Mercurial > repos > jjohnson > arriba
diff arriba.xml @ 7:25d207f7ff83 draft
"planemo upload for repository https://github.com/jj-umn/tools-iuc/tree/arriba/tools/arriba commit e113a79cc67e0bdb168babfe964f34873b2e1303"
| author | jjohnson |
|---|---|
| date | Mon, 11 Oct 2021 16:40:51 +0000 |
| parents | 7253b367c082 |
| children | 1a56888ddb7d |
line wrap: on
line diff
--- a/arriba.xml Mon Oct 11 01:47:22 2021 +0000 +++ b/arriba.xml Mon Oct 11 16:40:51 2021 +0000 @@ -55,7 +55,7 @@ #end if #end if -a '$genome_assembly' - -g '$gtf' + -g '$annotation' #if $blacklist -b '$blacklist' #else @@ -155,57 +155,8 @@ && samtools index Aligned.sortedByCoord.out.bam #end if #if str($visualization.do_viz) == "yes" -&& draw_fusions.R - --fusions=fusions.tsv - --alignments=Aligned.sortedByCoord.out.bam - --annotation='$gtf' - --output=fusions.pdf - #if $visualization.cytobands - --cytobands='$visualization.cytobands' - #end if - #if $protein_domains - --proteinDomains='$protein_domains' - #end if - ## Visualization Options - #if $visualization.options.transcriptSelection - --transcriptSelection=$visualization.options.transcriptSelection - #end if - #if $visualization.options.minConfidenceForCircosPlot - --minConfidenceForCircosPlot=$visualization.options.minConfidenceForCircosPlot - #end if - #if $visualization.options.showIntergenicVicinity - --showIntergenicVicinity=$visualization.options.showIntergenicVicinity - #end if - #if $visualization.options.squishIntrons - --squishIntrons=$visualization.options.squishIntrons - #end if - #if $visualization.options.mergeDomainsOverlappingBy - --mergeDomainsOverlappingBy=$visualization.options.mergeDomainsOverlappingBy - #end if - #if $visualization.options.printExonLabels - --printExonLabels=$visualization.options.printExonLabels - #end if - #if $visualization.options.render3dEffect - --render3dEffect=$visualization.options.render3dEffect - #end if - #if $visualization.options.optimizeDomainColors - --optimizeDomainColors=$visualization.options.optimizeDomainColors - #end if - #if $visualization.options.color1 - --color1=$visualization.options.color1 - #end if - #if $visualization.options.color2 - --color2=$visualization.options.color2 - #end if - #if $visualization.options.pdfWidth - --pdfWidth=$visualization.options.pdfWidth - #end if - #if $visualization.options.pdfHeight - --pdfHeight=$visualization.options.pdfHeight - #end if - #if $visualization.options.fontSize - --fontSize=$visualization.options.fontSize - #end if +#set $fusions = 'fusions.tsv' +&& @DRAW_FUSIONS@ #end if ]]></command> <inputs> @@ -243,7 +194,7 @@ </when> </conditional> <param name="genome_assembly" argument="-a" type="data" format="fasta" label="genome assembly fasta"/> - <param name="gtf" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/> + <param name="annotation" argument="-g" type="data" format="gtf" label="GTF file with gene annotation"/> <param name="blacklist" argument="-b" type="data" format="tabular,tabular.gz" optional="true" label="File containing blacklisted ranges."/> <param name="protein_domains" argument="-p" type="data" format="gff3" optional="true" label="File containing protein domains"/> <param name="known_fusions" argument="-k" type="data" format="tabular,tabular.gz" optional="true" label="File containing known fusions"> @@ -433,120 +384,15 @@ <option value="no">no</option> </param> <when value="yes"> - <param name="cytobands" argument="--cytobands" type="data" format="tabular" optional="true" label="Cytobands"/> - <section name="options" expanded="false" title="Visualization Options"> - <param argument="--transcriptSelection" type="select" optional="true" label="Transcript selection"> - <help>By default the transcript isoform with the highest coverage is drawn. - Alternatively, the transcript isoform that is provided in the columns - transcript_id1 and transcript_id2 in the given fusions file can be drawn. - Selecting the isoform with the highest coverage usually produces nicer plots, - in the sense that the coverage track is smooth and shows a visible increase in coverage after the fusion breakpoint. - However, the isoform with the highest coverage may not be the one that is involved in the fusion. - Often, genomic rearrangements lead to non-canonical isoforms being transcribed. - For this reason, it can make sense to rely on the transcript selection provided by the columns transcript_id1/2, - which reflect the actual isoforms involved in a fusion. -\ As a third option, the transcripts that are annotated as canonical can be drawn. - Transcript isoforms tagged with appris_principal, appris_candidate, or CCDS are considered canonical. - </help> - <option value="coverage">coverage</option> - <option value="provided">provided</option> - <option value="canonical">canonical</option> - </param> - <param argument="--minConfidenceForCircosPlot" type="select" optional="true" label="Transcript selection"> - <help>The fusion of interest is drawn as a solid line in the circos plot. - To give an impression of the overall degree of rearrangement, - all other fusions are drawn as semi-transparent lines in the background. - This option determines which other fusions should be included in the circos plot. - Values specify the minimum confidence a fusion must have to be included. - It usually makes no sense to include low-confidence fusions in circos plots, - because they are abundant and unreliable, and would clutter up the circos plot. - Default: medium - </help> - <option value="none">none - only the fusion of interest is drawn</option> - <option value="low">low</option> - <option value="medium">medium</option> - <option value="high">high</option> - </param> - <param argument="--showIntergenicVicinity" type="integer" value="" min="0" optional="true" label="Intergenic Vicinity"> - <help>This option only applies to intergenic breakpoints. - If it is set to a value greater than 0, then the script draws the genes - which are no more than the given distance away from an intergenic breakpoint. - Note that this option is incompatible with squishIntrons. - Default: 0 - </help> - </param> - <param argument="--squishIntrons" type="select" optional="true" label="Squish introns"> - <help>Exons usually make up only a small fraction of a gene. - They may be hard to see in the plot. i - Since introns are in most situations of no interest in the context of gene fusions, - this switch can be used to shrink the size of introns to a fixed, negligible size. - It makes sense to disable this feature, if breakpoints in introns are of importance. - Default: TRUE - </help> - <option value="TRUE">True</option> - <option value="FALSE">False</option> - </param> - - <param argument="--mergeDomainsOverlappingBy" type="float" value="" min="0." max="1.0" optional="true" label="Merge Domains Overlapping By"> - <help>Occasionally, domains are annotated redundantly. - For example, tyrosine kinase domains are frequently annotated as - Protein tyrosine kinase and Protein kinase domain. - In order to simplify the visualization, such domains can be merged into one, - given that they overlap by the given fraction. - The description of the larger domain is used. - Default: 0.9 - </help> - </param> - <param argument="--printExonLabels" type="select" optional="true" label="Print Exon Labels"> - <help>By default the number of an exon is printed inside each exon, - which is taken from the attribute exon_number of the GTF annotation. - When a gene has many exons, the boxes may be too narrow to contain the labels, - resulting in unreadable exon labels. In these situations, i - it may be better to turn off exon labels. - Default: TRUE - </help> - <option value="TRUE">True</option> - <option value="FALSE">False</option> - </param> - <param argument="--render3dEffect" type="select" optional="true" label="Render 3D effect"> - <help>Whether light and shadow should be rendered to give objects a 3D effect. - Default: TRUE - </help> - <option value="TRUE">True</option> - <option value="FALSE">False</option> - </param> - <param argument="--optimizeDomainColors" type="select" optional="true" label="Optimize Domain Colors"> - <help>By default, the script colorizes domains according to the colors - specified in the file given in --annotation. - This way, coloring of domains is consistent across all proteins. - But since there are more distinct domains than colors, - this can lead to different domains having the same color. - If this option is set to TRUE, the colors are recomputed for each fusion separately. - This ensures that the colors have the maximum distance for each individual fusion, - but they are no longer consistent across different fusions. - Default: FALSE - </help> - <option value="TRUE">True</option> - <option value="FALSE">False</option> - </param> - <param argument="--color1" type="color" value="" optional="true" label="Color of the 5' end of the fusion."/> - <param argument="--color2" type="color" value="" optional="true" label="Color of the 3' end of the fusion."/> - <param argument="--pdfWidth" type="float" value="" min="1." optional="true" label="Width of PDF output file in inches" - help="Default: 11.692"/> - <param argument="--pdfHeight" type="float" value="" min="1." optional="true" label="Height of PDF output file in inches" - help="Default: 8.267"/> - <param argument="--fontSize" type="float" value="" min="0." optional="true" label="Scale the size of text" - help="Default: 1.0"/> - </section> - + <expand macro="visualization_options" /> </when> <when value="no"/> </conditional> </inputs> <outputs> - <data name="fusions" format="tabular" label="${tool.name} on ${on_string}: fusions.tsv" from_work_dir="fusions.tsv"/> - <data name="discarded" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv"> + <data name="fusions_tsv" format="tabular" label="${tool.name} on ${on_string}: fusions.tsv" from_work_dir="fusions.tsv"/> + <data name="discarded_fusions_tsv" format="tabular" label="${tool.name} on ${on_string}: fusions.discarded.tsv" from_work_dir="fusions.discarded.tsv"> <filter> output_fusions_discarded == "yes"</filter> </data> <data name="aligned_bam" format="bam" label="${tool.name} on ${on_string}: Aligned.bam" from_work_dir="Aligned.sortedByCoord.out.bam"> @@ -564,13 +410,13 @@ <param name="input" ftype="sam" value="Aligned.out.sam"/> </conditional> <param name="genome_assembly" ftype="fasta" value="genome.fasta"/> - <param name="gtf" ftype="gtf" value="genome.gtf"/> + <param name="annotation" ftype="gtf" value="genome.gtf"/> <param name="protein_domains" ftype="gff3" value="protein_domains.gff3"/> <conditional name="visualization"> <param name="do_viz" value="no"/> <param name="cytobands" ftype="tabular" value="cytobands.tsv"/> </conditional> - <output name="fusions"> + <output name="fusions_tsv"> <assert_contents> <has_text_matching expression="BCR\tABL1"/> </assert_contents> @@ -583,15 +429,22 @@ <param name="input" ftype="sam" value="Aligned.out.sam"/> </conditional> <param name="genome_assembly" ftype="fasta" value="genome.fasta"/> - <param name="gtf" ftype="gtf" value="genome.gtf"/> + <param name="annotation" ftype="gtf" value="genome.gtf"/> + <param name="protein_domains" ftype="gff3" value="protein_domains.gff3"/> <conditional name="visualization"> <param name="do_viz" value="yes"/> + <param name="cytobands" ftype="tabular" value="cytobands.tsv"/> </conditional> - <output name="fusions"> + <output name="fusions_tsv"> <assert_contents> <has_text_matching expression="BCR\tABL1"/> </assert_contents> </output> + <output name="fusions_pdf"> + <assert_contents> + <has_size value= "64000" delta="5000" /> + </assert_contents> + </output> </test> </tests>