#!/usr/bin/perl
use Bio::SeqIO;

#=================================
#Script to remove sequences with redundant names from fasta files
#briandotoakleyatarsdotusdadotgov
#k.purdy at warwick.ac dot uk
#=================================

my $usage = "\nusage: $0 filename\n\n";
my $input_file = $ARGV[0] or die $usage;


#---Open output files----
$out_file = Bio::SeqIO->new(-file => ">uniq_seqs.fas",-format => 'fasta');

#----Read in list of all sequences------
my $seq_in  = Bio::SeqIO->new( -format => 'fasta',-file => $input_file);

#---push into array for next step--------
while ($seq_obj = $seq_in->next_seq()) {
push (@all_seqs, $seq_obj);
}

#----reduce list to unique values if any duplicates exist----
my %seen = ();
	foreach $seq(@all_seqs) {
	push(@uniq_seqs, $seq) unless $seen{$seq->id()}++;
	}


#----print out sequences------

foreach $seq(@uniq_seqs) {
	$out_file->write_seq($seq);
}

print "\nDone.   Sequences written to 'uniq_seqs.fas'\n\n";