8_getAnnotated.pl

#!/usr/bin/perl

# -----------------------------------------
# Updated Date: 2014/03/24
# Input: 
#       (1) Files were generated by getTranscript.pl.
#       (2) Annotated data from GENCODE. (or the format must be the same with the GENCODE)
#       (3) The package implemented by the pointer to access GENOCDE database easily.
# Output: The potential items whith their annotated data.
# Environemt: Linux or Windows
# Description: Try to add more information to the potential items, significant expression difference on both gene level
#			   and transcript level.
# -----------------------------------------

use strict;
use annotated;

# C:\>perl ./getAnnotated.pl ./gencode.v19.long_noncoding_RNAs.gtf ./bothGeTr.csv ./output.csv
if(scalar(@ARGV) < 3) {
	die("Usage: perl ./getAnnotated.pl <annotated.gtf> <geneAndTranscript.txt> <output.csv>");
}

# --------------------------------------------------------------------------
# deal with the annotated file
open(fin,"$ARGV[0]") or die("Error: Make sure that file $ARGV[0] exist.\n");

my @all_annotated = ();
my @tmp = ();
my @attribute = ();
my @eachComponent = ();

sub regular {
	# add ( and ) to get complete passed value
	my ($getString, $getOption) = @_;
	if($getOption == 0) {
		$getString =~ m/\s*?.*?\s*?"(.*?)"/;
		return $1;
	}
	elsif($getOption == 1) {
		$getString =~ m/"(.*?)"/;
		return $1;
	}
}

foreach my $line (<fin>) {
	chomp($line);
	# deal with the comment
	if($line =~ m/^##/) {
		next;
	}
	@tmp = split("\t",$line);
	$eachComponent[0] = $tmp[0];
	$eachComponent[1] = $tmp[1];
	$eachComponent[2] = $tmp[2];
	$eachComponent[3] = $tmp[6];
	@attribute = split(";",$tmp[8]);
	$eachComponent[4] = regular($attribute[0],0);
	$eachComponent[5] = regular($attribute[1],0); 
	$eachComponent[6] = regular($attribute[2],0);
	$eachComponent[7] = regular($attribute[4],0); 
	$eachComponent[8] = regular($attribute[7],0); 
	my $annotatedObj = new annotated(@eachComponent);
	push(@all_annotated, $annotatedObj);
}

close(fin);

print "Total annotated data count is: ";
print scalar(@all_annotated);
print "\n";
# --------------------------------------------------------------------------

# --------------------------------------------------------------------------
# deal with the significant file storing gene and transcript name
open(fin,"$ARGV[1]") or die("Error: Make sure that file $ARGV[1] exist.\n");
if(! open(fout,">$ARGV[2]")) {
	close(fin);
	die("Error: Output file $ARGV[2] went error.\n");
}

my $colLabel = 0;
my $catOutput = "";
@tmp = ();
@eachComponent = ();
foreach my $line (<fin>) {
	chomp($line);
	if($colLabel == 0) {
		$colLabel = 1;
		my $colLabelName = $line.",\"chr\",\"source\",\"type\",\"strand\",\"geneType\",\"geneName\",\"transcriptName\"";
		print fout "$colLabelName\n";
		next;
	}	
	@tmp = split(",",$line);
	$eachComponent[0] = regular($tmp[0],1);
	$eachComponent[1] = regular($tmp[1],1);
	$catOutput = ""; # clear the output string
	foreach my $obj (@all_annotated) {
		bless($obj,"annotated");
		if($obj -> getContent(4) eq $eachComponent[1] and $obj -> getContent(5) eq $eachComponent[0]) {
			for(my $i = 0; $i < 9; $i++) {
				if ($i == 4 or $i == 5) {
					next;
				}
				$catOutput .= "\"";
				$catOutput .= $obj -> getContent($i);
				$catOutput .= "\"";
				if($i != 8) {
					$catOutput .= ",";
				}
			}
			print fout "$line,$catOutput\n";
			last;
		}
	}
}

close(fout);
close(fin);
print "State: Output file $ARGV[2] was finished.\n";
# --------------------------------------------------------------------------