Mercurial > repos > yating-l > regtools_junctions_extract
comparison regtools_junctions_extract.xml @ 0:2626c5b4c665 draft
planemo upload commit db634d933827ebc78981c7a0aa18205a85fa42e6-dirty
| author | yating-l |
|---|---|
| date | Mon, 19 Dec 2016 13:07:32 -0500 |
| parents | |
| children | e9dcea52d079 |
comparison
equal
deleted
inserted
replaced
| -1:000000000000 | 0:2626c5b4c665 |
|---|---|
| 1 <tool id="regtools_junctions_extract" name="regtools junctions extract" version="0.1.0"> | |
| 2 <description>Extract splice junctions from a RNA-Seq BAM file</description> | |
| 3 <requirements> | |
| 4 <requirement type="package" version="0.3.0">regtools</requirement> | |
| 5 </requirements> | |
| 6 <stdio> | |
| 7 <exit_code range="1:" /> | |
| 8 </stdio> | |
| 9 <command><![CDATA[ | |
| 10 ## regtools expects an indexed BAM file | |
| 11 ## Use symlinks to link the BAM file and its index to the working directory | |
| 12 ## See: https://biostar.usegalaxy.org/p/10128/ | |
| 13 | |
| 14 ln -sf '${input1}' infile.bam && | |
| 15 ln -sf '${input1.metadata.bam_index}' infile.bam.bai && | |
| 16 | |
| 17 regtools junctions extract | |
| 18 -i $min_intron_length | |
| 19 -I $max_intron_length | |
| 20 -o $output1 | |
| 21 #if str($advanced_options.advanced_options_selector) == "on": | |
| 22 -a $advanced_options.min_anchor_length | |
| 23 | |
| 24 #if str($advanced_options.region): | |
| 25 -r "$advanced_options.region" | |
| 26 #end if | |
| 27 #end if | |
| 28 infile.bam && | |
| 29 | |
| 30 python $__tool_directory__/validator.py $output1 $fixed_output | |
| 31 ]]></command> | |
| 32 <inputs> | |
| 33 <param name="input1" type="data" format="bam" /> | |
| 34 | |
| 35 <param name="min_intron_length" type="integer" label="Minimum intron length" value="20" min="1"> | |
| 36 <help>Only considers spliced RNA-Seq reads with this minimum intron length (-i)</help> | |
| 37 </param> | |
| 38 <param name="max_intron_length" type="integer" label="Maximum intron length" value="500000" min="1"> | |
| 39 <help>Only considers spliced RNA-Seq reads with this maximum intron length (-I)</help> | |
| 40 </param> | |
| 41 | |
| 42 <conditional name="advanced_options"> | |
| 43 <param name="advanced_options_selector" type="select" label="Advanced options"> | |
| 44 <option value="off" selected="true">Hide advanced options</option> | |
| 45 <option value="on">Display advanced options</option> | |
| 46 </param> | |
| 47 <when value="on"> | |
| 48 <param name="min_anchor_length" type="integer" label="Minimum anchor length" value="8" min="1"> | |
| 49 <help>Only report splice junctions with this minimum anchor length on both sides of the junction (-a)</help> | |
| 50 </param> | |
| 51 <param name="region" type="text" optional="true" label="Only extract junctions in this region" value=""> | |
| 52 <help>Only report splice junctions within this region (format = chrom:start-end) (-r)</help> | |
| 53 <validator type="regex" | |
| 54 message="Region should be in the following format: chrom:start-end">^([^:]+):(\d+)-(\d+)$</validator> | |
| 55 </param> | |
| 56 </when> | |
| 57 | |
| 58 <when value="off" /> | |
| 59 </conditional> | |
| 60 </inputs> | |
| 61 <outputs> | |
| 62 <data name="output1" format="bed" message="original output"/> | |
| 63 <data name="fixed_output" format="bed" message="Check for lines with invalid BED format, if so remove the lines. This output is the one that should be used in HAC workflow"/> | |
| 64 </outputs> | |
| 65 <tests> | |
| 66 <test> | |
| 67 <!-- Test with default parameters --> | |
| 68 <param name="input1" value="Dbia3_adult_males_shallow.bam" /> | |
| 69 <output name="output1" file="Dbia3_adult_males_junctions_i20_I500000.bed" /> | |
| 70 <output name="fixed_output" file="Dbia3_adult_males_junctions_i20_I500000_fixed.bed" /> | |
| 71 </test> | |
| 72 <test> | |
| 73 <!-- Test with custom intron length thresholds --> | |
| 74 <param name="min_intron_length" value="50" /> | |
| 75 <param name="max_intron_length" value="50000" /> | |
| 76 <param name="input1" value="Dbia3_adult_males_shallow.bam" /> | |
| 77 <output name="output1" file="Dbia3_adult_males_junctions_i50_I50000.bed" /> | |
| 78 <output name="fixed_output" file="Dbia3_adult_males_junctions_i50_I50000_fixed.bed" /> | |
| 79 </test> | |
| 80 <test> | |
| 81 <!-- Test with advanced option and custom anchor size --> | |
| 82 <param name="advanced_options_selector" value="on" /> | |
| 83 <param name="min_anchor_length" value="10" /> | |
| 84 <param name="input1" value="Dbia3_adult_males_shallow.bam" /> | |
| 85 <output name="output1" | |
| 86 file="Dbia3_adult_males_junctions_i20_I500000_a10.bed" /> | |
| 87 <output name="fixed_output" | |
| 88 file="Dbia3_adult_males_junctions_i20_I500000_a10_fixed.bed" /> | |
| 89 </test> | |
| 90 <test> | |
| 91 <!-- Test with advanced option and selected region --> | |
| 92 <param name="advanced_options_selector" value="on" /> | |
| 93 <param name="region" value="contig2:10000-30000" /> | |
| 94 <param name="input1" value="Dbia3_adult_males_shallow.bam" /> | |
| 95 <output name="output1" file="Dbia3_adult_males_junctions_i20_I500000_rcontig2_10-30kb.bed" /> | |
| 96 <output name="fixed_output" file="Dbia3_adult_males_junctions_i20_I500000_rcontig2_10-30kb_fixed.bed"/> | |
| 97 </test> | |
| 98 <test> | |
| 99 <!--Test with output having invalid strand --> | |
| 100 <param name="input1" value="Dbia3.bam" /> | |
| 101 <output name="output1" file="Dbia3_i20_I500000.bed" /> | |
| 102 <output name="fixed_output" file="Dbia3_i20_I500000_fixed.bed" /> | |
| 103 </test> | |
| 104 </tests> | |
| 105 <help><![CDATA[ | |
| 106 **What it does** | |
| 107 | |
| 108 The `regtools junctions extract <https://regtools.readthedocs.io/en/latest/commands/junctions-extract/>`_ | |
| 109 tool creates a list of exon-exon junctions from spliced RNA-Seq reads within a BAM | |
| 110 alignment file. The format of the output BED file is similar to the ``junctions.bed`` | |
| 111 file produced by TopHat2. | |
| 112 | |
| 113 The extent of each BED feature corresponds to the maximum overhang of each splice | |
| 114 junction. The score of each BED feature corresponds to the number of spliced RNA-Seq | |
| 115 reads that support each junction. | |
| 116 | |
| 117 -------- | |
| 118 | |
| 119 .. class:: warningmark | |
| 120 | |
| 121 By default, the minimum intron size is **20 bp** and the maximum intron size is | |
| 122 **500,000 bp** so that they conform to the default intron size settings for | |
| 123 `HISAT2 <https://ccb.jhu.edu/software/hisat2/manual.shtml#options>`_. The minimum | |
| 124 intron size for the command-line version of ``regtools junctions extract`` is 70 bp. | |
| 125 | |
| 126 ]]></help> | |
| 127 <citations> | |
| 128 <citation type="bibtex"> | |
| 129 @misc{githubregtools, | |
| 130 author = {Griffith Lab}, | |
| 131 year = {2016}, | |
| 132 title = {regtools}, | |
| 133 publisher = {GitHub}, | |
| 134 journal = {GitHub repository}, | |
| 135 url = {https://github.com/griffithlab/regtools}, | |
| 136 }</citation> | |
| 137 </citations> | |
| 138 </tool> |
