format_silva_fasta_db.pl

#!/usr/bin/env perl


# The silva database has spaces between ever ten bases and there are U's
# where the T's are supposed to be.  This script fixes those two problems.

use strict;
use warnings;
use BioUtils::FastaIO;
use BioUtils::FastaSeq;

my $usage = "$0 <fasta_file> <output file>\n";

my $fasta_file = shift or die $usage;
my $out_file = shift or die $usage;


# create the fasta IO objects
my $in = BioUtils::FastaIO->new({stream_type => '<', file => $fasta_file});
my $out = BioUtils::FastaIO->new({stream_type => '>', file => $out_file});

# read in the sequences
while ( my $seq = $in->get_next_seq() ) { 
    my $temp_seq = $seq->get_seq();
    $temp_seq =~ tr/U/T/;
    $temp_seq =~ s/ //g;
    $seq->set_seq($temp_seq);
    
    # output the formated sequence
    $out->write_seq($seq);
}