Shell Programming and Scripting

var1 var2 var3 var4 var5 var6....
A G A T G T
G A A A A A
A A A A A A
G A G T A T

[root@node3 ~]# cat infile 
var1 var2 var3 var4 var5 var6
A G A T G T
G A A A A A
A A A A A A
G A G T A T
[root@node3 ~]# cat matrix_transpose 
#!/bin/bash

transpose() 
{ 
  awk ' 
      { 
         if (max_nf<NF) 
             max_nf=NF 
         max_nr=NR 
         for(x=1; x<=NF; ++x) 
             matrix[x, NR]=$x 
      } 
END   { 
         for (x=1; x<=max_nf; ++x) { 
              for (y=1; y<=max_nr; ++y) 
                   printf("%s ", matrix[x, y]) 
              printf("\n") 
         } 
      }' ${1} 
} 

transpose ${1} | \
awk   '
      {
         ++a[$2FS$3FS$4FS$5]
         b[$2FS$3FS$4FS$5]=b[$2FS$3FS$4FS$5]FS$1
      }
END   {
         for(i in a) 
            if(a[i]>1) 
               print b[i]
      }' 
[root@node3 ~]# bash matrix_transpose infile 
 var2 var5
 var4 var6

$ cat file1.txt
var1 var2 var3 var4 var5 var6
A G A T G T
G A A A A A
A A A A A A
G A G T A T

$ awk 'NR == 1 {
               split($0, var, FS)
               next
       }

       {
               for (x = 1; x < NF; x++)
                       for (y = x + 1; y <= NF; y++)
                               if ($x == $y)
                                       cnt[x, y]++
       }

       END {
               tot = NR - 1
               for (x = 1; x < NF; x++)
                       for (y = x + 1; y <= NF; y++)
                               if (cnt[x, y] >= perc / 100 * tot)
                                       print var[x], var[y]

       } '  perc=95 file1.txt > file2.txt

$ cat file2.txt
var2 var5
var4 var6

$