#!/usr/bin/perl

#=================================
#Script to split fasta file based on text file of sequence ids.
#Questions/commments to brian oakley at ars.usda dot gov
#k.purdy at warwick.ac dot uk
#=================================

use Bio::DB::Fasta;

my $usage = "\nUsage:  $0 fastafile textfile\n\n";

my $fastaFile = $ARGV[0] or die $usage;
chomp (my $queryFile = $ARGV[1]);


my $db = Bio::DB::Fasta->new( $fastaFile );
open (IN, $queryFile);
while (<IN>){
    chomp; 
    $seq = $_;
    my $sequence = $db->seq($seq);
    if  (defined( $sequence )) {
    print ">$seq\n", "$sequence\n";
    }
    
    if  (!defined( $sequence )) {
    open (OUT, ">>seqs_not_found.txt");
    print (OUT $seq,"\n");
    }
    
    
}