--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_dnaplotter.pl	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,465 @@
+#!/usr/bin/perl
+#
+#       Code written by Eric Rasche
+#               mailto:rasche.eric@yandex.ru
+#               tel:   404.692.2048
+#               http://eric.rasche.co.uk
+#       for
+#               Center for Phage Technology
+#
+
+use strict;
+use warnings;
+
+use CPT::GalaxyGetOpt;
+use Data::Dumper;
+use CPT::Bio;
+use CPT::Circos::Conf;
+my $bio = CPT::Bio->new();
+
+my @argv_copy;
+foreach(@ARGV){push(@argv_copy, "$_");}
+
+my $ggo  = CPT::GalaxyGetOpt->new();
+my $options = $ggo->getOptions(
+	'options' => [
+		[ 'file|f', 'Input file', { validate => 'File/Input',
+				file_format => ['genbank', 'embl', 'txt'],
+			} ],
+		[],
+		['Track Configuration'],
+		['track_key', 'Key to select from genbank data', { validate => 'Genomic/Tag', required => 1, multiple => 1 } ],
+		['track_feature_filter_invert', 'Should the qualifier search be inverted?', { validate => 'Option', options => { 'yes', 'Yes', 'no', 'No' } , multiple => 1 } ],
+		['track_feature_filter_hastag', 'Select a tag which should be present in that qualifier (e.g., signal/tmhelix/pseudo)', { validate => 'String' , multiple => 1 } ],
+		['track_feature_filter_textquery', 'Specify text which MUST be in that tag', { validate => 'String' , multiple => 1 } ],
+		['track_feature_filter_strand', 'Which strand should the feature appear on?', { validate => 'Option', options => { 'f', 'Forward', 'r', 'Reverse', 'a', 'Any' } , multiple => 1 } ],
+		[],
+		['enable_gc_skew_plot', 'Enable/Disable calculation of GC Skew Plot', { validate => 'Flag' } ],
+		['gc_skew_plot_window_size', 'Window size for calculation of GC Skew', { validate => 'Int', min => 1000, default => 10000} ],
+		['gc_skew_plot_step_size', 'Step size for calculation of GC Skew', { validate => 'Int', min => 200, default => 200 } ],
+	],
+	'outputs' => [
+		[
+			'output_circos_confs',
+			'Circos Configuration Files',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'out',
+				data_format    => 'archive',
+				default_format => 'zip',
+			}
+		],
+	],
+	'defaults' => [
+		'appid'   => 'CircularDNAPlotter',
+		'appname' => 'Circos based DNAPlotter',
+		'appdesc' => 'plots genomes similar to Artemis\'s DNAPlotter',
+		'appvers' => '1.94.1',
+	],
+);
+
+#perl cpt_dnaplotter.pl \
+	#-f ../t/test-files/moon.gbk \
+	#--track_key CDS --track_feature_filter_invert yes --track_feature_filter_hastag pseudo --track_feature_filter_strand f \
+	#--track_key CDS --track_feature_filter_invert yes --track_feature_filter_hastag pseudo  --track_feature_filter_strand r \
+	#--track_key CDS --track_feature_filter_hastag pseudo  --track_feature_filter_strand a \
+	#--track_key tRNA  --track_feature_filter_strand a \
+	#--track_key CDS  --track_feature_filter_hastag signal --track_feature_filter_strand a \
+	#--track_key CDS  --track_feature_filter_hastag tmhelix --track_feature_filter_strand a
+
+
+my @reorg_args = ();
+
+my $cum_gc_ske_mean = 0;
+
+
+
+my %latest = ();
+for(my $i = 0; $i < scalar(@argv_copy); $i++){
+	my $c = $argv_copy[$i];
+	# We have entered a new one block
+	if($c eq '--track_key'){
+		# If we have loaded data
+		if(scalar(keys(%latest)) > 0){
+			my %copy;
+			foreach(keys(%latest)){
+				$copy{$_} = "" . $latest{$_};
+			}
+			push(@reorg_args, \%copy);
+		}
+
+		# Clean out latest to prep for new data
+		foreach(keys(%latest)){
+			delete $latest{$_};
+		}
+	}
+
+	if($c =~ /^--track_(.*)/){
+		$latest{$1} = $argv_copy[$i+1];
+		# Artificially bump so we don't bother looking at the answer to
+		# this question. We can "get away" with this because none of
+		# the options are flags. However, I've disabled it in the event
+		# that flags ARE introduced
+		#$i++;
+	}
+}
+push(@reorg_args, \%latest);
+#$VAR1 = [
+          #{
+            #'feature_filter_invert' => 'yes',
+            #'feature_plot_color' => '005500',
+            #'feature_filter_strand' => 'f',
+            #'feature_filter_hastag' => 'pseudo',
+            #'key' => 'CDS'
+          #},
+          #{
+            #'feature_filter_strand' => 'a',
+            #'key' => 'RBS'
+          #}
+        #];
+my @files = ();
+
+my $number_of_tracks = 0;
+sub register_track {
+	#my $r0 = ( 90 - (10 * $number_of_tracks - 1)/2) / 100;
+	#my $r1 = ( 90 - (10 * $number_of_tracks - 9)/2) / 100;
+	my $r0 = ( 90 - (10 * $number_of_tracks - 1)/1) / 100;
+	my $r1 = ( 90 - (10 * $number_of_tracks - 9)/1) / 100;
+	$number_of_tracks++;
+	return ($r0, $r1);
+}
+
+sub circosconf {
+	my $cc = CPT::Circos::Conf->new();
+	$cc->include('etc/colors_fonts_patterns.conf');
+	# Features to plot along the genome
+	$cc->include('ideogram.conf');
+	# markings indicating position along genome
+	$cc->include('ticks.conf');
+	# Genome data
+	$cc->set('karyotype', 'karyotype.conf');
+	# Default image params are fine
+	$cc->start_block('image');
+	$cc->include('etc/image.conf');
+	$cc->end_block();
+	# ???
+	$cc->set('chromosome_units', '1000');
+	$cc->set('chromosome_display_default', 'yes');
+	#$cc->include('highlights.conf');
+	$cc->include('plots.conf');
+
+	$cc->include('etc/housekeeping.conf');
+	my $result = $cc->finalize();
+	$cc = CPT::Circos::Conf->new();
+	return $result;
+}
+sub ideogramconf{
+	my $cc = CPT::Circos::Conf->new();
+	$cc->start_block('ideogram');
+	$cc->start_block('spacing');
+	$cc->set('default','0u');
+	$cc->set('break','0u');
+	$cc->end_block();
+
+	$cc->set('thickness', '20p');
+	$cc->set('stroke_thickness', '2');
+	$cc->set('stroke_color', 'black');
+	$cc->set('fill','no');
+	$cc->set('fill_color','black');
+	$cc->set('radius','0.85r');
+	$cc->set('show_label','yes');
+	$cc->set('label_font','default');
+	$cc->set('label_radius','dims(ideogram,radius) + 0.05');
+	$cc->set('label_size','36');
+	$cc->set('label_parallel','yes');
+	$cc->set('label_case','upper');
+
+	$cc->set('band_stroke_thickness','2');
+	$cc->set('show_bands','yes');
+	$cc->set('fill_bands','yes');
+	$cc->end_block();
+
+	return $cc->finalize();
+}
+sub generate_feature_table {
+	my ($filename, %filter) = @_;
+	print "Filtering on features\n";
+	print Dumper \%filter;
+	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
+	# Only handing first sequence.
+	my $seq_object = $seqio_object->next_seq;
+	my $parent = $seq_object->display_id();
+	# Feature data
+	my @features;
+	foreach my $feat($seq_object->get_SeqFeatures()){
+		if($feat->primary_tag() eq $filter{key}){
+			# If they've said "hastag" AND we do indeed have that tag AND we haven't inverted this filter.
+			if(
+				($filter{feature_filter_hastag} && $feat->has_tag($filter{feature_filter_hastag}) && !$filter{feature_filter_invert})
+				||
+				($filter{feature_filter_hastag} && $filter{feature_filter_invert} && !$feat->has_tag($filter{feature_filter_hastag}))
+				||
+				(! $filter{feature_filter_hastag})
+			){
+				if(
+					!$filter{feature_filter_strand}
+					||
+					($feat->strand() == 1 && ( $filter{feature_filter_strand} eq 'f' ||  $filter{feature_filter_strand} eq 'a' ))
+					||
+					($feat->strand() == -1 && ( $filter{feature_filter_strand} eq 'r' ||  $filter{feature_filter_strand} eq 'a' ))
+					||
+					($feat->strand() == 0 && ( $filter{feature_filter_strand} eq 'a' ))
+				){
+					push(@features, join(' ', $parent, $feat->start, $feat->end));
+				}
+			}
+		}
+	}
+	print "Found " . scalar @features . " features \n";
+	push(@files, [ 'data/' . $filename, join("\n", @features) ] );
+}
+sub plotsconf{
+	my $cc = CPT::Circos::Conf->new();
+
+	$cc->start_block('plots');
+
+
+	my $idx = 0;
+	foreach(@reorg_args){
+		my %filter = %{$_};
+          #{
+            #'feature_filter_invert' => 'yes',
+            #'feature_plot_color' => '005500',
+            #'feature_filter_strand' => 'f',
+            #'feature_filter_hastag' => 'pseudo',
+            #'key' => 'CDS'
+          #},
+		$idx++;
+		my $filename = sprintf('org.features.%s.txt', $idx);
+		generate_feature_table($filename, %filter);
+
+		my ($r0,$r1) = register_track();
+		$cc->start_block('plot');
+		$cc->set('type','tile');
+		$cc->set('file',$filename);
+		$cc->set('orientation', 'center');
+		$cc->set('thickness', '30');
+		$cc->set('r1', $r1 . 'r');# '0.78r');
+		$cc->set('r0', $r0 . 'r');# '0.72r');
+		$cc->set('layers','3');
+		$cc->set('layers_overflow','collapse');
+		$cc->set('color','paired-6-qual-' . $idx);
+		$cc->end_block();
+	}
+
+	if($options->{enable_gc_skew_plot}){
+		my ($r0,$r1) = register_track();
+		$cc->start_block('plot');
+		$cc->set('type','histogram');
+		$cc->set('file','gc.txt');
+		$cc->set('r1',$r1 . 'r');
+		$cc->set('r0',$r0 . 'r');
+		$cc->set('fill_color','purple');
+		$cc->set('orientation','in');
+		$cc->start_block('rules');
+		$cc->start_block('rule');
+		$cc->set('condition','var(value) < 0');
+		$cc->set('fill_color', 'green');
+		$cc->end_block();
+		$cc->end_block();
+		$cc->end_block();
+	}
+
+	#$cc->start_block('plot');
+	#$cc->set('type','histogram');
+	#$cc->set('file','gc_cumulative.txt');
+	#$cc->set('r1','0.6r');
+	#$cc->set('r0','0.55r');
+	#$cc->set('fill_color','purple');
+	#$cc->set('orientation','out');
+	#$cc->start_block('rules');
+	#$cc->start_block('rule');
+	#$cc->set('condition','var(value) < ' . $cum_gc_ske_mean);
+	#$cc->set('fill_color', 'green');
+	#$cc->end_block();
+	#$cc->end_block();
+	#$cc->end_block();
+
+	$cc->end_block();
+	return $cc->finalize();
+}
+sub ticksconf{
+	my $cc = CPT::Circos::Conf->new();
+
+	$cc->set('show_ticks','yes');
+	$cc->set('show_tick_labels','yes');
+	$cc->start_block('ticks');
+	$cc->set('radius','1r');
+	$cc->set('color','black');
+	$cc->set('thickness','2p');
+	$cc->set('multiplier','1e-3');
+	$cc->set('format','%d');
+
+	$cc->start_block('tick');
+	$cc->set('spacing','1000u');
+	$cc->set('size','10p');
+	$cc->end_block();
+
+	$cc->start_block('tick');
+	$cc->set('spacing','10000u');
+	$cc->set('size','15p');
+	$cc->set('show_label','yes');
+	$cc->set('label_size','20p');
+	$cc->set('label_offset','10p');
+	$cc->set('format','%d');
+	$cc->end_block();
+	$cc->end_block();
+	return $cc->finalize();
+}
+sub karyotype {
+	my @karyotype_data = ();
+	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
+	# Only handing first sequence.
+	my $seq_object = $seqio_object->next_seq;
+	# Main 'chromosome' data
+	push(@karyotype_data, join(' ', 'chr', '-',$seq_object->display_id(),$seq_object->display_id(),0, $seq_object->length(),'black'));
+
+	return join("\n", @karyotype_data);
+}
+
+sub gcgraph_cumulative {
+	my @gcdata = ();
+	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
+	# Only handing first sequence.
+	my $seq_object = $seqio_object->next_seq;
+
+	my $parent = $seq_object->display_id();
+
+	my $seq = $seq_object->seq();
+	my $sep = int($options->{gc_skew_plot_window_size}/2);
+	my $stepsep = int($options->{gc_skew_plot_step_size}/2);
+	my $cumulative_gc_skew = 0;
+	my @cumgc_vals;
+
+	my $count = 0;
+	foreach(my $i = $sep; $i < $seq_object->length() - $sep - $options->{gc_skew_plot_step_size}; $i += $options->{gc_skew_plot_step_size}){
+		$count++;
+		$cumulative_gc_skew += _calculate_gc_skew_for_seq(substr($seq,$i-$sep,$options->{gc_skew_plot_window_size})),
+		push(@cumgc_vals, $cumulative_gc_skew);
+		push(@gcdata, join(" ",
+			$parent,
+			$i - $stepsep,
+			$i + $stepsep,
+			$cumulative_gc_skew
+		));
+	}
+
+	my $sum = 0;
+	foreach(@cumgc_vals){$sum += $_;}
+	$cum_gc_ske_mean = $sum / $count;
+
+	return join("\n", @gcdata);
+	# Main 'chromosome' data
+}
+sub gcgraph {
+	my @gcdata = ();
+	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
+	# Only handing first sequence.
+	my $seq_object = $seqio_object->next_seq;
+
+	my $parent = $seq_object->display_id();
+
+	my $seq = $seq_object->seq();
+	my $sep = int($options->{gc_skew_plot_window_size}/2);
+	my $stepsep = int($options->{gc_skew_plot_step_size}/2);
+	foreach(my $i = $sep; $i < $seq_object->length() - $sep - $options->{gc_skew_plot_step_size}; $i += $options->{gc_skew_plot_step_size}){
+		push(@gcdata, join(" ",
+			$parent,
+			$i - $stepsep,
+			$i + $stepsep,
+			_calculate_gc_skew_for_seq(substr($seq,$i-$sep,$options->{gc_skew_plot_window_size})),
+		));
+	}
+	return join("\n", @gcdata);
+	# Main 'chromosome' data
+}
+sub _calculate_gc_skew_for_seq {
+	my ($seq) = @_;
+	$seq = uc($seq);
+	my %counts;
+	foreach(split //,$seq){
+		$counts{$_}++;
+	}
+	if($counts{G} + $counts{C} > 0){
+		return ($counts{G} - $counts{C}) / ($counts{G} + $counts{C});
+	}
+	return 0;
+}
+
+push(@files, [ 'etc/karyotype.conf', karyotype() ]);
+push(@files, [ 'etc/circos.conf', circosconf() ]);
+push(@files, [ 'etc/ideogram.conf', ideogramconf() ]);
+if($options->{enable_gc_skew_plot}){
+	push(@files, [ 'data/gc.txt', gcgraph() ]);
+	push(@files, [ 'data/gc_cumulative.txt', gcgraph_cumulative() ]);
+}
+
+push(@files, [ 'etc/plots.conf', plotsconf() ]);
+push(@files, [ 'etc/ticks.conf', ticksconf() ]);
+
+
+use Archive::Any::Create;
+my $archive = Archive::Any::Create->new();
+$archive->container('conf');
+foreach(@files){
+	my ($location, $content) = @{$_};
+	$archive->add_file($location, $content);
+}
+
+use CPT::OutputFiles;
+my $crr_output = CPT::OutputFiles->new(
+	name => 'output_circos_confs',
+	GGO => $ggo,
+);
+$crr_output->CRR(data => $archive);
+
+=head1 NAME
+
+DNAPlotter
+
+=head1 DESCRIPTION
+
+Much like artemis's DNAPlotter, this tool plots genomes in a ciruclar fashion, and can plot gc-deviation tracks as well. The options are somewhat reduced compared to artemis, so if you need something that isn't available in this version please file a bug report.
+
+=head1 USE
+
+Each track has several parameters:
+
+=over 4
+
+=item track_key
+
+This selects a set of features from a genbank file, e.g., CDSs or tRNAs
+
+=item track_feature_filter_invert
+
+This parameter will invert (negate) the results of whatever query parameters you specify after it.
+
+=item track_feature_filter_hastag
+
+Require that a feature has a specific tag....
+
+=item track_feature_filter_textquery
+
+...with this specific text in it
+
+=item track_feature_filter_strand
+
+Which strand should the feature be on (not inverted)
+
+=back
+
+Additionally, users are able to enable/disable GC skew plots. it's suggested that these are generally left alone, as they can quickly increase runtime.
+
+=cut

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_genbank2circosk.pl	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,131 @@
+#!/usr/bin/perl
+#
+#       Code written by Eric Rasche
+#               mailto:rasche.eric@yandex.ru
+#               tel:404.692.2048
+#               http://eric.rasche.co.uk
+#       for
+#               Center for Phage Technology
+#
+
+use strict;
+use warnings;
+
+use CPT::GalaxyGetOpt;
+use Data::Dumper;
+
+my $ggo = CPT::GalaxyGetOpt->new();
+my %colors = map { $_ => $_ } qw(red orange yellow green blue gray black white);
+my %intensity = map { $_ => $_ } qw (vvvvl vvvl vvl vl vd vvd vvvd vvvvd);
+
+my $options = $ggo->getOptions(
+	'options' => [
+		[
+			'file',
+			'Input file',
+			{
+				required => 1,
+				validate => 'File/Input',
+				file_format => ['genbank', 'embl', 'txt'],
+			}
+		],
+		[
+			'chromosome' => 'Name for the
+			chromosome inside Circos',
+			{
+				required => 1,
+				validate => 'String'
+			}
+		],
+		[
+			'color' => 'Color to use for Circos plot',
+			{
+				required => 1,
+				validate => 'Option',
+				options  => \%colors,
+			}
+		],
+		[
+			'intensity' => 'Circos color intensity. ',
+			{
+				validate => 'Option',
+				options  => \%intensity,
+			}
+		],
+	],
+	'outputs' => [
+		[
+			'circosk',
+			'Circos Karyotype File',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'karyotype',
+				data_format    => 'text/plain',
+				default_format => 'TXT'
+			}
+		],
+	],
+	'defaults' => [
+		'appname' => 'Genbank2CircosK',
+		'appid'   => 'Genbank2CircosK',
+		'appvers' => '1.94',
+		'appdesc' =>
+'Convert genbank files to Circos Karyotype configuration files',
+	],
+	'tests' => [
+		{
+			test_name => "Default",
+			params => {
+				'file' => 'test-data/inputs/multi.gbk',
+				'chromosome' => 'test',
+				'color' => 'red',
+				'intensity' => 'vvvl',
+			},
+			outputs => {
+				'circosk' => ['karyotype.txt', 'test-data/outputs/circosk.conf'],
+			}
+		},
+	],
+);
+
+use CPT::Bio;
+my $bio = CPT::Bio->new();
+
+my @results;
+my $c = 0;
+my $seqio = $bio->requestCopyIO( file => $options->{file} );
+
+while(my $seqobj = $seqio->next_seq()){
+	foreach my $feat ( $seqobj->get_SeqFeatures () ) {
+
+		#band test 12 CDS__test_1gbk 5715 6335 red]
+		next if ( $feat->primary_tag ne 'CDS' );
+		my $id = $bio->_getIdentifier($feat);
+		$id =~ s/\s+/_/g;
+		push(
+			@results,
+			join(
+				' ',
+				(
+					'band',
+					$options->{'chromosome'},
+					$c++,
+					$id,
+					$feat->start,
+					$feat->end,
+					(defined $options->{'intensity'} ? $options->{'intensity'} : '') . $options->{'color'}
+				)
+			)
+		);
+	}
+}
+
+my $z = join( "\n", @results );
+
+use CPT::OutputFiles;
+my $output = CPT::OutputFiles->new(
+        name => 'circosk',
+        GGO => $ggo,
+);
+$output->CRR(data => $z);

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_psm_0_prep.pl	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,194 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use Storable;
+use Bio::SearchIO;
+use Bio::SeqIO;
+use Bio::Tools::CodonTable;
+use Data::Dumper;
+use File::Temp qw/tempfile tempdir/;
+
+
+use CPT::GalaxyGetOpt;
+my $ggo  = CPT::GalaxyGetOpt->new();
+my $options = $ggo->getOptions(
+	'options' => [
+		[ 'file', 'Input file', { validate => 'File/Input', multiple => 1, required => 1,
+				file_format => ['genbank', 'txt'],
+			} ],
+	],
+	'outputs' => [
+		[
+			'cpt_psm_object',
+			'Output PSM Object',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'cpt_psm',
+				data_format    => 'text/plain',
+				default_format => 'TXT'
+			}
+		],
+	],
+	'defaults' => [
+		'appid'   => 'PSM.Prep',
+		'appname' => 'PSM Prep',
+		'appdesc' => 'prepares data for the PSM Plotter',
+		'appvers' => '1.94.2',
+	],
+	'tests' => [],
+);
+
+
+
+use CPT::Bio;
+my $bio = CPT::Bio->new();
+
+my @genbank_files = @{$options->{file}};
+
+my %data = (
+	file_list => [],
+);
+
+my $GLOBAL_UNLINK_VAR = 1;
+my $tempdir = tempdir('cpt.psm2.XXXXXXX',CLEANUP => $GLOBAL_UNLINK_VAR);
+use CPT::Util::CRC64;
+my $crc = CPT::Util::CRC64->new();
+
+foreach my $file(@genbank_files){
+	my $seqio_object = Bio::SeqIO->new(-file => $file,-format=>'genbank');
+	while(my $seqobj = $seqio_object->next_seq){
+		my ( $fh, $path ) = tempfile('cds_export.XXXXXXXXX', UNLINK => $GLOBAL_UNLINK_VAR, DIR => $tempdir, SUFFIX => '.fa');
+
+		my @gi_array;
+		foreach my $feat ( $seqobj->get_SeqFeatures ) {
+			if($feat->primary_tag eq 'CDS'){
+				my $header = $bio->_getIdentifier($feat);
+				# This ensures proteins have a file-specific ID appeneded to them.
+				my $seq = $bio->translate(
+					$bio->intelligent_get_seq($feat));
+
+				# Proteins come with translated stop codon
+				$seq =~ s/\*//g;
+				$seq =~ s/\+//g;
+				$seq =~ s/#//g;
+				$header .= "_" . $crc->crc64($seq);
+				push @gi_array, $header;
+				print $fh ">$header\n$seq\n";
+			}
+		}
+		$data{gbk}{$seqobj->display_id()}{'gi'} = \@gi_array;
+		$data{gbk}{$seqobj->display_id()}{'fasta_location'} = $path;
+		$data{gbk}{$seqobj->display_id()}{'gbk_location'} = $file;
+		push(@{$data{file_list}}, $seqobj->display_id());
+		close $fh;
+	}
+}
+
+
+
+use IPC::Run3;
+
+# Concatenate Fasta Files
+my @fasta_files;
+foreach(@{$data{file_list}}){
+	push(@fasta_files, $data{gbk}{$_}{fasta_location});
+}
+my @command = ('cat', @fasta_files);
+my ($merged_fa_fh, $merged_fa_path) = tempfile('merged.XXXXXXXXX', UNLINK => 1, DIR => $tempdir, SUFFIX => '.fa');
+my ($in, $out, $err);
+run3 \@command, \$in, \$out, \$err;
+if($err){
+	print STDERR $err;
+}
+print $merged_fa_fh $out;
+close($merged_fa_fh);
+
+
+# Create Blast Database
+my ($blastdb_fh, $blastdb_path) = tempfile('blastdb.XXXXXXXXX', UNLINK => 1, DIR => $tempdir);
+@command = ('makeblastdb', 
+	'-dbtype', 'prot',
+	'-in', $merged_fa_path,
+	'-out', $blastdb_path,
+);
+my ($makeblast_in,$makeblast_out,$makeblast_err);
+run3 \@command, \$makeblast_in, \$makeblast_out, \$makeblast_err;
+
+# Blast files
+foreach(@{$data{file_list}}){
+	#push(@fasta_files, $data{gbk}{$_}{fasta_location});
+	my @blast_cmd = ('blastp',
+		'-query', $data{gbk}{$_}{fasta_location},
+		'-out', $data{gbk}{$_}{fasta_location} . ".xml",
+		'-outfmt', '5',
+		'-db', $blastdb_path,
+	);
+	my ($blast_in,$blast_out,$blast_err);
+	run3 \@blast_cmd, \$blast_in, \$blast_out, \$blast_err;
+}
+
+my $value;
+my @data_tsv;
+
+foreach(@{$data{file_list}}){
+	#push(@fasta_files, $data{gbk}{$_}{fasta_location});
+	my $file = $data{gbk}{$_}{fasta_location};
+
+	my $in = new Bio::SearchIO(
+		-format   => 'blastxml',
+		-tempfile => 1,
+		-file     => "$file.xml",
+	);
+	while( my $result = $in->next_result ) {
+		while( my $hit = $result->next_hit ) {
+			while( my $hsp = $hit->next_hsp ) {
+				my $Identity = $hsp->percent_identity/100 * $hsp->length('query');
+				my $IterationQueryLength = $result->query_length();
+				my $HitLength = $hit->length();
+				my $dice = (200*$Identity)/($HitLength + $IterationQueryLength);
+
+				my $c = $result->query_description();#genome_a_header
+				my $d = $hit->name();#genome_b_header
+				# Skip self-self links
+				next if($c eq $d);
+
+				push (@data_tsv,
+					[
+						$c,
+						$d,
+						$hsp->evalue(),
+						$dice,
+					]
+				);
+
+			}#close hsp
+		}#close hit
+	}#close result
+}#close for genomes
+
+$data{hit_table} = \@data_tsv;
+
+use CPT::OutputFiles;
+my $psmout = CPT::OutputFiles->new(
+	name => 'cpt_psm_object',
+	GGO => $ggo,
+);
+my @val = $psmout->CRR(data => "none", extension => 'psm');
+store \%data,$val[0];
+
+
+
+
+
+
+
+=head1 NAME
+
+PSM Prep
+
+=head1 DESCRIPTION
+
+This tool takes in 2 or more GenBank files, blasts, and prepares data structures for use in the companion tool: PSM Plotter. Select as many (multi)-gbk files as you I<might> want to plot. Once this tool is done, you can select any subset of those to plot then.
+
+=cut

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_psm_1_plot.pl	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,440 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use Storable;
+use CPT::GalaxyGetOpt;
+use CPT::Bio::NW_MSA;
+use Data::Dumper;
+use CPT::Circos::Conf;
+use POSIX;
+
+
+my $ggo  = CPT::GalaxyGetOpt->new();
+my $options = $ggo->getOptions(
+	'options' => [
+		[ 'file', 'PSM2 Data File', { validate => 'File/Input', required => 1 } ],
+		[ 'user_ordering', 'List of genome IDs used in the analysis, can be comma/space/newline separated.', { validate => 'String', required => 1 }],
+		[],
+		['Plot Options'],
+		['percent_filled'   , 'Percentage of a whole block that an individual gene is'                  , { validate => 'Float', default=>'0.8', min => '0.1', max => '1.0' }],
+		['ig_dist'          , 'Maximum length of links between genome comparisons'                      , { validate => 'Int', default => 100 }],
+		['stroke_thickness' , 'Thickness of inter-genome links'                                         , { validate => 'Int', default => '2', min => 1, max => 10 } ],
+		['every_nth'        , 'Plot every Nth gene a modified version of the main color for that genome', { validate => 'Int', default => '20'}],
+		[],
+		['Cutoffs'],
+		['evalue' , 'Evalue cutoff' , { validate => 'Float' , default => 1e-4 } ] ,
+		['dice'   , 'Dice cutoff'   , { validate => 'Float' , default => 50 } ]   ,
+		[],
+		['Alignment Options'],
+		['mismatch'    , 'Mismatch Score' , { validate => 'Float' , default => -0.1 } ] ,
+		['gap_penalty' , 'Gap Penalty'    , { validate => 'Float' , default => '0.0' } ] ,
+		['match'       , 'Match Score'    , { validate => 'Float' , default => 5 } ]  ,
+	],
+	'outputs' => [
+		[
+			'output_circos_confs',
+			'Output Circos Conf Object',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'psm3',
+				data_format    => 'archive',
+				default_format => 'tar.gz',
+			}
+		],
+	],
+	'defaults' => [
+		'appid'   => 'PSM.Plot',
+		'appname' => 'PSM Plotter',
+		'appdesc' => 'plots data from PSM Prep',
+		'appvers' => '1.94.2',
+	],
+	'tests' => [
+	],
+);
+
+my $percent_filled = $options->{percent_filled};
+my $width          = 1000*$percent_filled;
+my $spacing        = 1000-$width;
+
+
+
+my $offset = ($width+$spacing)/2;
+my $full_increment   = $width+$spacing;
+my $halfwidth        = $width/2;
+
+#my %option_map = (
+	#'offset'           => ($width+$spacing)/2,
+	#'full_increment'   => $width+$spacing,
+	#'halfwidth'        => $width/2,
+	#'gap_penalty'      => $options->{gap_penalty},
+	#'match'            => $options->{match},
+	#'heatmap'          => 1,
+	#'heatmap_low'      => hex("0xCCCCCC"),
+	#'heatmap_high'     => hex("0x333333"),
+	#'heatmap_bucket'   => 8,
+	#'every_nth'        => $options->{every_nth},
+	#'user_ordering'    => $options->{user_ordering},
+	#'dice'             => $options->{dice},
+	#'evalue'           => $options->{evalue},
+#);
+#Color/name correspondance, to be used in writing the circos-0.63-pre1 files
+
+my @user_ordering;
+push(@user_ordering, split(/[,\n\r\s]+/, $options->{user_ordering}));
+
+my @aligned_results;
+my %fh_relationship;
+my %precomputed_colour_hash;
+my %protein_position_quicklookup;
+my %response = ();
+my %data_file = %{retrieve($options->{file})};
+
+my %uo_idx;
+for(my $i=0;$i<scalar @user_ordering;$i++){
+	$uo_idx{$user_ordering[$i]} = $i;
+}
+
+align();
+my %compmap_proteins = %{compmap_proteins()};
+# a => "link text"
+my %linkages = %{linkages()};
+# a => b => "link text"
+
+sub align{
+	print STDERR "Aliging genomes\n";
+	my $msa = CPT::Bio::NW_MSA->new(
+		gap_penalty => $options->{'gap_penalty'},
+		match_score => $options->{'match'},
+		mismatch_score => $options->{'mismatch'},
+		bidi => 1,
+	);
+
+	my @hits = @{$data_file{hit_table}};
+
+	foreach my $hit(@hits){
+		my ($from, $to, $evalue, $dice) = @{$hit};
+		if($evalue < $options->{evalue} && $dice > $options->{dice}){
+			if($options->{verbose}){
+				print "$from $to\n";
+			}
+			$msa->add_relationship($from, $to);
+		}
+	}
+
+	foreach my $genome(@user_ordering){
+		print STDERR "\tAligning $genome\n";
+		my $gi_list_ref = $data_file{gbk}{$genome}{gi};#"GI" list
+		if(! defined $gi_list_ref){
+			warn "Could not find $genome genome in the data file. Please be sure you have correctly specified the name of a genome from a genbank file. (See the LOCUS line for the name).";
+		}else{
+			$msa->align_list($gi_list_ref);
+		}
+	}
+	@aligned_results = $msa->merged_array();
+}
+sub compmap_proteins{
+	my @Narr = ();#Keep count of how many items we've had in a single
+	#column, so the modulus whe we're colouring them in will work properly,
+	#rather than being on every Nth radial colum in the plot
+	#
+	my $_max = scalar @aligned_results;
+	my %protein_files;
+
+	#for(my $i = scalar @aligned_results - 1; $i >= 0; $i--){
+	for(my $i = 0; $i < scalar @aligned_results; $i++){
+		# Get the current row from the PSM result object
+		my @current_row = @{$aligned_results[$i]};
+		if($options->{verbose}){
+			print join("\t", @current_row) , "\n";
+		}
+
+		for(my $j = 0; $j < scalar @current_row; $j++){
+			if($current_row[$j] ne "-"){
+				$protein_position_quicklookup{$current_row[$j]} = [$i,$j];
+				$Narr[$j]++;
+				my $color_str = '';
+				if($Narr[$j] % $options->{every_nth} == 0){
+					$color_str = 'fill_color=accent-8-qual-inv-' . ($j+1) . ',';
+				}
+				my $str = join(' ',
+						'compmap ',
+						(($i+1) * $full_increment - $halfwidth ),
+						(($i+1) * $full_increment + $halfwidth ),
+						"${color_str}f=". $current_row[$j]
+					);
+				$protein_files{$user_ordering[$j]} .= $str . "\n";
+			}
+		}
+	}
+	return \%protein_files;
+}
+sub linkages{
+	my @hits = @{$data_file{hit_table}};
+	my %links;
+	foreach my $hit (@hits){
+		my ($from, $to, $evalue, $dice) = @{$hit};
+		if($evalue < $options->{evalue} && $dice > $options->{dice}){
+			if(defined $protein_position_quicklookup{$from} && defined $protein_position_quicklookup{$to}){
+				my ($theta0,$radius0) = @{$protein_position_quicklookup{$from}};
+				my ($theta1,$radius1) = @{$protein_position_quicklookup{$to}};
+				# If this is a self-self link, disable plotting because we don't care.
+				# If ig_dist is disabled or distance is between them is less than our minimum
+				if($radius0 != $radius1
+					&& ($options->{'ig_dist'} == "-1" || abs($theta0-$theta1) <= $options->{'ig_dist'})
+				){
+					# Create the dataset
+					my @row_data = ('compmap',
+					);
+					# We work under the assumption that all hits
+					# are bi-directional, so we swap them to be
+					# smallest first no matter what.
+					if($radius1 < $radius0){
+						my $tmp = $radius1;
+						$radius1 = $radius0;
+						$radius0 = $tmp;
+						# We also want to add in reverse order
+						push(@row_data,
+							(($theta0+1)*$full_increment),
+							(($theta1+1)*$full_increment),
+						);
+					}else{
+						push(@row_data,
+							(($theta1+1)*$full_increment),
+							(($theta0+1)*$full_increment),
+						);
+					}
+
+					# If it's a link with the same theta
+					# value, then we'll go ahead and hide
+					# behind the track to make it a little
+					# prettier.
+					my $zstr;
+					if($theta0 == $theta1){
+						$zstr="z=0";
+					}else{
+						$zstr="z=100";
+					}
+					
+					# Create the additional row data
+					push(@row_data,
+						join(',', "dice=$dice", "color=" . colorstr($dice))
+					);
+					$links{$radius0}{$radius1} .= join(' ', @row_data) . "\n";
+				}
+			}
+		}
+	}
+	return \%links;
+}
+sub colorstr {
+	my ($dice) = @_;
+	if($dice > 90) {
+		return 'black';
+	}else{
+		return 'greys-9-seq-' . floor($dice / 10);
+	}
+}
+sub circosconf {
+	my $cc = CPT::Circos::Conf->new();
+	$cc->include('etc/colors_fonts_patterns.conf');
+	$cc->start_block('colors');
+	$cc->set('accent-8-qual-inv-1', '42, 135, 42');
+	$cc->set('accent-8-qual-inv-2', '111, 83, 150');
+	$cc->set('accent-8-qual-inv-3', '182, 112, 46');
+	$cc->set('accent-8-qual-inv-4', '178, 178, 53');
+	$cc->set('accent-8-qual-inv-5', '13, 63, 128');
+	$cc->set('accent-8-qual-inv-6', '183, 0, 96');
+	$cc->set('accent-8-qual-inv-7', '116, 47, 0');
+	$cc->set('accent-8-qual-inv-8', '45, 45, 45');
+	$cc->end_block();
+	# markings indicating position along genome
+	$cc->include('example/etc/ideogram.conf');
+	#$cc->include('rules.conf');
+	# Genome data
+	$cc->set('karyotype', 'karyotype.conf');
+	# Default image params are fine
+	$cc->start_block('image');
+	$cc->include('etc/image.conf');
+	$cc->end_block();
+	#$cc->include('highlights.conf');
+	$cc->include('plots.conf');
+	#$cc->include('rules.conf');
+
+	$cc->include('etc/housekeeping.conf');
+	my $result = $cc->finalize();
+	$cc = CPT::Circos::Conf->new();
+	return $result;
+}
+sub karyotype {
+	my @karyotype_data = (
+		"chr - compmap compmap 0 ".((scalar @aligned_results)*1000+500)." white"
+	);
+	return join("\n", @karyotype_data);
+}
+
+my @files = ();
+
+my $number_of_tracks = 0;
+sub register_track {
+	my ($r0,$r1) = calculate_individual_track($number_of_tracks);
+	$number_of_tracks++;
+	return ($r0, $r1);
+}
+sub calculate_individual_track {
+	my ($idx) = @_;
+	my $r0 = ( 90 - (10 * $idx - 1)/1) / 100;
+	my $r1 = ( 90 - (10 * $idx - 9)/1) / 100;
+	return ($r0, $r1);
+}
+sub genome_data {
+	my $cc = CPT::Circos::Conf->new();
+	# Map string back to position in array.
+	#$cc->set('z',10);
+	# Loop across all our protein data sets
+	$cc->start_block('plots');
+	foreach my $genome(@user_ordering){
+		# Add protein file
+		my $filename = sprintf('org.features.%s.txt', $genome);
+		push(@files, [ 'data/'.$filename, $compmap_proteins{$genome}]);
+		# Create associated tracks
+
+		my ($r0,$r1) = register_track();
+		$cc->start_block('plot');
+		$cc->set('type','highlight');
+		$cc->set('file', $filename);
+		$cc->set('r0', $r0 .'r');
+		$cc->set('r1', $r1 .'r');
+		$cc->set('z', '50');
+		$cc->set('fill_color','accent-8-qual-' . ($uo_idx{$genome} + 1));
+		$cc->set('stroke_thickness', '1');
+		$cc->set('stroke_color', 'black');
+		$cc->end_block();
+	}
+
+
+	foreach my $from(@user_ordering){
+		foreach my $to(@user_ordering){
+			next if($from eq $to || $uo_idx{$from} > $uo_idx{$to});
+		
+			if($linkages{$uo_idx{$from}}{$uo_idx{$to}}){
+				my $filename = sprintf('links.%s.%s.txt', $from, $to);
+				push(@files, [ 'data/'.$filename, $linkages{$uo_idx{$from}}{$uo_idx{$to}}]);
+				#push(@files, [ 'data/'.$filename, 'blaaaaaaah']);
+
+				my ($r0a, $r0b) = calculate_individual_track($uo_idx{$to});
+				my ($r1a, $r1b) = calculate_individual_track($uo_idx{$from});
+		
+				# If they're in this ordering, they will be pointing at
+				# the "outsides" of each genome/protein track, so we
+				# swap with the internal ones.
+				if($r1b > $r0a){
+					$r0a = $r1a;
+					$r1b = $r0b;
+				}
+
+				$cc->start_block('plot');
+				$cc->set('type','connector');
+				$cc->set('thickness', $options->{stroke_thickness});
+				$cc->set('file', $filename);
+				if($r1b<$r0a){
+					$cc->set('r0', $r1b .'r');
+					$cc->set('r1', $r0a .'r');
+				}else{
+					$cc->set('r0', $r0a .'r');
+					$cc->set('r1', $r1b .'r');
+				}
+				$cc->set('connector_dims', '0,0.3,0.4,0.3,0');
+				$cc->set('color','black');
+				$cc->end_block();
+			}
+		}
+	}
+
+
+	$cc->end_block();
+	return $cc->finalize();
+}
+sub rulesconf {
+	my ($self) = @_;
+	my $cc = CPT::Circos::Conf->new();
+	$cc->start_block('rules');
+	for(my $i = 0; $i < 10; $i++){
+		$cc->start_block('rule');
+		$cc->set('importance', 10 - $i);
+		$cc->set('condition', 'var(dice) > ' . (10*$i));
+		if($i == 9){
+			$cc->set('color', 'black');
+		}else{
+			$cc->set('color', 'gray' . (10 * ($i+1)));
+		}
+		#$cc->set('z',10-$i);
+		$cc->end_block();
+	}
+	$cc->end_block();
+}
+
+push(@files, [ 'etc/karyotype.conf', karyotype() ]);
+push(@files, [ 'etc/circos.conf', circosconf() ]);
+#push(@files, [ 'etc/rules.conf', rulesconf() ]);
+push(@files, [ 'etc/plots.conf', genome_data() ]);
+
+
+
+use Archive::Any::Create;
+my $archive = Archive::Any::Create->new();
+$archive->container('conf');
+foreach(@files){
+	my ($location, $content) = @{$_};
+	$archive->add_file($location, $content);
+}
+
+use CPT::OutputFiles;
+my $crr_output = CPT::OutputFiles->new(
+	name => 'output_circos_confs',
+	GGO => $ggo,
+);
+$crr_output->CRR(data => $archive);
+
+
+=head1 NAME
+
+PSM Plotter
+
+=head1 DESCRIPTION
+
+Following the execution of the PSM Prep tool, this tool plots a subset of those genomes as ciruclar tracks with protein-protein relationships plotted as links between the boxes representing proteins.
+
+=head2 IMPORTANT PARAMETERS
+
+=over 4
+
+=item C<user_ordering>
+
+This parameter controls the order in which genomes are aligned and then plotted. This MUST contain (comma/space) separated values listing the order (outside to in) in which you want your genomes to appear. In this field, type the name of each genome. The name can be found on the first line of the file under "LOCUS    NC_00000001", where NC_00000001 would be the genome's name.
+
+=item C<evalue>, C<dice>
+
+Adjusting these parameters will affect which links are plotted. Links are heatmapped into bins based on dice score as that is the easiest measure to work with, and scales nicely from 0 to 100. For example, a link with a dice score of 20-29 would be plotted as 20% black (grey20), whereas a dice score of 90+ would be plotted as solid black
+
+=item C<mismatch>, C<gap_penalty>, C<match>
+
+These parameters control the Needleman-Wunsch Multiple Sequence Alignment library's scoring scheme. Mismatch scores are generally negative and discourage unrelated proteins from being plotted in a line together. Match scores encourage related proteins to line up. Gap penalty is set at zero as we generally prefer gaps to mismatches in this tool; phage genomes are small and gaps are "cheap" to use, whereas mismatches can sometimes give an incorrect impression of relatedness. That said, how your plots look is completely up to you and we encourage experimentation!
+
+=item C<every_nth>
+
+Every Nth gene in a genome will be plotted a slightly different color.
+
+=back
+
+=head2 Why Can't I Control Colors?
+
+    Brewer colors compose Brewer palettes which have been manually defined by
+    Cynthia Brewer for their perceptual properties.
+
+    http://circos.ca/tutorials/lessons/configuration/colors/
+
+Color palette choice is very important to creating an attractive and easy to read graphic. In the words of Dr. Krzywinski, L<Color palettes matter|http://mkweb.bcgsc.ca/jclub/biovis/brewer/colorpalettes.pdf>. Humans selecting from an RGB/HSV color palette tend to make poor choices, so we've removed the option in lieu of using the very attractive L<Brewer Palettes|http://colorbrewer2.org/>. Specifically, I've selected the 8 class qualtitative "Accent" color set, which has produced some very nice maps. If you would like the option of selecting amongst the other 8-class qualitative color sets, please file a bug report and let me know.
+
+
+=cut

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_psm_1_plot.xml	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,163 @@
+<tool id="PSM.Plot" name="PSM Plotter" version="1.94.2">
+  <description>plots data from PSM Prep</description>
+  <version_command>perl cpt_psm_1_plot.pl --version</version_command>
+  <stdio>
+    <exit_code range="1:" level="fatal"/>
+  </stdio>
+  <requirements>
+    <requirement type="package" version="5.22.1">perl</requirement>
+    <requirement type="package">perl-bioperl</requirement>
+    <requirement type="package">perl-moose</requirement>
+    <requirement type="package">perl-ipc-run</requirement>
+    <requirement type="package">perl-getopt-long-descriptive</requirement>
+  </requirements>
+  <command detect_errors="aggressive"><![CDATA[
+perl -Mlib='$__tool_directory__/lib' '$__tool_directory__/cpt_psm_1_plot.pl'
+--galaxy
+--outfile_supporting '$__new_file_path__'
+--file "${file}"
+
+--user_ordering "${user_ordering}"
+
+#if $percent_filled and $percent_filled is not "None":
+--percent_filled "${percent_filled}"
+#end if
+
+#if $ig_dist and $ig_dist is not "None":
+--ig_dist "${ig_dist}"
+#end if
+
+#if $stroke_thickness and $stroke_thickness is not "None":
+--stroke_thickness "${stroke_thickness}"
+#end if
+
+#if $every_nth and $every_nth is not "None":
+--every_nth "${every_nth}"
+#end if
+
+#if $evalue and $evalue is not "None":
+--evalue "${evalue}"
+#end if
+
+#if $dice and $dice is not "None":
+--dice "${dice}"
+#end if
+
+#if $mismatch and $mismatch is not "None":
+--mismatch "${mismatch}"
+#end if
+
+#if $gap_penalty and $gap_penalty is not "None":
+--gap_penalty "${gap_penalty}"
+#end if
+
+#if $match and $match is not "None":
+--match "${match}"
+#end if
+
+--output_circos_confs "${output_circos_confs}"
+
+--output_circos_confs_files_path "${output_circos_confs.files_path}"
+
+--output_circos_confs_format "${output_circos_confs_format}"
+
+--output_circos_confs_id "${output_circos_confs.id}"
+
+]]></command>
+  <inputs>
+    <param name="file" help="PSM2 Data File" optional="False" label="file" type="data"/>
+    <param name="user_ordering" help="List of genome IDs used in the analysis, can be comma/space/newline separated." optional="False" label="user_ordering" type="text"/>
+    <param min="0.1" value="0.8" max="1.0" name="percent_filled" optional="True" help="Percentage of a whole block that an individual gene is" type="float" label="percent_filled"/>
+    <param value="100" name="ig_dist" help="Maximum length of links between genome comparisons" optional="True" label="ig_dist" type="integer"/>
+    <param min="1" value="2" max="10" name="stroke_thickness" optional="True" help="Thickness of inter-genome links" type="integer" label="stroke_thickness"/>
+    <param value="20" name="every_nth" optional="True" help="Plot every Nth gene a modified version of the main color for that genome" label="every_nth" type="integer"/>
+    <param value="0.0001" name="evalue" optional="True" help="Evalue cutoff" label="evalue" type="float"/>
+    <param value="50" name="dice" optional="True" help="Dice cutoff" label="dice" type="float"/>
+    <param value="-0.1" name="mismatch" optional="True" help="Mismatch Score" label="mismatch" type="float"/>
+    <param value="0.0" name="gap_penalty" optional="True" help="Gap Penalty" label="gap_penalty" type="float"/>
+    <param value="5" name="match" optional="True" help="Match Score" label="match" type="float"/>
+    <param name="output_circos_confs_format" help="Output Circos Conf Object" optional="False" label="Format of output_circos_confs" type="select">
+      <option value="zip">zip</option>
+    </param>
+  </inputs>
+  <outputs>
+    <data name="output_circos_confs" format="tar.gz">
+      <change_format>
+        <when input="output_circos_confs_format" value="tar.gz" format="tar.gz"/>
+        <when input="output_circos_confs_format" value="zip" format="zip"/>
+        <when input="output_circos_confs_format" value="tar" format="tar"/>
+      </change_format>
+    </data>
+  </outputs>
+  <help>NAME
+====
+
+PSM Plotter
+
+DESCRIPTION
+===========
+
+Following the execution of the PSM Prep tool, this tool plots a subset
+of those genomes as ciruclar tracks with protein-protein relationships
+plotted as links between the boxes representing proteins.
+
+IMPORTANT PARAMETERS
+--------------------
+
+-  ``user_ordering``
+
+   This parameter controls the order in which genomes are aligned and
+   then plotted. This MUST contain (comma/space) separated values
+   listing the order (outside to in) in which you want your genomes to
+   appear. In this field, type the name of each genome. The name can be
+   found on the first line of the file under "LOCUS NC\_00000001", where
+   NC\_00000001 would be the genome's name.
+
+-  ``evalue``, ``dice``
+
+   Adjusting these parameters will affect which links are plotted. Links
+   are heatmapped into bins based on dice score as that is the easiest
+   measure to work with, and scales nicely from 0 to 100. For example, a
+   link with a dice score of 20-29 would be plotted as 20% black
+   (grey20), whereas a dice score of 90+ would be plotted as solid black
+
+-  ``mismatch``, ``gap_penalty``, ``match``
+
+   These parameters control the Needleman-Wunsch Multiple Sequence
+   Alignment library's scoring scheme. Mismatch scores are generally
+   negative and discourage unrelated proteins from being plotted in a
+   line together. Match scores encourage related proteins to line up.
+   Gap penalty is set at zero as we generally prefer gaps to mismatches
+   in this tool; phage genomes are small and gaps are "cheap" to use,
+   whereas mismatches can sometimes give an incorrect impression of
+   relatedness. That said, how your plots look is completely up to you
+   and we encourage experimentation!
+
+-  ``every_nth``
+
+   Every Nth gene in a genome will be plotted a slightly different
+   color.
+
+Why Can't I Control Colors?
+---------------------------
+
+::
+
+    Brewer colors compose Brewer palettes which have been manually defined by
+    Cynthia Brewer for their perceptual properties.
+
+    http://circos.ca/tutorials/lessons/configuration/colors/
+
+Color palette choice is very important to creating an attractive and
+easy to read graphic. In the words of Dr. Krzywinski, `Color palettes
+matter &lt;http://mkweb.bcgsc.ca/jclub/biovis/brewer/colorpalettes.pdf&gt;`__.
+Humans selecting from an RGB/HSV color palette tend to make poor
+choices, so we've removed the option in lieu of using the very
+attractive `Brewer Palettes &lt;http://colorbrewer2.org/&gt;`__. Specifically,
+I've selected the 8 class qualtitative "Accent" color set, which has
+produced some very nice maps. If you would like the option of selecting
+amongst the other 8-class qualitative color sets, please file a bug
+report and let me know.
+</help>
+  <tests/>
+</tool>

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/cpt_psm_2_gentable.pl	Mon Jun 05 02:48:47 2023 +0000
@@ -0,0 +1,168 @@
+#!/usr/bin/env perl
+use strict;
+use warnings;
+use Storable;
+use CPT::GalaxyGetOpt;
+use CPT::Bio::NW_MSA;
+use Data::Dumper;
+use CPT::Circos::Conf;
+use POSIX;
+
+
+my $ggo  = CPT::GalaxyGetOpt->new();
+my $options = $ggo->getOptions(
+	'options' => [
+		[ 'file', 'PSM2 Data File', { validate => 'File/Input', required => 1 } ],
+		[],
+		['Cutoffs'],
+		['evalue' , 'Evalue cutoff' , { validate => 'Float' , default => 1e-4 } ] ,
+		['dice'   , 'Dice cutoff'   , { validate => 'Float' , default => 50 } ]   ,
+		[],
+		['Alignment Options'],
+		['mismatch'    , 'Mismatch Score' , { validate => 'Float' , default => -1} ] ,
+		['gap_penalty' , 'Gap Penalty'    , { validate => 'Float' , default => '0.0' } ] ,
+		['match'       , 'Match Score'    , { validate => 'Float' , default => 5 } ]  ,
+	],
+	'outputs' => [
+		[
+			'diff_table',
+			'Output Comparison Table',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'genome_comp',
+				data_format    => 'text/tabular',
+				default_format => 'TSV_U',
+			},
+        ],
+        [
+			'blastclust',
+			'Output Blastclust Table',
+			{
+				validate       => 'File/Output',
+				required       => 1,
+				default        => 'blastclust',
+				data_format    => 'text/tabular',
+				default_format => 'TSV_U',
+			}
+		],
+	],
+	'defaults' => [
+		'appid'   => 'PSM.Comp',
+		'appname' => 'PSM Comparison Table',
+		'appdesc' => 'aligns and lists data from PSM Prep',
+		'appvers' => '1.94',
+	],
+	'tests' => [
+	],
+);
+
+
+my %data_file = %{retrieve($options->{file})};
+
+print STDERR "Aliging genomes\n";
+my $msa = CPT::Bio::NW_MSA->new(
+	gap_penalty => $options->{'gap_penalty'},
+	match_score => $options->{'match'},
+	mismatch_score => $options->{'mismatch'},
+	bidi => 1,
+);
+
+my @hits = @{$data_file{hit_table}};
+my @clusters;
+
+foreach my $hit(@hits){
+	my ($from, $to, $evalue, $dice) = @{$hit};
+	if($evalue < $options->{evalue} && $dice > $options->{dice}){
+		if($options->{verbose}){
+			print "$from $to\n";
+		}
+
+        my $foundmatch = 0;
+        foreach my $cluster(@clusters){
+            if($from ~~ @{$cluster} || $to ~~ @{$cluster}){
+                $foundmatch = 1;
+                if(!($from ~~ @{$cluster})){
+                    push(@{$cluster}, $from);
+                }
+                if(!($to ~~ @{$cluster})){
+                    push(@{$cluster}, $to);
+                }
+            }
+        }
+        if($foundmatch == 0){
+            push(@clusters, ["".($#clusters+2), $from, $to]);
+        }
+		$msa->add_relationship($from, $to);
+	}
+}
+my @fixed_clusters;
+foreach my $cluster (@clusters) {
+    my ($idx, @values) = @{$cluster};
+    push(@fixed_clusters, [$idx, join(',', @values)]);
+}
+
+my @user_ordering = keys($data_file{gbk});
+
+foreach my $genome(@user_ordering){
+	print STDERR "\tAligning $genome\n";
+	my $gi_list_ref = $data_file{gbk}{$genome}{gi};#"GI" list
+	if(! defined $gi_list_ref){
+		warn "Could not find $genome genome in the data file. Please be sure you have correctly specified the name of a genome from a genbank file. (See the LOCUS line for the name).";
+	}else{
+		$msa->align_list($gi_list_ref);
+	}
+}
+
+my @aligned_results = $msa->merged_array();
+# Remove CRC64 hashes from sequences
+foreach my $row(@aligned_results){
+	$row = [map { s/_[A-F0-9]{16}$//; $_ } @{$row}];
+    #my $key = ${$row}[0];
+    #foreach my $cluster(@clusters){
+
+    #}
+}
+
+my %table = (
+	'Sheet1' => {
+		header => \@user_ordering,
+		data =>  \@aligned_results,
+	}
+);
+
+
+use CPT::OutputFiles;
+my $crr_output = CPT::OutputFiles->new(
+	name => 'diff_table',
+	GGO => $ggo,
+);
+$crr_output->CRR(data => \%table);
+
+my %table2 = (
+    'Sheet1' => {
+        header => ['Cluster ID', 'Contents'],
+        data => \@fixed_clusters,
+    }
+);
+my $crr_output2 = CPT::OutputFiles->new(
+	name => 'blastclust',
+	GGO => $ggo,
+);
+$crr_output2->CRR(data => \%table2);
+
+=head1 DESCRIPTION
+
+Following the execution of the PSM Prep tool, this tool simply aligns the genomes and generates a table comparison the positions of all proteins. It can be very useful to figure out which genes are missing in which genomes.
+
+=head2 IMPORTANT PARAMETERS
+
+=over 4
+
+=item C<mismatch>, C<gap_penalty>, C<match>
+
+These parameters control the Needleman-Wunsch Multiple Sequence Alignment library's scoring scheme. Mismatch scores are generally negative and discourage unrelated proteins from being plotted in a line together. Match scores encourage related proteins to line up. Gap penalty is set at zero as we generally prefer gaps to mismatches in this tool; phage genomes are small and gaps are "cheap" to use, whereas mismatches can sometimes give an incorrect impression of relatedness. That said, how your plots look is completely up to you and we encourage experimentation!
+
+=back
+
+=cut

--- a/cpt_psm_plotter/cpt_dnaplotter.pl	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,465 +0,0 @@
-#!/usr/bin/perl
-#
-#       Code written by Eric Rasche
-#               mailto:rasche.eric@yandex.ru
-#               tel:   404.692.2048
-#               http://eric.rasche.co.uk
-#       for
-#               Center for Phage Technology
-#
-
-use strict;
-use warnings;
-
-use CPT::GalaxyGetOpt;
-use Data::Dumper;
-use CPT::Bio;
-use CPT::Circos::Conf;
-my $bio = CPT::Bio->new();
-
-my @argv_copy;
-foreach(@ARGV){push(@argv_copy, "$_");}
-
-my $ggo  = CPT::GalaxyGetOpt->new();
-my $options = $ggo->getOptions(
-	'options' => [
-		[ 'file|f', 'Input file', { validate => 'File/Input',
-				file_format => ['genbank', 'embl', 'txt'],
-			} ],
-		[],
-		['Track Configuration'],
-		['track_key', 'Key to select from genbank data', { validate => 'Genomic/Tag', required => 1, multiple => 1 } ],
-		['track_feature_filter_invert', 'Should the qualifier search be inverted?', { validate => 'Option', options => { 'yes', 'Yes', 'no', 'No' } , multiple => 1 } ],
-		['track_feature_filter_hastag', 'Select a tag which should be present in that qualifier (e.g., signal/tmhelix/pseudo)', { validate => 'String' , multiple => 1 } ],
-		['track_feature_filter_textquery', 'Specify text which MUST be in that tag', { validate => 'String' , multiple => 1 } ],
-		['track_feature_filter_strand', 'Which strand should the feature appear on?', { validate => 'Option', options => { 'f', 'Forward', 'r', 'Reverse', 'a', 'Any' } , multiple => 1 } ],
-		[],
-		['enable_gc_skew_plot', 'Enable/Disable calculation of GC Skew Plot', { validate => 'Flag' } ],
-		['gc_skew_plot_window_size', 'Window size for calculation of GC Skew', { validate => 'Int', min => 1000, default => 10000} ],
-		['gc_skew_plot_step_size', 'Step size for calculation of GC Skew', { validate => 'Int', min => 200, default => 200 } ],
-	],
-	'outputs' => [
-		[
-			'output_circos_confs',
-			'Circos Configuration Files',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'out',
-				data_format    => 'archive',
-				default_format => 'zip',
-			}
-		],
-	],
-	'defaults' => [
-		'appid'   => 'CircularDNAPlotter',
-		'appname' => 'Circos based DNAPlotter',
-		'appdesc' => 'plots genomes similar to Artemis\'s DNAPlotter',
-		'appvers' => '1.94.1',
-	],
-);
-
-#perl cpt_dnaplotter.pl \
-	#-f ../t/test-files/moon.gbk \
-	#--track_key CDS --track_feature_filter_invert yes --track_feature_filter_hastag pseudo --track_feature_filter_strand f \
-	#--track_key CDS --track_feature_filter_invert yes --track_feature_filter_hastag pseudo  --track_feature_filter_strand r \
-	#--track_key CDS --track_feature_filter_hastag pseudo  --track_feature_filter_strand a \
-	#--track_key tRNA  --track_feature_filter_strand a \
-	#--track_key CDS  --track_feature_filter_hastag signal --track_feature_filter_strand a \
-	#--track_key CDS  --track_feature_filter_hastag tmhelix --track_feature_filter_strand a
-
-
-my @reorg_args = ();
-
-my $cum_gc_ske_mean = 0;
-
-
-
-my %latest = ();
-for(my $i = 0; $i < scalar(@argv_copy); $i++){
-	my $c = $argv_copy[$i];
-	# We have entered a new one block
-	if($c eq '--track_key'){
-		# If we have loaded data
-		if(scalar(keys(%latest)) > 0){
-			my %copy;
-			foreach(keys(%latest)){
-				$copy{$_} = "" . $latest{$_};
-			}
-			push(@reorg_args, \%copy);
-		}
-
-		# Clean out latest to prep for new data
-		foreach(keys(%latest)){
-			delete $latest{$_};
-		}
-	}
-
-	if($c =~ /^--track_(.*)/){
-		$latest{$1} = $argv_copy[$i+1];
-		# Artificially bump so we don't bother looking at the answer to
-		# this question. We can "get away" with this because none of
-		# the options are flags. However, I've disabled it in the event
-		# that flags ARE introduced
-		#$i++;
-	}
-}
-push(@reorg_args, \%latest);
-#$VAR1 = [
-          #{
-            #'feature_filter_invert' => 'yes',
-            #'feature_plot_color' => '005500',
-            #'feature_filter_strand' => 'f',
-            #'feature_filter_hastag' => 'pseudo',
-            #'key' => 'CDS'
-          #},
-          #{
-            #'feature_filter_strand' => 'a',
-            #'key' => 'RBS'
-          #}
-        #];
-my @files = ();
-
-my $number_of_tracks = 0;
-sub register_track {
-	#my $r0 = ( 90 - (10 * $number_of_tracks - 1)/2) / 100;
-	#my $r1 = ( 90 - (10 * $number_of_tracks - 9)/2) / 100;
-	my $r0 = ( 90 - (10 * $number_of_tracks - 1)/1) / 100;
-	my $r1 = ( 90 - (10 * $number_of_tracks - 9)/1) / 100;
-	$number_of_tracks++;
-	return ($r0, $r1);
-}
-
-sub circosconf {
-	my $cc = CPT::Circos::Conf->new();
-	$cc->include('etc/colors_fonts_patterns.conf');
-	# Features to plot along the genome
-	$cc->include('ideogram.conf');
-	# markings indicating position along genome
-	$cc->include('ticks.conf');
-	# Genome data
-	$cc->set('karyotype', 'karyotype.conf');
-	# Default image params are fine
-	$cc->start_block('image');
-	$cc->include('etc/image.conf');
-	$cc->end_block();
-	# ???
-	$cc->set('chromosome_units', '1000');
-	$cc->set('chromosome_display_default', 'yes');
-	#$cc->include('highlights.conf');
-	$cc->include('plots.conf');
-
-	$cc->include('etc/housekeeping.conf');
-	my $result = $cc->finalize();
-	$cc = CPT::Circos::Conf->new();
-	return $result;
-}
-sub ideogramconf{
-	my $cc = CPT::Circos::Conf->new();
-	$cc->start_block('ideogram');
-	$cc->start_block('spacing');
-	$cc->set('default','0u');
-	$cc->set('break','0u');
-	$cc->end_block();
-
-	$cc->set('thickness', '20p');
-	$cc->set('stroke_thickness', '2');
-	$cc->set('stroke_color', 'black');
-	$cc->set('fill','no');
-	$cc->set('fill_color','black');
-	$cc->set('radius','0.85r');
-	$cc->set('show_label','yes');
-	$cc->set('label_font','default');
-	$cc->set('label_radius','dims(ideogram,radius) + 0.05');
-	$cc->set('label_size','36');
-	$cc->set('label_parallel','yes');
-	$cc->set('label_case','upper');
-
-	$cc->set('band_stroke_thickness','2');
-	$cc->set('show_bands','yes');
-	$cc->set('fill_bands','yes');
-	$cc->end_block();
-
-	return $cc->finalize();
-}
-sub generate_feature_table {
-	my ($filename, %filter) = @_;
-	print "Filtering on features\n";
-	print Dumper \%filter;
-	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
-	# Only handing first sequence.
-	my $seq_object = $seqio_object->next_seq;
-	my $parent = $seq_object->display_id();
-	# Feature data
-	my @features;
-	foreach my $feat($seq_object->get_SeqFeatures()){
-		if($feat->primary_tag() eq $filter{key}){
-			# If they've said "hastag" AND we do indeed have that tag AND we haven't inverted this filter.
-			if(
-				($filter{feature_filter_hastag} && $feat->has_tag($filter{feature_filter_hastag}) && !$filter{feature_filter_invert})
-				||
-				($filter{feature_filter_hastag} && $filter{feature_filter_invert} && !$feat->has_tag($filter{feature_filter_hastag}))
-				||
-				(! $filter{feature_filter_hastag})
-			){
-				if(
-					!$filter{feature_filter_strand}
-					||
-					($feat->strand() == 1 && ( $filter{feature_filter_strand} eq 'f' ||  $filter{feature_filter_strand} eq 'a' ))
-					||
-					($feat->strand() == -1 && ( $filter{feature_filter_strand} eq 'r' ||  $filter{feature_filter_strand} eq 'a' ))
-					||
-					($feat->strand() == 0 && ( $filter{feature_filter_strand} eq 'a' ))
-				){
-					push(@features, join(' ', $parent, $feat->start, $feat->end));
-				}
-			}
-		}
-	}
-	print "Found " . scalar @features . " features \n";
-	push(@files, [ 'data/' . $filename, join("\n", @features) ] );
-}
-sub plotsconf{
-	my $cc = CPT::Circos::Conf->new();
-
-	$cc->start_block('plots');
-
-
-	my $idx = 0;
-	foreach(@reorg_args){
-		my %filter = %{$_};
-          #{
-            #'feature_filter_invert' => 'yes',
-            #'feature_plot_color' => '005500',
-            #'feature_filter_strand' => 'f',
-            #'feature_filter_hastag' => 'pseudo',
-            #'key' => 'CDS'
-          #},
-		$idx++;
-		my $filename = sprintf('org.features.%s.txt', $idx);
-		generate_feature_table($filename, %filter);
-
-		my ($r0,$r1) = register_track();
-		$cc->start_block('plot');
-		$cc->set('type','tile');
-		$cc->set('file',$filename);
-		$cc->set('orientation', 'center');
-		$cc->set('thickness', '30');
-		$cc->set('r1', $r1 . 'r');# '0.78r');
-		$cc->set('r0', $r0 . 'r');# '0.72r');
-		$cc->set('layers','3');
-		$cc->set('layers_overflow','collapse');
-		$cc->set('color','paired-6-qual-' . $idx);
-		$cc->end_block();
-	}
-
-	if($options->{enable_gc_skew_plot}){
-		my ($r0,$r1) = register_track();
-		$cc->start_block('plot');
-		$cc->set('type','histogram');
-		$cc->set('file','gc.txt');
-		$cc->set('r1',$r1 . 'r');
-		$cc->set('r0',$r0 . 'r');
-		$cc->set('fill_color','purple');
-		$cc->set('orientation','in');
-		$cc->start_block('rules');
-		$cc->start_block('rule');
-		$cc->set('condition','var(value) < 0');
-		$cc->set('fill_color', 'green');
-		$cc->end_block();
-		$cc->end_block();
-		$cc->end_block();
-	}
-
-	#$cc->start_block('plot');
-	#$cc->set('type','histogram');
-	#$cc->set('file','gc_cumulative.txt');
-	#$cc->set('r1','0.6r');
-	#$cc->set('r0','0.55r');
-	#$cc->set('fill_color','purple');
-	#$cc->set('orientation','out');
-	#$cc->start_block('rules');
-	#$cc->start_block('rule');
-	#$cc->set('condition','var(value) < ' . $cum_gc_ske_mean);
-	#$cc->set('fill_color', 'green');
-	#$cc->end_block();
-	#$cc->end_block();
-	#$cc->end_block();
-
-	$cc->end_block();
-	return $cc->finalize();
-}
-sub ticksconf{
-	my $cc = CPT::Circos::Conf->new();
-
-	$cc->set('show_ticks','yes');
-	$cc->set('show_tick_labels','yes');
-	$cc->start_block('ticks');
-	$cc->set('radius','1r');
-	$cc->set('color','black');
-	$cc->set('thickness','2p');
-	$cc->set('multiplier','1e-3');
-	$cc->set('format','%d');
-
-	$cc->start_block('tick');
-	$cc->set('spacing','1000u');
-	$cc->set('size','10p');
-	$cc->end_block();
-
-	$cc->start_block('tick');
-	$cc->set('spacing','10000u');
-	$cc->set('size','15p');
-	$cc->set('show_label','yes');
-	$cc->set('label_size','20p');
-	$cc->set('label_offset','10p');
-	$cc->set('format','%d');
-	$cc->end_block();
-	$cc->end_block();
-	return $cc->finalize();
-}
-sub karyotype {
-	my @karyotype_data = ();
-	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
-	# Only handing first sequence.
-	my $seq_object = $seqio_object->next_seq;
-	# Main 'chromosome' data
-	push(@karyotype_data, join(' ', 'chr', '-',$seq_object->display_id(),$seq_object->display_id(),0, $seq_object->length(),'black'));
-
-	return join("\n", @karyotype_data);
-}
-
-sub gcgraph_cumulative {
-	my @gcdata = ();
-	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
-	# Only handing first sequence.
-	my $seq_object = $seqio_object->next_seq;
-
-	my $parent = $seq_object->display_id();
-
-	my $seq = $seq_object->seq();
-	my $sep = int($options->{gc_skew_plot_window_size}/2);
-	my $stepsep = int($options->{gc_skew_plot_step_size}/2);
-	my $cumulative_gc_skew = 0;
-	my @cumgc_vals;
-
-	my $count = 0;
-	foreach(my $i = $sep; $i < $seq_object->length() - $sep - $options->{gc_skew_plot_step_size}; $i += $options->{gc_skew_plot_step_size}){
-		$count++;
-		$cumulative_gc_skew += _calculate_gc_skew_for_seq(substr($seq,$i-$sep,$options->{gc_skew_plot_window_size})),
-		push(@cumgc_vals, $cumulative_gc_skew);
-		push(@gcdata, join(" ",
-			$parent,
-			$i - $stepsep,
-			$i + $stepsep,
-			$cumulative_gc_skew
-		));
-	}
-
-	my $sum = 0;
-	foreach(@cumgc_vals){$sum += $_;}
-	$cum_gc_ske_mean = $sum / $count;
-
-	return join("\n", @gcdata);
-	# Main 'chromosome' data
-}
-sub gcgraph {
-	my @gcdata = ();
-	my $seqio_object = Bio::SeqIO->new(-file => $options->{file}, -format=>'genbank');
-	# Only handing first sequence.
-	my $seq_object = $seqio_object->next_seq;
-
-	my $parent = $seq_object->display_id();
-
-	my $seq = $seq_object->seq();
-	my $sep = int($options->{gc_skew_plot_window_size}/2);
-	my $stepsep = int($options->{gc_skew_plot_step_size}/2);
-	foreach(my $i = $sep; $i < $seq_object->length() - $sep - $options->{gc_skew_plot_step_size}; $i += $options->{gc_skew_plot_step_size}){
-		push(@gcdata, join(" ",
-			$parent,
-			$i - $stepsep,
-			$i + $stepsep,
-			_calculate_gc_skew_for_seq(substr($seq,$i-$sep,$options->{gc_skew_plot_window_size})),
-		));
-	}
-	return join("\n", @gcdata);
-	# Main 'chromosome' data
-}
-sub _calculate_gc_skew_for_seq {
-	my ($seq) = @_;
-	$seq = uc($seq);
-	my %counts;
-	foreach(split //,$seq){
-		$counts{$_}++;
-	}
-	if($counts{G} + $counts{C} > 0){
-		return ($counts{G} - $counts{C}) / ($counts{G} + $counts{C});
-	}
-	return 0;
-}
-
-push(@files, [ 'etc/karyotype.conf', karyotype() ]);
-push(@files, [ 'etc/circos.conf', circosconf() ]);
-push(@files, [ 'etc/ideogram.conf', ideogramconf() ]);
-if($options->{enable_gc_skew_plot}){
-	push(@files, [ 'data/gc.txt', gcgraph() ]);
-	push(@files, [ 'data/gc_cumulative.txt', gcgraph_cumulative() ]);
-}
-
-push(@files, [ 'etc/plots.conf', plotsconf() ]);
-push(@files, [ 'etc/ticks.conf', ticksconf() ]);
-
-
-use Archive::Any::Create;
-my $archive = Archive::Any::Create->new();
-$archive->container('conf');
-foreach(@files){
-	my ($location, $content) = @{$_};
-	$archive->add_file($location, $content);
-}
-
-use CPT::OutputFiles;
-my $crr_output = CPT::OutputFiles->new(
-	name => 'output_circos_confs',
-	GGO => $ggo,
-);
-$crr_output->CRR(data => $archive);
-
-=head1 NAME
-
-DNAPlotter
-
-=head1 DESCRIPTION
-
-Much like artemis's DNAPlotter, this tool plots genomes in a ciruclar fashion, and can plot gc-deviation tracks as well. The options are somewhat reduced compared to artemis, so if you need something that isn't available in this version please file a bug report.
-
-=head1 USE
-
-Each track has several parameters:
-
-=over 4
-
-=item track_key
-
-This selects a set of features from a genbank file, e.g., CDSs or tRNAs
-
-=item track_feature_filter_invert
-
-This parameter will invert (negate) the results of whatever query parameters you specify after it.
-
-=item track_feature_filter_hastag
-
-Require that a feature has a specific tag....
-
-=item track_feature_filter_textquery
-
-...with this specific text in it
-
-=item track_feature_filter_strand
-
-Which strand should the feature be on (not inverted)
-
-=back
-
-Additionally, users are able to enable/disable GC skew plots. it's suggested that these are generally left alone, as they can quickly increase runtime.
-
-=cut

--- a/cpt_psm_plotter/cpt_genbank2circosk.pl	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,131 +0,0 @@
-#!/usr/bin/perl
-#
-#       Code written by Eric Rasche
-#               mailto:rasche.eric@yandex.ru
-#               tel:404.692.2048
-#               http://eric.rasche.co.uk
-#       for
-#               Center for Phage Technology
-#
-
-use strict;
-use warnings;
-
-use CPT::GalaxyGetOpt;
-use Data::Dumper;
-
-my $ggo = CPT::GalaxyGetOpt->new();
-my %colors = map { $_ => $_ } qw(red orange yellow green blue gray black white);
-my %intensity = map { $_ => $_ } qw (vvvvl vvvl vvl vl vd vvd vvvd vvvvd);
-
-my $options = $ggo->getOptions(
-	'options' => [
-		[
-			'file',
-			'Input file',
-			{
-				required => 1,
-				validate => 'File/Input',
-				file_format => ['genbank', 'embl', 'txt'],
-			}
-		],
-		[
-			'chromosome' => 'Name for the
-			chromosome inside Circos',
-			{
-				required => 1,
-				validate => 'String'
-			}
-		],
-		[
-			'color' => 'Color to use for Circos plot',
-			{
-				required => 1,
-				validate => 'Option',
-				options  => \%colors,
-			}
-		],
-		[
-			'intensity' => 'Circos color intensity. ',
-			{
-				validate => 'Option',
-				options  => \%intensity,
-			}
-		],
-	],
-	'outputs' => [
-		[
-			'circosk',
-			'Circos Karyotype File',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'karyotype',
-				data_format    => 'text/plain',
-				default_format => 'TXT'
-			}
-		],
-	],
-	'defaults' => [
-		'appname' => 'Genbank2CircosK',
-		'appid'   => 'Genbank2CircosK',
-		'appvers' => '1.94',
-		'appdesc' =>
-'Convert genbank files to Circos Karyotype configuration files',
-	],
-	'tests' => [
-		{
-			test_name => "Default",
-			params => {
-				'file' => 'test-data/inputs/multi.gbk',
-				'chromosome' => 'test',
-				'color' => 'red',
-				'intensity' => 'vvvl',
-			},
-			outputs => {
-				'circosk' => ['karyotype.txt', 'test-data/outputs/circosk.conf'],
-			}
-		},
-	],
-);
-
-use CPT::Bio;
-my $bio = CPT::Bio->new();
-
-my @results;
-my $c = 0;
-my $seqio = $bio->requestCopyIO( file => $options->{file} );
-
-while(my $seqobj = $seqio->next_seq()){
-	foreach my $feat ( $seqobj->get_SeqFeatures () ) {
-
-		#band test 12 CDS__test_1gbk 5715 6335 red]
-		next if ( $feat->primary_tag ne 'CDS' );
-		my $id = $bio->_getIdentifier($feat);
-		$id =~ s/\s+/_/g;
-		push(
-			@results,
-			join(
-				' ',
-				(
-					'band',
-					$options->{'chromosome'},
-					$c++,
-					$id,
-					$feat->start,
-					$feat->end,
-					(defined $options->{'intensity'} ? $options->{'intensity'} : '') . $options->{'color'}
-				)
-			)
-		);
-	}
-}
-
-my $z = join( "\n", @results );
-
-use CPT::OutputFiles;
-my $output = CPT::OutputFiles->new(
-        name => 'circosk',
-        GGO => $ggo,
-);
-$output->CRR(data => $z);

--- a/cpt_psm_plotter/cpt_psm_0_prep.pl	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,194 +0,0 @@
-#!/usr/bin/env perl
-use strict;
-use warnings;
-use Storable;
-use Bio::SearchIO;
-use Bio::SeqIO;
-use Bio::Tools::CodonTable;
-use Data::Dumper;
-use File::Temp qw/tempfile tempdir/;
-
-
-use CPT::GalaxyGetOpt;
-my $ggo  = CPT::GalaxyGetOpt->new();
-my $options = $ggo->getOptions(
-	'options' => [
-		[ 'file', 'Input file', { validate => 'File/Input', multiple => 1, required => 1,
-				file_format => ['genbank', 'txt'],
-			} ],
-	],
-	'outputs' => [
-		[
-			'cpt_psm_object',
-			'Output PSM Object',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'cpt_psm',
-				data_format    => 'text/plain',
-				default_format => 'TXT'
-			}
-		],
-	],
-	'defaults' => [
-		'appid'   => 'PSM.Prep',
-		'appname' => 'PSM Prep',
-		'appdesc' => 'prepares data for the PSM Plotter',
-		'appvers' => '1.94.2',
-	],
-	'tests' => [],
-);
-
-
-
-use CPT::Bio;
-my $bio = CPT::Bio->new();
-
-my @genbank_files = @{$options->{file}};
-
-my %data = (
-	file_list => [],
-);
-
-my $GLOBAL_UNLINK_VAR = 1;
-my $tempdir = tempdir('cpt.psm2.XXXXXXX',CLEANUP => $GLOBAL_UNLINK_VAR);
-use CPT::Util::CRC64;
-my $crc = CPT::Util::CRC64->new();
-
-foreach my $file(@genbank_files){
-	my $seqio_object = Bio::SeqIO->new(-file => $file,-format=>'genbank');
-	while(my $seqobj = $seqio_object->next_seq){
-		my ( $fh, $path ) = tempfile('cds_export.XXXXXXXXX', UNLINK => $GLOBAL_UNLINK_VAR, DIR => $tempdir, SUFFIX => '.fa');
-
-		my @gi_array;
-		foreach my $feat ( $seqobj->get_SeqFeatures ) {
-			if($feat->primary_tag eq 'CDS'){
-				my $header = $bio->_getIdentifier($feat);
-				# This ensures proteins have a file-specific ID appeneded to them.
-				my $seq = $bio->translate(
-					$bio->intelligent_get_seq($feat));
-
-				# Proteins come with translated stop codon
-				$seq =~ s/\*//g;
-				$seq =~ s/\+//g;
-				$seq =~ s/#//g;
-				$header .= "_" . $crc->crc64($seq);
-				push @gi_array, $header;
-				print $fh ">$header\n$seq\n";
-			}
-		}
-		$data{gbk}{$seqobj->display_id()}{'gi'} = \@gi_array;
-		$data{gbk}{$seqobj->display_id()}{'fasta_location'} = $path;
-		$data{gbk}{$seqobj->display_id()}{'gbk_location'} = $file;
-		push(@{$data{file_list}}, $seqobj->display_id());
-		close $fh;
-	}
-}
-
-
-
-use IPC::Run3;
-
-# Concatenate Fasta Files
-my @fasta_files;
-foreach(@{$data{file_list}}){
-	push(@fasta_files, $data{gbk}{$_}{fasta_location});
-}
-my @command = ('cat', @fasta_files);
-my ($merged_fa_fh, $merged_fa_path) = tempfile('merged.XXXXXXXXX', UNLINK => 1, DIR => $tempdir, SUFFIX => '.fa');
-my ($in, $out, $err);
-run3 \@command, \$in, \$out, \$err;
-if($err){
-	print STDERR $err;
-}
-print $merged_fa_fh $out;
-close($merged_fa_fh);
-
-
-# Create Blast Database
-my ($blastdb_fh, $blastdb_path) = tempfile('blastdb.XXXXXXXXX', UNLINK => 1, DIR => $tempdir);
-@command = ('makeblastdb', 
-	'-dbtype', 'prot',
-	'-in', $merged_fa_path,
-	'-out', $blastdb_path,
-);
-my ($makeblast_in,$makeblast_out,$makeblast_err);
-run3 \@command, \$makeblast_in, \$makeblast_out, \$makeblast_err;
-
-# Blast files
-foreach(@{$data{file_list}}){
-	#push(@fasta_files, $data{gbk}{$_}{fasta_location});
-	my @blast_cmd = ('blastp',
-		'-query', $data{gbk}{$_}{fasta_location},
-		'-out', $data{gbk}{$_}{fasta_location} . ".xml",
-		'-outfmt', '5',
-		'-db', $blastdb_path,
-	);
-	my ($blast_in,$blast_out,$blast_err);
-	run3 \@blast_cmd, \$blast_in, \$blast_out, \$blast_err;
-}
-
-my $value;
-my @data_tsv;
-
-foreach(@{$data{file_list}}){
-	#push(@fasta_files, $data{gbk}{$_}{fasta_location});
-	my $file = $data{gbk}{$_}{fasta_location};
-
-	my $in = new Bio::SearchIO(
-		-format   => 'blastxml',
-		-tempfile => 1,
-		-file     => "$file.xml",
-	);
-	while( my $result = $in->next_result ) {
-		while( my $hit = $result->next_hit ) {
-			while( my $hsp = $hit->next_hsp ) {
-				my $Identity = $hsp->percent_identity/100 * $hsp->length('query');
-				my $IterationQueryLength = $result->query_length();
-				my $HitLength = $hit->length();
-				my $dice = (200*$Identity)/($HitLength + $IterationQueryLength);
-
-				my $c = $result->query_description();#genome_a_header
-				my $d = $hit->name();#genome_b_header
-				# Skip self-self links
-				next if($c eq $d);
-
-				push (@data_tsv,
-					[
-						$c,
-						$d,
-						$hsp->evalue(),
-						$dice,
-					]
-				);
-
-			}#close hsp
-		}#close hit
-	}#close result
-}#close for genomes
-
-$data{hit_table} = \@data_tsv;
-
-use CPT::OutputFiles;
-my $psmout = CPT::OutputFiles->new(
-	name => 'cpt_psm_object',
-	GGO => $ggo,
-);
-my @val = $psmout->CRR(data => "none", extension => 'psm');
-store \%data,$val[0];
-
-
-
-
-
-
-
-=head1 NAME
-
-PSM Prep
-
-=head1 DESCRIPTION
-
-This tool takes in 2 or more GenBank files, blasts, and prepares data structures for use in the companion tool: PSM Plotter. Select as many (multi)-gbk files as you I<might> want to plot. Once this tool is done, you can select any subset of those to plot then.
-
-=cut

--- a/cpt_psm_plotter/cpt_psm_1_plot.pl	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,440 +0,0 @@
-#!/usr/bin/env perl
-use strict;
-use warnings;
-use Storable;
-use CPT::GalaxyGetOpt;
-use CPT::Bio::NW_MSA;
-use Data::Dumper;
-use CPT::Circos::Conf;
-use POSIX;
-
-
-my $ggo  = CPT::GalaxyGetOpt->new();
-my $options = $ggo->getOptions(
-	'options' => [
-		[ 'file', 'PSM2 Data File', { validate => 'File/Input', required => 1 } ],
-		[ 'user_ordering', 'List of genome IDs used in the analysis, can be comma/space/newline separated.', { validate => 'String', required => 1 }],
-		[],
-		['Plot Options'],
-		['percent_filled'   , 'Percentage of a whole block that an individual gene is'                  , { validate => 'Float', default=>'0.8', min => '0.1', max => '1.0' }],
-		['ig_dist'          , 'Maximum length of links between genome comparisons'                      , { validate => 'Int', default => 100 }],
-		['stroke_thickness' , 'Thickness of inter-genome links'                                         , { validate => 'Int', default => '2', min => 1, max => 10 } ],
-		['every_nth'        , 'Plot every Nth gene a modified version of the main color for that genome', { validate => 'Int', default => '20'}],
-		[],
-		['Cutoffs'],
-		['evalue' , 'Evalue cutoff' , { validate => 'Float' , default => 1e-4 } ] ,
-		['dice'   , 'Dice cutoff'   , { validate => 'Float' , default => 50 } ]   ,
-		[],
-		['Alignment Options'],
-		['mismatch'    , 'Mismatch Score' , { validate => 'Float' , default => -0.1 } ] ,
-		['gap_penalty' , 'Gap Penalty'    , { validate => 'Float' , default => '0.0' } ] ,
-		['match'       , 'Match Score'    , { validate => 'Float' , default => 5 } ]  ,
-	],
-	'outputs' => [
-		[
-			'output_circos_confs',
-			'Output Circos Conf Object',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'psm3',
-				data_format    => 'archive',
-				default_format => 'tar.gz',
-			}
-		],
-	],
-	'defaults' => [
-		'appid'   => 'PSM.Plot',
-		'appname' => 'PSM Plotter',
-		'appdesc' => 'plots data from PSM Prep',
-		'appvers' => '1.94.2',
-	],
-	'tests' => [
-	],
-);
-
-my $percent_filled = $options->{percent_filled};
-my $width          = 1000*$percent_filled;
-my $spacing        = 1000-$width;
-
-
-
-my $offset = ($width+$spacing)/2;
-my $full_increment   = $width+$spacing;
-my $halfwidth        = $width/2;
-
-#my %option_map = (
-	#'offset'           => ($width+$spacing)/2,
-	#'full_increment'   => $width+$spacing,
-	#'halfwidth'        => $width/2,
-	#'gap_penalty'      => $options->{gap_penalty},
-	#'match'            => $options->{match},
-	#'heatmap'          => 1,
-	#'heatmap_low'      => hex("0xCCCCCC"),
-	#'heatmap_high'     => hex("0x333333"),
-	#'heatmap_bucket'   => 8,
-	#'every_nth'        => $options->{every_nth},
-	#'user_ordering'    => $options->{user_ordering},
-	#'dice'             => $options->{dice},
-	#'evalue'           => $options->{evalue},
-#);
-#Color/name correspondance, to be used in writing the circos-0.63-pre1 files
-
-my @user_ordering;
-push(@user_ordering, split(/[,\n\r\s]+/, $options->{user_ordering}));
-
-my @aligned_results;
-my %fh_relationship;
-my %precomputed_colour_hash;
-my %protein_position_quicklookup;
-my %response = ();
-my %data_file = %{retrieve($options->{file})};
-
-my %uo_idx;
-for(my $i=0;$i<scalar @user_ordering;$i++){
-	$uo_idx{$user_ordering[$i]} = $i;
-}
-
-align();
-my %compmap_proteins = %{compmap_proteins()};
-# a => "link text"
-my %linkages = %{linkages()};
-# a => b => "link text"
-
-sub align{
-	print STDERR "Aliging genomes\n";
-	my $msa = CPT::Bio::NW_MSA->new(
-		gap_penalty => $options->{'gap_penalty'},
-		match_score => $options->{'match'},
-		mismatch_score => $options->{'mismatch'},
-		bidi => 1,
-	);
-
-	my @hits = @{$data_file{hit_table}};
-
-	foreach my $hit(@hits){
-		my ($from, $to, $evalue, $dice) = @{$hit};
-		if($evalue < $options->{evalue} && $dice > $options->{dice}){
-			if($options->{verbose}){
-				print "$from $to\n";
-			}
-			$msa->add_relationship($from, $to);
-		}
-	}
-
-	foreach my $genome(@user_ordering){
-		print STDERR "\tAligning $genome\n";
-		my $gi_list_ref = $data_file{gbk}{$genome}{gi};#"GI" list
-		if(! defined $gi_list_ref){
-			warn "Could not find $genome genome in the data file. Please be sure you have correctly specified the name of a genome from a genbank file. (See the LOCUS line for the name).";
-		}else{
-			$msa->align_list($gi_list_ref);
-		}
-	}
-	@aligned_results = $msa->merged_array();
-}
-sub compmap_proteins{
-	my @Narr = ();#Keep count of how many items we've had in a single
-	#column, so the modulus whe we're colouring them in will work properly,
-	#rather than being on every Nth radial colum in the plot
-	#
-	my $_max = scalar @aligned_results;
-	my %protein_files;
-
-	#for(my $i = scalar @aligned_results - 1; $i >= 0; $i--){
-	for(my $i = 0; $i < scalar @aligned_results; $i++){
-		# Get the current row from the PSM result object
-		my @current_row = @{$aligned_results[$i]};
-		if($options->{verbose}){
-			print join("\t", @current_row) , "\n";
-		}
-
-		for(my $j = 0; $j < scalar @current_row; $j++){
-			if($current_row[$j] ne "-"){
-				$protein_position_quicklookup{$current_row[$j]} = [$i,$j];
-				$Narr[$j]++;
-				my $color_str = '';
-				if($Narr[$j] % $options->{every_nth} == 0){
-					$color_str = 'fill_color=accent-8-qual-inv-' . ($j+1) . ',';
-				}
-				my $str = join(' ',
-						'compmap ',
-						(($i+1) * $full_increment - $halfwidth ),
-						(($i+1) * $full_increment + $halfwidth ),
-						"${color_str}f=". $current_row[$j]
-					);
-				$protein_files{$user_ordering[$j]} .= $str . "\n";
-			}
-		}
-	}
-	return \%protein_files;
-}
-sub linkages{
-	my @hits = @{$data_file{hit_table}};
-	my %links;
-	foreach my $hit (@hits){
-		my ($from, $to, $evalue, $dice) = @{$hit};
-		if($evalue < $options->{evalue} && $dice > $options->{dice}){
-			if(defined $protein_position_quicklookup{$from} && defined $protein_position_quicklookup{$to}){
-				my ($theta0,$radius0) = @{$protein_position_quicklookup{$from}};
-				my ($theta1,$radius1) = @{$protein_position_quicklookup{$to}};
-				# If this is a self-self link, disable plotting because we don't care.
-				# If ig_dist is disabled or distance is between them is less than our minimum
-				if($radius0 != $radius1
-					&& ($options->{'ig_dist'} == "-1" || abs($theta0-$theta1) <= $options->{'ig_dist'})
-				){
-					# Create the dataset
-					my @row_data = ('compmap',
-					);
-					# We work under the assumption that all hits
-					# are bi-directional, so we swap them to be
-					# smallest first no matter what.
-					if($radius1 < $radius0){
-						my $tmp = $radius1;
-						$radius1 = $radius0;
-						$radius0 = $tmp;
-						# We also want to add in reverse order
-						push(@row_data,
-							(($theta0+1)*$full_increment),
-							(($theta1+1)*$full_increment),
-						);
-					}else{
-						push(@row_data,
-							(($theta1+1)*$full_increment),
-							(($theta0+1)*$full_increment),
-						);
-					}
-
-					# If it's a link with the same theta
-					# value, then we'll go ahead and hide
-					# behind the track to make it a little
-					# prettier.
-					my $zstr;
-					if($theta0 == $theta1){
-						$zstr="z=0";
-					}else{
-						$zstr="z=100";
-					}
-					
-					# Create the additional row data
-					push(@row_data,
-						join(',', "dice=$dice", "color=" . colorstr($dice))
-					);
-					$links{$radius0}{$radius1} .= join(' ', @row_data) . "\n";
-				}
-			}
-		}
-	}
-	return \%links;
-}
-sub colorstr {
-	my ($dice) = @_;
-	if($dice > 90) {
-		return 'black';
-	}else{
-		return 'greys-9-seq-' . floor($dice / 10);
-	}
-}
-sub circosconf {
-	my $cc = CPT::Circos::Conf->new();
-	$cc->include('etc/colors_fonts_patterns.conf');
-	$cc->start_block('colors');
-	$cc->set('accent-8-qual-inv-1', '42, 135, 42');
-	$cc->set('accent-8-qual-inv-2', '111, 83, 150');
-	$cc->set('accent-8-qual-inv-3', '182, 112, 46');
-	$cc->set('accent-8-qual-inv-4', '178, 178, 53');
-	$cc->set('accent-8-qual-inv-5', '13, 63, 128');
-	$cc->set('accent-8-qual-inv-6', '183, 0, 96');
-	$cc->set('accent-8-qual-inv-7', '116, 47, 0');
-	$cc->set('accent-8-qual-inv-8', '45, 45, 45');
-	$cc->end_block();
-	# markings indicating position along genome
-	$cc->include('example/etc/ideogram.conf');
-	#$cc->include('rules.conf');
-	# Genome data
-	$cc->set('karyotype', 'karyotype.conf');
-	# Default image params are fine
-	$cc->start_block('image');
-	$cc->include('etc/image.conf');
-	$cc->end_block();
-	#$cc->include('highlights.conf');
-	$cc->include('plots.conf');
-	#$cc->include('rules.conf');
-
-	$cc->include('etc/housekeeping.conf');
-	my $result = $cc->finalize();
-	$cc = CPT::Circos::Conf->new();
-	return $result;
-}
-sub karyotype {
-	my @karyotype_data = (
-		"chr - compmap compmap 0 ".((scalar @aligned_results)*1000+500)." white"
-	);
-	return join("\n", @karyotype_data);
-}
-
-my @files = ();
-
-my $number_of_tracks = 0;
-sub register_track {
-	my ($r0,$r1) = calculate_individual_track($number_of_tracks);
-	$number_of_tracks++;
-	return ($r0, $r1);
-}
-sub calculate_individual_track {
-	my ($idx) = @_;
-	my $r0 = ( 90 - (10 * $idx - 1)/1) / 100;
-	my $r1 = ( 90 - (10 * $idx - 9)/1) / 100;
-	return ($r0, $r1);
-}
-sub genome_data {
-	my $cc = CPT::Circos::Conf->new();
-	# Map string back to position in array.
-	#$cc->set('z',10);
-	# Loop across all our protein data sets
-	$cc->start_block('plots');
-	foreach my $genome(@user_ordering){
-		# Add protein file
-		my $filename = sprintf('org.features.%s.txt', $genome);
-		push(@files, [ 'data/'.$filename, $compmap_proteins{$genome}]);
-		# Create associated tracks
-
-		my ($r0,$r1) = register_track();
-		$cc->start_block('plot');
-		$cc->set('type','highlight');
-		$cc->set('file', $filename);
-		$cc->set('r0', $r0 .'r');
-		$cc->set('r1', $r1 .'r');
-		$cc->set('z', '50');
-		$cc->set('fill_color','accent-8-qual-' . ($uo_idx{$genome} + 1));
-		$cc->set('stroke_thickness', '1');
-		$cc->set('stroke_color', 'black');
-		$cc->end_block();
-	}
-
-
-	foreach my $from(@user_ordering){
-		foreach my $to(@user_ordering){
-			next if($from eq $to || $uo_idx{$from} > $uo_idx{$to});
-		
-			if($linkages{$uo_idx{$from}}{$uo_idx{$to}}){
-				my $filename = sprintf('links.%s.%s.txt', $from, $to);
-				push(@files, [ 'data/'.$filename, $linkages{$uo_idx{$from}}{$uo_idx{$to}}]);
-				#push(@files, [ 'data/'.$filename, 'blaaaaaaah']);
-
-				my ($r0a, $r0b) = calculate_individual_track($uo_idx{$to});
-				my ($r1a, $r1b) = calculate_individual_track($uo_idx{$from});
-		
-				# If they're in this ordering, they will be pointing at
-				# the "outsides" of each genome/protein track, so we
-				# swap with the internal ones.
-				if($r1b > $r0a){
-					$r0a = $r1a;
-					$r1b = $r0b;
-				}
-
-				$cc->start_block('plot');
-				$cc->set('type','connector');
-				$cc->set('thickness', $options->{stroke_thickness});
-				$cc->set('file', $filename);
-				if($r1b<$r0a){
-					$cc->set('r0', $r1b .'r');
-					$cc->set('r1', $r0a .'r');
-				}else{
-					$cc->set('r0', $r0a .'r');
-					$cc->set('r1', $r1b .'r');
-				}
-				$cc->set('connector_dims', '0,0.3,0.4,0.3,0');
-				$cc->set('color','black');
-				$cc->end_block();
-			}
-		}
-	}
-
-
-	$cc->end_block();
-	return $cc->finalize();
-}
-sub rulesconf {
-	my ($self) = @_;
-	my $cc = CPT::Circos::Conf->new();
-	$cc->start_block('rules');
-	for(my $i = 0; $i < 10; $i++){
-		$cc->start_block('rule');
-		$cc->set('importance', 10 - $i);
-		$cc->set('condition', 'var(dice) > ' . (10*$i));
-		if($i == 9){
-			$cc->set('color', 'black');
-		}else{
-			$cc->set('color', 'gray' . (10 * ($i+1)));
-		}
-		#$cc->set('z',10-$i);
-		$cc->end_block();
-	}
-	$cc->end_block();
-}
-
-push(@files, [ 'etc/karyotype.conf', karyotype() ]);
-push(@files, [ 'etc/circos.conf', circosconf() ]);
-#push(@files, [ 'etc/rules.conf', rulesconf() ]);
-push(@files, [ 'etc/plots.conf', genome_data() ]);
-
-
-
-use Archive::Any::Create;
-my $archive = Archive::Any::Create->new();
-$archive->container('conf');
-foreach(@files){
-	my ($location, $content) = @{$_};
-	$archive->add_file($location, $content);
-}
-
-use CPT::OutputFiles;
-my $crr_output = CPT::OutputFiles->new(
-	name => 'output_circos_confs',
-	GGO => $ggo,
-);
-$crr_output->CRR(data => $archive);
-
-
-=head1 NAME
-
-PSM Plotter
-
-=head1 DESCRIPTION
-
-Following the execution of the PSM Prep tool, this tool plots a subset of those genomes as ciruclar tracks with protein-protein relationships plotted as links between the boxes representing proteins.
-
-=head2 IMPORTANT PARAMETERS
-
-=over 4
-
-=item C<user_ordering>
-
-This parameter controls the order in which genomes are aligned and then plotted. This MUST contain (comma/space) separated values listing the order (outside to in) in which you want your genomes to appear. In this field, type the name of each genome. The name can be found on the first line of the file under "LOCUS    NC_00000001", where NC_00000001 would be the genome's name.
-
-=item C<evalue>, C<dice>
-
-Adjusting these parameters will affect which links are plotted. Links are heatmapped into bins based on dice score as that is the easiest measure to work with, and scales nicely from 0 to 100. For example, a link with a dice score of 20-29 would be plotted as 20% black (grey20), whereas a dice score of 90+ would be plotted as solid black
-
-=item C<mismatch>, C<gap_penalty>, C<match>
-
-These parameters control the Needleman-Wunsch Multiple Sequence Alignment library's scoring scheme. Mismatch scores are generally negative and discourage unrelated proteins from being plotted in a line together. Match scores encourage related proteins to line up. Gap penalty is set at zero as we generally prefer gaps to mismatches in this tool; phage genomes are small and gaps are "cheap" to use, whereas mismatches can sometimes give an incorrect impression of relatedness. That said, how your plots look is completely up to you and we encourage experimentation!
-
-=item C<every_nth>
-
-Every Nth gene in a genome will be plotted a slightly different color.
-
-=back
-
-=head2 Why Can't I Control Colors?
-
-    Brewer colors compose Brewer palettes which have been manually defined by
-    Cynthia Brewer for their perceptual properties.
-
-    http://circos.ca/tutorials/lessons/configuration/colors/
-
-Color palette choice is very important to creating an attractive and easy to read graphic. In the words of Dr. Krzywinski, L<Color palettes matter|http://mkweb.bcgsc.ca/jclub/biovis/brewer/colorpalettes.pdf>. Humans selecting from an RGB/HSV color palette tend to make poor choices, so we've removed the option in lieu of using the very attractive L<Brewer Palettes|http://colorbrewer2.org/>. Specifically, I've selected the 8 class qualtitative "Accent" color set, which has produced some very nice maps. If you would like the option of selecting amongst the other 8-class qualitative color sets, please file a bug report and let me know.
-
-
-=cut

--- a/cpt_psm_plotter/cpt_psm_1_plot.xml	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,164 +0,0 @@
-<?xml version="1.0"?>
-<tool id="PSM.Plot" name="PSM Plotter" version="1.94.2">
-  <description>plots data from PSM Prep</description>
-  <version_command>perl cpt_psm_1_plot.pl --version</version_command>
-  <stdio>
-    <exit_code range="1:" level="fatal"/>
-  </stdio>
-  <requirements>
-      <requirement type="package" version="5.22.1">perl</requirement>
-      <requirement type="package">perl-bioperl</requirement>
-      <requirement type="package">perl-moose</requirement>
-      <requirement type="package">perl-ipc-run</requirement>
-      <requirement type="package">perl-getopt-long-descriptive</requirement>
-  </requirements>
-  <command detect_errors="aggressive"><![CDATA[
-perl -Mlib=$__tool_directory__/lib $__tool_directory__/cpt_psm_1_plot.pl
---galaxy
---outfile_supporting $__new_file_path__
---file "${file}"
-
---user_ordering "${user_ordering}"
-
-#if $percent_filled and $percent_filled is not "None":
---percent_filled "${percent_filled}"
-#end if
-
-#if $ig_dist and $ig_dist is not "None":
---ig_dist "${ig_dist}"
-#end if
-
-#if $stroke_thickness and $stroke_thickness is not "None":
---stroke_thickness "${stroke_thickness}"
-#end if
-
-#if $every_nth and $every_nth is not "None":
---every_nth "${every_nth}"
-#end if
-
-#if $evalue and $evalue is not "None":
---evalue "${evalue}"
-#end if
-
-#if $dice and $dice is not "None":
---dice "${dice}"
-#end if
-
-#if $mismatch and $mismatch is not "None":
---mismatch "${mismatch}"
-#end if
-
-#if $gap_penalty and $gap_penalty is not "None":
---gap_penalty "${gap_penalty}"
-#end if
-
-#if $match and $match is not "None":
---match "${match}"
-#end if
-
---output_circos_confs "${output_circos_confs}"
-
---output_circos_confs_files_path "${output_circos_confs.files_path}"
-
---output_circos_confs_format "${output_circos_confs_format}"
-
---output_circos_confs_id "${output_circos_confs.id}"
-
-]]></command>
-  <inputs>
-    <param name="file" help="PSM2 Data File" optional="False" label="file" type="data"/>
-    <param name="user_ordering" help="List of genome IDs used in the analysis, can be comma/space/newline separated." optional="False" label="user_ordering" type="text"/>
-    <param min="0.1" value="0.8" max="1.0" name="percent_filled" optional="True" help="Percentage of a whole block that an individual gene is" type="float" label="percent_filled"/>
-    <param value="100" name="ig_dist" help="Maximum length of links between genome comparisons" optional="True" label="ig_dist" type="integer"/>
-    <param min="1" value="2" max="10" name="stroke_thickness" optional="True" help="Thickness of inter-genome links" type="integer" label="stroke_thickness"/>
-    <param value="20" name="every_nth" optional="True" help="Plot every Nth gene a modified version of the main color for that genome" label="every_nth" type="integer"/>
-    <param value="0.0001" name="evalue" optional="True" help="Evalue cutoff" label="evalue" type="float"/>
-    <param value="50" name="dice" optional="True" help="Dice cutoff" label="dice" type="float"/>
-    <param value="-0.1" name="mismatch" optional="True" help="Mismatch Score" label="mismatch" type="float"/>
-    <param value="0.0" name="gap_penalty" optional="True" help="Gap Penalty" label="gap_penalty" type="float"/>
-    <param value="5" name="match" optional="True" help="Match Score" label="match" type="float"/>
-    <param name="output_circos_confs_format" help="Output Circos Conf Object" optional="False" label="Format of output_circos_confs" type="select">
-      <option value="zip">zip</option>
-    </param>
-  </inputs>
-  <outputs>
-    <data name="output_circos_confs" format="tar.gz">
-      <change_format>
-        <when input="output_circos_confs_format" value="tar.gz" format="tar.gz"/>
-        <when input="output_circos_confs_format" value="zip" format="zip"/>
-        <when input="output_circos_confs_format" value="tar" format="tar"/>
-      </change_format>
-    </data>
-  </outputs>
-  <help>NAME
-====
-
-PSM Plotter
-
-DESCRIPTION
-===========
-
-Following the execution of the PSM Prep tool, this tool plots a subset
-of those genomes as ciruclar tracks with protein-protein relationships
-plotted as links between the boxes representing proteins.
-
-IMPORTANT PARAMETERS
---------------------
-
--  ``user_ordering``
-
-   This parameter controls the order in which genomes are aligned and
-   then plotted. This MUST contain (comma/space) separated values
-   listing the order (outside to in) in which you want your genomes to
-   appear. In this field, type the name of each genome. The name can be
-   found on the first line of the file under "LOCUS NC\_00000001", where
-   NC\_00000001 would be the genome's name.
-
--  ``evalue``, ``dice``
-
-   Adjusting these parameters will affect which links are plotted. Links
-   are heatmapped into bins based on dice score as that is the easiest
-   measure to work with, and scales nicely from 0 to 100. For example, a
-   link with a dice score of 20-29 would be plotted as 20% black
-   (grey20), whereas a dice score of 90+ would be plotted as solid black
-
--  ``mismatch``, ``gap_penalty``, ``match``
-
-   These parameters control the Needleman-Wunsch Multiple Sequence
-   Alignment library's scoring scheme. Mismatch scores are generally
-   negative and discourage unrelated proteins from being plotted in a
-   line together. Match scores encourage related proteins to line up.
-   Gap penalty is set at zero as we generally prefer gaps to mismatches
-   in this tool; phage genomes are small and gaps are "cheap" to use,
-   whereas mismatches can sometimes give an incorrect impression of
-   relatedness. That said, how your plots look is completely up to you
-   and we encourage experimentation!
-
--  ``every_nth``
-
-   Every Nth gene in a genome will be plotted a slightly different
-   color.
-
-Why Can't I Control Colors?
----------------------------
-
-::
-
-    Brewer colors compose Brewer palettes which have been manually defined by
-    Cynthia Brewer for their perceptual properties.
-
-    http://circos.ca/tutorials/lessons/configuration/colors/
-
-Color palette choice is very important to creating an attractive and
-easy to read graphic. In the words of Dr. Krzywinski, `Color palettes
-matter &lt;http://mkweb.bcgsc.ca/jclub/biovis/brewer/colorpalettes.pdf&gt;`__.
-Humans selecting from an RGB/HSV color palette tend to make poor
-choices, so we've removed the option in lieu of using the very
-attractive `Brewer Palettes &lt;http://colorbrewer2.org/&gt;`__. Specifically,
-I've selected the 8 class qualtitative "Accent" color set, which has
-produced some very nice maps. If you would like the option of selecting
-amongst the other 8-class qualitative color sets, please file a bug
-report and let me know.
-</help>
-  <tests/>
-</tool>

--- a/cpt_psm_plotter/cpt_psm_2_gentable.pl	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,168 +0,0 @@
-#!/usr/bin/env perl
-use strict;
-use warnings;
-use Storable;
-use CPT::GalaxyGetOpt;
-use CPT::Bio::NW_MSA;
-use Data::Dumper;
-use CPT::Circos::Conf;
-use POSIX;
-
-
-my $ggo  = CPT::GalaxyGetOpt->new();
-my $options = $ggo->getOptions(
-	'options' => [
-		[ 'file', 'PSM2 Data File', { validate => 'File/Input', required => 1 } ],
-		[],
-		['Cutoffs'],
-		['evalue' , 'Evalue cutoff' , { validate => 'Float' , default => 1e-4 } ] ,
-		['dice'   , 'Dice cutoff'   , { validate => 'Float' , default => 50 } ]   ,
-		[],
-		['Alignment Options'],
-		['mismatch'    , 'Mismatch Score' , { validate => 'Float' , default => -1} ] ,
-		['gap_penalty' , 'Gap Penalty'    , { validate => 'Float' , default => '0.0' } ] ,
-		['match'       , 'Match Score'    , { validate => 'Float' , default => 5 } ]  ,
-	],
-	'outputs' => [
-		[
-			'diff_table',
-			'Output Comparison Table',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'genome_comp',
-				data_format    => 'text/tabular',
-				default_format => 'TSV_U',
-			},
-        ],
-        [
-			'blastclust',
-			'Output Blastclust Table',
-			{
-				validate       => 'File/Output',
-				required       => 1,
-				default        => 'blastclust',
-				data_format    => 'text/tabular',
-				default_format => 'TSV_U',
-			}
-		],
-	],
-	'defaults' => [
-		'appid'   => 'PSM.Comp',
-		'appname' => 'PSM Comparison Table',
-		'appdesc' => 'aligns and lists data from PSM Prep',
-		'appvers' => '1.94',
-	],
-	'tests' => [
-	],
-);
-
-
-my %data_file = %{retrieve($options->{file})};
-
-print STDERR "Aliging genomes\n";
-my $msa = CPT::Bio::NW_MSA->new(
-	gap_penalty => $options->{'gap_penalty'},
-	match_score => $options->{'match'},
-	mismatch_score => $options->{'mismatch'},
-	bidi => 1,
-);
-
-my @hits = @{$data_file{hit_table}};
-my @clusters;
-
-foreach my $hit(@hits){
-	my ($from, $to, $evalue, $dice) = @{$hit};
-	if($evalue < $options->{evalue} && $dice > $options->{dice}){
-		if($options->{verbose}){
-			print "$from $to\n";
-		}
-
-        my $foundmatch = 0;
-        foreach my $cluster(@clusters){
-            if($from ~~ @{$cluster} || $to ~~ @{$cluster}){
-                $foundmatch = 1;
-                if(!($from ~~ @{$cluster})){
-                    push(@{$cluster}, $from);
-                }
-                if(!($to ~~ @{$cluster})){
-                    push(@{$cluster}, $to);
-                }
-            }
-        }
-        if($foundmatch == 0){
-            push(@clusters, ["".($#clusters+2), $from, $to]);
-        }
-		$msa->add_relationship($from, $to);
-	}
-}
-my @fixed_clusters;
-foreach my $cluster (@clusters) {
-    my ($idx, @values) = @{$cluster};
-    push(@fixed_clusters, [$idx, join(',', @values)]);
-}
-
-my @user_ordering = keys($data_file{gbk});
-
-foreach my $genome(@user_ordering){
-	print STDERR "\tAligning $genome\n";
-	my $gi_list_ref = $data_file{gbk}{$genome}{gi};#"GI" list
-	if(! defined $gi_list_ref){
-		warn "Could not find $genome genome in the data file. Please be sure you have correctly specified the name of a genome from a genbank file. (See the LOCUS line for the name).";
-	}else{
-		$msa->align_list($gi_list_ref);
-	}
-}
-
-my @aligned_results = $msa->merged_array();
-# Remove CRC64 hashes from sequences
-foreach my $row(@aligned_results){
-	$row = [map { s/_[A-F0-9]{16}$//; $_ } @{$row}];
-    #my $key = ${$row}[0];
-    #foreach my $cluster(@clusters){
-
-    #}
-}
-
-my %table = (
-	'Sheet1' => {
-		header => \@user_ordering,
-		data =>  \@aligned_results,
-	}
-);
-
-
-use CPT::OutputFiles;
-my $crr_output = CPT::OutputFiles->new(
-	name => 'diff_table',
-	GGO => $ggo,
-);
-$crr_output->CRR(data => \%table);
-
-my %table2 = (
-    'Sheet1' => {
-        header => ['Cluster ID', 'Contents'],
-        data => \@fixed_clusters,
-    }
-);
-my $crr_output2 = CPT::OutputFiles->new(
-	name => 'blastclust',
-	GGO => $ggo,
-);
-$crr_output2->CRR(data => \%table2);
-
-=head1 DESCRIPTION
-
-Following the execution of the PSM Prep tool, this tool simply aligns the genomes and generates a table comparison the positions of all proteins. It can be very useful to figure out which genes are missing in which genomes.
-
-=head2 IMPORTANT PARAMETERS
-
-=over 4
-
-=item C<mismatch>, C<gap_penalty>, C<match>
-
-These parameters control the Needleman-Wunsch Multiple Sequence Alignment library's scoring scheme. Mismatch scores are generally negative and discourage unrelated proteins from being plotted in a line together. Match scores encourage related proteins to line up. Gap penalty is set at zero as we generally prefer gaps to mismatches in this tool; phage genomes are small and gaps are "cheap" to use, whereas mismatches can sometimes give an incorrect impression of relatedness. That said, how your plots look is completely up to you and we encourage experimentation!
-
-=back
-
-=cut

--- a/cpt_psm_plotter/lib/CPT.pm	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,37 +0,0 @@
-package CPT;
-use strict;
-use warnings;
-use Moose;
-
-# ABSTRACT: main library wrapping most actions needed by CPT's portal scripts.
-
-no Moose;
-1;
-
-__END__
-
-=pod
-
-=encoding UTF-8
-
-=head1 NAME
-
-CPT - main library wrapping most actions needed by CPT's portal scripts.
-
-=head1 VERSION
-
-version 1.99.4
-
-=head1 AUTHOR
-
-Eric Rasche <rasche.eric@yandex.ru>
-
-=head1 COPYRIGHT AND LICENSE
-
-This software is Copyright (c) 2014 by Eric Rasche.
-
-This is free software, licensed under:
-
-  The GNU General Public License, Version 3, June 2007
-
-=cut

--- a/cpt_psm_plotter/lib/CPT/Analysis/PAUSE.pm	Tue Jul 05 05:40:36 2022 +0000
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,197 +0,0 @@
-package CPT::Analysis::PAUSE;
-
-# ABSTRACT: Library for use in PAUSE analysis
-use strict;
-use warnings;
-use Moose;
-use List::Util qw(sum);
-use Statistics::Descriptive;
-
-sub max ($$) { shift; $_[ $_[0] < $_[1] ] }
-sub min ($$) { shift; $_[ $_[0] > $_[1] ] }
-
-sub derivative {
-	my ( $self, $data_ref ) = @_;
-	my @data = @{$data_ref};
-	my @new_data;
-	foreach ( my $i = 0 ; $i < scalar(@data) - 1 ; $i++ ) {
-		$new_data[ $i + 1 ] = $data[ $i + 1 ] - $data[$i];
-	}
-	return \@new_data;
-}
-
-sub find_peaks {
-	my ( $self, %data ) = @_;
-	use IPC::Run3;
-	use File::Temp qw/tempfile/;
-
-	# Store to CSV File
-	my @starts = @{ $data{data} };
-	my ( $fh0, $filename0 ) = tempfile('galaxy.pause.XXXXXXX');
-	printf $fh0 ( "%s,%s\n", 'position', 'count' );
-	for ( my $i = 0 ; $i < scalar(@starts) ; $i++ ) {
-		printf $fh0 "%d,%d\n", $i,
-		  ( defined $starts[$i] ? $starts[$i] : 0 );
-	}
-	close($fh0);
-
-	my ( $fh, $filename ) = tempfile('galaxy.pause.XXXXXXX');
-	my @cmd = (
-		'Rscript', $data{location_of_rscript_file},
-		$filename0, $filename, $data{snr}
-	);
-	my ( $in, $out, $err );
-	run3 \@cmd, \$in, \$out, \$err;
-
-	# Read in R data
-	my @values;
-	while (<$fh>) {
-		chomp;
-		push( @values, $_ );
-	}
-	close($fh);
-
-	unlink($filename0);
-	unlink($filename);
-
-	return @values;
-}
-
-sub smooth {
-	my ( $self, $data_ref ) = @_;
-	my @data = @{$data_ref};
-	my @new_data;
-	my $length = scalar @data;
-	foreach ( my $i = 0 ; $i < $length ; $i++ ) {
-		my $avg =
-		  sum( @data[ $i - 20 .. $i - 1, $i + 1 .. $i + 20 ] ) / 40;
-		$new_data[$i] = $avg;
-	}
-	return \@new_data;
-}
-
-sub histogram {
-	my ( $self, %data ) = @_;
-
-	my @coverage = @{ $data{data} };
-	my @return_coverage;
-	for ( my $i = 0 ; $i < scalar(@coverage) ; $i++ ) {
-		my $size = $coverage[$i];
-		unless ($size) { $size = 0 }
-		$return_coverage[$i] = [ $i, $size, "*" x $size ];
-	}
-	my %results = (
-		'Sheet1' => {
-			headers => [qw(Base Count Plot)],
-			data    => \@return_coverage,
-		}
-	);
-	return %results;
-}
-
-sub getCoverageDensity {
-	my ( $self, %data ) = @_;
-
-	# Load the sam file
-	my $sam = Bio::DB::Sam->new(
-		-bam       => $data{bam},
-		-fasta     => $data{genome},
-		-autoindex => 1,
-	);
-
-	# Get all alignments to our indicated FASTA file
-	my @alignments = $sam->get_features_by_location(
-		-seq_id => $data{fasta_id},
-		-start  => 1,
-		-end    => $data{fasta_length}
-	);
-
-	# Set up some variables
-	my $coverage_density_max_value = 0;
-	my ( @coverage_density, @read_starts, @read_ends );
-
-	# including some for statistics
-	my $stat_start = Statistics::Descriptive::Sparse->new();
-	my $stat_end   = Statistics::Descriptive::Sparse->new();
-
-	# Looping over alignments
-	for my $a (@alignments) {
-		my $start = $a->start;
-		my $end   = $a->end;
-
-		# Increment the number of reads starting there
-		$read_starts[$start]++;
-		$read_ends[$end]++;
-
-		# And increment the coverage density
-		foreach ( $start .. $end ) {
-			$coverage_density[$_]++;
-			if ( $coverage_density[$_] >
-				$coverage_density_max_value )
-			{
-				$coverage_density_max_value =
-				  $coverage_density[$_];
-			}
-		}
-	}
-	my @start_data_for_stats;
-	my @end_data_for_stats;
-	for ( my $i = 0 ; $i < $data{fasta_length} ; $i++ ) {
-		if ( $read_starts[$i] ) {
-			push( @start_data_for_stats, $read_starts[$i] );
-		}
-		if ( $read_ends[$i] ) {
-			push( @end_data_for_stats, $read_ends[$i] );
-		}
-	}
-	$stat_start->add_data(@start_data_for_stats);
-	$stat_end->add_data(@end_data_for_stats);
-
-	# Lots of data to return
-	use CPT::Analysis::PAUSE::ParsedSam;
-	my $psam = CPT::Analysis::PAUSE::ParsedSam->new(
-		coverage_density => \@coverage_density,
-		read_starts      => \@read_starts,
-		read_ends        => \@read_ends,
-		max              => $coverage_density_max_value,
-		stats_start_max  => $stat_start->max(),
-		stats_end_max    => $stat_end->max(),
-		stats_start_mean => $stat_start->mean(),
-		stats_end_mean   => $stat_end->mean(),
-		stats_start_standard_deviation =>
-		  $stat_start->standard_deviation(),
-		stats_end_standard_deviation => $stat_end->standard_deviation(),
-	);
-	return $psam;
-}
-
-no Moose;
-1;
-
-__END__
-
-=pod
-
-=encoding UTF-8
-
-=head1 NAME
-
-CPT::Analysis::PAUSE - Library for use in PAUSE analysis
-
-=head1 VERSION
-
-version 1.96
-
-=head1 AUTHOR
-
-Eric Rasche <rasche.eric@yandex.ru>
-
-=head1 COPYRIGHT AND LICENSE
-
-This software is Copyright (c) 2014 by Eric Rasche.
-
-This is free software, licensed under:
-
-  The GNU General Public License, Version 3, June 2007
-
-=cut