#!/usr/bin/perl

use strict;
use warnings;
use Bio::Seq;
use Bio::SeqIO;

my $uniqueFile = $ARGV[0];
my $goodProteinsFile = $ARGV[1];

## imports a bunch of gene IDs 
open (FILE, $uniqueFile);
my @data_in = <FILE>;
close FILE;

## create lookup hash; key = ID, val = sequence
my %goodProteins_hash;
my $in = Bio::SeqIO->new(-file=>$goodProteinsFile, -format=>'Fasta');
while (my $seq = $in -> next_seq() ) {
  my $id = $seq -> display_id();
  my $seq_string = $seq -> seq();
  $goodProteins_hash{$id} = $seq_string;
}

my $file_out = "strainSpecific_seqData.protein.fasta";

## iterate thru @data_in; if $id eq $_ then get at the value in 
## %goodProteins hash and store it in %strSpec... takes a while!
my %strSpec;
foreach (@data_in) {  
  chomp ($_);
  while (my ($id, $seq) = each %goodProteins_hash) {  
    if ($_ =~ /($id)$/) {  
      $strSpec_protein_hash{$id} = $seq;
    }
  }   
}

open (OUT, ">strainSpecific_seqData.protein.fasta");
while (my ($k, $v) = each %strSpec) {  ## print to file
  print OUT "\>$k\n$v\n";
}    
close OUT;
print "- Finished\n";