Trim seq - Revision history

Raj at 05:59, 2 January 2010

2010-01-02T05:59:13Z

← Older revision		Revision as of 05:59, 2 January 2010
Line 1:		Line 1:
	<source =lang=perl>		<source lang=perl>
	#! /usr/bin/perl -w		#! /usr/bin/perl -w
	# *************************************************************		# *************************************************************

Raj at 05:59, 2 January 2010

2010-01-02T05:59:02Z

← Older revision		Revision as of 05:59, 2 January 2010
Line 1:		Line 1:
	<~~pre~~>		<source =lang=perl>
	#! /usr/bin/perl -w		#! /usr/bin/perl -w
	# *************************************************************		# *************************************************************
Line 47:		Line 47:


	</~~pre~~>		</source>

Raj at 14:34, 1 November 2009

2009-11-01T14:34:00Z

← Older revision		Revision as of 14:34, 1 November 2009
Line 4:		Line 4:
	# This Programme does the following in sequence		# This Programme does the following in sequence
	# -> Parses a multi fasta		# -> Parses a multi fasta
	~~# -> Removes the sequences that has less than 250 bases in size~~
	# -> Removes the sequence if they have >20% of N		# -> Removes the sequence if they have >20% of N
	# -> Capture the results		# -> Capture the results
Line 37:		Line 36:
	my $count_N = ($sequence =~ tr/N//);		my $count_N = ($sequence =~ tr/N//);
	my $math = $count_seq * 0.2;		my $math = $count_seq * 0.2;

	if ($count_seq ~~> 250~~){ next; }		if ($count_seq < 300){ next; }
	if ($count_N > $math){ next; }		if ($count_N > $math){ next; }

Line 45:		Line 44:
	}		}

			# END


	~~# END~~
	</pre>		</pre>

Raj at 10:51, 1 November 2009

2009-11-01T10:51:28Z

← Older revision		Revision as of 10:51, 1 November 2009
Line 1:		Line 1:
			<pre>
	#! /usr/bin/perl -w		#! /usr/bin/perl -w
	# *************************************************************		# *************************************************************
Line 47:		Line 48:

	# END		# END
			</pre>

Raj: New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Parses a multi fasta # -> Removes the sequences tha...

2009-11-01T10:51:02Z

New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Parses a multi fasta # -> Removes the sequences tha...

New page

#! /usr/bin/perl -w
# *************************************************************
# This Programme does the following in sequence
# -> Parses a multi fasta
# -> Removes the sequences that has less than 250 bases in size
# -> Removes the sequence if they have >20% of N
# -> Capture the results

# Author: Rajkumar (itc@rajkumar.in)

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

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

# Variables
my $path = "/home/raj/bio";
my $multifasta = "$path/tobacco/data/singlet.fa";

# 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;

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

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

if ($count_seq > 250){ next; }
if ($count_N > $math){ next; }

print $fasta;

}

# END