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

View of /FigKernelScripts/fill_in_cell.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.2 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 2005 UTC (14 years, 4 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 1.1: +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;

$usage = "usage: fill_in_cell Organism Role";

(
 ($genome = shift @ARGV) &&
 ($role   = shift @ARGV)
) 
    || die $usage;

@poss = &find_role_in_org($fig,$role,$genome,"master",1.0e-10);
print &Dumper(\@poss);

sub find_role_in_org
{
    my($self,$role, $org, $user, $sims_cutoff) = @_;

    my($id2,$psc,$col_hdrs,$tab,$peg,$curr_func,$id2_func);
    my($seen,$peg);

    if (!$org)
    {
	return undef;
    }
    
    #
    # Create a list of candidates.
    #
    # These are the list of sequences that contain the given role,
    # sorted by the crude_estimate_of_distance from the given peg.
    # 
    
    my @cand = map { $_->[0] }
               sort { $a->[1] <=> $b->[1] }
               map {
	              $peg = $_;
	              [$peg,$self->crude_estimate_of_distance($org,&FIG::genome_of($peg))]
	           }
               $self->seqs_with_role($role,$user);
    
    my $hits = {};
    $seen = {};
    
    #
    # Pick the top 10 hits if there are more than 10.
    #
    my $how_many = ((@cand > 10) ? 10 : scalar @cand) - 1;
    
    $self->try_to_locate($org,$hits,[@cand[0..$how_many]],$seen, $sims_cutoff);
    
    if (keys(%$hits) == 0)
    {
	splice(@cand,0,$how_many+1);
	&try_to_locate($self,$org,$hits,\@cand,$seen, $sims_cutoff);
    }
    
    #
    # At this point %$hits contains the pegs in our organism that
    # may have the given role. The key is the peg, the value
    # is a pair [score, similar-peg]
    #
    #
    # We reformat this into a list of entries
    # [ $psc, $peg-in-this-org, $length, $current-fn, $matched-protein, $matched-len, $matched-fun]
    #

    
    $col_hdrs = ["P-Sc","PEG","Ln1","Current Function", "Protein Hit","Ln2","Function"];

    my @ret;

    foreach $peg ( sort {$hits->{$a}->[0] <=> $hits->{$b}->[0]} keys(%$hits))
    {
	($psc,$id2) = @{$hits->{$peg}};
	$curr_func = $self->function_of($peg,$user);
	$id2_func  = $self->function_of($id2,$user);

	push(@ret, [$psc, $peg, $self->translation_length($peg),
		    $curr_func, $id2, $self->translation_length($id2),$id2_func]);
    }
    return @ret;
}    

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3