Blast.pl

#! /usr/bin/perl -w

# *************************************************************
# This Programme does the following in sequence
# -> Performs regular Blast
# -> Infile as folder and write the progress
# Author : Rajkumar (itc@rajkumar.in)
# Release: JUL 2009
# *************************************************************

# Libraries
	use strict;
	use Bio::Perl;
	use Bio::SeqIO;
	use Parallel::ForkManager;

# At the top: Time Start
	my ($sec,$min,$hour,$mday,$mon,$year,$wday,$yday,$isdst) = localtime(time);

# Variables
	my $path            = "/home/raj/bio";
	my $path1           = "$path/user/raja";
	my $path2           = "$path1/blast/BES-NR";
	my $multifasta      = "$path2/BES.fa";
	my $infiledir       = "$path2/multifasta";
	my $outdir          = "$path2/blastout";
	
	my $db              = "$path/data/nr/nr";
	
	
	my ($i, $total)     = $_;
	my (@files, @files_)= @_;


# Multi-threading
	my $midstop     = "0"; # If midstop is 0 it deals with all the files		
	my $cpu         = "1";
	my $pm          = new Parallel::ForkManager(16);
	
# Getting the Grip of folders
	if (-e $outdir  ) {`rm -fr $outdir`;}
	if (! -e $outdir) {`mkdir $outdir`;}
	

# Functions

	opendir (DIR, "$infiledir") or die $!;
	@files = readdir(DIR);
	close(DIR);
	
	my $c_files = @files - 2;
	
	$i = 0;
	foreach my $file(@files) {
		next if ($file eq "."  or $file eq "..");
		$i++;
		
		#if ($i > $midstop) {last };
		
		$pm->start and next;
		
		my $percent = ($i/$c_files)*100;
		$percent = sprintf("%.2f", $percent);

		print "\n\tInitiated [$i of $c_files] | $percent% ";
		chdir $infiledir;
		`blastall -p blastx -d $db -i $file -m 9 -o $outdir/\/$file.out -a $cpu`;
			# -p program
			# -d database
			# -i query file
			# -e evalue
			# -m 8 tab delimited out
			# -o outfile
			# -a number of CPUs
			# -q  Penalty for a nucleotide mismatch (blastn only)   default = -3
			# -v  Number of database sequences to show one-line
			# -K  Number of best hits from a region to keep
		print "OK.";
		$pm->finish;

	}
	
	$pm->wait_all_children;

	print "\nAll Done!\n\n";
	

# At the End: Time Calculation
	my ($sec_,$min_,$hour_,$mday_,$mon_,$year_,$wday_,$yday_,$isdst_) = localtime(time);
	my $days = $mday_-$mday;
	my $hours = $hour_-$hour;
	my $mins = $min_-$min;
	my $secs = $sec_-$sec;
	print "\n------------------------\nDuration: ";
	if ($days>0) { print "$days days";}
	if ($hours>0) { print ": $hours hours";}
	if ($mins>0) { print ": $mins mins";}
	if ($secs>0) { print ": $secs secs";}
	print "\n------------------------\n";

# END