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

View of /FigKernelScripts/merge_annotations.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.3 - (download) (as text) (annotate)
Mon Dec 5 18:56:37 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.

# -*- 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 Carp;
use Data::Dumper;
use FIG;

$usage = "usage: merge_annotations [-sprout] File1 File2 ... > merged_annotations";

if ((@ARGV > 0) && ($ARGV[0] =~ /sprout/i))
{
    $sprout = 1;
    shift @ARGV;
}
else
{
    $sprout = 0;
}

(@ARGV > 1) || die $usage;

@ann = ();
foreach $file (@ARGV)
{
    &read_file($file,$sprout,\@ann);
}

@ann = sort { &FIG::by_fig_id($a->[0],$b->[0]) or ($a->[1] <=> $b->[1]) } @ann;
#print &Dumper(\@ann); die "aborted";


while (@ann > 0)
{
    $x = shift @ann;
    @set = ($x);
    while ((@ann > 0) && ($set[0]->[0] eq $ann[0]->[0]))
    {
	$x = shift @ann;
	push(@set,$x);
    }
    &process_set($sprout,\@set);
}
	
sub read_file {
    my($file,$sprout,$annL) = @_;
    my($line,$fid,$ts,$ann);

    $/ = $sprout ? "\n" : "\n//\n";
    if (open(ANN,"<$file"))
    {
	while (defined($line = <ANN>))
	{
	    chomp $line;
	    if ($sprout)
	    {
		if ($line =~ /^(fig\|\d+\.\d+\.[a-zA-Z]{2,10}\.\d+):\S+\t(\d+)\t(\S*?)\\n(.*)/)
		{
		    $fid = $1;
		    $ts  = $2;
		    $who = $3;
		    $ann = $4;
		    $ann =~ s/\\n/\n/g;
		    $ann =~ s/\\t/\t/g;
		    push(@$annL,[$fid,$ts,$who,$ann]);
		}
	    }
	    else
	    {
		if ($line =~ /^(fig\|\d+\.\d+\.[a-zA-Z]{2,10}\.\d+)\n(\d+)\n(\S+)\n(.*)/s)
		{
		    push(@$annL,[$1,$2,$3,$4]);
		}
	    }
	}
	close(ANN);
    }
    $/ = "\n";
}

sub process_set {
    my($sprout,$set) = @_;
    my($ann,$x);
    my %seen;

    my @kept = ();
    foreach $x (@$set)
    {
	$x->[3] =~ s/Set master:/Set /s;
	$x->[3] =~ s/\n*\Z//s;
	$x->[2] =~ s/master://;

	if ($x->[3] =~ /Set (\S+) function to\n(\S.*\S)/s)
	{
	    if ((! ($_ =  $seen{$1})) || ($_ ne $2))
	    {
		$seen{$1} = $2;
		push(@kept,$x);
	    }
	}
	else
	{
	    push(@kept,$x);
	}
    }

    foreach $x (@kept)
    {
	my($fid,$ts,$who,$ann) = @$x;

	if ($sprout)
	{
	    $ann =~ s/\t/\\t/gs;
	    $ann =~ s/\n/\\n/gs;
	    print "$fid:$ts\t$ts\t$who\\n$ann\n";
	}
	else
	{
	    print "$fid\n$ts\n$who\n$ann\n//\n";
	}
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3