Trim seq

1. ! /usr/bin/perl -w
2. *************************************************************
3. This Programme does the following in sequence
4. -> Parses a multi fasta
5. -> Removes the sequences that has less than 250 bases in size
6. -> Removes the sequence if they have >20% of N
7. -> Capture the results

1. Author: Rajkumar (itc@rajkumar.in)

1. *************************************************************

1. Libraries

use strict; use Bio::Perl; use Bio::SeqIO;

1. Variables

my $path = "/home/raj/bio"; my $multifasta = "$path/tobacco/data/singlet.fa";

1. making several Fasta files of GDNA

my $in = Bio::SeqIO->new(-file => "$multifasta", -format => 'Fasta'); my $identifier; my $sequence;

while ( my $seq = $in->next_seq() ) { $identifier = $seq->id;

 		$sequence = $seq->seq;

my ($fasta) = $_; $fasta = ">$identifier\n$sequence\n";

my $count_seq = length($sequence); my $count_N = ($sequence =~ tr/N//);

 		my $math = $count_seq * 0.2;

if ($count_seq > 250){ next; } if ($count_N > $math){ next; }

print $fasta;

}

1. END