BOL: Perl script to remove the duplicate sequences from multifasta file

BioScripts
Bulbul
Perl script to remove the duplicate sequences from multifasta file

Perl script to remove the duplicate sequences from multifasta file

By Bulbul 2679 days ago

use strict;
use Bio::SeqIO;
my %unique;

my $file   = "myseqs.fa";
my $seqio  = Bio::SeqIO->new(-file => $file, -format => "fasta");
my $outseq = Bio::SeqIO->new(-file => ">$file.uniq", -format => "fasta");

while(my $seqs = $seqio->next_seq) {
  my $id  = $seqs->display_id;
  my $seq = $seqs->seq;
  unless(exists($unique{$seq})) {
    $outseq->write_seq($seqs);
    $unique{$seq} +=1;
  }
}