Commit earlier refactoring

workflow/.old/apps/remc/GTF/Component/Concatenate_GTF_results.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table
+
+import sys, os, string, glob
+
+
+# return the file list
+def list_all_files(Path):
+    list_all_files = []
+    list_all_files = glob.glob(Path +'/*.txt.tsv')
+    return list_all_files
+
+
+# Main function
+
+try:
+   data_file_Path = sys.argv[1]
+   output_file_Path = sys.argv[2]
+except: 
+   print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
+   print ('Data file not found, error in given directory')
+   sys.exit(1)
+
+# Open the output file
+
+try:
+    output = open(output_file_Path, 'w')
+except OSError:
+    print ('output file error')
+
+# get all the GTF result files in given directory
+File_list = []
+File_list = list_all_files(data_file_Path)
+File_list.sort()
+
+i = 0
+for file in File_list:
+    #parse the file names given in absolute path
+    file_name = file.strip().split('/')[-1]
+    file_name = file_name.rstrip('.txt.tsv')
+    # function to read tsv files from a given directory
+    #open the file
+    data = open(file,'r')
+    #reading the label line
+    labelLine = data.readline()
+    label = labelLine.strip().split('\t')
+    #write the label
+    #updates2010July26: update following label writing code	
+    if i == 0:
+    #    output.write('cluster origin')
+        for element in label:
+            output.write(element)
+            output.write('\t')
+    i = i + 1
+    #updates2010July26 End
+    #switch to the next line
+    output.write('\n')
+
+    #read the GO terms
+    GOTermLines = data.readlines()
+    for GOTerm in GOTermLines:
+        GOTerm = GOTerm.strip().strip('\t')
+        if GOTerm != '':
+	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
+            #output.write(file_name)
+            #output.write('\t')
+	    ##updates2010July26 update end
+            output.write(GOTerm + '\n')
+            #output.write('\n')
+output.close()

workflow/.old/apps/remc/GTF/Component/analyze_v2.pl

@@ -0,0 +1,390 @@
+#!/usr/bin/perl
+
+# $Id: analyze.pl,v 1.9 2008/05/14 20:45:37 sherlock Exp $
+
+# Date   : 16th October 2003
+# Author : Gavin Sherlock
+
+# License information (the MIT license)
+
+# Copyright (c) 2003 Gavin Sherlock; Stanford University
+
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT.  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+use strict;
+use warnings;
+use diagnostics;
+
+use Data::Dumper;
+
+use Getopt::Long;
+
+use IO::File;
+
+use GO::TermFinder;
+use GO::AnnotationProvider::AnnotationParser;
+use GO::OntologyProvider::OboParser;
+
+use GO::TermFinderReport::Text;
+
+use GO::Utils::File    qw (GenesFromFile);
+use GO::Utils::General qw (CategorizeGenes);
+
+$|=1;
+
+###################################################################################
+sub Usage{
+###################################################################################
+
+    my $message = shift;
+
+    if (defined $message){
+
+	print $message, "\n";
+
+    }
+
+    print <<USAGE;
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will only
+output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+analyze.pl -a ../t/gene_association.sgd -n 7200 -o ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+USAGE
+
+    exit;
+
+}
+
+# we need at least 3 arguments, an annotation file, the number of
+# genes in the genome, and a file of input genes to test
+
+&Usage if (@ARGV < 3);
+
+# now get our annotation file and number of genes
+
+my $annotationFile = '';
+my $totalNum       = '';
+my $oboFile        = '';
+my $background	   = '';
+my $aspect	   = '';
+
+GetOptions(	"annotations=s"	=> \$annotationFile,
+		"obofile=s"	=> \$oboFile,
+		"background=s"	=> \$background,
+		"numGenes=i"	=> \$totalNum,
+		"aspect=s"	=> \$aspect
+	);
+
+if ($oboFile !~ /\.obo$/){
+
+    # require the obo file to have a .obo extension
+
+    &Usage("Your obo file does not have a .obo extension.");
+
+}
+
+if ($annotationFile !~ /\.sgd$/){
+	&Usage("Perhaps we are missing an annotation file.");
+}
+
+my @population = ();
+if ($background) {
+	@population = GenesFromFile($background)
+}
+
+# now set up the objects we need
+
+my $process   = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'P');
+my $component = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'C');
+my $function  = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'F');
+
+my $annotation = GO::AnnotationProvider::AnnotationParser->new(annotationFile=>$annotationFile);
+
+my @termFinders = ();
+
+if ($background) {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   population	     => \@population,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   population	     => \@population,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   population	     => \@population,
+						   aspect            => 'F');
+	}
+} else {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'F');
+	}
+}
+
+
+my $report = GO::TermFinderReport::Text->new();
+
+my $cutoff = 0.1;
+
+# now go through each file
+
+foreach my $file (@ARGV){
+
+    print "Analyzing $file\n";
+
+    my @genes = GenesFromFile($file); 
+
+    my (@list, @notFound, @ambiguous);
+
+    CategorizeGenes(annotation  => $annotation,
+		    genes       => \@genes,
+		    ambiguous   => \@ambiguous,
+		    unambiguous => \@list,
+		    notFound    => \@notFound);
+
+    my $outfile = $file.".terms";
+
+    my $fh = IO::File->new($outfile, q{>} )|| die "Cannot make $outfile : $!";
+
+    print "Results being put in $outfile\n";
+
+    if (@list){
+
+	print $fh "The following gene(s) will be considered:\n\n";
+
+	foreach my $gene (@list){
+
+	    print $fh $gene, "\t", $annotation->standardNameByName($gene), "\n";
+
+	}
+
+	print $fh "\n";
+
+    }else{
+
+	print $fh "None of the gene names were recognized\n";
+	print $fh "They were:\n\n";
+	print $fh join("\n", @notFound), "\n";
+	$fh->close;
+
+	next;
+
+    }
+
+    if (@ambiguous){
+
+	# note, some of these ambiguous names would be perfectly fine
+	# if put into GO::TermFinder if they are also standard names.
+	# Currently the behavior of analyze.pl differs from the
+	# default behavior of GO::TermFinder
+
+	print $fh "The following gene(s) are ambiguously named, and so will not be used:\n";
+	print $fh join("\n", @ambiguous), "\n\n";
+
+    }
+
+    if (@notFound){
+
+	print $fh "The following gene(s) were not recognized, and will not be considered:\n\n";
+	print $fh join("\n", @notFound), "\n\n";
+
+    }
+
+    foreach my $termFinder (@termFinders){
+
+	# it's possible that the supplied number of genes on the
+	# command line was less than indicated by the annotation
+	# provider, and thus the TermFinder may have used a larger
+	# number than was entered on the command line.
+
+	my $totalNumGenesUsedInBackground = $termFinder->totalNumGenes;
+
+	print $fh "Finding terms for ", $termFinder->aspect, "\n\n";
+
+	my @pvalues = $termFinder->findTerms(genes => \@list, calculateFDR => 1);
+  if($#pvalues == 0) {
+    print "WARNIING: NO p-value structures returned by findTerms(";
+    print join ",", @list;
+    print ")\n";
+  	print $fh "\n\n";
+    $fh->close;
+    exit();
+  }
+	my $numHypotheses = $report->print(pvalues  => \@pvalues,
+					   numGenes => scalar(@list),
+					   totalNum => $totalNumGenesUsedInBackground,
+					   cutoff   => $cutoff,
+					   fh       => $fh);
+
+  my $numProcesses = $#pvalues + 1;
+  print "Number of GO processes found: $numProcesses\n";
+  print "Number of hypotheses passed cutoff: $numHypotheses\n";
+
+	# if they had no significant P-values
+
+	if ($numHypotheses == 0){
+
+	    print $fh "No terms were found for this aspect with a corrected P-value <= $cutoff.\n";
+
+	}
+
+	print $fh "\n\n";
+
+    }
+
+    $fh->close;    
+    
+}
+
+=pod
+
+=head1 NAME
+
+analyze.pl - batch processor to find terms for lists of genes in various files
+
+=head1 SYNOPSIS
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will
+only output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+    analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+    analyze.pl ../t/gene_association.sgd 7200 ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+An example output file might look like this:
+
+    The following gene(s) will be considered:
+    
+    YDL235C YPD1
+    YDL224C WHI4
+    YDL225W SHS1
+    YDL226C GCS1
+    YDL227C HO
+    YDL228C YDL228C
+    YDL229W SSB1
+    YDL230W PTP1
+    YDL231C BRE4
+    YDL232W OST4
+    YDL233W YDL233W
+    YDL234C GYP7
+    
+    Finding terms for P
+    
+    
+    Finding terms for C
+    
+    
+    Finding terms for F
+    
+    -- 1 of 15--
+    GOID    GO:0005096
+    TERM    GTPase activator activity
+    CORRECTED P-VALUE       0.0113038452336839
+    UNCORRECTED P-VALUE     0.00113038452336839
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 31 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 2 of 15--
+    GOID    GO:0008047
+    TERM    enzyme activator activity
+    CORRECTED P-VALUE       0.0316194107645226
+    UNCORRECTED P-VALUE     0.00316194107645226
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 52 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 3 of 15--
+    GOID    GO:0005083
+    TERM    small GTPase regulatory/interacting protein activity
+    CORRECTED P-VALUE       0.0340606972468798
+    UNCORRECTED P-VALUE     0.00340606972468798
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 54 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 4 of 15--
+    GOID    GO:0030695
+    TERM    GTPase regulator activity
+    CORRECTED P-VALUE       0.0475469908576535
+    UNCORRECTED P-VALUE     0.00475469908576535
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 64 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+
+=head1 AUTHORS
+
+Gavin Sherlock, sherlock@genome.stanford.edu
+
+=cut

workflow/.old/apps/remc/GTF/Component/terms2tsv_v4.pl

@@ -0,0 +1,55 @@
+#!/usr/bin/perl
+use strict;
+use warnings;
+use diagnostics;
+
+use File::Map qw(map_file);
+
+my $infile = shift;
+
+my $input;
+
+map_file $input, $infile;
+
+{
+	local $_	= $input;
+	(my $f		= $infile) =~ s/(.*\/)?(.*)(\.[^\.]*){2}/$2/;
+	my %orfgene	= (/(Y\w+)\s+(\w+)\n/g);
+	my @indices	= (/\Q-- \E(\d+) of \d+\Q --\E/g);
+	my @ids		= (/GOID\s+GO:(\d+)/g);
+	my @terms	= (/TERM\s+(.*?)\n/g);
+	my @pvalues	= (/\nCORRECTED P-VALUE\s+(\d.*?)\n/g);
+	my @clusterf	= (/NUM_ANNOTATIONS\s+(\d+ of \d+)/g);
+	my @bgfreq	= (/, vs (\d+ of \d+) in the genome/g);
+	my @orfs	= (/The genes annotated to this node are:\n(.*?)\n/g);
+	
+	s/, /:/g for @orfs;
+
+	my @genes;
+	for my $orf (@orfs) {
+		my @otmp = split /:/, $orf;
+		my @gtmp = map { $orfgene{$_} } @otmp;
+		push @genes, (join ':', @gtmp);
+	}
+
+	&header();
+	for my $i (0 .. (@ids - 1)) {
+		&report($f, $ids[$i], $terms[$i], $pvalues[$i], $clusterf[$i], $bgfreq[$i], $orfs[$i], $genes[$i]);
+	}
+}
+
+sub header {
+	print "REMc ID\tGO_term ID\tGO-term\tCluster frequency\tBackground frequency\tP-value\tORFs\tGenes\n";
+}
+
+sub report {
+	my ($f, $id, $term, $p, $cfreq, $bgfreq, $orfs, $genes) = @_;
+
+	$cfreq =~ /(\d+) of (\d+)/;
+	$cfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	$bgfreq =~ /(\d+) of (\d+)/;
+	$bgfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	print "$f\t$id\t$term\t$cfreq\t$bgfreq\t$p\t$orfs\t$genes\n";
+}

workflow/.old/apps/remc/GTF/Concatenate_GTF_results.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table
+
+import sys, os, string, glob
+
+
+# return the file list
+def list_all_files(Path):
+    list_all_files = []
+    list_all_files = glob.glob(Path +'/*.txt.tsv')
+    return list_all_files
+
+
+# Main function
+
+try:
+   data_file_Path = sys.argv[1]
+   output_file_Path = sys.argv[2]
+except: 
+   print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
+   print ('Data file not found, error in given directory')
+   sys.exit(1)
+
+# Open the output file
+
+try:
+    output = open(output_file_Path, 'w')
+except OSError:
+    print ('output file error')
+
+# get all the GTF result files in given directory
+File_list = []
+File_list = list_all_files(data_file_Path)
+File_list.sort()
+
+i = 0
+for file in File_list:
+    #parse the file names given in absolute path
+    file_name = file.strip().split('/')[-1]
+    file_name = file_name.rstrip('.txt.tsv')
+    # function to read tsv files from a given directory
+    #open the file
+    data = open(file,'r')
+    #reading the label line
+    labelLine = data.readline()
+    label = labelLine.strip().split('\t')
+    #write the label
+    #updates2010July26: update following label writing code	
+    if i == 0:
+    #    output.write('cluster origin')
+        for element in label:
+            output.write(element)
+            output.write('\t')
+    i = i + 1
+    #updates2010July26 End
+    #switch to the next line
+    output.write('\n')
+
+    #read the GO terms
+    GOTermLines = data.readlines()
+    for GOTerm in GOTermLines:
+        GOTerm = GOTerm.strip().strip('\t')
+        if GOTerm != '':
+	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
+            #output.write(file_name)
+            #output.write('\t')
+	    ##updates2010July26 update end
+            output.write(GOTerm + '\n')
+            #output.write('\n')
+output.close()

workflow/.old/apps/remc/GTF/Function/Concatenate_GTF_results.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table
+
+import sys, os, string, glob
+
+
+# return the file list
+def list_all_files(Path):
+    list_all_files = []
+    list_all_files = glob.glob(Path +'/*.txt.tsv')
+    return list_all_files
+
+
+# Main function
+
+try:
+   data_file_Path = sys.argv[1]
+   output_file_Path = sys.argv[2]
+except: 
+   print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
+   print ('Data file not found, error in given directory')
+   sys.exit(1)
+
+# Open the output file
+
+try:
+    output = open(output_file_Path, 'w')
+except OSError:
+    print ('output file error')
+
+# get all the GTF result files in given directory
+File_list = []
+File_list = list_all_files(data_file_Path)
+File_list.sort()
+
+i = 0
+for file in File_list:
+    #parse the file names given in absolute path
+    file_name = file.strip().split('/')[-1]
+    file_name = file_name.rstrip('.txt.tsv')
+    # function to read tsv files from a given directory
+    #open the file
+    data = open(file,'r')
+    #reading the label line
+    labelLine = data.readline()
+    label = labelLine.strip().split('\t')
+    #write the label
+    #updates2010July26: update following label writing code	
+    if i == 0:
+    #    output.write('cluster origin')
+        for element in label:
+            output.write(element)
+            output.write('\t')
+    i = i + 1
+    #updates2010July26 End
+    #switch to the next line
+    output.write('\n')
+
+    #read the GO terms
+    GOTermLines = data.readlines()
+    for GOTerm in GOTermLines:
+        GOTerm = GOTerm.strip().strip('\t')
+        if GOTerm != '':
+	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
+            #output.write(file_name)
+            #output.write('\t')
+	    ##updates2010July26 update end
+            output.write(GOTerm + '\n')
+            #output.write('\n')
+output.close()

workflow/.old/apps/remc/GTF/Function/analyze_v2.pl

@@ -0,0 +1,390 @@
+#!/usr/bin/perl
+
+# $Id: analyze.pl,v 1.9 2008/05/14 20:45:37 sherlock Exp $
+
+# Date   : 16th October 2003
+# Author : Gavin Sherlock
+
+# License information (the MIT license)
+
+# Copyright (c) 2003 Gavin Sherlock; Stanford University
+
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT.  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+use strict;
+use warnings;
+use diagnostics;
+
+use Data::Dumper;
+
+use Getopt::Long;
+
+use IO::File;
+
+use GO::TermFinder;
+use GO::AnnotationProvider::AnnotationParser;
+use GO::OntologyProvider::OboParser;
+
+use GO::TermFinderReport::Text;
+
+use GO::Utils::File    qw (GenesFromFile);
+use GO::Utils::General qw (CategorizeGenes);
+
+$|=1;
+
+###################################################################################
+sub Usage{
+###################################################################################
+
+    my $message = shift;
+
+    if (defined $message){
+
+	print $message, "\n";
+
+    }
+
+    print <<USAGE;
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will only
+output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+analyze.pl -a ../t/gene_association.sgd -n 7200 -o ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+USAGE
+
+    exit;
+
+}
+
+# we need at least 3 arguments, an annotation file, the number of
+# genes in the genome, and a file of input genes to test
+
+&Usage if (@ARGV < 3);
+
+# now get our annotation file and number of genes
+
+my $annotationFile = '';
+my $totalNum       = '';
+my $oboFile        = '';
+my $background	   = '';
+my $aspect	   = '';
+
+GetOptions(	"annotations=s"	=> \$annotationFile,
+		"obofile=s"	=> \$oboFile,
+		"background=s"	=> \$background,
+		"numGenes=i"	=> \$totalNum,
+		"aspect=s"	=> \$aspect
+	);
+
+if ($oboFile !~ /\.obo$/){
+
+    # require the obo file to have a .obo extension
+
+    &Usage("Your obo file does not have a .obo extension.");
+
+}
+
+if ($annotationFile !~ /\.sgd$/){
+	&Usage("Perhaps we are missing an annotation file.");
+}
+
+my @population = ();
+if ($background) {
+	@population = GenesFromFile($background)
+}
+
+# now set up the objects we need
+
+my $process   = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'P');
+my $component = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'C');
+my $function  = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'F');
+
+my $annotation = GO::AnnotationProvider::AnnotationParser->new(annotationFile=>$annotationFile);
+
+my @termFinders = ();
+
+if ($background) {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   population	     => \@population,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   population	     => \@population,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   population	     => \@population,
+						   aspect            => 'F');
+	}
+} else {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'F');
+	}
+}
+
+
+my $report = GO::TermFinderReport::Text->new();
+
+my $cutoff = 0.1;
+
+# now go through each file
+
+foreach my $file (@ARGV){
+
+    print "Analyzing $file\n";
+
+    my @genes = GenesFromFile($file); 
+
+    my (@list, @notFound, @ambiguous);
+
+    CategorizeGenes(annotation  => $annotation,
+		    genes       => \@genes,
+		    ambiguous   => \@ambiguous,
+		    unambiguous => \@list,
+		    notFound    => \@notFound);
+
+    my $outfile = $file.".terms";
+
+    my $fh = IO::File->new($outfile, q{>} )|| die "Cannot make $outfile : $!";
+
+    print "Results being put in $outfile\n";
+
+    if (@list){
+
+	print $fh "The following gene(s) will be considered:\n\n";
+
+	foreach my $gene (@list){
+
+	    print $fh $gene, "\t", $annotation->standardNameByName($gene), "\n";
+
+	}
+
+	print $fh "\n";
+
+    }else{
+
+	print $fh "None of the gene names were recognized\n";
+	print $fh "They were:\n\n";
+	print $fh join("\n", @notFound), "\n";
+	$fh->close;
+
+	next;
+
+    }
+
+    if (@ambiguous){
+
+	# note, some of these ambiguous names would be perfectly fine
+	# if put into GO::TermFinder if they are also standard names.
+	# Currently the behavior of analyze.pl differs from the
+	# default behavior of GO::TermFinder
+
+	print $fh "The following gene(s) are ambiguously named, and so will not be used:\n";
+	print $fh join("\n", @ambiguous), "\n\n";
+
+    }
+
+    if (@notFound){
+
+	print $fh "The following gene(s) were not recognized, and will not be considered:\n\n";
+	print $fh join("\n", @notFound), "\n\n";
+
+    }
+
+    foreach my $termFinder (@termFinders){
+
+	# it's possible that the supplied number of genes on the
+	# command line was less than indicated by the annotation
+	# provider, and thus the TermFinder may have used a larger
+	# number than was entered on the command line.
+
+	my $totalNumGenesUsedInBackground = $termFinder->totalNumGenes;
+
+	print $fh "Finding terms for ", $termFinder->aspect, "\n\n";
+
+	my @pvalues = $termFinder->findTerms(genes => \@list, calculateFDR => 1);
+  if($#pvalues == 0) {
+    print "WARNIING: NO p-value structures returned by findTerms(";
+    print join ",", @list;
+    print ")\n";
+  	print $fh "\n\n";
+    $fh->close;
+    exit();
+  }
+	my $numHypotheses = $report->print(pvalues  => \@pvalues,
+					   numGenes => scalar(@list),
+					   totalNum => $totalNumGenesUsedInBackground,
+					   cutoff   => $cutoff,
+					   fh       => $fh);
+
+  my $numProcesses = $#pvalues + 1;
+  print "Number of GO processes found: $numProcesses\n";
+  print "Number of hypotheses passed cutoff: $numHypotheses\n";
+
+	# if they had no significant P-values
+
+	if ($numHypotheses == 0){
+
+	    print $fh "No terms were found for this aspect with a corrected P-value <= $cutoff.\n";
+
+	}
+
+	print $fh "\n\n";
+
+    }
+
+    $fh->close;    
+    
+}
+
+=pod
+
+=head1 NAME
+
+analyze.pl - batch processor to find terms for lists of genes in various files
+
+=head1 SYNOPSIS
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will
+only output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+    analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+    analyze.pl ../t/gene_association.sgd 7200 ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+An example output file might look like this:
+
+    The following gene(s) will be considered:
+    
+    YDL235C YPD1
+    YDL224C WHI4
+    YDL225W SHS1
+    YDL226C GCS1
+    YDL227C HO
+    YDL228C YDL228C
+    YDL229W SSB1
+    YDL230W PTP1
+    YDL231C BRE4
+    YDL232W OST4
+    YDL233W YDL233W
+    YDL234C GYP7
+    
+    Finding terms for P
+    
+    
+    Finding terms for C
+    
+    
+    Finding terms for F
+    
+    -- 1 of 15--
+    GOID    GO:0005096
+    TERM    GTPase activator activity
+    CORRECTED P-VALUE       0.0113038452336839
+    UNCORRECTED P-VALUE     0.00113038452336839
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 31 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 2 of 15--
+    GOID    GO:0008047
+    TERM    enzyme activator activity
+    CORRECTED P-VALUE       0.0316194107645226
+    UNCORRECTED P-VALUE     0.00316194107645226
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 52 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 3 of 15--
+    GOID    GO:0005083
+    TERM    small GTPase regulatory/interacting protein activity
+    CORRECTED P-VALUE       0.0340606972468798
+    UNCORRECTED P-VALUE     0.00340606972468798
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 54 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 4 of 15--
+    GOID    GO:0030695
+    TERM    GTPase regulator activity
+    CORRECTED P-VALUE       0.0475469908576535
+    UNCORRECTED P-VALUE     0.00475469908576535
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 64 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+
+=head1 AUTHORS
+
+Gavin Sherlock, sherlock@genome.stanford.edu
+
+=cut

workflow/.old/apps/remc/GTF/Function/terms2tsv_v4.pl

@@ -0,0 +1,55 @@
+#!/usr/bin/perl
+use strict;
+use warnings;
+use diagnostics;
+
+use File::Map qw(map_file);
+
+my $infile = shift;
+
+my $input;
+
+map_file $input, $infile;
+
+{
+	local $_	= $input;
+	(my $f		= $infile) =~ s/(.*\/)?(.*)(\.[^\.]*){2}/$2/;
+	my %orfgene	= (/(Y\w+)\s+(\w+)\n/g);
+	my @indices	= (/\Q-- \E(\d+) of \d+\Q --\E/g);
+	my @ids		= (/GOID\s+GO:(\d+)/g);
+	my @terms	= (/TERM\s+(.*?)\n/g);
+	my @pvalues	= (/\nCORRECTED P-VALUE\s+(\d.*?)\n/g);
+	my @clusterf	= (/NUM_ANNOTATIONS\s+(\d+ of \d+)/g);
+	my @bgfreq	= (/, vs (\d+ of \d+) in the genome/g);
+	my @orfs	= (/The genes annotated to this node are:\n(.*?)\n/g);
+	
+	s/, /:/g for @orfs;
+
+	my @genes;
+	for my $orf (@orfs) {
+		my @otmp = split /:/, $orf;
+		my @gtmp = map { $orfgene{$_} } @otmp;
+		push @genes, (join ':', @gtmp);
+	}
+
+	&header();
+	for my $i (0 .. (@ids - 1)) {
+		&report($f, $ids[$i], $terms[$i], $pvalues[$i], $clusterf[$i], $bgfreq[$i], $orfs[$i], $genes[$i]);
+	}
+}
+
+sub header {
+	print "REMc ID\tGO_term ID\tGO-term\tCluster frequency\tBackground frequency\tP-value\tORFs\tGenes\n";
+}
+
+sub report {
+	my ($f, $id, $term, $p, $cfreq, $bgfreq, $orfs, $genes) = @_;
+
+	$cfreq =~ /(\d+) of (\d+)/;
+	$cfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	$bgfreq =~ /(\d+) of (\d+)/;
+	$bgfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	print "$f\t$id\t$term\t$cfreq\t$bgfreq\t$p\t$orfs\t$genes\n";
+}

workflow/.old/apps/remc/GTF/GOontologyPar.sh

@@ -0,0 +1,5 @@
+#nohup sh ./Process.sh ORF_List_Without_DAmPs.txt ../../REMcRdy_lm_only/*.txt &
+#nohup sh ./Function.sh ORF_List_Without_DAmPs.txt ../../REMcRdy_lm_only/*.txt &
+#nohup sh ./Component.sh ORF_List_Without_DAmPs.txt ../../REMcRdy_lm_only/*.txt &
+
+sh ./Process.sh ORF_List_Without_DAmPs.txt ../../REMcRdy_lm_only/*.txt &

workflow/.old/apps/remc/GTF/Process/.~lock.PresltDebug.txt#

@@ -0,0 +1 @@
+,jwrodger,hartmanlab.genetics.uab.edu,28.07.2022 09:10,file:///home/jwrodger/.config/libreoffice/4;

workflow/.old/apps/remc/GTF/Process/Concatenate_GTF_results.py

@@ -0,0 +1,71 @@
+#!/usr/bin/env python
+
+# This code is to concatenate the batch GO Term Finder results (.tsv) generated from batch GTF perl code(Chris Johnson, U of Tulsa) into a list table
+
+import sys, os, string, glob
+
+
+# return the file list
+def list_all_files(Path):
+    list_all_files = []
+    list_all_files = glob.glob(Path +'/*.txt.tsv')
+    return list_all_files
+
+
+# Main function
+
+try:
+   data_file_Path = sys.argv[1]
+   output_file_Path = sys.argv[2]
+except: 
+   print ('Usage: python Concatenate_GTF_results.py /datasetPath /outputFilePath_and_Name')
+   print ('Data file not found, error in given directory')
+   sys.exit(1)
+
+# Open the output file
+
+try:
+    output = open(output_file_Path, 'w')
+except OSError:
+    print ('output file error')
+
+# get all the GTF result files in given directory
+File_list = []
+File_list = list_all_files(data_file_Path)
+File_list.sort()
+
+i = 0
+for file in File_list:
+    #parse the file names given in absolute path
+    file_name = file.strip().split('/')[-1]
+    file_name = file_name.rstrip('.txt.tsv')
+    # function to read tsv files from a given directory
+    #open the file
+    data = open(file,'r')
+    #reading the label line
+    labelLine = data.readline()
+    label = labelLine.strip().split('\t')
+    #write the label
+    #updates2010July26: update following label writing code	
+    if i == 0:
+    #    output.write('cluster origin')
+        for element in label:
+            output.write(element)
+            output.write('\t')
+    i = i + 1
+    #updates2010July26 End
+    #switch to the next line
+    output.write('\n')
+
+    #read the GO terms
+    GOTermLines = data.readlines()
+    for GOTerm in GOTermLines:
+        GOTerm = GOTerm.strip().strip('\t')
+        if GOTerm != '':
+	    #updates2010July26: remove the code to write the first column 'REMc cluster ID'
+            #output.write(file_name)
+            #output.write('\t')
+	    ##updates2010July26 update end
+            output.write(GOTerm + '\n')
+            #output.write('\n')
+output.close()

workflow/.old/apps/remc/GTF/Process/analyze_v2.pl

@@ -0,0 +1,390 @@
+#!/usr/bin/perl
+
+# $Id: analyze.pl,v 1.9 2008/05/14 20:45:37 sherlock Exp $
+
+# Date   : 16th October 2003
+# Author : Gavin Sherlock
+
+# License information (the MIT license)
+
+# Copyright (c) 2003 Gavin Sherlock; Stanford University
+
+# Permission is hereby granted, free of charge, to any person
+# obtaining a copy of this software and associated documentation files
+# (the "Software"), to deal in the Software without restriction,
+# including without limitation the rights to use, copy, modify, merge,
+# publish, distribute, sublicense, and/or sell copies of the Software,
+# and to permit persons to whom the Software is furnished to do so,
+# subject to the following conditions:
+
+# The above copyright notice and this permission notice shall be
+# included in all copies or substantial portions of the Software.
+
+# THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND,
+# EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
+# MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND
+# NONINFRINGEMENT.  IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS
+# BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN
+# ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN
+# CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+# SOFTWARE.
+
+use strict;
+use warnings;
+use diagnostics;
+
+use Data::Dumper;
+
+use Getopt::Long;
+
+use IO::File;
+
+use GO::TermFinder;
+use GO::AnnotationProvider::AnnotationParser;
+use GO::OntologyProvider::OboParser;
+
+use GO::TermFinderReport::Text;
+
+use GO::Utils::File    qw (GenesFromFile);
+use GO::Utils::General qw (CategorizeGenes);
+
+$|=1;
+
+###################################################################################
+sub Usage{
+###################################################################################
+
+    my $message = shift;
+
+    if (defined $message){
+
+	print $message, "\n";
+
+    }
+
+    print <<USAGE;
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will only
+output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+analyze.pl -a ../t/gene_association.sgd -n 7200 -o ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+USAGE
+
+    exit;
+
+}
+
+# we need at least 3 arguments, an annotation file, the number of
+# genes in the genome, and a file of input genes to test
+
+&Usage if (@ARGV < 3);
+
+# now get our annotation file and number of genes
+
+my $annotationFile = '';
+my $totalNum       = '';
+my $oboFile        = '';
+my $background	   = '';
+my $aspect	   = '';
+
+GetOptions(	"annotations=s"	=> \$annotationFile,
+		"obofile=s"	=> \$oboFile,
+		"background=s"	=> \$background,
+		"numGenes=i"	=> \$totalNum,
+		"aspect=s"	=> \$aspect
+	);
+
+if ($oboFile !~ /\.obo$/){
+
+    # require the obo file to have a .obo extension
+
+    &Usage("Your obo file does not have a .obo extension.");
+
+}
+
+if ($annotationFile !~ /\.sgd$/){
+	&Usage("Perhaps we are missing an annotation file.");
+}
+
+my @population = ();
+if ($background) {
+	@population = GenesFromFile($background)
+}
+
+# now set up the objects we need
+
+my $process   = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'P');
+my $component = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'C');
+my $function  = GO::OntologyProvider::OboParser->new(ontologyFile => $oboFile,
+						     aspect       => 'F');
+
+my $annotation = GO::AnnotationProvider::AnnotationParser->new(annotationFile=>$annotationFile);
+
+my @termFinders = ();
+
+if ($background) {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   population	     => \@population,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   population	     => \@population,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   population	     => \@population,
+						   aspect            => 'F');
+	}
+} else {
+	if ($aspect =~ /^P$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+		   				   ontologyProvider  => $process,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'P');
+	}
+	
+	if ($aspect =~ /^C$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $component,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'C');
+	}
+	
+	if ($aspect =~ /^F$|^$/) {
+		push @termFinders, GO::TermFinder->new(annotationProvider=> $annotation,
+						   ontologyProvider  => $function,
+						   totalNumGenes     => $totalNum,
+						   aspect            => 'F');
+	}
+}
+
+
+my $report = GO::TermFinderReport::Text->new();
+
+my $cutoff = 0.1;
+
+# now go through each file
+
+foreach my $file (@ARGV){
+
+    print "Analyzing $file\n";
+
+    my @genes = GenesFromFile($file); 
+
+    my (@list, @notFound, @ambiguous);
+
+    CategorizeGenes(annotation  => $annotation,
+		    genes       => \@genes,
+		    ambiguous   => \@ambiguous,
+		    unambiguous => \@list,
+		    notFound    => \@notFound);
+
+    my $outfile = $file.".terms";
+
+    my $fh = IO::File->new($outfile, q{>} )|| die "Cannot make $outfile : $!";
+
+    print "Results being put in $outfile\n";
+
+    if (@list){
+
+	print $fh "The following gene(s) will be considered:\n\n";
+
+	foreach my $gene (@list){
+
+	    print $fh $gene, "\t", $annotation->standardNameByName($gene), "\n";
+
+	}
+
+	print $fh "\n";
+
+    }else{
+
+	print $fh "None of the gene names were recognized\n";
+	print $fh "They were:\n\n";
+	print $fh join("\n", @notFound), "\n";
+	$fh->close;
+
+	next;
+
+    }
+
+    if (@ambiguous){
+
+	# note, some of these ambiguous names would be perfectly fine
+	# if put into GO::TermFinder if they are also standard names.
+	# Currently the behavior of analyze.pl differs from the
+	# default behavior of GO::TermFinder
+
+	print $fh "The following gene(s) are ambiguously named, and so will not be used:\n";
+	print $fh join("\n", @ambiguous), "\n\n";
+
+    }
+
+    if (@notFound){
+
+	print $fh "The following gene(s) were not recognized, and will not be considered:\n\n";
+	print $fh join("\n", @notFound), "\n\n";
+
+    }
+
+    foreach my $termFinder (@termFinders){
+
+	# it's possible that the supplied number of genes on the
+	# command line was less than indicated by the annotation
+	# provider, and thus the TermFinder may have used a larger
+	# number than was entered on the command line.
+
+	my $totalNumGenesUsedInBackground = $termFinder->totalNumGenes;
+
+	print $fh "Finding terms for ", $termFinder->aspect, "\n\n";
+
+	my @pvalues = $termFinder->findTerms(genes => \@list, calculateFDR => 1);
+  if($#pvalues == 0) {
+    print "WARNIING: NO p-value structures returned by findTerms(";
+    print join ",", @list;
+    print ")\n";
+  	print $fh "\n\n";
+    $fh->close;
+    exit();
+  }
+	my $numHypotheses = $report->print(pvalues  => \@pvalues,
+					   numGenes => scalar(@list),
+					   totalNum => $totalNumGenesUsedInBackground,
+					   cutoff   => $cutoff,
+					   fh       => $fh);
+
+  my $numProcesses = $#pvalues + 1;
+  print "Number of GO processes found: $numProcesses\n";
+  print "Number of hypotheses passed cutoff: $numHypotheses\n";
+
+	# if they had no significant P-values
+
+	if ($numHypotheses == 0){
+
+	    print $fh "No terms were found for this aspect with a corrected P-value <= $cutoff.\n";
+
+	}
+
+	print $fh "\n\n";
+
+    }
+
+    $fh->close;    
+    
+}
+
+=pod
+
+=head1 NAME
+
+analyze.pl - batch processor to find terms for lists of genes in various files
+
+=head1 SYNOPSIS
+
+This program takes a list of files, each of which contain a list of
+genes, with one gene per line.  It will findTerms for the lists of
+genes in each of the GO aspects, outputting the results to a file
+named for the original file, but with a .terms extension.  It will
+only output terms with a corrected P-value of <= 0.05.
+
+It will use the first supplied argument as the annotation file, the
+second argument as the expected number of genes within the organism,
+the third argument is the name of the obo file, and all subsequent
+files as ones containing lists of genes.
+
+Usage:
+
+    analyze.pl <annotation_file> <numGenes> <obofile> <file1> <file2> <file3> ... <fileN>
+
+e.g.
+
+    analyze.pl ../t/gene_association.sgd 7200 ../t/gene_ontology_edit.obo genes.txt genes2.txt
+
+An example output file might look like this:
+
+    The following gene(s) will be considered:
+    
+    YDL235C YPD1
+    YDL224C WHI4
+    YDL225W SHS1
+    YDL226C GCS1
+    YDL227C HO
+    YDL228C YDL228C
+    YDL229W SSB1
+    YDL230W PTP1
+    YDL231C BRE4
+    YDL232W OST4
+    YDL233W YDL233W
+    YDL234C GYP7
+    
+    Finding terms for P
+    
+    
+    Finding terms for C
+    
+    
+    Finding terms for F
+    
+    -- 1 of 15--
+    GOID    GO:0005096
+    TERM    GTPase activator activity
+    CORRECTED P-VALUE       0.0113038452336839
+    UNCORRECTED P-VALUE     0.00113038452336839
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 31 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 2 of 15--
+    GOID    GO:0008047
+    TERM    enzyme activator activity
+    CORRECTED P-VALUE       0.0316194107645226
+    UNCORRECTED P-VALUE     0.00316194107645226
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 52 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 3 of 15--
+    GOID    GO:0005083
+    TERM    small GTPase regulatory/interacting protein activity
+    CORRECTED P-VALUE       0.0340606972468798
+    UNCORRECTED P-VALUE     0.00340606972468798
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 54 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+    -- 4 of 15--
+    GOID    GO:0030695
+    TERM    GTPase regulator activity
+    CORRECTED P-VALUE       0.0475469908576535
+    UNCORRECTED P-VALUE     0.00475469908576535
+    NUM_ANNOTATIONS 2 of 12 in the list, vs 64 of 7272 in the genome
+    The genes annotated to this node are:
+    YDL234C, YDL226C
+
+=head1 AUTHORS
+
+Gavin Sherlock, sherlock@genome.stanford.edu
+
+=cut

workflow/.old/apps/remc/GTF/Process/terms2tsv_v4.pl

@@ -0,0 +1,55 @@
+#!/usr/bin/perl
+use strict;
+use warnings;
+use diagnostics;
+
+use File::Map qw(map_file);
+
+my $infile = shift;
+
+my $input;
+
+map_file $input, $infile;
+
+{
+	local $_	= $input;
+	(my $f		= $infile) =~ s/(.*\/)?(.*)(\.[^\.]*){2}/$2/;
+	my %orfgene	= (/(Y\w+)\s+(\w+)\n/g);
+	my @indices	= (/\Q-- \E(\d+) of \d+\Q --\E/g);
+	my @ids		= (/GOID\s+GO:(\d+)/g);
+	my @terms	= (/TERM\s+(.*?)\n/g);
+	my @pvalues	= (/\nCORRECTED P-VALUE\s+(\d.*?)\n/g);
+	my @clusterf	= (/NUM_ANNOTATIONS\s+(\d+ of \d+)/g);
+	my @bgfreq	= (/, vs (\d+ of \d+) in the genome/g);
+	my @orfs	= (/The genes annotated to this node are:\n(.*?)\n/g);
+	
+	s/, /:/g for @orfs;
+
+	my @genes;
+	for my $orf (@orfs) {
+		my @otmp = split /:/, $orf;
+		my @gtmp = map { $orfgene{$_} } @otmp;
+		push @genes, (join ':', @gtmp);
+	}
+
+	&header();
+	for my $i (0 .. (@ids - 1)) {
+		&report($f, $ids[$i], $terms[$i], $pvalues[$i], $clusterf[$i], $bgfreq[$i], $orfs[$i], $genes[$i]);
+	}
+}
+
+sub header {
+	print "REMc ID\tGO_term ID\tGO-term\tCluster frequency\tBackground frequency\tP-value\tORFs\tGenes\n";
+}
+
+sub report {
+	my ($f, $id, $term, $p, $cfreq, $bgfreq, $orfs, $genes) = @_;
+
+	$cfreq =~ /(\d+) of (\d+)/;
+	$cfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	$bgfreq =~ /(\d+) of (\d+)/;
+	$bgfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	print "$f\t$id\t$term\t$cfreq\t$bgfreq\t$p\t$orfs\t$genes\n";
+}

workflow/.old/apps/remc/GTF/SeanEmailPython2

@@ -0,0 +1,11 @@
+
+DconJG.py issue
+Santos, Sean M
+Tue 2/22/2022 9:20 PM
+Hi John,
+
+ I found if you use python2 instead of python you should be able to run the code.
+
+Best,
+Sean
+

workflow/.old/apps/remc/GTF/terms2tsv_v4.pl

@@ -0,0 +1,55 @@
+#!/usr/bin/perl
+use strict;
+use warnings;
+use diagnostics;
+
+use File::Map qw(map_file);
+
+my $infile = shift;
+
+my $input;
+
+map_file $input, $infile;
+
+{
+	local $_	= $input;
+	(my $f		= $infile) =~ s/(.*\/)?(.*)(\.[^\.]*){2}/$2/;
+	my %orfgene	= (/(Y\w+)\s+(\w+)\n/g);
+	my @indices	= (/\Q-- \E(\d+) of \d+\Q --\E/g);
+	my @ids		= (/GOID\s+GO:(\d+)/g);
+	my @terms	= (/TERM\s+(.*?)\n/g);
+	my @pvalues	= (/\nCORRECTED P-VALUE\s+(\d.*?)\n/g);
+	my @clusterf	= (/NUM_ANNOTATIONS\s+(\d+ of \d+)/g);
+	my @bgfreq	= (/, vs (\d+ of \d+) in the genome/g);
+	my @orfs	= (/The genes annotated to this node are:\n(.*?)\n/g);
+	
+	s/, /:/g for @orfs;
+
+	my @genes;
+	for my $orf (@orfs) {
+		my @otmp = split /:/, $orf;
+		my @gtmp = map { $orfgene{$_} } @otmp;
+		push @genes, (join ':', @gtmp);
+	}
+
+	&header();
+	for my $i (0 .. (@ids - 1)) {
+		&report($f, $ids[$i], $terms[$i], $pvalues[$i], $clusterf[$i], $bgfreq[$i], $orfs[$i], $genes[$i]);
+	}
+}
+
+sub header {
+	print "REMc ID\tGO_term ID\tGO-term\tCluster frequency\tBackground frequency\tP-value\tORFs\tGenes\n";
+}
+
+sub report {
+	my ($f, $id, $term, $p, $cfreq, $bgfreq, $orfs, $genes) = @_;
+
+	$cfreq =~ /(\d+) of (\d+)/;
+	$cfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	$bgfreq =~ /(\d+) of (\d+)/;
+	$bgfreq = sprintf "%d out of %d genes, %.1f%%", $1, $2, (100*$1/$2);
+
+	print "$f\t$id\t$term\t$cfreq\t$bgfreq\t$p\t$orfs\t$genes\n";
+}

workflow/.old/apps/remc/ORF_List_DAmPs_Only.txt

@@ -0,0 +1,879 @@
+YAL025C
+YKR008W
+YKR037C
+YBL097W
+YKR083C
+YLL003W
+YLL008W
+YLL034C
+YLR008C
+YCL004W
+YDL058W
+YLR116W
+YLR163C
+YDL132W
+YLR175W
+YDL126C
+YBL041W
+YDL139C
+YBL050W
+YBL073W
+YDL143W
+YBL074C
+YBL076C
+YDL147W
+YDL148C
+YBL084C
+YDL150W
+YBL092W
+YDL152W
+YBL105C
+YDL153C
+YBR004C
+YDL163W
+YBR011C
+YDL164C
+YBR029C
+YDL140C
+YLR215C
+YLR272C
+YDR050C
+YLR277C
+YDR088C
+YLR298C
+YDR145W
+YML015C
+YDR303C
+YML046W
+YDR325W
+YML049C
+YDR394W
+YML092C
+YML098W
+YML114C
+YEL055C
+YMR005W
+YDL165W
+YBR038W
+YBR055C
+YDL193W
+YBR060C
+YDL195W
+YBR070C
+YBR079C
+YDL205C
+YBR080C
+YDL207W
+YBR087W
+YDL208W
+YBR088C
+YDL209C
+YBR089W
+YDL212W
+YBR091C
+YDL217C
+YBR102C
+YDL220C
+YBR109C
+YER006W
+YMR043W
+YER021W
+YMR061W
+YER022W
+YMR146C
+YMR197C
+YMR203W
+YMR227C
+YER168C
+YMR239C
+YMR270C
+YMR277W
+YNL007C
+YNL026W
+YBR110W
+YDL235C
+YBR121C
+YDR002W
+YDR013W
+YBR124W
+YDR021W
+YBR135W
+YBR140C
+YDR037W
+YBR142W
+YDR041W
+YBR143C
+YDR044W
+YBR152W
+YDR045C
+YBR153W
+YDR047W
+YBR154C
+YDR052C
+YBR155W
+YFL038C
+YNL062C
+YFR002W
+YNL188W
+YFR004W
+YNL189W
+YFR031C
+YNL221C
+YFR051C
+YNL251C
+YGL044C
+YNL261W
+YGL055W
+YNR016C
+YGL065C
+YNR035C
+YGL073W
+YNR043W
+YGL075C
+YNR053C
+YOL123W
+YGL098W
+YOL149W
+YDR053W
+YBR160W
+YDR054C
+YBR167C
+YDR060W
+YBR190W
+YDR062W
+YBR192W
+YBR193C
+YBR196C
+YDR082W
+YBR202W
+YDR087C
+YBR234C
+YDR091C
+YBR236C
+YDR113C
+YBR237W
+YDR118W
+YBR243C
+YGL099W
+YOR046C
+YOR056C
+YGL120C
+YOR057W
+YOR145C
+YOR151C
+YGR075C
+YOR194C
+YGR098C
+YOR232W
+YOR260W
+YGR116W
+YOR281C
+YGR147C
+YOR341W
+YOR373W
+YGR158C
+YPL011C
+YDR141C
+YBR247C
+YDR160W
+YBR252W
+YDR164C
+YBR254C
+YDR166C
+YBR256C
+YDR167W
+YBR257W
+YDR168W
+YBR265W
+YDR170C
+YCL017C
+YDR172W
+YCL031C
+YDR177W
+YCL041C
+YDR180W
+YCL043C
+YDR182W
+YCL052C
+YDR187C
+YCL054W
+YPL016W
+YPL028W
+YPL043W
+YGR245C
+YPL076W
+YGR246C
+YPL124W
+YPL169C
+YPL175W
+YHR083W
+YPL233W
+YHR170W
+YPL235W
+YPL242C
+YPL252C
+YIL021W
+YCL059C
+YDR189W
+YCR012W
+YDR190C
+YDR196C
+YCR035C
+YDR201W
+YCR052W
+YDR208W
+YCR054C
+YDR211W
+YCR057C
+YDR212W
+YCR072C
+YDR224C
+YCR093W
+YDR228C
+YDL003W
+YDR232W
+YDL004W
+YDR235W
+YDL007W
+YIL046W
+YPR034W
+YIL078W
+YPR041W
+YPR086W
+YIL126W
+YPR161C
+YIL142W
+YPR178W
+YIR010W
+YAL003W
+YIR012W
+YAL032C
+YJL014W
+YAL033W
+YAL038W
+YAL041W
+YAL043C
+YDL008W
+YDR238C
+YDL014W
+YDR240C
+YDL015C
+YDR243C
+YDR246W
+YDL017W
+YDR267C
+YDL028C
+YDL029W
+YDR288W
+YDL030W
+YDR292C
+YDL031W
+YDR299W
+YDL043C
+YDR301W
+YDL045C
+YDR302W
+YDL055C
+YJL050W
+YAR007C
+YJL076W
+YAR008W
+YAR019C
+YJR112W
+YBL004W
+YKL042W
+YBL014C
+YBL018C
+YKL059C
+YBL020W
+YKL125W
+YBL023C
+YKL165C
+YBL030C
+YKL173W
+YBL035C
+YDR308C
+YDL060W
+YDR311W
+YDR324C
+YDL087C
+YDR331W
+YDL097C
+YDR339C
+YDL098C
+YDR341C
+YDL102W
+YDR355C
+YDL105W
+YDR356W
+YDL108W
+YDR361C
+YDL111C
+YDR362C
+YDL120W
+YGL097W
+YDR367W
+YDR373W
+YDR376W
+YDR381W
+YDR390C
+YGL116W
+YDR397C
+YGL123W
+YDR398W
+YDR404C
+YGL130W
+YDR407C
+YGL137W
+YDR412W
+YGL142C
+YJR141W
+YHR166C
+YKL012W
+YHR186C
+YKL014C
+YHR196W
+YHR197W
+YKL019W
+YIL003W
+YKL021C
+YIL019W
+YKL022C
+YIL022W
+YIL026C
+YKL028W
+YIL031W
+YKL033W
+YGL145W
+YDR429C
+YGL169W
+YDR434W
+YGL171W
+YDR437W
+YGL201C
+YDR454C
+YDR460W
+YGL225W
+YDR464W
+YGL233W
+YDR468C
+YGL238W
+YDR472W
+YGL239C
+YKL035W
+YIL051C
+YIL061C
+YKL045W
+YIL062C
+YKL049C
+YIL063C
+YKL052C
+YIL068C
+YKL060C
+YIL075C
+YKL078W
+YIL083C
+YKL082C
+YKL083W
+YIL104C
+YKL088W
+YIL115C
+YKL095W
+YIL118W
+YDR473C
+YGL245W
+YDR478W
+YDR487C
+YDR498C
+YGR013W
+YDR499W
+YDR510W
+YGR030C
+YDR526C
+YGR046W
+YDR527W
+YDR531W
+YGR048W
+YEL002C
+YGR060W
+YGR065C
+YIL129C
+YIL144W
+YKL108W
+YIL147C
+YIL150C
+YKL112W
+YIL171W
+YKL122C
+YIR006C
+YKL141W
+YIR008C
+YKL144C
+YKL145W
+YIR015W
+YIR022W
+YJL001W
+YKL154W
+YJL002C
+YEL032W
+YGR073C
+YEL035C
+YGR074W
+YEL058W
+YER003C
+YGR083C
+YER008C
+YGR090W
+YGR091W
+YER012W
+YGR094W
+YER013W
+YGR095C
+YER023W
+YGR099W
+YER025W
+YGR113W
+YER036C
+YGR114C
+YER038C
+YJL005W
+YKL182W
+YJL008C
+YKL186C
+YJL009W
+YKL189W
+YJL010C
+YKL192C
+YJL011C
+YKL193C
+YJL015C
+YKL195W
+YJL018W
+YKL203C
+YJL025W
+YKL210W
+YJL026W
+YKR002W
+YJL031C
+YKR004C
+YJL032W
+YKR022C
+YJL033W
+YER043C
+YGR120C
+YGR140W
+YER112W
+YGR145W
+YER125W
+YGR175C
+YER126C
+YGR185C
+YER133W
+YGR186W
+YGR190C
+YER147C
+YGR191W
+YGR198W
+YKR025W
+YJL034W
+YKR038C
+YJL035C
+YKR062W
+YJL054W
+YKR063C
+YJL061W
+YKR068C
+YKR071C
+YJL072C
+YKR079C
+YJL074C
+YKR081C
+YJL081C
+YLL004W
+YJL085W
+YLL011W
+YJL087C
+YLL031C
+YJL090C
+YER159C
+YGR211W
+YFL002C
+YGR251W
+YFL005W
+YFL008W
+YGR264C
+YFL009W
+YGR265W
+YFL017C
+YGR267C
+YFL022C
+YFL024C
+YGR278W
+YFL037W
+YHL015W
+YHR005C
+YLL035W
+YJL091C
+YJL097W
+YLL037W
+YJL109C
+YLL050C
+YLR002C
+YJL125C
+YLR005W
+YJL143W
+YLR007W
+YLR009W
+YJL167W
+YLR010C
+YLR022C
+YJL174W
+YLR026C
+YJL194W
+YJL195C
+YFR003C
+YHR007C
+YFR005C
+YFR027W
+YFR028C
+YFR029W
+YHR036W
+YFR037C
+YHR040W
+YHR042W
+YFR050C
+YHR058C
+YFR052W
+YHR062C
+YGL001C
+YHR065C
+YGL008C
+YGL011C
+YLR033W
+YJL203W
+YLR066W
+YJR007W
+YLR071C
+YJR012C
+YLR076C
+YJR013W
+YLR078C
+YJR016C
+YLR086W
+YJR017C
+YLR088W
+YJR022W
+YGL018C
+YHR070W
+YGL022W
+YGL040C
+YHR085W
+YGL047W
+YGL048C
+YHR101C
+YGL061C
+YGL068W
+YHR118C
+YGL069C
+YGL074C
+YGL091C
+YGL092W
+YHR164C
+YLR103C
+YLR105C
+YJR045C
+YLR106C
+YJR046W
+YLR115W
+YJR057W
+YLR117C
+YLR127C
+YJR065C
+YLR129W
+YJR067C
+YLR132C
+YJR068W
+YLR140W
+YJR072C
+YLR141W
+YJR076C
+YLR145W
+YJR093C
+YLR153C
+YMR301C
+YLR166C
+YMR308C
+YLR167W
+YMR309C
+YMR314W
+YLR195C
+YNL002C
+YLR196W
+YNL006W
+YLR197W
+YNL038W
+YLR198C
+YNL039W
+YNL061W
+YLR212C
+YNL075W
+YLR222C
+YNL088W
+YLR223C
+YNL102W
+YOR075W
+YPR016C
+YOR077W
+YPR025C
+YOR095C
+YPR033C
+YOR098C
+YPR035W
+YPR048W
+YOR103C
+YOR110W
+YPR056W
+YOR116C
+YPR082C
+YOR117W
+YPR085C
+YOR119C
+YPR088C
+YOR122C
+YLR229C
+YNL103W
+YLR230W
+YNL110C
+YLR243W
+YNL112W
+YLR249W
+YNL113W
+YLR259C
+YNL114C
+YLR274W
+YNL124W
+YLR276C
+YLR291C
+YNL131W
+YLR305C
+YNL132W
+YLR310C
+YNL137C
+YLR314C
+YPR103W
+YPR104C
+YOR148C
+YPR105C
+YOR149C
+YPR107C
+YOR157C
+YPR108W
+YOR159C
+YPR110C
+YOR160W
+YPR112C
+YOR168W
+YPR113W
+YPR133C
+YOR174W
+YOR176W
+YPR137W
+YOR181W
+YPR142C
+YLR316C
+YLR317W
+YNL151C
+YLR321C
+YLR323C
+YNL158W
+YLR336C
+YNL161W
+YLR339C
+YNL162W
+YNL163C
+YLR347C
+YNL172W
+YLR355C
+YLR359W
+YNL181W
+YLR378C
+YNL182C
+YLR379W
+YNL207W
+YPR143W
+YOR204W
+YPR144C
+YOR206W
+YOR207C
+YPR168W
+YOR217W
+YPR169W
+YOR218C
+YPR175W
+YOR224C
+YPR176C
+YOR236W
+YOR244W
+YPR180W
+YOR249C
+YOR254C
+YLR397C
+YNL216W
+YLR409C
+YNL222W
+YLR424W
+YNL232W
+YLR430W
+YNL240C
+YLR440C
+YNL244C
+YLR457C
+YNL245C
+YLR458W
+YNL247W
+YNL256W
+YML010W
+YNL258C
+YML023C
+YNL260C
+YML025C
+YNL262W
+YML031W
+YNL263C
+YPR183W
+YOR256C
+YPR186C
+YOR257W
+YPR190C
+YOR261C
+YAL034W-A
+YOR262W
+YER048W-A
+YOR272W
+YHR005C-A
+YOR278W
+YOR287C
+YLR438C-A
+YOR294W
+YOR310C
+YOR319W
+YML043C
+YNL267W
+YML064C
+YNL272C
+YML065W
+YNL282W
+YML069W
+YNL287W
+YML077W
+YNL290W
+YML091C
+YNL306W
+YML093W
+YNL308C
+YNL310C
+YML125C
+YNL312W
+YML126C
+YNL313C
+YNL317W
+YNR003C
+YOR326W
+YOR329C
+YOR335C
+YOR336W
+YOR340C
+YOR353C
+YOR361C
+YOR370C
+YPL010W
+YMR001C
+YNR011C
+YMR013C
+YNR017W
+YMR028W
+YNR026C
+YMR047C
+YNR038W
+YMR049C
+YNR046W
+YMR059W
+YNR054C
+YMR076C
+YOL005C
+YMR079W
+YOL010W
+YMR093W
+YOL021C
+YMR094W
+YOL022C
+YOL026C
+YMR113W
+YOL034W
+YPL012W
+YPL020C
+YPL063W
+YPL075W
+YPL083C
+YPL085W
+YPL093W
+YPL094C
+YPL117C
+YPL122C
+YMR117C
+YOL038W
+YMR128W
+YMR131C
+YOL066C
+YMR134W
+YOL069W
+YMR149W
+YOL077C
+YMR168C
+YOL078W
+YMR185W
+YOL094C
+YMR200W
+YOL097C
+YMR208W
+YOL102C
+YMR211W
+YMR213W
+YMR218C
+YOL130W
+YPL128C
+YPL143W
+YPL146C
+YPL151C
+YPL160W
+YPL209C
+YMR220W
+YOL133W
+YMR229C
+YOL134C
+YMR235C
+YOL135C
+YMR236W
+YOL139C
+YMR240C
+YOL144W
+YMR260C
+YOL146W
+YMR268C
+YOR004W
+YMR281W
+YOR020C
+YMR288W
+YOR048C
+YMR290C
+YOR060C
+YMR298W
+YOR074C
+YPL210C
+YPL218W
+YPL228W
+YPL231W
+YPL238C
+YPL243W
+YPL255W
+YPL266W

workflow/.old/apps/remc/REMcJava/java-1.8.0-openjdk-1.8.0.342.b07-1.el7_9.x86_64/jre/ASSEMBLY_EXCEPTION

@@ -0,0 +1,27 @@
+
+OPENJDK ASSEMBLY EXCEPTION
+
+The OpenJDK source code made available by Oracle America, Inc. (Oracle) at
+openjdk.java.net ("OpenJDK Code") is distributed under the terms of the GNU
+General Public License <http://www.gnu.org/copyleft/gpl.html> version 2
+only ("GPL2"), with the following clarification and special exception.
+
+    Linking this OpenJDK Code statically or dynamically with other code
+    is making a combined work based on this library.  Thus, the terms
+    and conditions of GPL2 cover the whole combination.
+
+    As a special exception, Oracle gives you permission to link this
+    OpenJDK Code with certain code licensed by Oracle as indicated at
+    http://openjdk.java.net/legal/exception-modules-2007-05-08.html
+    ("Designated Exception Modules") to produce an executable,
+    regardless of the license terms of the Designated Exception Modules,
+    and to copy and distribute the resulting executable under GPL2,
+    provided that the Designated Exception Modules continue to be
+    governed by the licenses under which they were offered by Oracle.
+
+As such, it allows licensees and sublicensees of Oracle's GPL2 OpenJDK Code
+to build an executable that includes those portions of necessary code that
+Oracle could not provide under GPL2 (or that Oracle has provided under GPL2
+with the Classpath exception).  If you modify or add to the OpenJDK code,
+that new GPL2 code may still be combined with Designated Exception Modules
+if the new code is made subject to this exception by its copyright holder.

workflow/.old/apps/remc/REMcJava/java-1.8.0-openjdk-1.8.0.342.b07-1.el7_9.x86_64/jre/LICENSE

@@ -0,0 +1,347 @@
+The GNU General Public License (GPL)
+
+Version 2, June 1991
+
+Copyright (C) 1989, 1991 Free Software Foundation, Inc.
+51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+
+Everyone is permitted to copy and distribute verbatim copies of this license
+document, but changing it is not allowed.
+
+Preamble
+
+The licenses for most software are designed to take away your freedom to share
+and change it.  By contrast, the GNU General Public License is intended to
+guarantee your freedom to share and change free software--to make sure the
+software is free for all its users.  This General Public License applies to
+most of the Free Software Foundation's software and to any other program whose
+authors commit to using it.  (Some other Free Software Foundation software is
+covered by the GNU Library General Public License instead.) You can apply it to
+your programs, too.
+
+When we speak of free software, we are referring to freedom, not price.  Our
+General Public Licenses are designed to make sure that you have the freedom to
+distribute copies of free software (and charge for this service if you wish),
+that you receive source code or can get it if you want it, that you can change
+the software or use pieces of it in new free programs; and that you know you
+can do these things.
+
+To protect your rights, we need to make restrictions that forbid anyone to deny
+you these rights or to ask you to surrender the rights.  These restrictions
+translate to certain responsibilities for you if you distribute copies of the
+software, or if you modify it.
+
+For example, if you distribute copies of such a program, whether gratis or for
+a fee, you must give the recipients all the rights that you have.  You must
+make sure that they, too, receive or can get the source code.  And you must
+show them these terms so they know their rights.
+
+We protect your rights with two steps: (1) copyright the software, and (2)
+offer you this license which gives you legal permission to copy, distribute
+and/or modify the software.
+
+Also, for each author's protection and ours, we want to make certain that
+everyone understands that there is no warranty for this free software.  If the
+software is modified by someone else and passed on, we want its recipients to
+know that what they have is not the original, so that any problems introduced
+by others will not reflect on the original authors' reputations.
+
+Finally, any free program is threatened constantly by software patents.  We
+wish to avoid the danger that redistributors of a free program will
+individually obtain patent licenses, in effect making the program proprietary.
+To prevent this, we have made it clear that any patent must be licensed for
+everyone's free use or not licensed at all.
+
+The precise terms and conditions for copying, distribution and modification
+follow.
+
+TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+0. This License applies to any program or other work which contains a notice
+placed by the copyright holder saying it may be distributed under the terms of
+this General Public License.  The "Program", below, refers to any such program
+or work, and a "work based on the Program" means either the Program or any
+derivative work under copyright law: that is to say, a work containing the
+Program or a portion of it, either verbatim or with modifications and/or
+translated into another language.  (Hereinafter, translation is included
+without limitation in the term "modification".) Each licensee is addressed as
+"you".
+
+Activities other than copying, distribution and modification are not covered by
+this License; they are outside its scope.  The act of running the Program is
+not restricted, and the output from the Program is covered only if its contents
+constitute a work based on the Program (independent of having been made by
+running the Program).  Whether that is true depends on what the Program does.
+
+1. You may copy and distribute verbatim copies of the Program's source code as
+you receive it, in any medium, provided that you conspicuously and
+appropriately publish on each copy an appropriate copyright notice and
+disclaimer of warranty; keep intact all the notices that refer to this License
+and to the absence of any warranty; and give any other recipients of the
+Program a copy of this License along with the Program.
+
+You may charge a fee for the physical act of transferring a copy, and you may
+at your option offer warranty protection in exchange for a fee.
+
+2. You may modify your copy or copies of the Program or any portion of it, thus
+forming a work based on the Program, and copy and distribute such modifications
+or work under the terms of Section 1 above, provided that you also meet all of
+these conditions:
+
+    a) You must cause the modified files to carry prominent notices stating
+    that you changed the files and the date of any change.
+
+    b) You must cause any work that you distribute or publish, that in whole or
+    in part contains or is derived from the Program or any part thereof, to be
+    licensed as a whole at no charge to all third parties under the terms of
+    this License.
+
+    c) If the modified program normally reads commands interactively when run,
+    you must cause it, when started running for such interactive use in the
+    most ordinary way, to print or display an announcement including an
+    appropriate copyright notice and a notice that there is no warranty (or
+    else, saying that you provide a warranty) and that users may redistribute
+    the program under these conditions, and telling the user how to view a copy
+    of this License.  (Exception: if the Program itself is interactive but does
+    not normally print such an announcement, your work based on the Program is
+    not required to print an announcement.)
+
+These requirements apply to the modified work as a whole.  If identifiable
+sections of that work are not derived from the Program, and can be reasonably
+considered independent and separate works in themselves, then this License, and
+its terms, do not apply to those sections when you distribute them as separate
+works.  But when you distribute the same sections as part of a whole which is a
+work based on the Program, the distribution of the whole must be on the terms
+of this License, whose permissions for other licensees extend to the entire
+whole, and thus to each and every part regardless of who wrote it.
+
+Thus, it is not the intent of this section to claim rights or contest your
+rights to work written entirely by you; rather, the intent is to exercise the
+right to control the distribution of derivative or collective works based on
+the Program.
+
+In addition, mere aggregation of another work not based on the Program with the
+Program (or with a work based on the Program) on a volume of a storage or
+distribution medium does not bring the other work under the scope of this
+License.
+
+3. You may copy and distribute the Program (or a work based on it, under
+Section 2) in object code or executable form under the terms of Sections 1 and
+2 above provided that you also do one of the following:
+
+    a) Accompany it with the complete corresponding machine-readable source
+    code, which must be distributed under the terms of Sections 1 and 2 above
+    on a medium customarily used for software interchange; or,
+
+    b) Accompany it with a written offer, valid for at least three years, to
+    give any third party, for a charge no more than your cost of physically
+    performing source distribution, a complete machine-readable copy of the
+    corresponding source code, to be distributed under the terms of Sections 1
+    and 2 above on a medium customarily used for software interchange; or,
+
+    c) Accompany it with the information you received as to the offer to
+    distribute corresponding source code.  (This alternative is allowed only
+    for noncommercial distribution and only if you received the program in
+    object code or executable form with such an offer, in accord with
+    Subsection b above.)
+
+The source code for a work means the preferred form of the work for making
+modifications to it.  For an executable work, complete source code means all
+the source code for all modules it contains, plus any associated interface
+definition files, plus the scripts used to control compilation and installation
+of the executable.  However, as a special exception, the source code
+distributed need not include anything that is normally distributed (in either
+source or binary form) with the major components (compiler, kernel, and so on)
+of the operating system on which the executable runs, unless that component
+itself accompanies the executable.
+
+If distribution of executable or object code is made by offering access to copy
+from a designated place, then offering equivalent access to copy the source
+code from the same place counts as distribution of the source code, even though
+third parties are not compelled to copy the source along with the object code.
+
+4. You may not copy, modify, sublicense, or distribute the Program except as
+expressly provided under this License.  Any attempt otherwise to copy, modify,
+sublicense or distribute the Program is void, and will automatically terminate
+your rights under this License.  However, parties who have received copies, or
+rights, from you under this License will not have their licenses terminated so
+long as such parties remain in full compliance.
+
+5. You are not required to accept this License, since you have not signed it.
+However, nothing else grants you permission to modify or distribute the Program
+or its derivative works.  These actions are prohibited by law if you do not
+accept this License.  Therefore, by modifying or distributing the Program (or
+any work based on the Program), you indicate your acceptance of this License to
+do so, and all its terms and conditions for copying, distributing or modifying
+the Program or works based on it.
+
+6. Each time you redistribute the Program (or any work based on the Program),
+the recipient automatically receives a license from the original licensor to
+copy, distribute or modify the Program subject to these terms and conditions.
+You may not impose any further restrictions on the recipients' exercise of the
+rights granted herein.  You are not responsible for enforcing compliance by
+third parties to this License.
+
+7. If, as a consequence of a court judgment or allegation of patent
+infringement or for any other reason (not limited to patent issues), conditions
+are imposed on you (whether by court order, agreement or otherwise) that
+contradict the conditions of this License, they do not excuse you from the
+conditions of this License.  If you cannot distribute so as to satisfy
+simultaneously your obligations under this License and any other pertinent
+obligations, then as a consequence you may not distribute the Program at all.
+For example, if a patent license would not permit royalty-free redistribution
+of the Program by all those who receive copies directly or indirectly through
+you, then the only way you could satisfy both it and this License would be to
+refrain entirely from distribution of the Program.
+
+If any portion of this section is held invalid or unenforceable under any
+particular circumstance, the balance of the section is intended to apply and
+the section as a whole is intended to apply in other circumstances.
+
+It is not the purpose of this section to induce you to infringe any patents or
+other property right claims or to contest validity of any such claims; this
+section has the sole purpose of protecting the integrity of the free software
+distribution system, which is implemented by public license practices.  Many
+people have made generous contributions to the wide range of software
+distributed through that system in reliance on consistent application of that
+system; it is up to the author/donor to decide if he or she is willing to
+distribute software through any other system and a licensee cannot impose that
+choice.
+
+This section is intended to make thoroughly clear what is believed to be a
+consequence of the rest of this License.
+
+8. If the distribution and/or use of the Program is restricted in certain
+countries either by patents or by copyrighted interfaces, the original
+copyright holder who places the Program under this License may add an explicit
+geographical distribution limitation excluding those countries, so that
+distribution is permitted only in or among countries not thus excluded.  In
+such case, this License incorporates the limitation as if written in the body
+of this License.
+
+9. The Free Software Foundation may publish revised and/or new versions of the
+General Public License from time to time.  Such new versions will be similar in
+spirit to the present version, but may differ in detail to address new problems
+or concerns.
+
+Each version is given a distinguishing version number.  If the Program
+specifies a version number of this License which applies to it and "any later
+version", you have the option of following the terms and conditions either of
+that version or of any later version published by the Free Software Foundation.
+If the Program does not specify a version number of this License, you may
+choose any version ever published by the Free Software Foundation.
+
+10. If you wish to incorporate parts of the Program into other free programs
+whose distribution conditions are different, write to the author to ask for
+permission.  For software which is copyrighted by the Free Software Foundation,
+write to the Free Software Foundation; we sometimes make exceptions for this.
+Our decision will be guided by the two goals of preserving the free status of
+all derivatives of our free software and of promoting the sharing and reuse of
+software generally.
+
+NO WARRANTY
+
+11. BECAUSE THE PROGRAM IS LICENSED FREE OF CHARGE, THERE IS NO WARRANTY FOR
+THE PROGRAM, TO THE EXTENT PERMITTED BY APPLICABLE LAW.  EXCEPT WHEN OTHERWISE
+STATED IN WRITING THE COPYRIGHT HOLDERS AND/OR OTHER PARTIES PROVIDE THE
+PROGRAM "AS IS" WITHOUT WARRANTY OF ANY KIND, EITHER EXPRESSED OR IMPLIED,
+INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND
+FITNESS FOR A PARTICULAR PURPOSE.  THE ENTIRE RISK AS TO THE QUALITY AND
+PERFORMANCE OF THE PROGRAM IS WITH YOU.  SHOULD THE PROGRAM PROVE DEFECTIVE,
+YOU ASSUME THE COST OF ALL NECESSARY SERVICING, REPAIR OR CORRECTION.
+
+12. IN NO EVENT UNLESS REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING WILL
+ANY COPYRIGHT HOLDER, OR ANY OTHER PARTY WHO MAY MODIFY AND/OR REDISTRIBUTE THE
+PROGRAM AS PERMITTED ABOVE, BE LIABLE TO YOU FOR DAMAGES, INCLUDING ANY
+GENERAL, SPECIAL, INCIDENTAL OR CONSEQUENTIAL DAMAGES ARISING OUT OF THE USE OR
+INABILITY TO USE THE PROGRAM (INCLUDING BUT NOT LIMITED TO LOSS OF DATA OR DATA
+BEING RENDERED INACCURATE OR LOSSES SUSTAINED BY YOU OR THIRD PARTIES OR A
+FAILURE OF THE PROGRAM TO OPERATE WITH ANY OTHER PROGRAMS), EVEN IF SUCH HOLDER
+OR OTHER PARTY HAS BEEN ADVISED OF THE POSSIBILITY OF SUCH DAMAGES.
+
+END OF TERMS AND CONDITIONS
+
+How to Apply These Terms to Your New Programs
+
+If you develop a new program, and you want it to be of the greatest possible
+use to the public, the best way to achieve this is to make it free software
+which everyone can redistribute and change under these terms.
+
+To do so, attach the following notices to the program.  It is safest to attach
+them to the start of each source file to most effectively convey the exclusion
+of warranty; and each file should have at least the "copyright" line and a
+pointer to where the full notice is found.
+
+    One line to give the program's name and a brief idea of what it does.
+
+    Copyright (C) <year> <name of author>
+
+    This program is free software; you can redistribute it and/or modify it
+    under the terms of the GNU General Public License as published by the Free
+    Software Foundation; either version 2 of the License, or (at your option)
+    any later version.
+
+    This program is distributed in the hope that it will be useful, but WITHOUT
+    ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+    FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+    more details.
+
+    You should have received a copy of the GNU General Public License along
+    with this program; if not, write to the Free Software Foundation, Inc.,
+    51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA.
+
+Also add information on how to contact you by electronic and paper mail.
+
+If the program is interactive, make it output a short notice like this when it
+starts in an interactive mode:
+
+    Gnomovision version 69, Copyright (C) year name of author Gnomovision comes
+    with ABSOLUTELY NO WARRANTY; for details type 'show w'.  This is free
+    software, and you are welcome to redistribute it under certain conditions;
+    type 'show c' for details.
+
+The hypothetical commands 'show w' and 'show c' should show the appropriate
+parts of the General Public License.  Of course, the commands you use may be
+called something other than 'show w' and 'show c'; they could even be
+mouse-clicks or menu items--whatever suits your program.
+
+You should also get your employer (if you work as a programmer) or your school,
+if any, to sign a "copyright disclaimer" for the program, if necessary.  Here
+is a sample; alter the names:
+
+    Yoyodyne, Inc., hereby disclaims all copyright interest in the program
+    'Gnomovision' (which makes passes at compilers) written by James Hacker.
+
+    signature of Ty Coon, 1 April 1989
+
+    Ty Coon, President of Vice
+
+This General Public License does not permit incorporating your program into
+proprietary programs.  If your program is a subroutine library, you may
+consider it more useful to permit linking proprietary applications with the
+library.  If this is what you want to do, use the GNU Library General Public
+License instead of this License.
+
+
+"CLASSPATH" EXCEPTION TO THE GPL
+
+Certain source files distributed by Oracle America and/or its affiliates are
+subject to the following clarification and special exception to the GPL, but
+only where Oracle has expressly included in the particular source file's header
+the words "Oracle designates this particular file as subject to the "Classpath"
+exception as provided by Oracle in the LICENSE file that accompanied this code."
+
+    Linking this library statically or dynamically with other modules is making
+    a combined work based on this library.  Thus, the terms and conditions of
+    the GNU General Public License cover the whole combination.
+
+    As a special exception, the copyright holders of this library give you
+    permission to link this library with independent modules to produce an
+    executable, regardless of the license terms of these independent modules,
+    and to copy and distribute the resulting executable under terms of your
+    choice, provided that you also meet, for each linked independent module,
+    the terms and conditions of the license of that module.  An independent
+    module is a module which is not derived from or based on this library.  If
+    you modify this library, you may extend this exception to your version of
+    the library, but you are not obligated to do so.  If you do not wish to do
+    so, delete this exception statement from your version.

workflow/.old/apps/remc/REMcJava/java-1.8.0-openjdk-1.8.0.342.b07-1.el7_9.x86_64/jre/lib/amd64/jvm.cfg

@@ -0,0 +1,35 @@
+# Copyright (c) 2003, 2013, Oracle and/or its affiliates. All rights reserved.
+# DO NOT ALTER OR REMOVE COPYRIGHT NOTICES OR THIS FILE HEADER.
+#
+# This code is free software; you can redistribute it and/or modify it
+# under the terms of the GNU General Public License version 2 only, as
+# published by the Free Software Foundation.  Oracle designates this
+# particular file as subject to the "Classpath" exception as provided
+# by Oracle in the LICENSE file that accompanied this code.
+#
+# This code is distributed in the hope that it will be useful, but WITHOUT
+# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+# FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+# version 2 for more details (a copy is included in the LICENSE file that
+# accompanied this code).
+#
+# You should have received a copy of the GNU General Public License version
+# 2 along with this work; if not, write to the Free Software Foundation,
+# Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA.
+#
+# Please contact Oracle, 500 Oracle Parkway, Redwood Shores, CA 94065 USA
+# or visit www.oracle.com if you need additional information or have any
+# questions.
+#
+# 
+# List of JVMs that can be used as an option to java, javac, etc.
+# Order is important -- first in this list is the default JVM.
+# NOTE that this both this file and its format are UNSUPPORTED and
+# WILL GO AWAY in a future release.
+#
+# You may also select a JVM in an arbitrary location with the
+# "-XXaltjvm=<jvm_dir>" option, but that too is unsupported
+# and may not be available in a future release.
+#
+-server KNOWN
+-client IGNORE