     V450    V451     V452\n",
      "\r\n",
      "1 2014-124 2014-125 2014-126 2014-127 2014-128 2014-129 2014-13 2014-130\n",
      "\r\n",
      "2        A        G        A        A        A        A       A        A\n",
      "\r\n",
      "3        N        T        T        T        T        T       T        T\n",
      "\r\n",
      "4        N        C        A        M        M        C       A        A\n",
      "\r\n",
      "5        N        C        A        M        M        C       A        A\n",
      "\r\n",
      "6        T        C        C        Y        T        T       C        C\n",
      "\r\n",
      "      V453     V454     V455     V456     V457    V458     V459     V460\n",
      "\r\n",
      "1 2014-131 2014-132 2014-133 2014-134 2014-135 2014-14 2014-141 2014-142\n",
      "\r\n",
      "2        A        G        A        A        R       A        A        A\n",
      "\r\n",
      "3        T        C        T        C        C       C        T        Y\n",
      "\r\n",
      "4        A        C        A        C        C       A        A        M\n",
      "\r\n",
      "5        A        C        A        A        N       C        A        A\n",
      "\r\n",
      "6        C        T        C        C        N       T        C        C\n",
      "\r\n",
      "      V461     V462     V463    V464    V465    V466    V467    V468   V469\n",
      "\r\n",
      "1 2014-143 2014-144 2014-147 2014-15 2014-16 2014-17 2014-18 2014-19 2014-2\n",
      "\r\n",
      "2        A        A        A       G       A       A       A       A      A\n",
      "\r\n",
      "3        T        T        C       C       C       C       C       C      T\n",
      "\r\n",
      "4        A        A        C       C       C       C       C       C      A\n",
      "\r\n",
      "5        A        A        A       C       A       A       A       A      A\n",
      "\r\n",
      "6        C        C        C       T       C       C       C       C      C\n",
      "\r\n",
      "     V470    V471    V472    V473    V474    V475    V476    V477    V478\n",
      "\r\n",
      "1 2014-20 2014-21 2014-22 2014-23 2014-24 2014-25 2014-26 2014-27 2014-28\n",
      "\r\n",
      "2       A       A       A       N       A       A       A       A       A\n",
      "\r\n",
      "3       C       C       C       T       Y       T       T       T       T\n",
      "\r\n",
      "4       C       C       C       A       M       A       A       A       A\n",
      "\r\n",
      "5       A       A       A       A       A       A       A       A       A\n",
      "\r\n",
      "6       C       C       C       C       C       C       C       C       C\n",
      "\r\n",
      "     V479   V480    V481    V482    V483    V484    V485    V486    V487\n",
      "\r\n",
      "1 2014-29 2014-3 2014-30 2014-31 2014-32 2014-33 2014-34 2014-35 2014-36\n",
      "\r\n",
      "2       A      G       A       A       A       A       A       A       A\n",
      "\r\n",
      "3       C      C       T       C       C       C       T       C       Y\n",
      "\r\n",
      "4       C      C       A       C       C       C       A       C       M\n",
      "\r\n",
      "5       A      C       A       A       A       N       A       A       A\n",
      "\r\n",
      "6       C      T       C       C       C       Y       C       C       C\n",
      "\r\n",
      "     V488    V489    V490   V491    V492    V493    V494    V495    V496\n",
      "\r\n",
      "1 2014-37 2014-38 2014-39 2014-4 2014-40 2014-41 2014-42 2014-43 2014-44\n",
      "\r\n",
      "2       A       A       A      A       A       A       A       A       A\n",
      "\r\n",
      "3       C       T       T      T       T       T       T       C       T\n",
      "\r\n",
      "4       C       A       A      A       A       A       A       C       A\n",
      "\r\n",
      "5       A       A       A      A       A       A       A       C       A\n",
      "\r\n",
      "6       C       C       C      C       C       C       C       N       C\n",
      "\r\n",
      "     V497    V498    V499    V500   V501    V502    V503    V504    V505\n",
      "\r\n",
      "1 2014-46 2014-47 2014-48 2014-49 2014-5 2014-50 2014-51 2014-52 2014-54\n",
      "\r\n",
      "2       A       A       A       N      A       A       A       A       A\n",
      "\r\n",
      "3       C       C       Y       Y      C       T       N       T       T\n",
      "\r\n",
      "4       C       C       M       M      C       A       N       A       A\n",
      "\r\n",
      "5       A       A       A       M      A       A       A       A       A\n",
      "\r\n",
      "6       C       C       C       Y      C       C       C       C       C\n",
      "\r\n",
      "     V506    V507    V508    V509    V510   V511    V512    V513    V514\n",
      "\r\n",
      "1 2014-55 2014-56 2014-57 2014-58 2014-59 2014-6 2014-60 2014-61 2014-62\n",
      "\r\n",
      "2       A       A       A       A       A      A       A       N       G\n",
      "\r\n",
      "3       T       T       T       T       T      T       T       Y       C\n",
      "\r\n",
      "4       A       A       A       A       A      A       A       M       C\n",
      "\r\n",
      "5       A       A       A       A       A      A       A       M       C\n",
      "\r\n",
      "6       C       C       C       C       C      C       C       Y       T\n",
      "\r\n",
      "     V515    V516    V517    V518    V519    V520    V521   V522    V523\n",
      "\r\n",
      "1 2014-63 2014-64 2014-65 2014-66 2014-67 2014-68 2014-69 2014-7 2014-70\n",
      "\r\n",
      "2       A       A       R       A       A       A       A      A       G\n",
      "\r\n",
      "3       T       T       Y       T       T       T       T      C       C\n",
      "\r\n",
      "4       A       A       M       A       A       A       A      C       C\n",
      "\r\n",
      "5       A       A       M       A       A       A       A      A       C\n",
      "\r\n",
      "6       C       C       Y       C       C       Y       Y      C       T\n",
      "\r\n",
      "     V524    V525    V526    V527    V528    V529    V530    V531    V532\n",
      "\r\n",
      "1 2014-71 2014-72 2014-73 2014-74 2014-75 2014-76 2014-77 2014-78 2014-79\n",
      "\r\n",
      "2       G       A       G       A       R       A       A       A       A\n",
      "\r\n",
      "3       C       T       C       T       C       T       T       T       T\n",
      "\r\n",
      "4       C       A       C       A       C       A       A       A       A\n",
      "\r\n",
      "5       C       A       C       A       C       A       A       A       A\n",
      "\r\n",
      "6       T       C       T       C       T       C       C       C       C\n",
      "\r\n",
      "    V533    V534    V535    V536    V537    V538    V539    V540    V541\n",
      "\r\n",
      "1 2014-8 2014-80 2014-81 2014-82 2014-83 2014-84 2014-85 2014-86 2014-87\n",
      "\r\n",
      "2      A       A       A       A       A       A       A       A       A\n",
      "\r\n",
      "3      T       T       C       C       T       T       N       T       T\n",
      "\r\n",
      "4      A       A       A       A       A       A       A       A       A\n",
      "\r\n",
      "5      A       A       A       A       A       A       A       A       A\n",
      "\r\n",
      "6      C       C       C       C       C       C       C       C       C\n",
      "\r\n",
      "     V542    V543   V544    V545    V546    V547    V548    V549    V550\n",
      "\r\n",
      "1 2014-88 2014-89 2014-9 2014-90 2014-91 2014-92 2014-93 2014-94 2014-95\n",
      "\r\n",
      "2       R       N      A       R       N       A       A       A       A\n",
      "\r\n",
      "3       Y       Y      C       Y       Y       T       T       T       T\n",
      "\r\n",
      "4       M       M      C       M       M       A       A       A       A\n",
      "\r\n",
      "5       M       M      A       M       M       A       A       A       A\n",
      "\r\n",
      "6       Y       Y      C       Y       Y       C       C       C       C\n",
      "\r\n",
      "     V551    V552    V553    V554  V555   V556   V557   V558   V559   V560\n",
      "\r\n",
      "1 2014-96 2014-97 2014-98 2014-99 22DC6 DF155F DF227N DF317N E15006 E15008\n",
      "\r\n",
      "2       G       A       R       G     A      A      A      A      A      A\n",
      "\r\n",
      "3       C       C       N       C     T      T      T      T      T      T\n",
      "\r\n",
      "4       C       C       N       C     A      A      A      A      A      A\n",
      "\r\n",
      "5       C       A       N       C     A      A      A      A      A      A\n",
      "\r\n",
      "6       T       C       N       T     C      C      C      C      C      C\n",
      "\r\n",
      "    V561   V562   V563   V564   V565   V566   V567   V568   V569   V570   V571\n",
      "\r\n",
      "1 E15009 E15010 E15013 E15033 E15035 E15049 E15050 E15051 E15052 E15079 E15097\n",
      "\r\n",
      "2      A      A      A      A      A      A      A      A      A      A      A\n",
      "\r\n",
      "3      T      T      T      T      C      T      T      T      C      C      T\n",
      "\r\n",
      "4      A      A      A      A      C      A      A      A      C      C      A\n",
      "\r\n",
      "5      A      A      A      A      C      A      A      A      A      A      A\n",
      "\r\n",
      "6      C      C      C      C      T      C      C      C      C      C      C\n",
      "\r\n",
      "    V572   V573   V574   V575   V576   V577   V578   V579   V580   V581   V582\n",
      "\r\n",
      "1 E15115 E15132 E15137 E15139 E15146 E15149 E15160 E15165 E15181 E15187 E15195\n",
      "\r\n",
      "2      A      A      A      A      A      A      A      A      A      G      A\n",
      "\r\n",
      "3      T      T      C      C      C      C      T      C      T      C      C\n",
      "\r\n",
      "4      A      A      C      C      C      C      A      C      A      C      C\n",
      "\r\n",
      "5      A      A      A      A      A      A      A      A      A      C      C\n",
      "\r\n",
      "6      C      C      C      C      C      C      C      C      C      C      T\n",
      "\r\n",
      "    V583   V584   V585   V586   V587   V588   V589   V590   V591   V592   V593\n",
      "\r\n",
      "1 E15209 E15214 E15217 E15220 E15223 E15231 E15238 E15242 E15245 E15249 E15294\n",
      "\r\n",
      "2      A      A      A      G      G      G      G      G      G      G      A\n",
      "\r\n",
      "3      T      T      T      C      C      C      C      C      C      C      T\n",
      "\r\n",
      "4      A      A      A      C      C      C      C      C      C      C      A\n",
      "\r\n",
      "5      A      A      A      C      C      C      C      C      C      C      A\n",
      "\r\n",
      "6      C      C      C      T      T      T      T      T      T      T      C\n",
      "\r\n",
      "    V594   V595   V596   V597   V598   V599   V600   V601   V602   V603   V604\n",
      "\r\n",
      "1 E15299 E15300 E15301 E15307 E15309 E15316 E15320 E15322 E15323 E15324 E15325\n",
      "\r\n",
      "2      G      A      A      A      G      G      A      A      G      A      G\n",
      "\r\n",
      "3      C      T      T      T      C      C      T      T      C      T      C\n",
      "\r\n",
      "4      C      A      A      A      C      C      A      A      C      A      C\n",
      "\r\n",
      "5      C      A      A      A      C      C      A      A      C      A      C\n",
      "\r\n",
      "6      T      C      C      C      T      T      C      T      T      T      T\n",
      "\r\n",
      "    V605   V606   V607   V608   V609   V610   V611   V612   V613   V614   V615\n",
      "\r\n",
      "1 E15328 E15336 E15337 E15338 E15339 E15345 E15346 E15347 E15349 E15350 E15351\n",
      "\r\n",
      "2      A      G      A      A      G      R      A      A      A      A      A\n",
      "\r\n",
      "3      T      C      T      T      C      Y      T      T      T      T      T\n",
      "\r\n",
      "4      A      C      A      A      C      M      A      C      C      A      M\n",
      "\r\n",
      "5      A      C      A      A      C      M      A      C      C      A      M\n",
      "\r\n",
      "6      C      T      C      C      T      T      C      T      T      C      Y\n",
      "\r\n",
      "    V616   V617   V618   V619   V620   V621   V622   V623   V624   V625   V626\n",
      "\r\n",
      "1 E15368 E15369 E15370 E15372 E15380 E15387 E15389 E15390 E15392 E15393 E15394\n",
      "\r\n",
      "2      A      A      A      A      A      A      A      A      A      A      A\n",
      "\r\n",
      "3      C      T      C      Y      T      T      T      T      T      T      T\n",
      "\r\n",
      "4      C      A      C      M      A      A      A      A      A      C      A\n",
      "\r\n",
      "5      C      A      C      M      A      A      A      A      A      C      A\n",
      "\r\n",
      "6      T      C      T      Y      C      C      C      C      C      T      C\n",
      "\r\n",
      "    V627   V628   V629   V630   V631   V632   V633   V634   V635   V636   V637\n",
      "\r\n",
      "1 E15396 E15398 E16005 E16025 E16026 E16030 E16031 E16036 E16044 E16083 E16099\n",
      "\r\n",
      "2      A      A      A      G      A      A      A      G      A      G      A\n",
      "\r\n",
      "3      T      T      C      C      C      C      C      C      C      C      T\n",
      "\r\n",
      "4      A      A      C      C      C      C      C      C      C      C      A\n",
      "\r\n",
      "5      A      A      C      C      C      C      C      C      C      C      A\n",
      "\r\n",
      "6      C      C      C      T      T      T      T      T      C      T      C\n",
      "\r\n",
      "    V638   V639   V640   V641   V642   V643   V644   V645   V646   V647   V648\n",
      "\r\n",
      "1 E16109 E16113 E16114 E16115 E16138 E16141 E16144 E16149 E16168 E16184 E16186\n",
      "\r\n",
      "2      A      G      G      A      A      A      A      A      G      A      A\n",
      "\r\n",
      "3      T      C      C      T      T      T      T      T      C      T      T\n",
      "\r\n",
      "4      A      C      C      A      A      A      A      A      A      A      A\n",
      "\r\n",
      "5      A      C      C      A      A      A      A      A      A      A      A\n",
      "\r\n",
      "6      C      T      T      C      C      C      C      C      C      C      C\n",
      "\r\n",
      "    V649   V650   V651   V652   V653   V654   V655   V656   V657   V658   V659\n",
      "\r\n",
      "1 E16188 E16189 E16191 E16204 E16214 E16215 E16221 E16232 E16250 E16253 E16254\n",
      "\r\n",
      "2      A      A      A      A      A      A      G      A      A      A      A\n",
      "\r\n",
      "3      T      T      T      T      T      T      C      T      T      T      T\n",
      "\r\n",
      "4      A      A      A      A      A      A      C      A      A      A      A\n",
      "\r\n",
      "5      A      A      A      A      A      A      C      A      A      A      A\n",
      "\r\n",
      "6      C      C      T      C      T      T      T      C      C      C      C\n",
      "\r\n",
      "    V660   V661   V662   V663   V664   V665   V666   V667   V668   V669   V670\n",
      "\r\n",
      "1 E16265 E16266 E16267 E16268 E16280 E16289 E16291 E16293 E16304 E16305 E16342\n",
      "\r\n",
      "2      A      G      R      G      G      A      A      A      A      A      A\n",
      "\r\n",
      "3      T      C      Y      C      C      C      T      T      T      C      T\n",
      "\r\n",
      "4      A      C      C      C      C      C      A      A      A      C      A\n",
      "\r\n",
      "5      A      C      C      C      C      A      A      A      A      A      A\n",
      "\r\n",
      "6      C      T      T      T      Y      C      C      C      C      C      Y\n",
      "\r\n",
      "    V671   V672   V673   V674   V675   V676   V677   V678   V679   V680   V681\n",
      "\r\n",
      "1 E16346 E16379 E16380 E16381 E16387 E16398 E16400 E16410 E16411 E16412 E16418\n",
      "\r\n",
      "2      G      G      G      A      A      A      A      G      A      A      A\n",
      "\r\n",
      "3      C      C      C      T      T      C      C      C      C      C      C\n",
      "\r\n",
      "4      C      C      C      A      A      C      C      C      C      C      C\n",
      "\r\n",
      "5      C      A      C      A      A      A      A      C      A      A      A\n",
      "\r\n",
      "6      T      C      T      C      C      C      C      T      C      C      C\n",
      "\r\n",
      "    V682   V683   V684   V685   V686   V687       V688         V689       V690\n",
      "\r\n",
      "1 E16439 E16447 E16804 E16805 E16806 E16807 E16822gray E16822tawney E16824gray\n",
      "\r\n",
      "2      A      A      A      A      A      A          A            A          A\n",
      "\r\n",
      "3      C      T      T      T      T      T          T            T          T\n",
      "\r\n",
      "4      C      A      A      A      A      A          A            A          A\n",
      "\r\n",
      "5      A      A      A      A      A      A          A            A          A\n",
      "\r\n",
      "6      C      C      C      C      C      C          C            C          C\n",
      "\r\n",
      "          V691       V692         V693       V694         V695   V696   V697\n",
      "\r\n",
      "1 E16824tawney E16827gray E16827tawney E16829gray E16829tawney E16830 E17509\n",
      "\r\n",
      "2            A          A            A          A            A      A      A\n",
      "\r\n",
      "3            T          T            T          T            T      T      T\n",
      "\r\n",
      "4            A          A            A          A            A      A      C\n",
      "\r\n",
      "5            A          A            A          A            A      A      C\n",
      "\r\n",
      "6            C          C            C          C            C      C      T\n",
      "\r\n",
      "    V698   V699   V700    V701      V702      V703\n",
      "\r\n",
      "1 E17512 E17524 E17812 GL2765N ZFS1420LS ZFS1528LS\n",
      "\r\n",
      "2      A      A      A       A         A         A\n",
      "\r\n",
      "3      T      T      T       C         T         T\n",
      "\r\n",
      "4      C      C      C       C         A         A\n",
      "\r\n",
      "5      C      C      C       A         A         A\n",
      "\r\n",
      "6      T      T      T       C         C         C\n",
      "\n"
     ]
    }
   ],
   "source": [
    "print(rdata.head())"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [],
   "source": [
    "r_df=transfunc(rdata)\n",
    "## After runing this function, a csv file with correct data format will be created."
   ]
  },
  {
   "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"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}