#! C:\Perl\bin\perl
#########################################################
# probe.pl- converts affy probe set files to excel files#
# by D. Newkirk on 9/9/03                               #
#########################################################
use strict;
use warnings;

print STDOUT 'Please state the file containing the probes: ';
chomp(my $input=<STDIN>);
open (INPUT, "$input")or die "Cannot open file: $!";

print STDOUT 'Please name the output file: ';
chomp(my $output=<STDIN>);
open (OUTPUT, ">$output")or die "Cannot open file: $!";

$_=<INPUT>;

my ($target_name, %probes);
$target_name=$1 if m[:(\d{6})_]x;
#print "$target_name\n";
do {
	if ($_=~ m/$target_name/) {
		chomp(my $probe=<INPUT>);
		if ($probe=~ /^(\w{20})/) {print "$probe\n";
			push @{$probes{$target_name}}, $probe;
		}
	}
	if ($_ !=~ [$target_name]) { 
		$_= m[:(\d{6})_]x;
		$target_name=$_;
		print "$target_name\n";
	}
}until eof INPUT;

for $target_name(sort{@{probes{$b}}<=>@{probes{a}}}keys %probes) {
	print OUTPUT "$target_name, ", join(", ", sort @{$probes{$target_name}}), "\n";
}

close (INPUT);
close (OUTPUT);
exit;

_input_
>probe:ATH1-121501:244901_at:594:703;Interrogation_Position=56;Antisense;TTGCTGCTATTCTATCTATTTGTGC
Times 11
>probe:ATH1121501:244902_at:522:511;Interrogation_Position=153;Antisense;
GGTATTTTCCGTTTCTTCGGATGAT
Times 11

_output_
244901, AACACTTACAAATGCCACTTCTTCC, AGCAATTTGCCTACTCTTGTATCTC, AGCTGTGAATTCGAACTTTTTGGTA, ATATTCCTATTATGTCAATGCCAAT, CCAACGGTGGCAGCTGCGGAATCCG, GAAGAATCGCAGCAATTCCCCAATC, GAAGTAGTTCCTCCGGAATCCAATG, GACTTTCAAAGTGACTCTCGACGGG, GAGCCTCCAGGCTATTCAGGAAGAA, GAGTCCGAGGTACTATTGCTGTAGA, GATGGGTCAAGTATTTGCTTCATTG, GCAAGCTTTGTTATGCCGAAACCTA, GCGGAATCCGCTATTGGGTTAGCCA, GGTATTTTCCGTTTCTTCGGATGAT, GTATTCGGGGAATCCTCCTTAATAG, GTCGCATCCGTTTTCAGGACGATCT, TAACTTTCCGAGTCCGAGGTACTAT, TAGCCATTTTCGTTATAACTTTCCG, TCAGCTTGCGAATTTGTGGCACCGT, TGCTTCATTGGTTCCAACGGTGGCA, TTACCAATGGCACGCTGTGCGCCTA, TTGCTGCTATTCTATCTATTTGTGC