Mercurial > repos > mheinzl > variant_analyzer2

comparison read2mut.xml @ 55:8fbe6aba07e5 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload for repository https://github.com/Single-Molecule-Genetics/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8
author mheinzl
date Fri, 12 Mar 2021 14:18:45 +0000
parents d21960b45a6b
children 66c1245436b9
comparison
equal deleted inserted replaced
54:95c27bcb1b7a 55:8fbe6aba07e5
1 <?xml version="1.0" encoding="UTF-8"?> 1 <?xml version="1.0" encoding="UTF-8"?>
2 <tool id="read2mut" name="Call specific mutations in reads:" version="2.1.0" profile="19.01"> 2 <tool id="read2mut" name="Call specific mutations in reads:" version="2.1.1" profile="19.01">
3 <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description> 3 <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description>
4 <macros> 4 <macros>
5 <import>va_macros.xml</import> 5 <import>va_macros.xml</import>
6 </macros> 6 </macros>
7 <requirements> 7 <requirements>
24 --trim '$trim' 24 --trim '$trim'
25 $chimera_correction 25 $chimera_correction
26 --softclipping_dist '$softclipping_dist' 26 --softclipping_dist '$softclipping_dist'
27 --reads_threshold '$reads_threshold' 27 --reads_threshold '$reads_threshold'
28 --outputFile '$output_xlsx' 28 --outputFile '$output_xlsx'
29 --outputFile_csv '$outputFile_csv'
29 --outputFile2 '$output_xlsx2' 30 --outputFile2 '$output_xlsx2'
30 --outputFile3 '$output_xlsx3' 31 --outputFile3 '$output_xlsx3'
31 ]]> 32 ]]>
32 </command> 33 </command>
33 <inputs> 34 <inputs>
42 <param name="softclipping_dist" type="integer" label="Distance between artifact and softclipping of the reads" min="1" value="15" help="Count mutation as an artifact if mutation lies within this parameter away from the softclipping part of the reads. Default = 20"/> 43 <param name="softclipping_dist" type="integer" label="Distance between artifact and softclipping of the reads" min="1" value="15" help="Count mutation as an artifact if mutation lies within this parameter away from the softclipping part of the reads. Default = 20"/>
43 <param name="reads_threshold" type="float" label="Minimum percentage of softclipped reads in a family" min="0.0" max="1.0" value="1.0" help="Float number which specifies the minimum percentage of softclipped reads in a family to be considered in the softclipping tiers. Default: 1.0, means all reads of a family have to be softclipped."/> 44 <param name="reads_threshold" type="float" label="Minimum percentage of softclipped reads in a family" min="0.0" max="1.0" value="1.0" help="Float number which specifies the minimum percentage of softclipped reads in a family to be considered in the softclipping tiers. Default: 1.0, means all reads of a family have to be softclipped."/>
44 </inputs> 45 </inputs>
45 <outputs> 46 <outputs>
46 <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/> 47 <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/>
48 <data name="outputFile_csv" format="csv" label="${tool.name} on ${on_string}: CSV summary"/>
47 <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/> 49 <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/>
48 <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/> 50 <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/>
49 </outputs> 51 </outputs>
50 <tests> 52 <tests>
51 <test> 53 <test>
58 <param name="trim" value="10"/> 60 <param name="trim" value="10"/>
59 <param name="chimera_correction"/> 61 <param name="chimera_correction"/>
60 <param name="softclipping_dist" value="15"/> 62 <param name="softclipping_dist" value="15"/>
61 <param name="reads_threshold" value="1.0"/> 63 <param name="reads_threshold" value="1.0"/>
62 <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/> 64 <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/>
65 <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true" lines_diff="10"/>
63 <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/> 66 <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/>
64 <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/> 67 <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/>
65 </test> 68 </test>
66 </tests> 69 </tests>
67 <help> <![CDATA[ 70 <help> <![CDATA[
73 from the raw reads. 76 from the raw reads.
74 77
75 **Input** 78 **Input**
76 79
77 **Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 80 **Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g.
78 generated by the `FreeBayes variant caller <https://arxiv.org/abs/1207.3907>`_. 81 generated by the `FreeBayes <https://arxiv.org/abs/1207.3907>`_ or `LoFreq <https://academic.oup.com/nar/article/40/22/11189/1152727>`_ variant caller.
79 82
80 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 83 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the
81 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_. 84 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.
82 85
83 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool 86 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool
89 is called in the DCS. 92 is called in the DCS.
90 93
91 **Output** 94 **Output**
92 95
93 The output are three XLSX files containing frequencies stats for DCS mutations based 96 The output are three XLSX files containing frequencies stats for DCS mutations based
94 on information from the raw reads. In addition to that a tier based 97 on information from the raw reads and a CSV file containing the summary information without color-coding. In addition to that a tier based
95 classification is provided based on the amout of support for a true variant call. 98 classification is provided based on the amout of support for a true variant call.
99
96 100
97 ]]> 101 ]]>
98 </help> 102 </help>
99 <expand macro="citation" /> 103 <expand macro="citation" />
100 </tool> 104 </tool>