# HG changeset patch # User jjohnson # Date 1644606531 0 # Node ID 463dd21dc267b818a40b1768bc06bf508ee7f133 "planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/arriba commit c1d05da7c2c76feae94cbc640be7b010f31397d2-dirty" diff -r 000000000000 -r 463dd21dc267 arriba_get_filters.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/arriba_get_filters.xml Fri Feb 11 19:08:51 2022 +0000 @@ -0,0 +1,71 @@ + + to history + + macros.xml + + + + + + + GRCh38 GRCh37 hg38 hg19 GRCm38 mm10 + + + + + + + + + + + + + + + + + + + + + + + + + + + diff -r 000000000000 -r 463dd21dc267 macros.xml --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/macros.xml Fri Feb 11 19:08:51 2022 +0000 @@ -0,0 +1,209 @@ + + 2.2.1 + 0 + + + arriba + + + + + + 10.1101/gr.257246.119 + + + + + arriba -h | grep Version | sed 's/^.* //' + + + + + + + + + + + + + + + + + + + + +#if str($genome.genome_source) == "history" + #if $genome.assembly + #set $genome_assembly = $genome.assembly + #end if + #set $genome_annotation = $genome.annotation +#else + #set $genome_assembly = $genome.arriba_ref.fields.fasta + #set $genome_annotation = $genome.arriba_ref.fields.gtf +#end if + + + + +
+ + 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. + + + + + + + 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 + + + + + + + + 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 + + + + 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 + + + + + + + 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 + + + + 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 + + + + + + Whether light and shadow should be rendered to give objects a 3D effect. + Default: TRUE + + + + + + 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 + + + + + + + + + +
+
+ +draw_fusions.R + --fusions='$fusions' + --alignments='Aligned.sortedByCoord.out.bam' + --annotation='$genome.annotation' + --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 + +
diff -r 000000000000 -r 463dd21dc267 static/images/draw-fusions-example.png Binary file static/images/draw-fusions-example.png has changed diff -r 000000000000 -r 463dd21dc267 test-data/genome.fasta.gz Binary file test-data/genome.fasta.gz has changed diff -r 000000000000 -r 463dd21dc267 test-data/genome.gtf.gz Binary file test-data/genome.gtf.gz has changed diff -r 000000000000 -r 463dd21dc267 tool-data/arriba_indexes.loc.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool-data/arriba_indexes.loc.sample Fri Feb 11 19:08:51 2022 +0000 @@ -0,0 +1,17 @@ +#This is a sample file distributed with Galaxy that enables tools +#to use a directory of Ariba data files. +#The Arriba script download_references.sh retrieves a genome assembly fasta +#and a related GTF annotation file, then builds a STAR index. +#You will need to create these data files and then create a +#arriba_indexes.loc similar to this one (store it in this +#directory) that points to the directories in which those files are stored. +#The arriba_indexes.loc file has this format (longer white space +#characters are TAB characters): +# +# +# +#Note that STAR indices can become quite large. +# +# +#GRCh38+ENSEMBL93 GRCh38+ENSEMBL93 /depot/GRCh38+ENSEMBL93/genome.fa /depot/GRCh38+ENSEMBL93/genome.gtf /depot/GRCh38+ENSEMBL93/STAR_index/ + diff -r 000000000000 -r 463dd21dc267 tool_data_table_conf.xml.sample --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.sample Fri Feb 11 19:08:51 2022 +0000 @@ -0,0 +1,6 @@ + + + value, name, fasta, gtf, star_index + +
+
diff -r 000000000000 -r 463dd21dc267 tool_data_table_conf.xml.test --- /dev/null Thu Jan 01 00:00:00 1970 +0000 +++ b/tool_data_table_conf.xml.test Fri Feb 11 19:08:51 2022 +0000 @@ -0,0 +1,6 @@ + + + value, name, fasta, gtf, star_index + +
+