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

View of /FigKernelScripts/upstream.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.3 - (download) (as text) (annotate)
Mon Dec 5 18:56:38 2005 UTC (13 years, 11 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, caBIG-05Apr06-00, 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, caBIG-13Feb06-00, rast_rel_2009_03_26, mgrast_dev_10262011, rast_rel_2008_11_24, rast_rel_2008_08_07, HEAD
Changes since 1.2: +17 -0 lines
Add license words.

#
# 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;
my $fig = new FIG;

use Sim;

my $usage = "usage: upstream [upstream=U] [plus=NfromStart] < PEG > MarkedFastA";

my $upstream = 200;
my $coding   = 100;

foreach $arg (@ARGV)
{
    if ($arg =~ /^upstream=(\d+)/)
    {
	$upstream = $1;
    }
    elsif ($arg =~ /^plus=(\d+)/)
    {
	$coding = $1;
    }
}

my $id;
@pegs = map { chop; $_ =~ /(\S+)$/; 
	      $id = $1;  
	      if ($id =~ /^fig\|/)
	      {
		  $id;
	      }
	      else
	      {
		  if ($peg = $fig->by_alias($id))
		  {
		      $peg;
		  }
		  else
		  {
		      ();
		  }
	      }
            } <STDIN>;

foreach $peg (@pegs)
{
    if (! $seen{$peg})
    {
	$seen{$peg} = 1;
	my($contig,$beg,$end) = $fig->boundaries_of(scalar $fig->feature_location($peg));
	my $genome = $fig->genome_of($peg);
	if (defined($contig) && ($contig_ln = $fig->contig_ln($genome,$contig)))
	{
	    if ($beg < $end)
	    {
		$b = &FIG::max(1,$beg-$upstream);
		$e = &FIG::max(1,$beg-1);
		if ($e > $b)
		{
		    $u_seq = lc $fig->dna_seq($genome,join("_",($contig,$b,$e)));
		    $end1 = &FIG::min($end,$beg+$coding-1);
		    $c_seq = ($end1 > $beg) ? uc $fig->dna_seq($genome,join("_",($contig,$beg,$end1))) : "";
		    (undef,undef,$e_ov) = $fig->genes_in_region($genome,$contig,$b,$e);
		    if ($e_ov && ($e_ov >= $b))
		    {
			my $ov_ln = ($e_ov - $b) + 1;
			$gene_before = uc substr($u_seq,0,$ov_ln);
			$inter_genic = substr($u_seq,$ov_ln);
		    }
		    else
		    {
			$gene_before = "";
			$inter_genic = $u_seq;
		    }
		}
	    }
	    else
	    {
		$b = &FIG::min($contig_ln,$beg+$upstream);
		$e = &FIG::min($contig_ln,$beg+1);
		if ($e < $b)
		{
		    $u_seq = lc $fig->dna_seq($genome,join("_",($contig,$b,$e)));
		    $end1 = &FIG::max($end,$beg-$coding+1);
		    $c_seq = ($end1 < $beg) ? uc $fig->dna_seq($genome,join("_",($contig,$beg,$end1))) : "";
		    (undef,$b_ov,undef) = $fig->genes_in_region($genome,$contig,$e,$b);
		    if ($b_ov && ($b_ov <= $b))
		    {
			my $ov_ln = ($b - $b_ov) + 1;
			$gene_before = uc substr($u_seq,0,$ov_ln);
			$inter_genic = substr($u_seq,$ov_ln);
		    }
		    else
		    {
			$gene_before = "";
			$inter_genic = $u_seq;
		    }
		}
	    }
	    $seq = join(($c_seq ? "-" : ""),($gene_before . $inter_genic,$c_seq));
	    &FIG::display_id_and_seq($peg,\$seq);
	}
    }
}


MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3