find_identical_fasta.pl

#! /usr/bin/perl
use strict; use warnings;

# This script will find identical fasta sequences with different
# identifiers and output them into a new file in the form of 
# (id1|id2). All of the other fasta entries will output as is
# Example:
# >id1
# ATTCGGTCC
# >id2
# AAAGGGTTTCCC
# >id3
# ATTCGGTCC
# Will be output as:
# # >id1|id3
# ATTCGGTCC
# >id2
# AAAGGGTTTCCC

my $fasta = shift or die "Please provide valid fasta file!\n";

my %fasta_hash = ();

open( my $fasta_fh, "<", $fasta ) or die "Cannot open file: $!\n";
while( <$fasta_fh> ) 
{
    chomp;
    if ( $_ =~ m/^>(.+)/ ) 
    {
        $fasta_hash{$1} = ();
    }
    else 
    {
        $fasta_hash{$1} = $_;
    }
}


my %reverse = ();
while ( my ($key, $value) = each %fasta_hash ) 
{
    push( @{$reverse{$value}}, $key );
}

for ( keys %reverse ) 
{
    print ">", join( '|', @{ $reverse{$_} } ) , "\n";
    print "$_\n";
}