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

View of /FigKernelScripts/prepare_metagenome_files_for_download.pl

Parent Directory Parent Directory | Revision Log Revision Log


Revision 1.4 - (download) (as text) (annotate)
Wed Jan 30 15:40:49 2008 UTC (12 years ago) by mkubal
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: +5 -1 lines
full loop

if(scalar(@ARGV) != 1){
    print "usage: prepare_metagenome_files_for_download location_of_jobs_dir\n";
    print "example: prepare_metagenome_files_for_download /vol/mg-rast/Jobs.dev\n";
    exit;
}

#$job_dirs such as /vol/mg-rast/Jobs.dev
my $jobs_dir = shift(@ARGV);


opendir(DIR,$jobs_dir);
@jobs = readdir(DIR);
close(DIR);

foreach my $job (@jobs){

    if(! -e "$jobs_dir/$job/PUBLIC"){next}

    print "working on $job\n";

    my $mg_id;
    open(IN,"$jobs_dir/$job/GENOME_ID");
    while($_ = <IN>){
	chomp($_);
	$mg_id = $_;
    }
    close(IN);

    if(! -d "$jobs_dir/$job/download"){
	`mkdir $jobs_dir/$job/download`;
    };
    
    `cp $jobs_dir/$job/rp/$mg_id/Features/peg/fasta $jobs_dir/$job/download/$mg_id.protein.fa`;
    `gzip $jobs_dir/$job/download/$mg_id.protein.fa`;

    `cp $jobs_dir/$job/rp/$mg_id/assigned_functions $jobs_dir/$job/download/$mg_id.functions.txt`;
    `gzip $jobs_dir/$job/download/$mg_id.functions.txt`;   
    
    opendir(DIR,"$jobs_dir/$job/proc");
    my @files = readdir(DIR);
    close(DIR);
    foreach my $file (@files){
	if($file =~/(\d+.fa)$/){
	    `cp $jobs_dir/$job/proc/$file $jobs_dir/$job/download/$mg_id.dna.fa`;
	    `gzip $jobs_dir/$job/download/$mg_id.dna.fa`;
	    last;
	}
    }

    open(INDEX,">$jobs_dir/$job/download/index");
    print INDEX "$mg_id.all_internal_data.tar.gz      MGRAST data directories\n";
    print INDEX "$mg_id.complete.gbk.gz       Genbank File\n";
    print INDEX "$mg_id.dna.fa.gz        Normalized DNA FASTA\n";
    print INDEX "$mg_id.functions.txt.gz Assigned Protein Functions\n";
    print INDEX "$mg_id.protein.fa.gz    Assigned Protein Sequences FASTA\n";
    print INDEX "$mg_id.user_id_to_normalized_unique.txt    User Fragment ID Mapping to MG-RAST ID\n";
    close(INDEX);

    `tar -czf $jobs_dir/$job/download/$mg_id.all_internal_data.tar.gz $jobs_dir/$job/proc $jobs_dir/$job/rp/$mg_id`; 
} 

MCS Webmaster
ViewVC Help
Powered by ViewVC 1.0.3