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

View of /FigKernelScripts/get_sims_for_start_predictions.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.5 - (download) (as text) (annotate)
Fri Nov 30 21:53:05 2007 UTC (11 years, 11 months ago) by gdpusch
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 1.4: +24 -8 lines
Added FIGV support. -- /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_Config;

use FIG;
use FIGV;
my $fig = new FIG;

$usage = "usage: get_sims_for_start_prediction [-help] [-orgdir=OrgDir] AA_for_ORFs < PEGs > similarities";

$trouble   = 0;
while (@ARGV)
{
    if ($ARGV[0] =~ m/-h(elp)?/) {
	die "\n\tusage: $usage\n\n";
    }
    elsif ($ARGV[0] =~ /-orgdir=(\S+)/) {
	$fig = new FIGV($1);
    }
    elsif (-s $ARGV[0]) {
	$aa_for_orfs = $ARGV[0];
	open(ORFPROTSEQS, "<$aa_for_orfs") || die "Could not read-open $aa_for_orfs";
    }
    else {
	warn "Invalid argument $ARGV[0]\n";
    }
    shift @ARGV;
}
die "\nusage: $usage\n\n" if $trouble;


@pegs = <STDIN>;
chomp @pegs;
## print "NPEGS=", scalar(@pegs), "\n";
for ($i=0; $i < @pegs; $i++)  # strip off all but peg ids at front
{
    if ($pegs[$i] =~ /(\S+)\t.*/)
    {
        $pegs[$i] = $1;
    }
}

my $pegprots = "$FIG_Config::temp/pegprots$$";
my %seqs;

$/ = "\n>";
open(PEGPROTSEQS, ">$pegprots");
while (defined($_ = <ORFPROTSEQS>))
{
    chomp;
    if ($_ =~ /^>?(\S+)[^\n]*\n(.*)/s)
    {
	$id  =  $1;
	$seq =  $2;
	$seq =~ s/\s//g;
	$seqs{$id} = $seq;
	print PEGPROTSEQS ">$id\n$seq\n";
    }
}
close(ORFPROTSEQS);
close(PEGPROTSEQS);

$/ = "\n";
$fig->run("$FIG_Config::ext_bin/formatdb -i $pegprots");

for $id (@pegs)
{
    if ($seq = $seqs{$id})
    {
	open(TMP,">$FIG_Config::temp/tmporf$$");
	print TMP ">$id\n$seq\n";
	close(TMP);
	$fig->run("$FIG_Config::ext_bin/blastall -m 8 -e 1.0e-20 -i $FIG_Config::temp/tmporf$$ -FF -d $pegprots -p blastp");
    }
}
system "rm $pegprots\*";
unlink("$FIG_Config::temp/tmporf$$");

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3