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

View of /FigKernelScripts/make_spreadsheet_and_notes.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.

#
# 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;

$usage = "usage: make_spreadsheet_and_notes CouplingData SubsysDir User < expanded";

(
 ($couplingF = shift @ARGV) &&
 ($subsysD   = shift @ARGV) &&
 ($user      = shift @ARGV)
)
    || die $usage;

&FIG::verify_dir($subsysD);

open(SPREADSHEET,">$subsysD/spreadsheet") || die "could not open $subsysD/spreadsheet";
open(NOTES,">$subsysD/notes") || die "could not open $subsysD/notes";

if (defined($_ = <STDIN>) && ($_ =~ /^(\d+)/))
{
    print NOTES "Original genomes were required to contain at least $1 of the signature columns\n";
    $_ = <STDIN>;
}
else
{
    die "invalid input";
}

$/ = "\n//\n";
if (defined($_ = <STDIN>))
{
    print SPREADSHEET $_;
    chomp;
    @abbr = map { $_ =~ /^(\S+)/; $1 } split(/\n/,$_);
    
    print SPREADSHEET "All\n\nAll\n//\n";
}

$/ = "\n";
while (defined($_ = <STDIN>) && ($_ !~ /^\/\//))
{
    print SPREADSHEET $_;
    chop;
    @flds = split(/\t/,$_);
    
    for ($i=2; ($i < @flds); $i++)
    {
	@pegs = map { "fig\|$flds[0]\.peg\.$_" } split(/,/,$flds[$i]);
	foreach $peg (@pegs)
	{
	    push(@{$in_col{$peg}},$i-2);
	}
    }
}
print SPREADSHEET "//\n";
close(SPREADSHEET);

open(COUPLED,"<$couplingF") || die "could not open $coupledF";
while (defined($_ = <COUPLED>))
{
    if (($_ =~ /(fig\|\d+\.\d+\.peg\.\d+).*(fig\|\d+\.\d+\.peg\.\d+)/) &&
	(($peg1,$peg2) = ($1,$2)) && ($_ =~ /\s(\d+)\s/) && ($sc = $1))
    {
	$key1 = "$peg1\t$peg2";
	$key2 = "$peg2\t$peg1";
	if ((! $best{$key1}) || ($best{$key1} < $sc))
	{
	    $best{$key1} = $best{$key2} = $sc;
	}
    }
}
close(COUPLED);

@pegs = keys(%in_col);
for ($i=0; ($i < @pegs); $i++)
{
    $peg1 = $pegs[$i];
    $in1  = $in_col{$peg1};
    for ($j=0; ($j < @pegs); $j++)
    {
	if ($i != $j)
	{
	    $peg2 = $pegs[$j];
	    if ($sc = $best{"$peg1\t$peg2"})
	    {
		$in2  = $in_col{$peg2};
		foreach $col1 (@$in1)
		{
		    foreach $col2 (@$in2)
		    {
			$key1 = "$col1\t$col2";
			$key2 = "$col2\t$col1";
			if ((! $bestC{$key1}) || (($_ = $bestC{$key1}) < $sc))
			{
			    $bestC{$key1} = $bestC{$key2} = $sc;
			}
		    }
		}
	    }
	}
    }
}
close(SPREADSHEET);

print NOTES "\nBEGIN COUPLING MATRIX\n\n";
for ($i=0; ($i < $#abbr); $i++)
{
    $abbr1 = $abbr[$i];
    for ($j=$i+1; ($j < @abbr); $j++)
    {
	if ($sc = $bestC{"$i\t$j"})
	{
	    $abbr2 = $abbr[$j];
	    print NOTES "$abbr1\t$abbr2\t$sc\n";
	}
    }
}
print NOTES "\nEND COUPLING MATRIX\n\n";
close(NOTES);

open(LOG,">$subsysD/curation.log") || die "could not open $subsysD/curation.log";
print LOG join("\t",(time,$user,"started")),"\n";
close(LOG);

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3