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

View of /FigKernelScripts/make_ncbi_files.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (download) (as text) (annotate)
Wed May 30 18:00:39 2007 UTC (12 years, 8 months ago) by wilke
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, 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
Changes since 1.3: +11 -4 lines
changed check for existing directories

# -*- 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 FIG;

use Cwd;
use Carp;
use Data::Dumper;
use File::Path;

$0 =~ m/([^\/]+)$/;
$usage = "$1 [-noget] InDir OutDir";

$noget = "";
if ($ARGV[0] && ($ARGV[0] =~ m/-noget/)) { $noget = shift; }

(($indir = shift @ARGV) && ($outdir = shift @ARGV))
    || die "\n\tusage: $usage\n\n";

if (!-d "$indir/NCBI"){
    
    unless ( $noget ) {
	mkpath("$indir/NCBI",  1, 0777)  || die "Could not create $indir/NCBI";
    }
    die "Input directory $indir/NCBI not exists\n";
}


if (!-d "$outdir/NCBI"){
    mkpath("$outdir/NCBI", 1, 0777) || die "Could not create $outdir/NCBI";
}

$base = getcwd();


#+++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++
# get data from ftp://ftp.ncbi.nlm.nih.gov/blast/db/FASTA/
#-----------------------------------------------------------------------
$ncbi_url = "ftp://ftp.ncbi.nlm.nih.gov/blast/db/FASTA";
unless ($noget)
{
    chdir("$indir/NCBI") || die "Could not chdir to $indir/NCBI/, return-code $!";
    if (($test = `which wget`) && ($test !~ m/^which: no wget in/))
    {
	&FIG::run("wget --passive-ftp $ncbi_url/nr.gz");
    }
    elsif (($test = `which curl`) && ($test !~ m/^which: no curl in/))
    {
	&FIG::run("curl --ftp-pasv -O $ncbi_url/nr.gz");
    }
    else
    {
	die "Sorry, could not find either \`wget\` or \`curl\` in path $ENV{PATH}";
    }
    chdir($base)  || die "Could not chdir to $base: $!";
}


if (-s "$indir/NCBI/nr")
{
    print STDERR "Reformating $indir/NCBI/nr --> $outdir/NCBI/fasta\n";
    &FIG::run("reformat_fasta -strip < $indir/NCBI/nr > $outdir/NCBI/fasta");
    open(HDR,  "grep '^>' $indir/NCBI/nr |") || die "could not open $indir/NCBI/nr";
}
elsif (-s "$indir/NCBI/nr.gz")
{
    print STDERR "Reformating $indir/NCBI/nr.gz --> $outdir/NCBI/fasta\n";
    &FIG::run("gunzip -c $indir/NCBI/nr.gz | reformat_fasta -strip > $outdir/NCBI/fasta");
    open(HDR,  "gunzip -c $indir/NCBI/nr.gz | grep '^>' |")
	|| die "could not open $indir/NCBI/nr.gz";
}
else
{
    die "Could not find either $indir/NCBI/nr or $indir/NCBI/nr.gz";
}

open(FUNC, ">$outdir/NCBI/assigned_functions") 
    || die "could not open $outdir/NCBI/assigned_functions";
open(ORG,  ">$outdir/NCBI/org.table") || die "could not open $outdir/NCBI/org.table";

print STDERR "Extracting $outdir/NCBI/assigned_functions and $outdir/NCBI/org.table\n";
while (defined($_ = <HDR>))
{
    if ($_ =~ /^>(\S+)\s+([^\[]+[^ \t\[])?(\s+\[([^\]]+)\])?/)
    {
	$func = $2 ? $2 : "";
	$org  = $4 ? $4 : "";
	$gi = $1;
	$gi =~ s/^([^\|\s]+\|[^\|\s]+).*$/$1/;
	if ($func =~ /included to/) { $func = "" }
	if ($func)
	{
	    print FUNC "$1\t$func\n";
	}
	if ($org =~ /(include|contain)/i) { $org = "" }
	if ($org)
	{
	    print ORG "$1\t$org\n";
	}
    }
    else
    {
	print STDERR $_;
    }
}

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3