filter_by_length.pl

#! /usr/bin/perl

# This script will extract a subset of fasta or fastq reads
# in a specified size range and save them to file

use strict; use warnings;

use Bio::SeqIO;
use Number::Range;
use Getopt::Long;

my $infile; # input file
my $outfile; # output file
my $format; #file format
my $help; # print help
my $min; # minimum length
my $max; # maximum length


if ( @ARGV != 10 || defined($help) ) 
{
	die <<END;
	####################################################
	This script prints out sequences of specified 
        length and their ids in fasta format for any bioperl 
        object containing primary sequence        
	####################################################
	USAGE:
	perl filter_by_length.pl --in-file <file_name> --out-file <file_name> --format <file_format> --min <INT> --max <INT>
END
} 


GetOptions(
            'in-file=s'  => \$infile,
            'out-file=s' => \$outfile,
            'format=s'   => \$format,
            'min=i'      => \$min,
            'max=i'      => \$max,
            'help'       => \$help,
) or die "Incorrect usage!\n$help\n";


my $in_seq = Bio::SeqIO->new(-file => "<$infile",
                             -format => $format,
                            );

my $seq_out = Bio::SeqIO->new(
                              -file   => ">$outfile",
                              -format => $format,
                              );

while ( my $seq = $in_seq->next_seq ) 
{
	my $length = $seq->length;
	if ( $length >= $min && $length <= $max ) 
        {
             $seq_out->write_seq($seq);
        }
}