Outline Lecture 14
April 18, 2006

I. Introduction to Perl
A. Writing Files
B. Conditional Statements
C. Pattern Matching and Regular Expressions
D. Subroutines and program modules
E. BioPerl

#Program 1: writing to a file ###################################
#
# use  perl strip_cr.pl input.pdb output.pdb
#
# read the file name : first argument
$in_name= $ARGV[0];
# read the output file name : second argument
$out_name= $ARGV[1];
print "Striping CR from file $in_name and writing to $out_name \n";
# open the file and associate a file handle
open(infile,$in_name) or die " can not open $in_name \n"; 
# open an output file and associate a file handle
open(outfile,">$out_name") or die " can not create $out_name \n";
# now read the file in a loop
while($line = <infile>) {
	# replace macintosh cr with windows lf
	$line =~ s/\r/\n/g;
	print outfile $line;
	}
# close the file because we are done
close infile;
close outfile;
exit;

# program 2 logical tests ############################
$a=(10 > 1);
#$a=(10 < 1);
print "here is a logical test\n";
print "the logical ($a) is";
if ($a) {print " true "}
if (!$a) {print " false "}
if ($a == 0) {print " zero "}
if ($a == 1) {print " one "}
if ($a eq "") {print " blank "}
if ($a ne "") {print " not blank"}

#Program 3: Conditional statements ###################################
#note: this program has some non-standard word characters
print "Enter your age: ";
$age = <>;
chomp $age;
if ($age < 21) {
	  print "You are too young for this kind of work!\n";
	  die "too young";
} # if end
print "You are old enough to know better!\n";

#Program 4: Fun with Strings ###################################
#
$line ='SEQRES  1  A 153  ALA LYS HIS VAL LEU';
print "$line \n\n";
$location = index($line,' A ') + 1;
$string = substr($line,11,1);
print "The string variable $string is found at location $location \n";
# Check for occurrence of a string
$b='ALA';
if($line =~ /$b/){
	print "The string contains ALA \n";
	}
if($line =~ /^SEQ/){
	print "The string starts with SEQ \n";
	}
	else {
		print "But the String did not start with SEQ \n";
	}
# split the string at one or more white spaces into an array
print "Splitting the string into an array \n";
@array = split(/\s+/,$line);
for $a (@array) {
	print $a,"\n";

}
# program 5: hash example ###############################
%three_to_one = (
	ALA => A, CYS => C, ASP => D, GLU => E, PHE => F,
	GLY => G, HIS => H, ILE => I, LYS => K, LEU => L,
	MET => M, ASN => N, PRO => P, GLN => Q, ARG => R,
	SER => S, THR => T, VAl => V, TRP => W, TYR => Y,
);
print "Input your three letter amino acid code: ";
while($code=<>){
	chomp $code;
	$code = uc $code;
	if (exists $three_to_one{$code}) {
	print "\n The code for $code is $three_to_one{$code} \n";
	}else{
	print "Bad codon \"$code\"!! \n";
	}
	print "\nInput your three letter amino acid code: ";
}

# Program 6: Subrouties ################################################
#!/usr/local/bin/perl
$a = 6;
$b = 10;
print "Average $a and $b \n";
$average = calc_ave ($a, $b);  # subroutine invocation.
print "The average is $average\n";
exit;
# subroutine definition starts here
sub calc_ave {
   my ($x, $y) = @_;
   my ($result);
   $result = ($x + $y) / 2;
   return $result;
}
# program 7: including a program module #############################
# print out subroutine include path
print "The path for included subroutines is:\n";
print @INC, "\n";
# add a path
print "Adding an extra directory to the include path \n";
push(@INC,'C:\Perl\programs');
print @INC, "\n";
# require or use the new program module
use BeginPerlBioinfo;
#require('BeginPerlBioinfo.pm');
pause();
$line="ALA PHE LEU ILE PRO MET\nALA PHE PRO PRO";
print "The input sequence is\n", $line,"\n";
$out=iub3to1($line);
print "The translated sequence is\n",$out,"\n";
pause();
exit;
sub pause{
	print "\n Pausing - press enter to continue ?";
	my $input = <STDIN>;
}

# Installing BioPerl ####################################################
ppm> rep add Bioperl http://bioperl.org/DIST 
ppm> rep add Kobes http://theoryx5.uwinnipeg.ca/ppms 
ppm> rep add Bribes http://www.Bribes.org/perl/ppm
ppm> search Bioperl
ppm> install <number> 
ppm> query bioperl
Ppm> exit

# Program 8: Bioperl ####################################################
use Bio::Perl;
  # this script will only work if you have an internet connection on the
  # computer you're using, the databases you can get sequences from 
  # are 'swiss', 'genbank', 'genpept', 'embl', and 'refseq'
  $seq_object = get_sequence('swiss',"ROA1_HUMAN");
  write_sequence(">roa1.fasta",'fasta',$seq_object);
  print "Sequence name is ",$seq_object->display_id,"\n";
  print "Sequence acc  is ",$seq_object->accession_number,"\n";
  print "The sequence is \n",$seq_object->seq(),"\n";

# Program 9: Bioperl ####################################################
use Bio::Perl;
  $seq = get_sequence('swiss',"ROA1_HUMAN");
  # uses the default database - nr in this case
  $blast_result = blast_sequence($seq);
  write_blast(">roa1.blast",$blast_result);