Shell Programming and Scripting

       ind1   ind2  ind3  ind4  ind5  ind6
rs1    AA    AG    GG    GA   AA    GG
rs2    CT    TT    TT    --    CC    TC
rs3    AG    AA    --    GG    GA    GA
rs4    TT    CT    --    TT    TC    --
rs5    GG    --    GA    AA    GG    AG
rs6    CG    CG    CC    GG    --    GC

ind1 A A C T A G T T G G C G
ind2 A G T T A A C T 0 0 C G
ind3 G G T T 0 0 0 0 G A C C
ind4 G A 0 0 G G T T A A G G
ind5 A A C C G A T C G G 0 0
ind6 G G T C G A 0 0 A G G C

nawk '{for(i=1;i<=NF;i++) if(NR==1) A[i]=$i" ";else B[i-1]=B[i-1]$i}
      END{for(i=1;i<=NF-1;i++) {gsub(/./,"& ",B[i]); print A[i],B[i]}}' infile

#!/bin/ksh

#set -x

typeset TEMP=.tmp.$$.dat

function transpose_file
{
#set -x
  typeset file=$1
  typeset -Z3 i=0  ## -Zn, n is the order of maximum number of columns. So if n is 3 here, max number of columns can be only 999

  cat $file | while read -A fields
  do
    fld_cnt=${#fields[@]}	## Number of fields in the current record
    for ((i=0 ; i< ${fld_cnt} ; i++))
    do
      ## Print the value of every field in a separate file
      ## You can tweak the value here, before printing it out to the file
      print -n -R "${fields[i]} " >> ${TEMP}.$i
    done
  done

  ## Append a newline to each of the temp files (here is an assumption that number of fields is same for each record)
  for ((i=0 ; i< ${fld_cnt} ; i++))
  do
    print >> ${TEMP}.$i
  done
  
  ## cat all the temp files together
  cat ${TEMP}.*

  rm ${TEMP}.*
}


file=${1:-input.dat}
output=${2:-output.dat}

transpose_file $file > $output

ind1 A 
ind1 A 
ind1 C 
ind1 T 
ind1 A 
ind1 G 
...
ind2 A 
ind2 G 
ind2 T
ind2 T 
...
indN G
indN G 
indN T 
indN T
...

KEY:ind1 
A 
A 
C 
T 
A 
G 
...
KEY:indN
G
G 
T 
T
...