Raj at 11:31, 16 July 2010

2010-07-16T11:31:15Z

← Older revision		Revision as of 11:31, 16 July 2010
Line 1:		Line 1:
	[[Category: Bioinformatics]]		[[Category: Bioinformatics]]
	<source=lang=perl>		<source lang=perl>

	#! /usr/bin/perl -w		#! /usr/bin/perl -w
	# *************************************************************		# *************************************************************

Raj: Created page with 'Category: Bioinformatics #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequenc…'

2010-07-16T11:30:31Z

Created page with 'Category: Bioinformatics <source=lang=perl> #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequenc…'

New page

[[Category: Bioinformatics]]
<source=lang=perl>
#! /usr/bin/perl -w
# *************************************************************
# This Programme does the following in sequence
# -> Parses a multi fasta
# -> Removes the sequence if they have <50bp and of 'N'
# -> Capured as individual files.
# Author : Rajkumar (itc@rajkumar.in)
# Release: JUL 2009
# *************************************************************

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

# Variables
my $path = "/home/raj/bio";
my $path1 = "$path/user/raja";
my $path2 = "$path1/blast/BES-NR";
my $multifasta = "$path2/BES.fa";
my $resdir = "$path2/multifasta";

# Getting the Grip of folders
if (-e $resdir) {`rm -fr $resdir`;}
if (! -e $resdir) {`mkdir $resdir`;}

# making several Fasta files of GDNA
my $in = Bio::SeqIO->new(-file => "$multifasta", -format => 'Fasta');
my $identifier;
my $sequence;

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

#Trim the identifier
$identifier =~ s/_Size:[0-9]+bp//g;

my ($fasta) = $_;
$fasta = ">$identifier\n$sequence\n";

my $count_seq = length($sequence);
my $count_N = ($sequence =~ tr/N//);
my $math = $count_seq * 0.2;

$sequence =~ s/-/N/;
if ($count_seq < 50){ next; }
if ($count_N > $math){ next; }

open (FASTA, ">".$resdir."/".$identifier.".fa");
print FASTA $fasta;
close FASTA;

# print "$identifier\t$count_seq\n";

}
# END

</source>

BES-NR blast.pl - Revision history

Raj at 11:31, 16 July 2010

Raj: Created page with 'Category: Bioinformatics #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequenc…'