subset_random_seq.pl

#!/usr/bin/env perl

use strict;
use warnings;

my $usage = "Usage: $0 <infile.fa> <number> <length>\n";
my $fasta = shift or die $usage;
my $num = shift or die $usage;
my $len = shift or die $usage;

my $seq = '';
open(IN,'<',$fasta) || die "Could not open $fasta: $!\n";
while(<IN>){
   chomp;
   next if /^>/;
   $seq .= $_;
}
close(IN);

my $seq_len = length($seq);
my $limit = $seq_len - $len + 1;

if ($len > $seq_len){
   die "Your read length is longer than the input sequence\n";
}

my $fake_qual = 'B' x $len;

for (1 .. $num){
   my $random_start = int(rand($limit));
   my $substring = substr($seq,$random_start,$len);
   my $pos = $random_start + 1;
   print "\@$_:$pos\n$substring\n+\n$fake_qual\n";
}

exit(0);