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

View of /FigKernelScripts/uni_lit_to_dlits.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Wed Jun 25 16:27:30 2008 UTC (11 years, 4 months ago) by overbeek
Branch: MAIN
CVS Tags: mgrast_dev_08112011, rast_rel_2009_05_18, mgrast_dev_08022011, rast_rel_2014_0912, myrast_rel40, 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, 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
dlit support

########################################################################
# -*- 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 strict;
use FIG;
my $fig = new FIG;

my $max_prot = 100;

my @lit;
my %title;
my %count;
my ( $id, $acc, $def, $pmid, $title );

# usage: uni_lit_to_dlits [peg.synonyms] < uniprot_sprot.dat > dlits

my $syns = $ARGV[0] ? $ARGV[0] : "$FIG_Config::global/peg.synonyms";

my %corr;
open(SYN,"<$syns")
    || die "could not open $syns";
while (defined($_ = <SYN>))
{
    if ($_ =~ /^\S+\t(\S.*\S)/)
    {
	my $x = $1;
	my @pairs = map { $_ =~ /^([^,]+),(\d+)/; [$1,$2] } split(/;/,$x);
	my @figP  = grep { $_->[0] =~ /^fig/ } @pairs;
	my @sp    = map { ($_->[0] =~ /^(uni|tr|sp)\|(\S+)/) ? [$2,$_->[1]] : () } @pairs;
	if ((@figP  > 0) && (@sp > 0))
	{
	    my %to_fig;
	    foreach $x (@figP)
	    {
		$to_fig{$x->[1]} = $x->[0];
	    }
	    foreach my $sp (@sp)
	    {
		if (my $peg = $to_fig{$sp->[1]})
		{
		    $corr{$sp->[0]} = $peg;
		}
	    }
	}
    }
}
close(SYN);

while (<>)
{
    chomp;
    my ( $key ) = $_ =~ m/^(\S\S) /;
    s/^(\S\S)   //;
    next unless $key && $_;
    if    ( $key eq 'ID' )
    {
        ( $id ) = split;
        $acc   = [];
        $def   = '';
        $pmid  = undef;
        $title = '';
    }
    elsif ( $key eq 'AC' )
    {
        s/;$//;
        push @$acc, grep { $corr{$_} } split /; /;
    }
    elsif ( $key eq 'DE' )
    {
        $def .= ( $def ? ' ' : '' ) . $_;
    }
    elsif ( $key eq 'RX' )
    {
        ( $pmid ) = $_ =~ /PubMed=(\d+)/;
    }
    elsif ( $key eq 'RT' )
    {
        $title .= ( $title ? ' ' : '' ) . $_;
    }
    elsif ( $key eq 'RL' )
    {
        if ( @$acc && $def && $pmid && $title )
        {
            $def =~ s/\.$//;
            $title =~ s/^"//;
            $title =~ s/";$//;
            $title{ $pmid } = $title;
            $count{ $pmid }++;
            push @lit, [ $pmid, $acc, $def ];
        }
        $pmid  = undef;
        $title = '';
    }
}

foreach (keys(%count))
{
    if ($count{$_} > $max_prot)
    {
#	print STDERR "$count{$_}\t$_\t$title{$_}\n";
    }
}

foreach ( @lit )
{
    ( $pmid, $acc, $def ) = @$_;
    next if ( $count{ $pmid } > $max_prot );
    
    my $i;
    for ($i=0; ($i < @$acc) && (! $corr{$acc->[$i]}); $i++) {}
    if ($i < @$acc)
    {
	my $peg   = $corr{$acc->[$i]};
	my $hash  = $fig->md5_of_peg($peg);
	print join("\t",(" ",$hash,$pmid,"","")),"\n";
	print STDERR join("\t",($pmid,$title{$pmid})),"\n";
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3