comparison fuma.xml @ 0:a4cfaa0e3e5d draft

planemo upload for repository https://bitbucket.org/EMCbioinf/galaxy-tool-shed-tools/raw/master/fuma commit f56125b28ec44aa28943ed040b7b202fed9c875b-dirty

0:a4cfaa0e3e5d

<?xml version="1.0" encoding="UTF-8"?>
<tool id="fuma" name="FuMa" version="2.7.1.b">
	<description>FuMa (FusionMatcher) matches detected fusion genes based on gene name subset matching (designed in particular for RNA-Seq).</description>
	
	<requirements>
		<requirement type="package" version="2.7.1">fuma</requirement>
	</requirements>
	
	<version_command>fuma --version 2>&amp;1 | head -n 1</version_command><!-- -V also works, but is not GNU standard -->
	
	<command>
		#import pipes
		
		#set $gene_annotations = []
		#set $samples = []
		#set $links = []
		
		#for $i, $d in enumerate( $datasets )
			
			#set $sample_name = pipes.quote(str($d['sample'].name))
			
			#set $gene_annotations = $gene_annotations + [ "ga_" + str($i) + ":" + str($d['gene_annotation'].file_name) ]
			
			#set $samples = $samples + [ $sample_name + ":" + str($d['format']) + ":" + str($d['sample'].file_name) ]
			#set $links = $links + [ $sample_name + ":" + str("ga_") + str($i) ]
		#end for
		
		#set $gene_annotations_str = " ".join(gene_annotations)
		#set $samples_str = " ".join(samples)
		#set $links_str = " ".join(links)
		
		fuma 
		  -a
		    $gene_annotations_str
		  -s
		    $samples_str
		  -l
		    $links_str
		#if $output_format.value == "list_boolean"
		  -f list
		#else
		  -f $output_format.value
		#end if
		  -o $fuma_overview ; 
		
		
		
		#if $output_format.value == "list_boolean"
			fuma-list-to-boolean-list -o tmp.txt $fuma_overview &amp;&amp;
			mv tmp.txt $fuma_overview
		#end if
	</command>
	
	<inputs>
		<repeat name="datasets" title="FusionGene Datasets" min="2">
			<param name="sample" type="data" format="txt,tabular" label="Dataset (RNA-Seq fusion gene detection experiment)" />
			<param name="format" type="select" label="Format of dataset">
				<option value="chimerascan">ChimeraScan</option>
				<option value="defuse">DeFuse</option>
				<option value="complete-genomics">Complete Genomics</option>
				<option value="fusion-catcher_final">Fusion Catcher (final-list file)</option>
				<option value="fusionmap">FusionMap</option>
				<option value="trinity-gmap">GMAP (As step after Trinity)</option>
				<option value="oncofuse">OncoFuse</option>
				<option value="rna-star_chimeric">STAR (chimeric file)</option>
				<option value="tophat-fusion_pre">Tophat Fusion Pre (fusions.out)</option>
				<option value="tophat-fusion_post_potential_fusion">Tophat Fusion Post (potential_fusion.txt)</option>
				<option value="tophat-fusion_post_result">Tophat Fusion Post (result.txt)</option>
			</param>
			<param name="gene_annotation" type="data" format="bed" label="Corresponding gene-name annotation file (BED format)" help="Make use of persistent gene annotations! Gene annotations should only be different if different reference genome builds were used." />
		</repeat>
		
		<param name="output_format" type="select" label="Output format">
			<option value="list_boolean" selected="true">List (Boolean)</option>
			<option value="list">List</option>
			<option value="summary">Count summary</option>
		</param>
	</inputs>
	
	<outputs>
		<data format="tabular" name="fuma_overview" label="${tool.name} on ${', '.join([ str(d['sample'].hid)+': '+d['sample'].name for d in $datasets ])}" />
	</outputs>
	
	<tests>
		<test>
			<!-- <repeat name="datasets"> -->
				<param name="datasets_0|sample" value="chimerascan.txt" ftype="tabular" />
				<param name="datasets_0|format" value="chimerascan" />
				<param name="datasets_0|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
			<!-- </repeat> -->
			<!-- <repeat name="datasets"> -->
				<param name="datasets_1|sample" value="defuse.txt" ftype="tabular" />
				<param name="datasets_1|format" value="defuse" />
				<param name="datasets_1|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
			<!-- </repeat> -->
			<!-- <repeat name="datasets"> -->
				<param name="datasets_2|sample" value="fusion-map.txt" ftype="tabular" />
				<param name="datasets_2|format" value="fusionmap" />
				<param name="datasets_2|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
			<!-- </repeat> -->
			<!-- <repeat name="datasets"> -->
				<param name="datasets_3|sample" value="edgren_tp.txt" ftype="tabular" />
				<param name="datasets_3|format" value="fusionmap" />
				<param name="datasets_3|gene_annotation" value="refseq_genes_hg19.bed" ftype="bed" />
			<!-- </repeat> -->
			
			<param name="output_format" value="summary" />
			
			<output name="fuma_overview" file="output.txt" />
		</test>
	</tests>
	
	<help>============
Introduction
============

FuMa (Fusion Matcher) matches predicted fusion events (both genomic and transcriptomic) according to chromosomal location or assocatiated gene annotation(s) where the latter should be genome build inspecific.

Because RNA-Sequencing deals with samples that may have undergrond splicing, reads may split up because of biological processes. If a fusion event takes place, the same thing may happen. Therefore we hypothesize that using spanning read distances may be unreliable, because there are known introns of > 100kb. Therefore, FuMa translates the breakpoint to gene names, and only overlaps breakpoints with the same genename(s).

=====
Usage
=====

After you have uploaded the results of your Fusion Gene detection experiment, and selected the format to be *tabular*, you can start the FuMa wrapper. For each dataset you simply have to add another repeat. Then you have to select a corresponding format:

*******
Formats
*******

+-------------------+-----------------------+-------------------------------------+
|Tools              | File                  | Format string                       |
+===================+=======================+=====================================+
|ChimeraScan        | chimeras.bedpe        | chimerascan                         |
+-------------------+-----------------------+-------------------------------------+
|Complete Genomics  | highConfidenceJu*.tsv | complete-genomics                   |
+-------------------+-----------------------+-------------------------------------+
|Complete Genomics  | allJunctionsBeta*.tsv | complete-genomics                   |
+-------------------+-----------------------+-------------------------------------+
|DeFuse             | results.txt           | defuse                              |
+-------------------+-----------------------+-------------------------------------+
|DeFuse             | results.classify.txt  | defuse                              |
+-------------------+-----------------------+-------------------------------------+
|DeFuse             | results.filtered.txt  | defuse                              |
+-------------------+-----------------------+-------------------------------------+
|Fusion Catcher     | final-list_cand*.txt  | fusion-catcher_final                |
+-------------------+-----------------------+-------------------------------------+
|FusionMap          |                       | fusionmap                           |
+-------------------+-----------------------+-------------------------------------+
|Trinity + GMAP     |                       | trinity-gmap                        |
+-------------------+-----------------------+-------------------------------------+
|OncoFuse           |                       | oncofuse                            |
+-------------------+-----------------------+-------------------------------------+
|RNA STAR           | Chimeric.out.junction | rna-star_chimeric                   |
+-------------------+-----------------------+-------------------------------------+
|TopHat Fusion pre  | fusions.out           | tophat-fusion_pre                   |
+-------------------+-----------------------+-------------------------------------+
|TopHat Fusion post | potential_fusion.txt  | tophat-fusion_post_potential_fusion |
+-------------------+-----------------------+-------------------------------------+
|TopHat Fusion post | result.txt            | tophat-fusion_post_result           |
+-------------------+-----------------------+-------------------------------------+

To annotate genes upon the breakpoints you must provide a BED file that contains gene annotations for the user genome build. Make sure **your BED file contains one gene per line**. You should use BED files that contain one exon per line only if you want restrict your analysis to fusion genes detected within exons.

UCSC genome browser provides a very simple way of obtaining BED files with one gene per line by selecting their *RefSeq Genes*-track and *knownGene*-table and putting the export format to BED. Galaxy should have a built-in UCSC table browser.

	</help>
</tool>