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

View of /FigKernelScripts/check_fasta_for_dups.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Thu May 31 19:24:43 2007 UTC (12 years, 5 months ago) by olson
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
Missing scripts.

#
# Scan a fasta file and report on identifiers that are repeated in the file and if
# they have the same sequence data or not.
#

use FIG;
use strict;
use Digest::MD5;

@ARGV == 1 or @ARGV == 2 or die "usage: check_fasta_for_dups filename [unique-output]\n";

my $file = shift;
my $fh = new FileHandle($file);
$fh or die "Cannot read $file: $!\n";

my $output = shift;
my $out_fh;
if ($output)
{
    $out_fh = new FileHandle(">$output");
    $out_fh or die "Cannot open $output for writing: $!\n";
}

my %cksum_to_id;
my %id_to_cksum;

my $digest = Digest::MD5->new();

while (my($id, $seq, $comment) = &FIG::read_fasta_record($fh))
{
    $digest->add($$seq);
    my $cksum = $digest->hexdigest();

    my $prev_cksum = $id_to_cksum{$id};
    my $prev_seq = $cksum_to_id{$cksum};

    if (defined($prev_cksum))
    {
	if ($prev_cksum eq $cksum)
	{
	    print "$id\tduplicate-id-and-sequence\t$cksum\n";
	}
	else
	{
	    print "$id\tduplicate-id-different-sequence\t$cksum\t$prev_cksum\n";
	}
    }
    else
    {
	if ($out_fh)
	{
	    &FIG::display_id_and_seq($id, $seq, $out_fh);
	}
    }
    if (defined($prev_seq))
    {
	print "$id\tduplicate-sequence\t$prev_seq\t$cksum\n";
    }

    $id_to_cksum{$id} = $cksum;
    $cksum_to_id{$cksum} = $id;
}

if ($out_fh)
{
    $out_fh->close();
}
    

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3