[Bio] / FigKernelScripts / purge_fasta.pl Repository:
ViewVC logotype

View of /FigKernelScripts/purge_fasta.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Fri Mar 17 00:30:12 2006 UTC (13 years, 8 months ago) by overbeek
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, rast_rel_2008_06_18, myrast_rel40, rast_rel_2008_06_16, mgrast_dev_05262011, rast_rel_2008_12_18, mgrast_dev_04082011, rast_rel_2008_07_21, rast_rel_2010_0928, rast_2008_0924, mgrast_version_3_2, mgrast_dev_12152011, rast_rel_2008_04_23, mgrast_dev_06072011, rast_rel_2008_09_30, rast_rel_2009_0925, rast_rel_2010_0526, rast_rel_2014_0729, mgrast_dev_02212011, rast_rel_2010_1206, mgrast_release_3_0, mgrast_dev_03252011, rast_rel_2010_0118, mgrast_rel_2008_0924, mgrast_rel_2008_1110_v2, rast_rel_2009_02_05, rast_rel_2011_0119, mgrast_rel_2008_0625, mgrast_release_3_0_4, mgrast_release_3_0_2, mgrast_release_3_0_3, mgrast_release_3_0_1, mgrast_dev_03312011, mgrast_release_3_1_2, mgrast_release_3_1_1, mgrast_release_3_1_0, mgrast_dev_04132011, rast_rel_2008_10_09, mgrast_dev_04012011, rast_release_2008_09_29, mgrast_rel_2008_0806, mgrast_rel_2008_0923, mgrast_rel_2008_0919, rast_rel_2009_07_09, rast_rel_2010_0827, mgrast_rel_2008_1110, myrast_33, rast_rel_2011_0928, rast_rel_2008_09_29, mgrast_rel_2008_0917, rast_rel_2008_10_29, mgrast_dev_04052011, mgrast_dev_02222011, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Removes duplicate entries from fasta file. -- /gdp

# -*- perl -*-
#
# Copyright (c) 2003-2006 University of Chicago and Fellowship
# for Interpretations of Genomes. All Rights Reserved.
#
# This file is part of the SEED Toolkit.
# 
# The SEED Toolkit is free software. You can redistribute
# it and/or modify it under the terms of the SEED Toolkit
# Public License. 
#
# You should have received a copy of the SEED Toolkit Public License
# along with this program; if not write to the University of Chicago
# at info@ci.uchicago.edu or the Fellowship for Interpretation of
# Genomes at veronika@thefig.info or download a copy from
# http://www.theseed.org/LICENSE.TXT.
#


use FIG;

use Pod::Text;
# use File::Basename;   $this_tool_name = basename($0);
if ((@ARGV == 1) && ($ARGV[0] =~ m/-help/))  {
    pod2text($0);  exit(0);
}

=pod

=over 5

=item Usage:     purge_fasta  < fasta_in  > fasta_out

=item Function:  Removes duplicate entries, and reformats a fasta file to a uniform 60 chars per line.

=back

=cut

if ($ARGV[0] && (-e $ARGV[0]))
{
    open(FIN, "<$ARGV[0]") or die "could not open $ARGV[0] as input";
    $fin = \*FIN;
}
else
{
    $fin = \*STDIN;
}

if ($ARGV[1])
{
    open(FOUT, ">$ARGV[1]") or die "could not open $ARGV[1] as output";
    $fout = \*FOUT;
}
else
{
    $fout = \*STDOUT;
}

while (($id, $seqP) = &FIG::read_fasta_record($fin))
{
    $seq_of{$id} = $$seqP;
}

foreach $id (sort { &FIG::by_fig_id($a, $b) } keys %seq_of)
{
    &FIG::display_id_and_seq( $id, \$seq_of{$id}, $fout );
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3