Mercurial > repos > abossers > mummer_toolsuite

--- a/MUMmer/README_mummer	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,56 +0,0 @@
-# Created/shared May 2011
-#
-# Alex Bossers
-# Central Veterinary Institute
-# Wageningen University and Research centre
-# Lelystad, The Netherlands
-#
-# Comments/improvements/bugs: Alex (dot) Bossers (at) wur (dot) nl
-
-
-# WHAT IT DOES
-The MUMmer suite is a set of very basic wrappers for the MUMmer genome comparison tools. Most common operations should be possible
-by using these wrappers. MUMmer works fast on smaller (bacterial) genomes but can also cope with eukaryotic genomes.
-
-In addition to the original MUMmer tools it also contains an additional conversion script to convert MUMmer comparison files,
-the so-called coords files into a readible format for Artemis Comparison Tool (ACT; Sanger UK).
-
-
-# REQUIREMENTS
-- Perl
-- Galaxy :)
-- MUMmer newer than version 3.20;
-      even though older versions might work as well.
-      Get your MUMmer here: http://mummer.sourceforge.net/
-      Make sure MUMmer is in your PATH and/or update the tool xml configs and wrappers for the full MUMmer path
-      if it is different from /opt/MUMmer/MUMmer.
-- ACT can be run locally or via Webstart if you want to visualise genome comparisons in detail: http://www.sanger.ac.uk/resources/software/act
-- GNUplot is a requirement for the MUMmerplot part (see MUMmer installation documentation)
-
-
-# SETUP
-Just unpack the tool xml and perl script somewhere appropriate and adapt the MUMmer installation part if different from above. Plug the tool in the tool_config.xml
-of your galaxy instance and refresh the tools or restart the galaxy server.
-
-
-# TESTING
-You can test the code by running Nucmer on the test data and visualise the results in MUMmerplot.
-It should return a MUMmerplot identical to the image provided. For reference I also included the corresponding log file.
-
-
-# LICENSE
-Copyright (c) 2011 Central Veterinary Institute of Wageningen UR, Lelystad, The Netherlands.
-MUMmer is copyright by its respective owner. See their licensing details.
-
-Our wrappers/programs are free software; you can redistribute it and/or modify
-it under the terms of the GNU General Public License as published by
-the Free Software Foundation; either version 3 of the License, or
-(at your option) any later version.
-
-When distributing the tools please include this original reference.
-
-Use this tool at your own risk. Even though we tried to build tools and wrappers that free of errors,
-check your output since it might be erroneous. We will not be relyable to any failure this may have caused.
-
-If you like these scripts, please acknowledge our work.
-
--- a/MUMmer/mummer_clustering.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,237 +0,0 @@
-<tool id="mummer_clustering" name="MUMmer Clustering" version="0.9.alx" force_history_refresh="True">
-  <description>: order sequence matches in clusters</description>
-  <command>
-	<!-- update this path to the installed location -->
-	/opt/MUMmer/MUMmer/$tool.cmd
-		#if $tool.cmd=="gaps":
-			$in_reference
-			#if $tool.gaps_r=="yes":
-				-r
-			#end if
-		#end if
-		#if $tool.cmd=="mgaps":
-			#if $tool.cmd_C=="yes":
-				-C
-			#end if
-			-d $tool.cmd_d
-			#if $tool.cmd_e=="yes":
-				-e
-			#end if
-			-f $tool.cmd_f
-			-l $tool.cmd_l
-			-s $tool.cmd_s
-		#end if
-		&lt; $tool.in_match_list
-		&gt; $out_tool
-
-  </command>
-	<inputs>
-	  <conditional name="tool">
-		<param name="cmd" type="select" label="MUMmer maximal matching" help="Algorithms are run with default parameters (none). For specific args see help below" >
-			<option value="gaps" selected="true">gaps</option>
-			<option value="mgaps">mgaps</option>
-		</param>
-		<when value="gaps">
-			<param name="in_reference" type="data" format="fasta" label="Reference FastA file" />
-			<param name="gaps_r" type="select" label="Use reversed [-r]" >
-				<option value="no" selected="true">No</option>
-				<option value="yes">Yes</option>
-			</param>
-			<param name="in_match_list" type="data" format="text" label="MUMmer match list" help="See help for more details" />
-		</when>
-		<when value="mgaps">
-			<param name="in_match_list" type="data" format="text" label="MUMmer match list" help="See help for more details" />
-			<param name="cmd_C" type="select" label="Check input header labels have reversed keyword [-C]" >
-				<option value="no" selected="true">No</option>
-				<option value="yes">Yes</option>
-			</param>
-			<param name="cmd_d" type="integer" size="5" value="5" label="Max fixed diagonal difference [-d]" />
-			<param name="cmd_e" type="select" label="Use extent of cluster [-e]" >
-				<option value="no" selected="true">No</option>
-				<option value="yes">Yes</option>
-			</param>
-			<param name="cmd_f" type="float" size="5" value="0.05" label="Max fraction separation for diagonal difference [-f]" />
-			<param name="cmd_l" type="integer" size="5" value="200" label="Min cluster length [-l]" />
-			<param name="cmd_s" type="integer" size="5" value="1000" label="Max separation adjecent matches in cluster [-s]" />
-		</when>
-	  </conditional>
-	</inputs>
-	<outputs>
-		<data name="out_tool" format="text" label="Clustering output" />
-	</outputs>
-	<requirements>
-	  <requirement type="binary">gaps</requirement>
-	  <requirement type="binary">mgaps</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-
-
-**Reference**
-=============
-
-- **MUMmer clustering Galaxy tool wrapper:** Alex Bossers, CVI of Wageningen UR, The Netherlands.
-
-- **MUMmer suite v3.22:** http://mummer.sourceforge.net
-
-- **MUMmer tutorials:** http://mummer.sourceforge.net/examples/
-
-If you found these tools/wrappers usefull in your research, please acknowledge our work. If you improve
-or modify the wrappers please add instead of substitute yourself into the acknowlegement section :)
-
-
-**MUMmer Clustering**
-=====================
-
-MUMmer's clustering algorithms attempt to order small individual matches into larger match clusters
-in order to make the output of mummer more intelligible. A dot plot makes it easy to spot alignment
-regions from a match list, however when examining the data without graphic aids, it is very difficult
-to draw any reasonable conclusions from the simple flat file list of matches. Clustering the matches
-together into larger groups of neighboring matches makes this process much easier by ordering the
-data and removing spurious matches.
-
-
-Gaps
-----
-
-*gaps* is the primary clustering algorithm for run-mummer1, and although classified as a "clustering"
-step, gaps is more of a sorting routine. It implements the LIS (longest increasing subset) algorithm
-to extract the longest consistent set of matches between two sequences, and generates a single
-cluster that represents the best "straight-line" arrangement of matches between the sequences. By
-straight-line, we mean no rearrangements or inversions, just a simple path of agreeing matches
-between the two sequences. This limits the usability of this program to the alignment of genomes
-that are very similar and with no large scale mutations. *gaps* is best suited for the comparison of
-near identical sequences with the goal of finding minor mutations like SNPs and small indels.
-
-Input can be filtered mummer output. The strange syntax is a result of a legacy issue described in
-the Known problems (manual) section, and requires the header be stripped from the mummer output. In
-addition, gaps is only designed to handle a single reference and a single query sequence, thus the
-preceding mummer run must also follow this constraint. The -r is optional and designates the incoming
-matches as reverse complement matches which must reference the reverse complement of the sequence,
-therefore forcing mummer to be run without the -c option.
-
-Reference: http://mummer.sourceforge.net/manual/#gaps
-
-**Output:**
-::
-
- > /home/aphillip/data/GHP.1con  Consistent matches
-      183       17     22    none      -      -
-      238       72    108    none     33     33
-      347      181     92    none      1      1
-      458      292     50    none     19     19
-      705      539     44    none      1      1
-      750      584     38    none      1      1
-      807      641     23     -16      0      4
- (output continues ...)
- > Wrap around
-   334398   329917     47    none      -    225
-   334446   329965     62    none      1      1
-   334539   330058     20    none     31     31
-   334560   330079     92    none      1      1
-   334653   330172     77    none      1      1
-   334740   330259     41    none     10     10
- (output continues ...)
- > /home/aphillip/data/GHP.1con  Other matches
-  1317231     4891     21    none      -      -
-  1317275     4927     21    none      -      -
-  1317804     5399     25    none    508    451
-   947580     5436     36    none      -      -
-    23406     5518     34    none      -      -
-   333079     6592     32    none      -      -
- (output continues ...)
-
-Where the first line is the location of the reference file, and the first three columns are the same
-as the three column match format described in the mummer section. The final three columns are the
-overlap between this match and the previous match, the gap between the start of this match and the
-end of the previous match in the reference, and the gap between the start of this match and the end
-of the previous match in the query respectively.
-
-
-mgaps
------
-
-*mgaps* was introduced into the MUMmer pipeline in an effort to better handle large-scale
-rearrangements and duplications. Unlike gaps, mgaps is a full clustering algorithm that is capable
-of generating multiple groups of consistently ordered matches. Clustering is controlled by a set of
-command-line parameters that adjust the minimum cluster size, maximum gap between matches, etc. Only
-matches that were included in clusters will appear in the output, so by adjusting the command-line
-parameters it is possible to filter out many of the spurious matches, thus leaving only the larger
-areas of conservation between the input sequences. The major advantage of mgaps is its ability to
-identify these "islands" of conservation. This frees the user from the single LIS restraints of the
-gaps program and allows for the identification of large-scale rearrangements, duplications, gene
-families and so on.
-
-Gaps can fail to identify clusters because they were not consistent with the LIS. However, by using
-mgaps, all regions of conservation can now been identified. The only fallback being the increased
-complexity of the output, where you once had only one cluster for the whole comparison, you usually
-now get more. Because of this, it can sometimes be difficult separating the repetitive clusters from
-"correct" clusters, *making mgaps more suited for global alignments instead of localized error detection*.
-
-Input can be raw mummer output. *mgaps* is only designed to handle a single reference and one or
-more query sequences, thus the preceding mummer run must also follow this constraint. Please refer
-to the run-mummer3 script (see online manual) for an example of how to use this program in an
-alignment pipeline. Note that in order to cluster reverse complement matches, the reverse complement
-matches must reference the reverse complement strand of the query sequence, therefore forcing mummer
-to be run without the -c option. A rewrite of this algorithm to handle multiple reference sequences
-and a better coordinate system (forward coordinates for reverse complement matches) is doubtful but
-may eventually appear.
-
-The -d option can be interpreted as the number of insertions allowed between two matches in the same
-cluster, while the -f option is a fraction equal to (diagonal difference / match separation) where
-a higher value will increase the indel tolerance. Minimum cluster length is the sum of the contained
-matches unless the -e option is used. The best way to get a feel for what each parameter controls
-is to cluster the same data set numerous times with different values and observe the resulting
-differences. It can also be helpful to set these parameters to the size of the element you wish to
-capture, i.e. set the minimum cluster size to say the smallest exon you expect and set the max gap
-to the smallest intron you expect to obtain clusters that could represent single exons (depending
-of course of the similarity of the two sequences).
-
-Reference: http://mummer.sourceforge.net/manual/#mgaps
-
-**Output format**
-
-Output of *mgaps* shares much in common with the output of mummer and gaps, with a slightly different
-header formatting than gaps to allow for multiple query sequences and multiple clusters. The output
-of mgaps run on both forward and reverse complement matches is as follows:
-::
-
- > ID41
- > ID41 Reverse
-  5177399        1    232    none      -      -
-  5177632      234   6794    none      1      1
-  5184433     7035     24    none      7      7
-  5184468     7069     23    none     11     10
- > ID42
-    10181       43   1521    none      -      -
- > ID42 Reverse
-  4654536       17     36    none      -      -
-  4654578       57    298    none      6      4
-  4654877      356    226    none      1      1
- #
-  4655139      845     28    none      -      -
-  4655178      884    694    none     11     11
-  4655873     1579     20    none      1      1
- #
-  4850044       17   1492    none      -      -
-  4851537     1510    711    none      1      1
-  4852249     2222     42    none      1      1
- (output continues ...)
-
-
-Headers containing the ID for each query sequence are listed after the '>' characters, and a
-following Reverse keyword identifies the reverse matches for that query sequence. Individual clusters
-for each sequence are separated by a '#' character, and the six columns are exactly the same as the
-gaps output (see the gaps section for more details).
-
-
-|
-|
-
-	</help>
-</tool>
-
--- a/MUMmer/mummer_maxmatch.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,170 +0,0 @@
-<tool id="mummer_maxmatch" name="MUMmer MaxMatch" version="0.9.alx" force_history_refresh="True">
-  <description>: Maximal exact sequence matching</description>
-  <command>
-	<!-- update this path to the installed location -->
-	/opt/MUMmer/MUMmer/$tool.cmd
-		#if $tool.cmd=="mummer":
-			$tool.cmd_extra
-			$tool.mum_ref_in
-			$tool.mum_q_in
-		#end if
-		#if $tool.cmd=="repeat-match":
-			-n $tool.rm_n
-			#if $tool.rm_E=="yes":
-				-E
-			#end if
-			$tool.cmd_extra
-			$tool.in_seq
-		#end if
-		#if $tool.cmd=="exact-tandems":
-			$tool.in_seq
-			$tool.et_minl
-		#end if
-		<!-- unfortunate somehow error state gets set also on succesfull jobs. Pipe io stderr to dev/null -->
-		2&gt;&amp;-
-		> $out_tool
-
-  </command>
-	<inputs>
-	  <conditional name="tool">
-		<param name="cmd" type="select" value="mummer" label="MUMmer maximal matching" help="Algorithms are run with default parameters (none). For specific args see help below" >
-			<option value="mummer">mummer</option>
-			<option value="repeat-match">repeat-match</option>
-			<option value="exact-tandems">exact-tandems</option>
-		</param>
-		<when value="mummer">
-			<param name="mum_ref_in" type="data" format="fasta" label="Reference FastA file" />
-			<param name="mum_q_in" type="data" format="fasta" label="Query (multi) FastA sequence" />
-			<param name="cmd_extra" type="text" size="40" value="" label="Extra cmd line options" help="See specific cmd line options below for each tool" />
-		</when>
-		<when value="repeat-match">
-			<param name="in_seq" type="data" format="fasta" label="FastA sequence file" />
-			<param name="rm_n" type="text" size="5" value="20" label="Minimum exact match length [-n]" />
-			<param name="rm_E" type="select" value="no" label="Use exhaustive (slow) search to find matches [-E]" >
-				<option value="no">No</option>
-				<option value="yes">Yes</option>
-			</param>
-			<param name="cmd_extra" type="text" size="40" value="" label="Extra cmd line options" help="-n and -E are configured above. More specific cmd line options in help below." />
-		</when>
-		<when value="exact-tandems">
-			<param name="in_seq" type="data" format="fasta" label="FastA sequence file" />
-			<param name="et_minl" type="text" size="5" value="20" label="Minimum length" />
-		</when>
-	  </conditional>
-	</inputs>
-	<outputs>
-		<data name="out_tool" format="text" label="Max exact match output" />
-	</outputs>
-	<requirements>
-	  <requirement type="binary">mummer</requirement>
-	  <requirement type="binary">repeat-match</requirement>
-	  <requirement type="binary">exact-tandems</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-
-
-**Reference**
-=============
-
-- **MUMmer MaxExactMatch Galaxy tool wrapper:** Alex Bossers, CVI of Wageningen UR, The Netherlands.
-
-- **MUMmer suite v3.22:** http://mummer.sourceforge.net
-
-- **MUMmer tutorials:** http://mummer.sourceforge.net/examples/
-
-Please do not use any of the command line options that modify prefixes or file names. As obvious
-they are quite useless within galaxy and are likely to fail the routine!
-
-If you found these tools/wrappers usefull in your research, please acknowledge our work. If you improve
-or modify the wrappers please add instead of substitute yourself into the acknowlegement section :)
-
-
-
-**MUMmer Maximal exact matching**
-=================================
-
-The heart of the MUMmer package is its suffix tree based maximal matching routines. These can be
-used for repeat detection within a single sequence as is done by *repeat-match* and *exact-tandems*,
-or can be used for the alignment of two or more sequences as is done by *mummer*.
-
-Mummer
-------
-
-mummer is a suffix tree algorithm designed to find maximal exact matches of some minimum length
-between two input sequences. by default mummer will only find maximal matches that are unique in
-the entire set of reference sequences. The match lists produced by mummer can be used alone to
-generate alignment dot plots, or can be passed on to the clustering algorithms for the identification
-of longer non-exact regions of conservation. These match lists have great versatility because they
-contain huge amounts of information and can be passed forward to other interpretation programs for
-clustering, analysis, searching, etc.
-
-
-Repeat-match
-------------
-
-repeat-match is a suffix tree algorithm designed to find maximal exact repeats within a single input
-sequence. It uses a similar algorithm to mummer, but altered slightly to find maximal exact matches
-within a single sequence.
-
-Output formatting varies depending on the command line parameters and the output can be quite large.
-The standard output format that results from running repeat-match with default parameters is as follows:
-::
-
- Long Exact Matches:
-    Start1     Start2    Length
-   4919485    4919506r       22
-
-The three columns are the first position of the repeat, the second position of the repeat, and the
-length of the repeat respectively. Reverse complement repeat positions are denoted by an 'r'
-following the Start2 position, and are relative to the forward strand of the sequence.
-
-
-Exact-tandems
--------------
-
-exact-tandems is a wrapper script for the repeat-match program. It provides a list of exact tandem
-repeats within a single input sequence. As with repeat-match the sequence file should contain only
-one sequence in FastA format, however if multiple sequences exist the first one will be used. The
-sequence may contain any set of upper and lowercase characters, thus DNA and protein sequence are
-both allowed and matching is case insensitive. The minimum match length parameter should be a
-positive integer, this value will be passed to the repeat-match program via the -n option.
-
-The output format of exact-tandems is as follows:
-::
-
- Finding matches
- Tandem repeats
-    Start   Extent  UnitLen     Copies
-   416173      150       45        3.3
-
-The four columns are the first position of the tandem, the extent of the repeat region, the length
-of each tandem repeat unit, and the number of repeat units respectively.
-
-
-
-**Manuals and CMD line options (specific for each tool!):**
-===========================================================
-
-**Mummer**
-
-http://mummer.sourceforge.net/manual/#mummer
-
-**Repeat-match**
-
-http://mummer.sourceforge.net/manual/#repeat
-
-**exact-tandems**
-
-http://mummer.sourceforge.net/manual/#exact
-
-|
-|
-
-	</help>
-</tool>
-
--- a/MUMmer/mummer_tool.sh	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,107 +0,0 @@
-#!/bin/bash
-## use #!/bin/bash -x for debugging
-
-## Galaxy wrapper for MUMmer (nucmer/promer)
-## Alex Bossers, CVI of Wageningen UR, NL
-## alex_dot_bossers_at_wur_dot_nl
-##
-## Sep 2010
-##
-## Wrapper runs MUMmer nucmer/promer and additional args
-## Calculates the comparison scores (delta and optional coords file)
-## Generates the optional STATIC comparison mummerplot to png (from delta file)
-##
-## finally the script renames (optional) output files to outfiles expected by Galaxy
-##
-##
-## INPUT args:
-## nucmer_tool.sh $input_ref $input_query $out_delta $out_coords $out_png $logfile
-##                    @0          @1          @2          @3        @4       @5
-##                $algorithm $keep_delta $make_coords $keep_log $make_image $cmd_extra
-##                     @6        @7           @8          @9        @10         @11
-##
-
-# path to where mummer suite is installed
-# adjust this for your machine
-# this is the only hard coded path in the scripts
-mum_path="/opt/MUMmer/MUMmer"
-
-# since we have more than 9 arguments we need to shift the sections or use own array
-args=("$@")
-# to keep things readible assign vars
-input_ref="${args[0]}"
-input_query="${args[1]}"
-out_delta="${args[2]}"
-out_coords="${args[3]}"
-out_png="${args[4]}"
-logfile="${args[5]}"
-algorithm="${args[6]}"
-keep_delta="${args[7]}"
-make_coords="${args[8]}"
-keep_log="${args[9]}"
-make_image="${args[10]}"
-cmd_extra="${args[11]}"
-
-# enable/disable the STDOUT log file
-if [ "$keep_log" == "yes" ]; then
-	logfile_c="2>$logfile"
-	logfile_a="2>>$logfile"
-else
-	#dump to dev/null
-	logfile_c="2>&-"
-	logfile_a="2>&-"
-fi
-
-# extra mummer cmd line options
-
-## generate coords file on the fly?
-if [ "$make_coords" == "yes" ]; then
-	options=" --coords"
-fi
-## extra cmd line args to be concatenated in options? We need to prevent extra spaces!
-if [ "$cmd_extra" != "" ]; then
-	if [ "$options" == "" ]; then
-		options=" $cmd_extra"
-	else
-		options="$options $cmd_extra"
-	fi
-fi
-
-# run nucmer/promer
-eval "$mum_path/$algorithm$options $input_ref $input_query $logfile_c"
-
-## generate large png if option make_image = yes
-## suppress error from mummerplot since some is deprecated but not a real error
-## error can be easily avoided by modifying the source of mummerplot... just in case
-## however we need to check if a valid png was generated. This is not the case is alignment is none
-## 1 is stderr and 2 stdout. redirect to dev/null
-
-if [ "${make_image}" == "yes" ]; then
-	eval "$mum_path/mummerplot --large --png out.delta 1>&- $logfile_a"
-	if [ -f "out.png" ]; then
-		mv out.png $out_png
-		#cleanup temp gnuplot file
-		rm out.gp
-	else
-		echo "not exist the req png file!"
-	fi
-
-	## clean up remaining files
-	rm out.fplot
-	rm out.rplot
-
-fi
-
-# keep/rename or delete delta file
-if [ "$keep_delta" == "yes" ]; then
-	mv out.delta "$out_delta"
-else
-	rm out.delta
-fi
-
-# keep/rename coords file if it was created
-if [ "$make_coords" == "yes" ]; then
-	mv out.coords "$out_coords"
-fi
-
-# end script
--- a/MUMmer/mummer_tool.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,104 +0,0 @@
-<tool id="mummer_tool" name="MUMmer" version="0.4.alx" force_history_refresh="True">
-  <description>: Compare genomes (Nucmer or Promer)</description>
-  <command interpreter="bash">
-  	mummer_tool.sh
-		$input_ref $input_query
-		$out_delta $out_coords $out_png $out_log
-		$algorithm
-		$keep_delta $make_coords $keep_log $make_image
-		$cmd_extra
-  </command>
-	<inputs>
-		<param name="algorithm" type="select" format="text" value="nucmer" label="Algorithm" help="Nucmer dna or Promer protein (FASTA: protein. Dna is six frame translated)">
-			<option value="nucmer">Nucmer DNA</option>
-			<option value="promer">Promer</option>
-		</param>
-		<param name="input_ref" type="data" format="fasta" label="Reference sequence" />
-		<param name="input_query" type="data" format="fasta" label="Sequence query file"/>
-		<param name="make_image" type="select" format="text" value="yes" label="Generate MUMmerplot" help="MUMmerplot will be run with default settings and --large --png as fixed image.">
-			<option value="yes">Yes</option>
-			<option value="no">No</option>
-		</param>
-		<param name="keep_delta" type="select" format="text" value="no" label="Keep delta file" help="i.e. for further processing">
-			<option value="no">No</option>
-			<option value="yes">Yes</option>
-		</param>
-		<param name="make_coords" type="select" format="text" value="yes" label="Make coords file" help="Uses the -r argument to sort lines by reference.">
-			<option value="no">No</option>
-			<option value="yes">Yes</option>
-		</param>
-		<param name="keep_log" type="select" format="text" value="no" label="Keep console log file" help="i.e. for debugging">
-			<option value="no">No</option>
-			<option value="yes">Yes</option>
-		</param>
-		<param name="cmd_extra" type="text" size="40" value="" label="Extra cmd line options" help="the --coords is run by default" />
-	</inputs>
-	<outputs>
-		<data name="out_coords" format="tabular" label="${algorithm.value_label} coords">
-			<filter>make_coords=="yes"</filter>
-		</data>
-		<data name="out_delta" format="tabular" label="${algorithm.value_label} delta">
-			<filter>keep_delta=="yes"</filter>
-		</data>
-		<data name="out_png" format="png" label="${algorithm.value_label} mummerplot">
-			<filter>make_image=="yes"</filter>
-		</data>
-		<data name="out_log" format="tabular" label="Console log file">
-			<filter>keep_log=="yes"</filter>
-		</data>
-	</outputs>
-	<requirements>
-	  <requirement type="binary">nucmer</requirement>
-	  <requirement type="binary">promer</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-
-
-**Reference**
--------------
-
-- **Nucmer Galaxy tool wrapper: Alex Bossers, CVI of Wageningen UR, The Netherlands.**
-
-- **Nucmer or Promer of MUMmer suite:** v3.22 http://mummer.sourceforge.net/manual/
-
-- **MUMmer tutorials:** http://mummer.sourceforge.net/examples/
-
-
-If you found these tools/wrappers useful in your research, please acknowledge our work. If you improve
-or modify the wrappers please add instead of substitute yourself into the acknowlegement section :)
-
-
-**Command line arguments**
---------------------------
-
---mum  Use anchor matches that are unique in both the reference and query
---mumreference  Use anchor matches that are unique in the reference but not necessarily unique in the query (default behavior)
---maxmatch  Use all anchor matches regardless of their uniqueness
---breaklen  Distance an alignment extension will attempt to extend poor scoring regions before giving up (default 200)
---mincluster  Minimum cluster length (default 65)
---delta  Toggle the creation of the delta file. Setting --nodelta prevents the alignment extension step and only outputs the match clusters (default --delta)
---depend  Print the dependency information and exit
---diagfactor  Maximum diagonal difference factor for clustering, i.e. diagonal difference / match separation (default 0.12)
---extend  Toggle the outward extension of alignments from their anchoring clusters. Setting --noextend will prevent alignment extensions but still align the DNA between clustered matches and create the .delta file (default --extend)
---forward  Align only the forward strands of each sequence
---maxgap  Maximum gap between two adjacent matches in a cluster (default 90)
---help  Print the help information and exit
---minmatch  Minimum length of an maximal exact match (default 20)
---optimize  Toggle alignment score optimization. Setting --nooptimize will prevent alignment score optimization and result in sometimes longer, but lower scoring alignments (default --optimize)
---reverse  Align only the reverse strand of the query sequence to the forward strand of the reference
---simplify  Simplify alignments by removing shadowed clusters. Turn this option off (--nosimplify) if aligning a sequence to itself to look for repeats (default --simplify)
---version  Print the version information and exit
---coords  **Automatically ON in galaxy wrapper!** It generates the .coords file using the 'show-coords' program with the -r option.
---prefix  **Do NOT use in Galaxy wrapper!** Set the output file prefix (default out)
-
-|
-|
-
-	</help>
-</tool>
-
--- a/MUMmer/mummer_utilities_tool.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,187 +0,0 @@
-<tool id="mummer_utilities_tool" name="MUMmer utilities" version="0.9.alx" force_history_refresh="True">
-  <description>: Show and filter on sequence delta file</description>
-  <command>
-  	<!-- update this path to the installed location -->
-	/opt/MUMmer/MUMmer/$tool.cmd
-		$cmd_extra
-		$input_delta
-		#if $tool.cmd=="show-aligns":
-			$tool.aligns1
-			$tool.aligns2
-		#end if
-		> $out_tool
-  </command>
-	<inputs>
-	  <conditional name="tool">
-		<param name="cmd" type="select" value="show-snps" label="MUMmer utility" help="Utilities are run with default parameters (none). For utility specific args see help below" >
-			<option value="show-snps">show SNPs</option>
-			<option value="show-tiling">show tiling</option>
-			<option value="show-diff">show diff</option>
-			<option value="show-coords">show coords</option>
-			<option value="show-aligns">show aligns</option>
-			<option value="delta-filter">delta filter</option>
-		</param>
-		<when value="show-aligns">
-			<param name="aligns1" type="text" size="40" value="" label="IdR" help="the FastA header tag of the desired reference sequence" />
-			<param name="aligns2" type="text" size="40" value="" label="IdQ" help="the FastA header tag of the desired query sequence" />
-		</when>
-		<when value="show-snps" />
-		<when value="show-tiling" />
-		<when value="show-coords" />
-		<when value="show-diff" />
-		<when value="delta-filter" />
- 	  </conditional>
-		<param name="input_delta" type="data" format="tabular" label="MUMmer delta file" />
-		<param name="cmd_extra" type="text" size="40" value="" label="Extra cmd line options" help="see specific cmd line options below for each tool" />
-	</inputs>
-	<outputs>
-		<data name="out_tool" format="text" />
-	</outputs>
-	<requirements>
-	  <requirement type="binary">mummer-tiling</requirement>
-	  <requirement type="binary">mummer-snps</requirement>
-	  <requirement type="binary">mummer-diff</requirement>
-	  <requirement type="binary">mummer-coords</requirement>
-	  <requirement type="binary">mummer-aligns</requirement>
-	  <requirement type="binary">delta-filter</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-
-
-**Reference**
-=============
-
-- **MUMmer_utilities Galaxy tool wrapper:** Alex Bossers, CVI of Wageningen UR, The Netherlands.
-
-- **MUMmer utilities running on MUMmer delta file:** http://mummer.sourceforge.net/manual
-
-- **MUMmer tutorials:** http://mummer.sourceforge.net/examples/
-
-If you found these tools/wrappers usefull in your research, please acknowledge our work. If you improve
-or modify the wrappers please add instead of substitute yourself into the acknowlegement section :)
-
-
-**MUMmer Utilities**
-====================
-
-All tools are using the MUMmer generated DELTA file! Additional arguments are only required for show-aligns.
-
-Show-coords
------------
-
-show-coords parses the delta alignment output of NUCmer and PROmer, and displays summary
-information such as position, percent identity and so on, of each alignment. It is the most
-commonly used tool for analyzing the delta files. *Usually the -r is used to sort lines by reference*
-
-
-Show-tiling
------------
-
-show-tiling attempts to construct a tiling path out of the query contigs as mapped to the reference
-sequences. Given the delta alignment information of a few long reference sequences and many small
-query contigs, show-tiling will determine the best mapped location of each query contig. Note that
-each contig may only be tiled once, so repetitive regions may cause this program some difficulty.
-This program is useful for aiding in the scaffolding and closure of an unfinished set of contigs,
-if a suitable, high similarity reference genome is available. Or, if using PROmer, show-tiling will
-help in the identification of syntenic regions and their contig's mapping to the references.
-
-This program is not suitable for "many vs. many" assembly comparisons, however a new tool based on
-the concepts of show-tiling should be available in the near future that will facilitate the mapping
-of assembly contigs.
-
-
-Show-snps
----------
-
-show-snps is a utility program for reporting polymorphisms contained in a delta encoded alignment
-file output by NUCmer or PROmer. It catalogs all of the single nucleotide polymorphisms (SNPs) and
-insertions/deletions within the delta file alignments. Polymorphisms are reported one per line, in
-a delimited fashion similar to show-coords. Pairing this program with the appropriate MUMmer tools
-can create an easy to use SNP pipeline for the rapid identification of putative SNPs between any
-two sequence sets, as demonstrated in the manual SNP detection section.
-
-
-Show-diff
----------
-
-Outputs a list of structural differences for each sequence in
-the reference and query, sorted by position. For a reference
-sequence R, and its matching query sequence Q, differences are
-categorized as GAP (gap between two mutually consistent alignments),
-DUP (inserted duplication), BRK (other inserted sequence), JMP
-(rearrangement), INV (rearrangement with inversion), SEQ
-(rearrangement with another sequence). The first five columns of
-the output are seq ID, feature type, feature start, feature end,
-and feature length. Additional columns are added depending on the
-feature type. Negative feature lengths indicate overlapping adjacent
-alignment blocks.
-::
-
-  IDR GAP gap-start gap-end gap-length-R gap-length-Q gap-diff
-  IDR DUP dup-start dup-end dup-length
-  IDR BRK gap-start gap-end gap-length
-  IDR JMP gap-start gap-end gap-length
-  IDR INV gap-start gap-end gap-length
-  IDR SEQ gap-start gap-end gap-length prev-sequence next-sequence
-
-Positions always reference the sequence with the given ID. The
-sum of the fifth column (ignoring negative values) is the total
-amount of inserted sequence. Summing the fifth column after removing
-DUP features is total unique inserted sequence. Note that unaligned
-sequence are not counted, and could represent additional "unique"
-sequences. See documentation for tips on how to interpret these
-alignment break features.
-
-
-Show-aligns
------------
-
-show-aligns parses the delta encoded alignment output of NUCmer and PROmer, and displays
-the pair-wise alignments from the two sequences specified on the command line. It is handy
-for identifying the exact location of errors and looking for SNPs between two sequences.
-
-
-Delta-filter
-------------
-
-delta-filter is a utility program for the manipulation of the delta encoded alignment files output
-by the NUCmer and PROmer pipelines. It takes a delta file as input and filters the information based
-on the various command line switches, outputting only the desired alignments to stdout. Options to filter by
-alignment length, identity, uniqueness and consistency are provided. Certain combinations of these
-options can greatly reduce the number of unwanted alignments in the delta file, thus making the output
-of programs such as show-coords more comprehendible.
-
-
-
-**CMD line options (specific for each tool!):**
-===============================================
-
-**Show-coords**
-
-http://mummer.sourceforge.net/manual/#coords
-
-**Show-tiling**
-
-http://mummer.sourceforge.net/manual/#tiling
-
-**Show-snps**
-
-http://mummer.sourceforge.net/manual/#snps
-
-**Show-aligns**
-
-http://mummer.sourceforge.net/manual/#aligns
-
-**Delta-filter**
-
-http://mummer.sourceforge.net/manual/#filter
-
-
-	</help>
-</tool>
-
--- a/MUMmer/mummerplot_tool.sh	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,45 +0,0 @@
-#!/bin/bash
-
-## simple bash to generate mummerplot of MATCH file
-##
-## Galaxy wrapper by Alex Bossers, CVI of Wageningen UR, Lelystad, NL
-## alex_dot_bossers_at_wur_dot_nl
-##
-##
-## needs a rename of the fixed name to something recognised by galaxy
-## needs cleanout of temp files
-##
-## call is mummerplot $format  $in_match $out_file $cmd_extra
-##             $0        $1         $2       $3       $4
-##
-## since mummerplot uses some deprecated syntax which can be fixed in the source
-## we redirect STDERR to dev/null to circumvent errorstatus in galaxy
-## io redirects 0=stdin 1=stdout 2=stderr to dev/null (or &-)
-
-# path to where mummer suite is installed
-# adjust this for your machine
-# this is the only hard coded path in the scripts
-mum_path="/opt/MUMmer/MUMmer"
-
-# some default options to generate a LARGE fixed PNG/POSTSCRIPT image and not an interactive one.
-
-if [ "$1" = "png" ]; then
-	extension="png"
-else
-	extension="ps"
-fi
-
-eval "$mum_path/mummerplot --large --$1 $2 1>&- 2>&-"
-
-if [ -f "out.$extension" ]; then
-	#conditional move to something known by galaxy
-	mv out.$extension $3
-	#remove gnuplot file
-	rm out.gp
-fi
-
-## clean up
-rm out.fplot
-rm out.rplot
-
-#end script
--- a/MUMmer/mummerplot_tool.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,111 +0,0 @@
-<tool id="mummerplot_tool" name="MUMmer plot" version="1.0.1" force_history_refresh="true">
-  <description>: Generate MUMmerplots from MUMmer match file</description>
-  <command interpreter="bash">
-  	mummerplot_tool.sh
-		#if $img_format=="png"
-			png $input_match $out_png
-		#else
-			postscript $input_match $out_postscript
-		#end if
-		$cmd_extra
-  </command>
-	<inputs>
-		<param name="input_match" type="data" format="tabular" label="MUMmer match (delta or tiling) file" />
-		<param name="img_format" type="select" label="Output format" >
-			<option value="png" selected="true">PNG image</option>
-			<option value="postscript">Postscript</option>
-		</param>
-		<param name="cmd_extra" type="text" size="40" value="" label="Extra cmd line options" help="See cmd line options below" />
-	</inputs>
-	<outputs>
-		<data name="out_png" format="png" label="MUMmerplot png">
-			<filter>img_format=="png"</filter>
-		</data>
-		<data name="out_postscript" format="ps" label="MUMmerplot ps">
-			<filter>img_format=="postscript"</filter>
-		</data>
-	</outputs>
-	<requirements>
-	  <requirement type="binary">mummerplot</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-
-
-**Reference**
-=============
-
-- **MUMmerplot Galaxy tool wrapper: Alex Bossers, CVI of Wageningen UR, The Netherlands**
-
-- **MUMmerplot running on MUMmer-match file:** http://mummer.sourceforge.net/manual#mummerplot
-
-- **MUMmer tutorials:** http://mummer.sourceforge.net/examples/
-
-If you found these tools/wrappers usefull in your research, please acknowledge our work. If you improve
-or modify the wrappers please add instead of substitute yourself into the acknowlegement section :)
-
-
-**MUMmerplot**
-==============
-
-| This plotting tool requires a MUMmer match file (either the delta file or the tiling result file)!
-| MUMmerplot requires gnuplot (www.gnuplot.info) to be installed.
-|
-| **The plotting has by default set the arguments --large and --png/--postscript to generate a fixed image instead of an interactive view!** Optional cmd line arguments can be used.
-|
-
-
-
-Mummerplot is a script utility that takes output from *MUMmer, nucmer or promer* as DELTA file, or the
-*show-tiling* result file, and converts it to a format suitable for plotting with gnuplot. The primary
-plot type is an alignment dotplot where a sequence is laid out on each axis and a point is plotted at
-every position where the two sequences show similarity. As an extension to this plot style, mummerplot
-is also able to offset multiple 1-vs-1 dotplots to form a multiplot where multiple sequences can be
-laid out on each axis. This plot style is especially handy for browsing an alignment of two contig
-sets. Identity plots are also possible by coloring each data point with a color gradient representing
-identity, or by collapsing the y-axis data onto a single line and then vertically offsetting the
-data points by their identities. In addition to producing the plot data, mummerplot also generates a
-gnuplot script that will be evaluated in order to generate the graph.
-
-
-The *match file* can either be a three column match list from mummer (either 3 or 4 column format),
-the delta file from nucmer or promer, or the default output from show-tiling. mummerplot will
-automatically detect the type of input file it is given, regardless of its file extension, or it
-will fail if the input file is of an unrecognized type.
-
-
-
-Optional command line arguments
--------------------------------
-
---breaklen  Highlight alignments with a breakpoint further than the given distance from the nearest sequence end
---nocolor  Color plot lines with a percent similarity gradient or turn off all color (default color by match direction)
---coverage  Generate a reference coverage plot, also known as a percent identity plot (default behavior for show-tiling input)
---depend  Print dependency information and exit
---filter  Only display alignments which represent the "best" one-to-one mapping of reference and query subsequences (requires delta formatted input)
---help  Print help information and exit
---layout  Layout a multiplot by ordering and orienting sequences such that the largest hits cluster near the main diagonal (requires delta formatted input)
---prefix  *do not use in galaxy!* Set the output file prefix (default 'out')
---rv  Reverse video, swap the foreground and background colors for x11 plots (requires x11 terminal)
---IdR  Select a specific reference sequence for the x-axis
---IdQ  Select a specific query sequence for the y-axis
---Rfile  Generate a multiplot by using the order and length information contained in this file, either a FastA file of the desired reference sequences or a tab-delimited list of sequence IDs, lengths and orientations [ +-]
---Qfile  Generate a multiplot by using the order and length information contained in this file, either a FastA file of the desired query sequences or a tab-delimited list of sequence IDs, lengths and orientations [ +-]
---size  Set the output size to small, medium or large
---large  **default enabled to generate highres image**. Other sizes no effect: --small  --medium --large
---SNP  Highlight SNP locations in the alignment
---terminal  *do not use in galaxy* Set the output terminal to x11, postscript or png
---png  **either png or postscript for fixed image**. Other interactive x11 not enabled
---postscript  Alternate output format instead of png.
---xrange  Set the x-range for the plot in the form "[min,max]"
---yrange  Set the y-range for the plot in the form "[min,max]"
---version  Display version information and exit
-
-
-	</help>
-</tool>
-
--- a/MUMmer/nucmer_coords2ACT_galaxy.pl	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,42 +0,0 @@
-#!/usr/bin/perl
-
-# converts the MUMmer-nucmer coords file in a file readable for Artemis Comparison Tool
-# Output format is like crunch of BLAST
-#
-# [nov 2010] Galaxy wrapped up version
-#
-# Alex.Bossers@wur.nl
-
-
-use warnings;
-use strict;
-
-#$filename=shift;
-   #$ARGV[0] =~ m/^([A-Z0-9_.-]+)$/ig;
-my $filename = $ARGV[0];
-   #$ARGV[1] =~ m/^([A-Z0-9_.-]+)$/ig;
-my $fileout = $ARGV[1];
-#my $filename	=	"Curated_vs_noncurated_8067_01.nucmer.coords";
-#my $fileout	=	"Curated_vs_noncurated_8067_01.nucmer.tab";
-
-open (COORDS,$filename) || die "error opening input coords file";
-open (OUT,">$fileout") || die "error opening tab output file";
-
-while (<COORDS>)
-         {
-    unless ($_ =~ /^(\s*)\d/){next}
-    $_ =~ s/\|//g;
-
-    my @f = split;
-          # create crude match score = ((length_of_match * %identity)-(length_of_match * (100 - %identity))) /20
-    my $crude_plus_score=($f[4]*$f[6]);
-    my $crude_minus_score=($f[4]*(100-$f[6]));
-    my $crude_score=  int(($crude_plus_score  - $crude_minus_score) / 20);
-          # reorganise columns and print crunch format to stdout
-          # score        %id   S1    E1    seq1  S2    E2    seq2  (description)
-    print OUT " $crude_score $f[6] $f[0] $f[1] $f[7] $f[2] $f[3] $f[8] nucmer comparison coordinates\n"
-         }
-
-close (COORDS);
-close (OUT);
-print "Done!\n\n";
--- a/MUMmer/nucmer_coords2ACT_galaxy.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,39 +0,0 @@
-<tool id="MUMmer2ACT_tool" name="MUMmer2ACT" version="0.1.alx" force_history_refresh="True">
-  <description>: convert MUMmer comparison (coords) file to ACT (Artemis)</description>
-  <command interpreter="perl">
-  	nucmer_coords2ACT_galaxy.pl $in_coords $out_act
-  </command>
-	<inputs>
-		<param name="in_coords" type="data" format="tabular" label="MUMmer coords file to use" help="i.e. a nucmer comparison (coords) file" />
-	</inputs>
-	<outputs>
-		<data name="out_act" format="tabular" label="ACT conversion of coords" />
-	</outputs>
-	<requirements>
-	  <requirement type="perl-script">nucmer_coords2ACT_galaxy.pl</requirement>
-	</requirements>
-	<tests>
-		<test>
-		</test>
-	</tests>
-	<help>
-|
-|
-
-**Info**
---------
-
-This tool will convert the MUMmer comparison file (run MUMmer with the coords option) into a "blast crunch" file
-that can be read as a comparison file in Artemic Comparison Tool (ACT).
-
-It will output a single tabular crunch file (save as extension .tab on windows systems).
-
-**Reference/questions/remarks**
-
-- *Conversion perl script and wrapper:* Alex Bossers, CVI of Wageningen UR, The Netherlands.
-
-
-
-	</help>
-</tool>
-
--- a/MUMmer/suite_config.xml	Tue Jun 07 17:22:27 2011 -0400
+++ /dev/null	Thu Jan 01 00:00:00 1970 +0000
@@ -1,22 +0,0 @@
-<suite id="MUMmer_toolsuite" name="Suite of MUMmer tools" version="1.0.0">
-	<description>This suite contains MUMmer genome alignment tools and parsers</description>
-	<tool id="mummer_tool" name="MUMmer" version="0.4.alx">
-		<description>: Compare genomes by alignment (Nucmer or Promer)</description>
-	</tool>
-	<tool id="mummer_maxmatch" name="MUMmer MaxMatch" version="0.9.alx" >
-		<description>: Maximal exact sequence matching</description>
-	</tool>
-	<tool id="mummer_clustering" name="MUMmer Clustering" version="0.9.alx">
-		<description>: order sequence matches in clusters</description>
-	</tool>
-	<tool id="mummer_utilities_tool" name="MUMmer utilities" version="0.9.alx">
-		<description>: Show and filter on sequence delta file</description>
-	</tool>
-	<tool id="mummerplot_tool" name="MUMmer plot" version="1.0.1">
-		<description>: Generate MUMmerplots from MUMmer match file</description>
-	</tool>
-	<tool id="MUMmer2ACT_tool" name="MUMmer2ACT" version="0.1.alx">
-		<description>: convert MUMmer comparison (coords) file to ACT (Artemis)</description>
-	</tool>
-</suite>
-
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/MUMmer/tool_dependencies.xml	Tue Oct 28 16:59:05 2014 +0100
@@ -0,0 +1,13 @@
+<?xml version="1.0"?>
+<tool_dependency>
+    <!-- <set_environment version="3.23">
+        <environment_variable name="MUMMER_PATH" action="set_to">$REPOSITORY_INSTALL_DIR</environment_variable>
+    </set_environment>-->
+
+    <package name="mummer" version="3.23">
+        <repository changeset_revision="020178be49ee" name="package_mummer_3_23" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+	<package name="gnuplot" version="4.6">
+        <repository changeset_revision="cdff8e702d51" name="package_gnuplot_4_6" owner="iuc" toolshed="https://testtoolshed.g2.bx.psu.edu" />
+    </package>
+</tool_dependency>
\ No newline at end of file