|
0
|
1 <tool id="te_finder_1" name="TEfinder" version="1.0.1" profile="21.05">
|
|
|
2 <description>A bioinformatics tool for detecting novel transposable element insertions</description>
|
|
|
3
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="1.15.1">samtools</requirement>
|
|
|
6 <requirement type="package" version="2.30.0">bedtools</requirement>
|
|
|
7 <requirement type="package" version="2.27.4">picard</requirement>
|
|
|
8 <requirement type="package" version="3.4">grep</requirement>
|
|
|
9 <requirement type="package" version="1.07.1">bc</requirement>
|
|
|
10 </requirements>
|
|
|
11
|
|
|
12 <command>
|
|
|
13 <![CDATA[
|
|
|
14 '$__tool_directory__/TEfinder' -fa '$required_inputs.FastaFile'
|
|
|
15 -alignment '$required_inputs.alignmentFile'
|
|
|
16 -gtf '$required_inputs.TransposonsInGenome'
|
|
|
17 -te '$required_inputs.TransposonsToSearch'
|
|
|
18 -bamo '$discordantreads'
|
|
|
19 -bedo '$bteinsertion'
|
|
|
20 -threads '\${GALAXY_SLOTS:-1}'
|
|
|
21 -fis $($advanced_options.FragmentInsertSize)
|
|
|
22 -md $($advanced_options.MaxDistanceForMerge)
|
|
|
23 -k $($advanced_options.MaxTSDLength)
|
|
|
24 #if str( $advanced_options.OutFormat) == "gtf":
|
|
|
25 -gtfo '$gteinsertion'
|
|
|
26 -out $($advanced_options.OutFormat)
|
|
|
27 #end if
|
|
|
28 ]]>
|
|
|
29 </command>
|
|
|
30
|
|
|
31 <inputs>
|
|
|
32 <!-- <param format="fasta" name="input" type="data" label="Source file"/> -->
|
|
|
33 <section name="required_inputs" title="Required Inputs" expanded="True">
|
|
|
34 <param name="FastaFile" type="data" format="fasta" label="Select reference genome FASTA index (FA/FASTA file)" />
|
|
|
35 <param name="alignmentFile" type="data" format="bam" label="Select sample reads aligned to reference genome (BAM/SAM file)" />
|
|
|
36 <param name="TransposonsInGenome" type="data" format="gtf" label="Select reference genome TE annotation (GFF/GTF file)" />
|
|
|
37 <param name="TransposonsToSearch" type="data" format="text" label="Select TE names (single column text file)" />
|
|
|
38 </section>
|
|
|
39 <!-- Advanced Options -->
|
|
|
40 <section name="advanced_options" title="Advanced Options" expanded="False">
|
|
|
41 <param name="FragmentInsertSize" argument="-fis" type="integer" min="0" value="400" label="Short-read sequencing fragment insert size [400]" />
|
|
|
42 <param name="MaxDistanceForMerge" argument="-md" type="integer" min="0" value="150" label="Maximum distance between reads for bedtools merge" />
|
|
|
43 <param name="MaxTSDLength" argument="-k" type="integer" min="0" value="20" label="Maximum TE target site duplication (TSD) length" />
|
|
|
44 <param name="OutFormat" argument="-out" type="select" display="radio" label="Select output format as GTF [BED]" help="See help below for more details">
|
|
|
45 <option value="gtf">Other available format is GTF (-out gtf)</option>
|
|
|
46 <option value="bed" selected="True">Default format is BED</option>
|
|
|
47 </param>
|
|
|
48 </section>
|
|
|
49 </inputs>
|
|
|
50
|
|
|
51 <outputs>
|
|
|
52 <data format="bed" name="bteinsertion" label="${tool.name} on ${on_string}: BED" />
|
|
|
53 <data format="gtf" name="gteinsertion" label="${tool.name} on ${on_string}: GTF">
|
|
|
54 <filter>advanced_options['OutFormat'] and 'gtf' in advanced_options['OutFormat']</filter>
|
|
|
55 </data>
|
|
|
56 <data format="bam" name="discordantreads" />
|
|
|
57 </outputs>
|
|
|
58
|
|
|
59 <tests>
|
|
|
60 <!-- Test for the most simple case for BED output : Running TEfinder with a .bam file and a .fasta file -->
|
|
|
61 <test expect_num_outputs="2">
|
|
|
62 <!-- TEfinder commands: TEfinder -alignment sample.bam -fa reference.fa -gtf TEs.gtf -te List_of_TEs.txt -->
|
|
|
63 <param name="FastaFile" ftype="fasta" value="reference.fa"/>
|
|
|
64 <param name="alignmentFile" ftype="bam" value="sample.bam"/>
|
|
|
65 <param name="TransposonsInGenome" ftype="gtf" value="TEs.gtf"/>
|
|
|
66 <param name="TransposonsToSearch" ftype="txt" value="List_of_TEs.txt"/>
|
|
|
67 <param name="OutFormat" value="bed" />
|
|
|
68 <output name="bteinsertion" file="TEinsertions.bed" ftype="bed"/>
|
|
|
69 <output name="discordantreads" file="DiscordantReads.bam" ftype="bam"/>
|
|
|
70 </test>
|
|
|
71
|
|
|
72 <!-- Test for the GTF output -->
|
|
|
73 <test expect_num_outputs="3">
|
|
|
74 <!-- TEfinder commands: TEfinder -alignment sample.bam -fa reference.fa -gtf TEs.gtf -te List_of_TEs.txt -out gtf -->
|
|
|
75 <param name="FastaFile" ftype="fasta" value="reference.fa"/>
|
|
|
76 <param name="alignmentFile" ftype="bam" value="sample.bam"/>
|
|
|
77 <param name="TransposonsInGenome" ftype="gtf" value="TEs.gtf"/>
|
|
|
78 <param name="TransposonsToSearch" ftype="txt" value="List_of_TEs.txt"/>
|
|
|
79 <param name="OutFormat" value="gtf" />
|
|
|
80 <output name="bteinsertion" file="TEinsertions.bed" ftype="bed"/>
|
|
|
81 <output name="gteinsertion" file="TEinsertions.gtf" ftype="gtf"/>
|
|
|
82 <output name="discordantreads" file="DiscordantReads.bam" ftype="bam"/>
|
|
|
83 </test>
|
|
|
84 </tests>
|
|
|
85
|
|
|
86 <help>
|
|
|
87 <![CDATA[
|
|
|
88 A bioinformatics tool for detecting novel transposable element insertions
|
|
|
89
|
|
|
90 Authors: Vista Sohrab & Dilay Hazal Ayhan
|
|
|
91
|
|
|
92 TEfinder uses discordant reads to detect novel transposable element insertion events in paired-end sample sequencing data.
|
|
|
93
|
|
|
94 **Output files**::
|
|
|
95
|
|
|
96 TE_insertions.bed contains identified TE insertion events in sample (in the final column, FILTER attribute with "PASS" refers to high confidence insertion events while instances labeled as "in_repeat", "weak_evidence", "strand bias" or a combination of these three labels indicate less confident insertion events)
|
|
|
97
|
|
|
98 TE_insertions.gtf is provided with the same information as the BED file if using -out GTF
|
|
|
99
|
|
|
100 DiscordantReads.bam contains all discordant reads that have been identified based on the TEs of interest that have been submitted to TEfinder
|
|
|
101
|
|
|
102 **Note**::
|
|
|
103
|
|
|
104 Modifying the maximum TSD length (-k) could be useful if there is an unexpected number of insertion events identified with the default parameter. The optimal maximum TSD length can vary across datasets.
|
|
|
105 Modifying the fragment insert size (-fis) based on the sequencing library preparation can be useful.
|
|
|
106
|
|
|
107 ]]>
|
|
|
108 </help>
|
|
|
109
|
|
|
110 <citations>
|
|
|
111 <citation type="doi">10.5281/zenodo.4479946</citation>
|
|
|
112 </citations>
|
|
|
113
|
|
|
114 </tool> |
