https://bioinformaticsonline.com/snippets/owner/bulbul? https://bioinformaticsonline.com/snippets/view/30354/perl-script-to-remove-the-duplicate-sequences-from-multifasta-file Fri, 23 Dec 2016 08:47:47 -0600 https://bioinformaticsonline.com/snippets/view/30354/perl-script-to-remove-the-duplicate-sequences-from-multifasta-file 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; } }]]> Bulbul