So I'm working with a kmer project and I needed to generate a 4**21 by 197 matrix to record the information I need for each kmer since I'm doing 21mer right now. However, it shows out of memory when I try to generate the matrix. Is there any way I can get around with it?

Here is the script I wrote:

#!/usr/bin/perl
use strict;
use warnings;


#initialize matrix
my @matrix;
my $i; #column
my $j; #roll
my @sum;
for ($i=0; $i<197; $i++){
        for ($j=0; $j<4**21; $j++){
                $matrix[$i][$j]=0;
        if($i==0)
        {
            $sum[$j]=0;
            }
    }
}

#inport file names
my $fn = $ARGV[0];
chomp $fn;
unless (open(FILE, $fn)){
        print "Can't open file \"$fn\"\n\n";
        exit;
}

chomp(my @line = <FILE>);
my $n;

for ($n=0; $n<scalar @line; $n++){

#open each kmer file
        unless (open(KMER, $line[$n])){
                print "Can't open file \"$line[$n]\"\n\n";
                exit;
        }
        my @kmers = <KMER>;
        my @all_kmer;
        my $kmer;
        foreach $kmer (@kmers){
                my @split = split(/\s+/,$kmer); #obtain kmer reference
+ number
                $matrix[$n][$split[0]] = 1; 
                #print OUT "$matrix[$n][$split[0]]\t";
                $sum[$split[0]]=$sum[$split[0]]+1;
                
        }
        close $line[$n];
}
close $fn;

#creat outfile
my $outfile = $ARGV[1];
unless(open OUT, '>' .$outfile){
    die "\nUnable to create $outfile\n";
}


#sum up
for ($j=0; $j<4**21; $j++){

                print OUT "$sum[$j]\n";

}
[download]