Shell Programming and Scripting

- C1 C2 C3 C4 C5
R1 AA AA - - CC
R2 AC AA AA CC CC
R3 AT AT TT TT TT
R5 AT TT AA AA AA

- C1 C2 C3 C4 C5
R1 1 1 0 0 -1
R2 0 1 1 -1 -1
R3 0 0 1 1 1
R5 0 -1 1 1 1

awk 'NR>1{ for (i=2;i<=NF;i++) { if ( substr($i,1,1)==substr($i,2) ) {x[i]++ ; for (c in x ) { if ( c > max ) c=max ; else if ( c < max ) max2=c } else $i="0"} END {print max, max2}' file

- C1 C2 C3 C4 C5
R1 1 1 0 0 -1
R2 -1 1 1 1 1
R3 -1 -1 1 1 1
R5 -1 -1 1 1 1

R2 AC AA AA CC CC

R2 0 1 1 -1 -1

R2 0 -1 -1 1 1

R3 AT AT TT TT TT

R3 0 0 1 1 1

function quicksort(data, left, right,    i, last)
{
    if (left >= right)  # do nothing if array contains fewer
        return          # than two elements

    quicksort_swap(data, left, int((left + right) / 2))
    last = left
    for (i = left + 1; i <= right; i++)
        if (count[data[i]]<count[data[left]])
            quicksort_swap(data, ++last, i)
    quicksort_swap(data, left, last)
    quicksort(data, left, last - 1, less_than)
    quicksort(data, last + 1, right, less_than)
}

# quicksort_swap --- helper function for quicksort, should really be inline

function quicksort_swap(data, i, j, temp)
{
    temp = data[i]
    data[i] = data[j]
    data[j] = temp
}
BEGIN {
   split("AA,TT,GG,CC", tA,",")
   for(i=1;i in tA;i++)
     goodA[tA[i]]
}

FNR==1 {print;next}
{
  split("",arr)
  split("",count)
  tally=0
  for(i=2;i<=NF;i++) {
    if (!($i in goodA)) continue
    if (!($i in count)) arr[++tally]=$i
    count[$i]++
  }
  quicksort(arr,1,tally)
  printf $1
  for(i=2;i<=NF;i++) {
    if ($i == arr[tally])
      $i=1
    else if ($i == arr[tally-1])
           $i=-1
         else $i=0
    printf("%s%d%s", OFS, $i, (i==NF)?ORS:"")
  }
}

- C1 C2 C3 C4 C5
R1 1 1 0 0 -1
R2 0 -1 -1 1 1
R3 0 0 1 1 1
R5 0 -1 1 1 1

awk '
  BEGIN {
    A["AA"]; A["CC"]; A["GG"]; A["TT"]
  } 
  NR>1 { 
    minkey=""; max=0
    for(i=2; i<=NF; i++) if($i in A) {
      A[$i]++
      if(max<A[$i]) {
        max=A[$i]
        maxkey=$i
      }
    }
    for(i in A) {
      if(i!=maxkey && !minkey && A[i]>0) minkey=i
      A[i]=""
    }
    for(i=2; i<=NF; i++) $i=($i==minkey)?-1:($i==maxkey)?1:0
  }
  1
' file

- C1 C2 C3 C4 C5
R1 1 1 0 0 -1
R2 0 1 1 -1 -1
R3 0 0 1 1 1
R5 0 -1 1 1 1

R1 AA AA AA AA - - CC CC TT TT TT

R1 1 1 1 1 0 0 -1 -1 0 0 0

awk '
BEGIN   {A["AA"]; A["CC"]; A["GG"]; A["TT"] }

NR>1    {mx2key=""; max=max2=0
         for(i=2; i<=NF; i++) if ($i in A) { A[$i]++ }
         for (i in A)   {if(max<A[i])   {max2=max
                                         mx2key=maxkey
                                         max=A[i]
                                         maxkey=i
                                        }
                         else if (max2<A[i])    {max2=A[i]; mx2key=i}
                         A[i]=""
                        }
         for (i=2; i<=NF; i++) $i=($i==mx2key)?-1:($i==maxkey)?1:0
        }
 
1
' file

R1 1 1 1 1 0 0 0 0 -1 -1 -1