Mercurial > repos > mheinzl > variant_analyzer2

comparison read2mut.xml @ 78:fdfe9a919ff7 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-dirty
author mheinzl
date Fri, 22 Jul 2022 09:19:44 +0000
parents 56f271641828
children d7aea14291e8
comparison
equal deleted inserted replaced
77:1797e461d674 78:fdfe9a919ff7
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="2.1.4" profile="19.01"> 2 <tool id="read2mut" name="Call specific mutations in reads:" version="3.0.0" 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 a 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 <expand macro="requirements"> 7 <expand macro="requirements">
8 <requirement type="package" version="1.1.0">xlsxwriter</requirement> 8 <requirement type="package" version="1.1.0">xlsxwriter</requirement>
26 --outputFile2 '$output_xlsx2' 26 --outputFile2 '$output_xlsx2'
27 --outputFile3 '$output_xlsx3' 27 --outputFile3 '$output_xlsx3'
28 ]]> 28 ]]>
29 </command> 29 </command>
30 <inputs> 30 <inputs>
31 <param name="file1" type="data" format="vcf" label="DCS Mutation File" optional="false" help="VCF file with DCS mutations. See Help section below for a detailed explanation."/> 31 <param name="file1" type="data" format="vcf" label="DCS Mutation File" optional="false" help="VCF file with DCS mutations. See the Help section below for a detailed explanation."/>
32 <param name="file2" type="data" format="bam" label="BAM File of raw reads" optional="false" help="BAM file with aligned raw reads of selected tags."/> 32 <param name="file2" type="data" format="bam" label="BAM File of raw reads" optional="false" help="BAM file with aligned raw reads of selected tags."/>
33 <param name="file3" type="data" format="json" label="JSON File with DCS tag stats" optional="false" help="JSON file generated by DCS mutations to tags/reads"/> 33 <param name="file3" type="data" format="json" label="JSON File with DCS tag stats" optional="false" help="JSON file generated by DCS mutations to tags/reads"/>
34 <param name="file4" type="data" format="json" label="JSON File with SSCS tag stats" optional="false" help="JSON file generated by DCS mutations to SSCS stats."/> 34 <param name="file4" type="data" format="json" label="JSON File with SSCS tag stats" optional="false" help="JSON file generated by DCS mutations to SSCS stats."/>
35 <param name="thresh" type="integer" label="Tag count threshold" value="0" help="Integer threshold for displaying mutations. Only mutations occuring in DCS of less than thresh tags are displayed. Default of 0 displays all."/> 35 <param name="thresh" type="integer" label="Tag count threshold" value="0" help="Integer threshold for displaying mutations. Only mutations occurring in DCS of less than thresh tags are displayed. Default of 0 displays all."/>
36 <param name="phred" type="integer" label="Phred quality score threshold" min="0" max="41" value="20" help="Integer threshold for Phred quality score. Only reads higher than this threshold are considered. Default = 20."/> 36 <param name="phred" type="integer" label="Phred quality score threshold" min="0" max="41" value="20" help="Integer threshold for Phred quality score. Only reads higher than this threshold is considered. Default = 20."/>
37 <param name="trim" type="integer" label="Trimming threshold" value="10" help="Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10."/> 37 <param name="trim" type="integer" label="Trimming threshold" value="10" help="Integer threshold for assigning mutations at start and end of reads to lower tier. Default 10."/>
38 <param name="chimera_correction" type="boolean" label="Apply chimera correction?" truevalue="--chimera_correction" falsevalue="" checked="False" help="Count chimeric variants and correct the variant frequencies."/> 38 <param name="chimera_correction" type="boolean" label="Apply chimera correction?" truevalue="--chimera_correction" falsevalue="" checked="False" help="Count chimeric variants and correct the variant frequencies."/>
39 <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"/> 39 <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"/>
40 <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."/> 40 <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."/>
41 </inputs> 41 </inputs>
55 <param name="phred" value="20"/> 55 <param name="phred" value="20"/>
56 <param name="trim" value="10"/> 56 <param name="trim" value="10"/>
57 <param name="chimera_correction"/> 57 <param name="chimera_correction"/>
58 <param name="softclipping_dist" value="15"/> 58 <param name="softclipping_dist" value="15"/>
59 <param name="reads_threshold" value="1.0"/> 59 <param name="reads_threshold" value="1.0"/>
60 <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/> 60 <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true"/>
61 <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true" lines_diff="10"/> 61 <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true"/>
62 <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/> 62 <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true"/>
63 <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/> 63 <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true"/>
64 </test> 64 </test>
65 </tests> 65 </tests>
66 <help> <![CDATA[ 66 <help> <![CDATA[
67 **What it does** 67 **What it does**
68 68
71 as input and calculates frequencies and stats for DCS mutations based on information 71 as input and calculates frequencies and stats for DCS mutations based on information
72 from the raw reads. 72 from the raw reads.
73 73
74 **Input** 74 **Input**
75 75
76 **Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 76 **Dataset 1:** VCF file with duplex consensus sequence (DCS) mutations. E.g.
77 generated by the `FreeBayes <https://arxiv.org/abs/1207.3907>`_ or `LoFreq <https://academic.oup.com/nar/article/40/22/11189/1152727>`_ variant caller. 77 generated by the `FreeBayes <https://arxiv.org/abs/1207.3907>`_ or `LoFreq <https://academic.oup.com/nar/article/40/22/11189/1152727>`_ variant caller.
78 78
79 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 79 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the
80 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_. 80 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.
81 81
82 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool 82 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool
83 containing dictonaries of the tags of reads containing mutations 83 containing dictionaries of the tags of reads containing mutations
84 in the DCS. 84 in the DCS.
85 85
86 **Dataset 4:** JSON file generated by the **DCS mutations to SSCS stats** tool 86 **Dataset 4:** JSON file generated by the **DCS mutations to SSCS stats** tool
87 stats of tags that carry a mutation in the SSCS at the same position a mutation 87 stats of tags that carry a mutation and the reference allele in the SSCS at the same position a mutation
88 is called in the DCS. 88 is called in the DCS.
89 89
90 **Output** 90 **Output**
91 91
92 The output are three XLSX files containing frequencies stats for DCS mutations based 92 The output is three XLSX files containing frequencies stats for DCS mutations based
93 on information from the raw reads and a CSV file containing the summary information without color-coding. In addition to that a tier based 93 on information from the raw reads and a CSV file containing the summary information without color-coding. In addition to that, a tier-based
94 classification is provided based on the amout of support for a true variant call. 94 classification is provided based on the amount of support for a true variant call.
95 95
96 96
97 ]]> 97 ]]>
98 </help> 98 </help>
99 <expand macro="citation" /> 99 <expand macro="citation" />