docParser.pm 
 
package docParser; 
use strict; 
 
sub new { 
  my $class = shift; 
  my $self = bless {}, $class; 
  my $seqname=shift; 
  my $sequence=shift; 
  $self->{_seqname}=$seqname; 
  $self->{_sequence}=$sequence; 
  return $self; 
} 
 
sub CAG_count { 
  my ($self)=shift; 
  my $seqname=$self->{_seqname}; 
  my $sequence=$self->{_sequence}; 
  my $count_of_CAG=0; 
 
   my @seq=split(//,$sequence); 
   my $aa=''; 
  
  my @position; 
  my $len; 
  my $amino_acid_number; 
  for (my $index=0; $index<$#seq-2; $index+=3) { 
  
    if ($sequence=~m/((CAG){6,})/g){ 
      $count_of_CAG++; 
      @position=index($sequence,$1); 
        $len=length($1)/3; 
             $amino_acid_number=shift(@position); 
    } 
  } 
        print "For the sequence ".$seqname." we found a CAG string "; 
        print "with $len\n repeats "; 
     
  print "at amino acid number ".$amino_acid_number."\n\n"; 
       
      if ($len<35) 
      { 
        print "Risk Evaluation:  Normal"."\n\n"; 
     
      } 
      elsif ($len>36||$len<48) 
      { 
        print "Risk Evaluation:  Warning"."\n\n"; 
      } 
      elsif ($len>48) 
      { 
        print "Risk Evaluation: Dangerous"."\n\n"; 
      } 
  } 
1;