Shell Programming and Scripting

use strict;
use warnings;

### open the FILEA
(open my $FILEA,"<","FILEA.txt") || die "could not open FILEA file";

### open an output file
(open my $OUT,">","FILEB.txt") || die "could not open output file";


### go through the file, line by line
while(<$FILEA>)
{
   chomp;    ### to get rid of carriage returns at the end of each line
   
   #### contents of each line are stored in a variable called $_ , which does not need to be indicated for many of the function calls below
   next if(/^#/);     #### skips any lines that being with #
   my @f=split /\t/;  #### splits the line on the tab characters, storing each part in an array called @f with n elements numbered 0 to n-1 
   
   my $chrom=$f[0];   #### Type is the 0th element
   my $start=$f[3];   #### start is the 3rd element
   my $stop=$f[4];    #### stop is the 4th element
   my $strand=$f[6];  #### strand is the 6th element
   my $name=$f[8];    #### names 
   
   print "$name\n";   ### print the name to the terminal window (STDOUT)
   
   #### will use the program "fastacmd" to extract values from the database "NMR_DATA" stored in a subdirectory here
   #### the program fastacmd should be in the same directory as this script
   
   ### fastacmd refers to strand as either 1 or 2 (+ or -).  
   ### this line checks if strand is "+".  if it is then strandnum is set to 1.  if it is not then strandnum is set to 2
   my $strandnum=($strand eq "+") ? 1 : 2;  
   
   #### prepare the command
   #### arguments to fastacmd
   #### -d database
   #### -p Type, F=nucleotide
   #### -s search string in header, here we use the chromosome in the form chrX
   #### -L start,stop positions
   #### -S strandnum
   
   my $command="fastacmd.exe -d NMR_DATA/NMR_DATA -p F -s $chrom -L $start,$stop -S $strandnum";
   
   ### remove the comment character from this line and it will show the command that is being run in the terminal window
   print "$command\n";
   
   ### run the command and capture the results, which should be a fasta sequence record
   my $seqrec=`$command`;
   
   my @seqreclines=split /\n/,$seqrec;   #### split the sequence record into lines, store in array @seqreclines
   my $defline=shift @seqreclines;       #### the 0th element is the defline, remove it using shift and capture in a variable $defline
   my $seq = join("",@seqreclines);      #### the remaining elements are sequence, join them all together into a single line
   
   
   
   #### print out to the file
   
   
   print $OUT "$name\t$chrom\t$start\t$stop\t$strand\t$defline\t$seq\n";
   
   
   
   


}