#### Per line ####
my $ptt_file="/g/Viruses/prophage_data/prophage_region.ptt1";
open ($fh, '<', $ppt_file);

## precompile a regex to capture the geneid on each line
## I assume the gene id is the first thing on each line
my $gene_id;
my $rx_find_geneid = qr/^(\w+) (?{ $gene_id = $1; })/x;

## I prefer to avoid $_ for clarity
my $saved_lines = '';
while (my $line = <$fh>)
{
  ## run precompiled regex
  $line =~ /$rx_find_geneid/;
  
  ## check to see if it exists in the hash
  ## if not, save it
  if (! exists $geneids_to_remove->{$gene_id})
  {
    $saved_lines .= $line;
  }    
}
close ($fh);