Make data file ssr.pl - Revision history

Raj at 09:54, 3 January 2010

2010-01-03T09:54:30Z

← Older revision		Revision as of 09:54, 3 January 2010
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 a multi fasta ~~file~~		# -> Open a multi fasta files
			# -> combine camal and grandis sequeces
	# -> Count the number of bases in each fasta		# -> Count the number of bases in each fasta
	# -> Filter off the seq that have less than ~~600bp~~		# -> Filter off the seq that have less than 350bp \| more than 10% of N
	~~# -> combine camal and grandis sequeces~~
	# -> Output as fasta		# -> Output as fasta
	# Author: Rajkumar (itc@rajkumar.in)		# Author: Rajkumar (itc@rajkumar.in)

	# ~~*******~~**************************************************		# ****************************************************

	# Libraries		# Libraries
Line 32:		Line 33:

	if (-e "$outdir/$outfile") {`rm $outdir/$outfile`; }		if (-e "$outdir/$outfile") {`rm $outdir/$outfile`; }
	~~if (-e "$temp") {`rm $temp`; }~~


	my $in = Bio::SeqIO->new(-file => "$~~infile~~", -format => 'Fasta');		# Making a common inputfile for SSR mining
	~~my $identifier;~~
	~~my $sequence;~~		`cat $infile $grand_infile >$temp`;


			# Further Triming (Removing the N component)

			# Clear the variables
			my ($in, $identifier, $sequence) = ();

			# Opening
			$in = Bio::SeqIO->new(-file => "$temp", -format => 'Fasta');


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

	my $length = ($sequence =~ tr/[A-Z]\|[a-z]//);		my $length = ($sequence =~ tr/[A-Z]\|[a-z]//);
			my $count_N = ($sequence =~ tr/N//);
			my $math = ($count_N * 100) / $length;

			# conditions to remove seq with <350 and > 10% of N
			if ( $length < 350 ) { next; }
			if ( $math > 10 ) { next; }

			# Removing N at beging and end
			$sequence =~ s/^N+//g;
			$sequence =~ s/N+$//g;

			# Trimming and naming the identifier
	~~if ( $length < 400 ) { next; }~~
	$identifier =~ s/\\|/_/g;		$identifier =~ s/\\|/_/g;
	$identifier =~ s/(.+)/CAMAL_$1/g;		if ($identifier !~ m/^GRA/) {$identifier =~ s/(.+)/CAMAL_$1/g;}
	$identifier =~ s/(.+)_$/$1/g;		$identifier =~ s/(.+)_$/$1/g;



			#print "$identifier\t$length\t$count_N\n$sequence\n";

			# Write the results
	my $fasta = ">$identifier\n$sequence\n";		my $fasta = ">$identifier\n$sequence\n";
	open (FH, ">>".$~~temp~~);		open (FH, ">>".$outdir."/".$outfile);
	print FH $fasta;		print FH $fasta;
	close FH ;		close FH ;
	}
			}

	~~# Making a common inputfile for SSR mining~~		`rm $temp`;
			# END
	~~chdir $outdir;~~
	`~~cat~~ $temp ~~$grand_infile >$outdir/$outfile~~`;

	~~`rm $temp`;~~

	~~# END~~
	</source>		</source>

Raj at 13:23, 2 January 2010

2010-01-02T13:23:25Z

← Older revision		Revision as of 13:23, 2 January 2010
Line 47:		Line 47:


	if ( $length < ~~600~~ ) { next; }		if ( $length < 400 ) { next; }
	$identifier =~ s/\\|/_/g;		$identifier =~ s/\\|/_/g;
	$identifier =~ s/(.+)/CAMAL_$1/g;		$identifier =~ s/(.+)/CAMAL_$1/g;

Raj at 10:09, 30 December 2009

2009-12-30T10:09:22Z

← Older revision		Revision as of 10:09, 30 December 2009
Line 23:		Line 23:
	my $datadir = "$path/euca/data/camal";		my $datadir = "$path/euca/data/camal";
	my $infile = "$datadir/camal_all.fa";		my $infile = "$datadir/camal_all.fa";
	my $outdir = "$path/euca/ssr/~~data~~";		my $outdir = "$path/euca/ssr/glo-gra-ssr";
	my $grand_infile = "$path/euca/data/grandis/scaffold/ssr/scaf_ssr.fa";		my $grand_infile = "$path/euca/data/grandis/scaffold/ssr/scaf_ssr.fa";
	my $temp = "$path/euca/ssr/temp";		my $temp = "$path/euca/ssr/temp";

Raj: New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Open a multi fasta file # -> C...

2009-12-30T09:57:46Z

New page: <source lang=perl> #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Open a multi fasta file # -> C...

New page

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

# *************************************************************
# This Programme does the following in sequence
# -> Open a multi fasta file
# -> Count the number of bases in each fasta
# -> Filter off the seq that have less than 600bp
# -> combine camal and grandis sequeces
# -> Output as fasta
# Author: Rajkumar (itc@rajkumar.in)

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

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

# Variables
my $path = "/home/raj/bio";
my $datadir = "$path/euca/data/camal";
my $infile = "$datadir/camal_all.fa";
my $outdir = "$path/euca/ssr/data";
my $grand_infile = "$path/euca/data/grandis/scaffold/ssr/scaf_ssr.fa";
my $temp = "$path/euca/ssr/temp";
my $outfile = "camal_grand.fa";

# Making the res dir clear

if (-e "$outdir/$outfile") {`rm $outdir/$outfile`; }
if (-e "$temp") {`rm $temp`; }

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

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

my $length = ($sequence =~ tr/[A-Z]|[a-z]//);

if ( $length < 600 ) { next; }
$identifier =~ s/\|/_/g;
$identifier =~ s/(.+)/CAMAL_$1/g;
$identifier =~ s/(.+)_$/$1/g;

my $fasta = ">$identifier\n$sequence\n";
open (FH, ">>".$temp);
print FH $fasta;
close FH ;
}

# Making a common inputfile for SSR mining

chdir $outdir;
`cat $temp $grand_infile >$outdir/$outfile`;

`rm $temp`;

# END
</source>