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

View of /FigKernelScripts/ListLits.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.1 - (download) (as text) (annotate)
Wed Sep 3 20:22:42 2008 UTC (11 years, 2 months ago) by parrello
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_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_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, HEAD
New script to count literature references for NMPDR.

#!/usr/bin/perl -w

#
# 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 Tracer;
use SFXlate;
use FIG;
use Stats;

=head1 ListLits Script

    ListLits [options] 

Count literature references.

=head2 Introduction

This script counts the C<dlit> and C<ilit> evidence codes for features in NMPDR
genomes. The output will contain the total counts for all genomes and the counts
for only the five core genomes.


=head2 Command-Line Options

=over 4

=item trace

Specifies the tracing level. The higher the tracing level, the more messages
will appear in the trace log. Use E to specify emergency tracing.
[ %END option_map %]

=item user

Name suffix to be used for log files. If omitted, the PID is used.

=item sql

If specified, turns on tracing of SQL activity.

=item background

Save the standard and error output to files. The files will be created
in the FIG temporary directory and will be named C<err>I<User>C<.log> and
C<out>I<User>C<.log>, respectively, where I<User> is the value of the
B<user> option above.

=item help

Display this command's parameters and options.

=item warn

Create an event in the RSS feed when an error occurs.

=item phone

Phone number to message when the script is complete.

=back

=cut

# Get the command-line options and parameters.
my ($options, @parameters) = StandardSetup([qw(ERDB Sprout) ],
                                           {
                                              phone => ["", "phone number (international format) to call when load finishes"]
                                           },
                                           "",
                                           @ARGV);
# Set a variable to contain return type information.
my $rtype;
# Insure we catch errors.
eval {
    # Get the Sprout object.
    my $sprout = SFXlate->new_sprout_only();
    my $fig = FIG->new();
    # Get a hash that can be used to identify the core genomes.
    my %cores = map { $_ => 1 } $sprout->CoreGenomes('core');
    # Get a list of all the genomes.
    my @genomes = $sprout->Genomes();
    # Create a statistics object to count the literature references.
    my $stats = Stats->new(qw(ilit_core dlit_core ilit_all dlit_all));
    # Loop through the genomes.
    for my $genome (@genomes) {
        Trace("Processing $genome.") if T(3);
        # Compute each literature type separately.
        for my $type (qw(dlit ilit)) {
            my $count = $fig->query_attributes('$object LIKE ? AND $key = ? AND $value LIKE ?',
                                               ["fig|$genome.%", 'evidence_code', "$type%"]);
            Trace("Genome $genome has $count $type references.") if T(3);
            if ($cores{$genome}) {
                $stats->Add("${type}_core" => $count);
            }
            $stats->Add("${type}_all", $count);
        }
    }
    # Display the results.
    Trace("Total counts\n" . $stats->Show()) if T(2);
};
if ($@) {
    Trace("Script failed with error: $@") if T(0);
    $rtype = "error";
} else {
    Trace("Script complete.") if T(2);
    $rtype = "no error";
}
if ($options->{phone}) {
    my $msgID = Tracer::SendSMS($options->{phone}, "ListLits terminated with $rtype.");
    if ($msgID) {
        Trace("Phone message sent with ID $msgID.") if T(2);
    } else {
        Trace("Phone message not sent.") if T(2);
    }
}

1;

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3