Trim seq: Difference between revisions
Jump to navigation
Jump to search
m New page: #! /usr/bin/perl -w # ************************************************************* # This Programme does the following in sequence # -> Parses a multi fasta # -> Removes the sequences tha... |
mNo edit summary |
||
| (3 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
<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 | ||
# -> Parses a multi fasta | # -> Parses a multi fasta | ||
# -> 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 36: | 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 | if ($count_seq < 300){ next; } | ||
if ($count_N > $math){ next; } | if ($count_N > $math){ next; } | ||
| Line 44: | Line 44: | ||
} | } | ||
# END | |||
</source> | |||
Latest revision as of 05:59, 2 January 2010
#! /usr/bin/perl -w
# *************************************************************
# This Programme does the following in sequence
# -> Parses a multi fasta
# -> 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 < 300){ next; }
if ($count_N > $math){ next; }
print $fasta;
}
# END