# always start your program with these two lines.
# The do a lot of your error checking for you and are
# more accurate than your eyeballs.
use strict;
use warnings;

#-----------------------------------------
# store counts in a hash of array references.
# - There is one hash key for each DNA base
# - The value assigned to each hash key is an array
#   reference. Its Nth element stores the number of times
#   that base appears at the Nth position.
#   (N=0 is first position)
#-----------------------------------------
my %hFrequency;
my @aTotalAtPos;
my $iMaxSequenceLength = 0;
my $sBase;
my $iPos;

# <DATA> Reads in one line of data from the stream DATA.
# see below at __DATA__ for the actual data

while (my $sSequence = <DATA>){

  #remove end of record marker, i.e. newline, from sequence
  chomp $sSequence;

  # regex // can be used to split a string into characters
  my @aBases = split(//, $sSequence);

  # keep track of maximum sequence length: we'll need it
  # later to print out the matrix

  my $iSequenceLength = scalar(@aBases);
  if ($iSequenceLength > $iMaxSequenceLength) {
    $iMaxSequenceLength = $iSequenceLength;
  }

  # up the count for each base/position found
  for($iPos=0; $iPos <= $#aBases; $iPos++) {

    $sBase = $aBases[$iPos]; #current char
    $hFrequency{$sBase}[$iPos] ++;
    $aTotalAtPos[$iPos]++;
  }
}

#-----------------------------------------
# print the matrix
# done with sprintf, but you might prefer
# to use standard Perl formatting.
#-----------------------------------------

# use a constant so we make sure we have the
# same format for the base column each time
# we print out a row

my $BASE_FORMAT = "%4s |";

# use a constant so we make sure we have the
# same width each time we print out a row

my $POS_WIDTH = 5;

# print out header

print sprintf($BASE_FORMAT, 'Base');  #label row
for($iPos=0; $iPos < $iMaxSequenceLength; $iPos++) {
  print sprintf("%${POS_WIDTH}d |", $iPos);
}
print "\n";  #end row

# print out divider bar below header

print '---- |';  #label row
for($iPos=0; $iPos < $iMaxSequenceLength; $iPos++) {
  print (('-' x $POS_WIDTH) . ' |');
}
print "\n";  #end row

# print out one row for each base

foreach $sBase (sort keys %hFrequency) {
  my $aCounts = $hFrequency{$sBase};

  print sprintf($BASE_FORMAT, $sBase);  #label row
  # $aCounts is an array reference
  # @$aCounts extracts the array

  for($iPos=0; $iPos < $iMaxSequenceLength; $iPos++) {
    my $iCount = $aCounts->[$iPos];
    my $iTotal = $aTotalAtPos[$iPos];
    $iCount = 0 unless defined($iCount);
    my $dPct = $iTotal ? $iCount/$iTotal : 0;
     print sprintf("%-$POS_WIDTH.2f |", $dPct);
  }
  print "\n";  #end row
}

# This is a quick way to put in some test data
# To read it in you use data as a file handle
# see above for an example

__DATA__
ACCGT
AGCCG
CATTC
GTAAA