Raj at 10:35, 30 December 2009

2009-12-30T10:35:11Z

← Older revision		Revision as of 10:35, 30 December 2009
Line 1:		Line 1:
	<source lang=perl>		<source lang=perl>
	#! /usr/bin/perl -w		#! /usr/bin/perl -w


	# *************************************************************		# *************************************************************
	# This Programme does the following in sequence		# This Programme does the following in sequence
	# -> ~~Open the misa results~~		# -> Runs MISA
	# -> ~~Parse the files~~		# -> Produces 2 outfiles, one ssr and other statistics
	~~# -> compare the original EST file~~ and ~~pick the sequence that have repeats~~		# Author: Author: Thomas Thiel ; Modified by Rajkumar (itc@rajkumar.in)
	~~# -> Outputs as fasta~~		# Release: JUL 2008
	# Author: Rajkumar (itc@rajkumar.in)

	# *************************************************************		# *************************************************************

	# Libraries		# Libraries
	use strict;		use strict;
	~~use Bio::SeqIO;~~
	~~use Bio::Perl;~~

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

	# Variables		# Variables
	my $path = "/home/raj/bio";		my $path = "/home/raj/bio";
	my $ssrdir = "$path/euca/ssr";		my $ssrdir = "$path/euca/ssr/glo-gra-ssr";
	my $~~datadir~~ = "$ssrdir/~~data~~";		my $infile = "$ssrdir/camal_grand.fa";
	my $resdir = "$ssrdir/result";		my $resdir = "$ssrdir/result";

	~~my $est = "$datadir/globulus_est_trim.fa";~~
	~~my $repeat = "$resdir/globulus_est_trim.fa.misa";~~
	~~my $resfile = "$datadir/globulus_est_repeat.fa";~~

	~~my ($i, $ssr_id, $total, $math ) = $_;~~
	~~my (@repeat_id, @identifier) = @_;~~


	~~# Function~~

	~~# Lets Clean it~~
	~~if (-e "$resfile") {`rm $resfile`;}~~

	# ~~start your hack~~		# Running the File

	~~open~~(~~CSV,~~ "$~~repeat~~") ~~or die "Idiot! Where is that Misa Outfile ? 'CSV':~~ $~~!\n"~~;		if (-e "$resdir") {`rm -fr $resdir`;}
	~~<CSV>; # skip header line~~		if (! -e "$resdir") {`mkdir $resdir`;}
	~~while~~ (my $~~line = <CSV>~~) {

	~~my (~~$~~ssr_id) = split('\t', $line)~~;		chdir $ssrdir;
	~~next if ($ssr_id =~ m/^ID~~/);		`./misa.pl $infile`;

	~~push (@repeat_id, "~~$~~ssr_id")~~;
	}

	~~# Making them Unique~~
	~~my %seen;~~
	~~my @unique_repeat_id = grep !$seen{$_}++, @repeat_id;~~

	~~# Getting some statistics~~
	~~my $count_unique_repeat_id = @unique_repeat_id;~~
	~~$i = 0;~~

	~~# Lets Grab the sequence~~
	~~foreach my $repeat_id(@unique_repeat_id) {~~

	~~$i++;~~
	~~my $in = Bio::SeqIO->new(-file => "$est", -format => 'Fasta');~~
	~~my $identifier;~~
	~~my $sequence;~~

	~~while ( my $seq = $in->next_seq() ) {~~
	~~$identifier = $seq->id;~~
	~~$sequence = $seq->seq;~~

	~~next if ($repeat_id ne $identifier);~~

	~~if ($repeat_id eq $identifier) {~~

	~~my $fasta = ">$identifier\n$sequence\n";~~
	~~open (FH, ">>".$resfile);~~
	~~print FH $fasta ;~~
	~~close FH ;~~
	~~print "\r\tWritten $identifier. Still $i of $count_unique_repeat_id to be written!";~~
	}
	}
	}

	print "\n\~~tDone All Man\nOutfile written into~~ $~~resfile~~\n\n";		# At the End: Time Calculation
			my ($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		# END
	</source>		</source>

Raj: New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Open the misa results # -> Par...

2009-12-30T10:34:37Z

New page: <source lang=perl> #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Open the misa results # -> Par...

New page

<source lang=perl>
#! /usr/bin/perl -w

# *************************************************************
# This Programme does the following in sequence
# -> Open the misa results
# -> Parse the files
# -> compare the original EST file and pick the sequence that have repeats
# -> Outputs as fasta
# Author: Rajkumar (itc@rajkumar.in)

# *************************************************************

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

# Variables
my $path = "/home/raj/bio";
my $ssrdir = "$path/euca/ssr";
my $datadir = "$ssrdir/data";
my $resdir = "$ssrdir/result";

my $est = "$datadir/globulus_est_trim.fa";
my $repeat = "$resdir/globulus_est_trim.fa.misa";
my $resfile = "$datadir/globulus_est_repeat.fa";

my ($i, $ssr_id, $total, $math ) = $_;
my (@repeat_id, @identifier) = @_;

# Function

# Lets Clean it
if (-e "$resfile") {`rm $resfile`;}

# start your hack

open(CSV, "$repeat") or die "Idiot! Where is that Misa Outfile ? 'CSV': $!\n";
<CSV>; # skip header line
while (my $line = <CSV>) {

my ($ssr_id) = split('\t', $line);
next if ($ssr_id =~ m/^ID/);

push (@repeat_id, "$ssr_id");
}

# Making them Unique
my %seen;
my @unique_repeat_id = grep !$seen{$_}++, @repeat_id;

# Getting some statistics
my $count_unique_repeat_id = @unique_repeat_id;
$i = 0;

# Lets Grab the sequence
foreach my $repeat_id(@unique_repeat_id) {

$i++;
my $in = Bio::SeqIO->new(-file => "$est", -format => 'Fasta');
my $identifier;
my $sequence;

while ( my $seq = $in->next_seq() ) {
$identifier = $seq->id;
$sequence = $seq->seq;

next if ($repeat_id ne $identifier);

if ($repeat_id eq $identifier) {

my $fasta = ">$identifier\n$sequence\n";
open (FH, ">>".$resfile);
print FH $fasta ;
close FH ;
print "\r\tWritten $identifier. Still $i of $count_unique_repeat_id to be written!";
}
}
}

print "\n\tDone All Man\nOutfile written into $resfile\n\n";

# END
</source>

Misa run1.pl - Revision history

Raj at 10:35, 30 December 2009

Raj: New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Open the misa results # -> Par...