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

View of /FigKernelScripts/find_selenoproteins.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (download) (as text) (annotate)
Thu Dec 6 01:41:57 2007 UTC (11 years, 11 months ago) by golsen
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
Changes since 1.3: +18 -2 lines
Add functions to reference selenoproteins, and add change the set
slightly.  Report function of best matching protein.  Optionally
report the id of the best matching protein.

# -*- perl -*-
########################################################################
# Copyright (c) 2003-2007 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 strict;
use gjoseqlib;
use find_special_proteins;

my $usage = <<'End_of_Usage';

Usage: find_selenoproteins [options] < contigs > loc_seq_note_func

Output records have the following format:

   location \t sequence \t note \t function_of_most_similar_ref_protein

Options:

   -c              Allow C in reference to align with proposed selenocysteine.
   -d directory    Directory for temp files. If it exists, files are retained.
   -i              Include id of reference protein as fifth field.
   -n 'note text'  Note in third output field (D = selenoprotein or
                        pyrrolysylprotein, as appropriate).
   -p              Find pyrrolysylproteins, rather than selenoproteins.
   -r refprotfile  Read selenoprotein reference sequences from specified file.
   -t tmp          Directory for directory of temporary files.  The default
                        depends on whether the program is running in a SEED
                        environment or not.

Normally, U or X in the reference sequence must align with a proposed
selenocysteine.  The -c option allows C as well. This is an exploratory
tool for finding new selenoproteins by using a genome as a reference
(via the -r option).

End_of_Usage

my $allow_C = 0;
my $id = 0;
my $note;
my $pyrrolys = 0;
my $reffile;
my $tmpdir;
my $tmp;

while ( $ARGV[0] =~ s/^-// )
{
    $_ = shift;

    #  These options consume the flag and a value

    if ( s/^d// ) { $tmpdir   = $_ || shift; next }
    if ( s/^n// ) { $note     = $_ || shift; next }
    if ( s/^r// ) { $reffile  = $_ || shift; next }
    if ( s/^t// ) { $tmp      = $_ || shift; next }

    #  These options just consume the flag letter, and can be combined

    if ( s/c//g ) { $allow_C  = 1 }
    if ( s/i//g ) { $id       = 1 }
    if ( s/p//g ) { $pyrrolys = 1 }

    #  So nothing should remain if we get here

    if ( $_ )
    {
        print STDERR "Bad flag '$_'.\n", $usage;
        exit;
    }
}

my @refs;
if ( $reffile )
{
    -f $reffile
        or print STDERR "Bad reference sequence file '$reffile'.\n", $usage
        and exit;

    @refs = gjoseqlib::read_fasta( $reffile );
    @refs or print STDERR "No reference sequences in '$reffile'.\n", $usage
          and exit;
}

my @contigs = gjoseqlib::read_fasta();
@contigs
    or print STDERR "No contig sequences read.\n", $usage
    and exit;

my $params = { contigs => \@contigs,
               allow_C =>  $allow_C
             };
$params->{ comment     } =  $note     if $note;
$params->{ pyrrolysine } =  $pyrrolys if $pyrrolys;
$params->{ references  } = \@refs     if @refs;
$params->{ tmp         } =  $tmp      if $tmp;
$params->{ tmpdir      } =  $tmpdir   if $tmpdir;

my @prots = find_special_proteins::find_selenoproteins( $params );

my $entry;
foreach $entry ( @prots )
{
    print join( "\t", map { $entry->{$_} || '' }
                      qw( location sequence comment reference_def ),
                      ( $id ? 'reference_id' : () )
              ),
          "\n";
}

exit;

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3