comparison read2mut.xml @ 6:11a2a34f8a2b draft

planemo upload for repository https://github.com/gpovysil/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8
author mheinzl
date Mon, 18 Jan 2021 09:49:15 +0000
parents 386438cd4c3b
children 84a1a3f70407
comparison
equal deleted inserted replaced
5:d9cbf833624e 6:11a2a34f8a2b
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="1.0.5" profile="19.01"> 2 <tool id="read2mut" name="Call specific mutations in reads:" version="2.1.0" 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 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 <requirements>
8 <requirement type="package" version="2.7">python</requirement>
9 <requirement type="package" version="1.4.0">matplotlib</requirement>
10 <requirement type="package" version="0.15">pysam</requirement>
8 <requirement type="package" version="1.1.0">xlsxwriter</requirement> 11 <requirement type="package" version="1.1.0">xlsxwriter</requirement>
9 </expand> 12 <requirement type="package" version="0.11.6">cyvcf2</requirement>
13 </requirements>
10 <command><![CDATA[ 14 <command><![CDATA[
11 ln -s '$file2' bam_input.bam && 15 ln -s '$file2' bam_input.bam &&
12 ln -s '${file2.metadata.bam_index}' bam_input.bam.bai && 16 ln -s '${file2.metadata.bam_index}' bam_input.bam.bai &&
13 python '$__tool_directory__/read2mut.py' 17 python '$__tool_directory__/read2mut.py'
14 --mutFile '$file1' 18 --mutFile '$file1'
17 --sscsJson '$file4' 21 --sscsJson '$file4'
18 --thresh '$thresh' 22 --thresh '$thresh'
19 --phred '$phred' 23 --phred '$phred'
20 --trim '$trim' 24 --trim '$trim'
21 $chimera_correction 25 $chimera_correction
26 --softclipping_dist '$softclipping_dist'
27 --reads_threshold '$reads_threshold'
22 --outputFile '$output_xlsx' 28 --outputFile '$output_xlsx'
29 --outputFile2 '$output_xlsx2'
30 --outputFile3 '$output_xlsx3'
23 ]]> 31 ]]>
24 </command> 32 </command>
25 <inputs> 33 <inputs>
26 <param name="file1" type="data" format="tabular" label="DCS Mutation File" optional="false" help="TABULAR file with DCS mutations. See Help section below for a detailed explanation."/> 34 <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."/>
27 <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."/> 35 <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."/>
28 <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"/> 36 <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"/>
29 <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."/> 37 <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."/>
30 <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."/> 38 <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."/>
31 <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."/> 39 <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."/>
32 <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."/> 40 <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."/>
33 <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."/> 41 <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."/>
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="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."/>
34 </inputs> 44 </inputs>
35 <outputs> 45 <outputs>
36 <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX"/> 46 <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/>
47 <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/>
48 <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/>
37 </outputs> 49 </outputs>
38 <tests> 50 <tests>
39 <test> 51 <test>
40 <param name="file1" value="DCS_Mutations_test_data_VA.tabular"/> 52 <param name="file1" value="FreeBayes_test.vcf"/>
41 <param name="file2" value="Interesting_Reads_test_data_VA.trim.bam"/> 53 <param name="file2" value="Interesting_Reads_test.trim.bam"/>
42 <param name="file3" value="tag_count_dict_test_data_VA.json"/> 54 <param name="file3" value="tag_count_dict_test.json"/>
43 <param name="file4" value="SSCS_counts_test_data_VA.json"/> 55 <param name="file4" value="SSCS_counts_test.json"/>
44 <param name="thresh" value="0"/> 56 <param name="thresh" value="0"/>
45 <param name="phred" value="20"/> 57 <param name="phred" value="20"/>
46 <param name="trim" value="10"/> 58 <param name="trim" value="10"/>
47 <param name="chimera_correction" value="False"/> 59 <param name="chimera_correction"/>
48 <output name="output_xlsx" file="mutant_reads_summary_short_trim_test_data_VA.xlsx" decompress="true" lines_diff="10"/> 60 <param name="softclipping_dist" value="15"/>
61 <param name="reads_threshold" value="1.0"/>
62 <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/>
63 <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"/>
49 </test> 65 </test>
50 </tests> 66 </tests>
51 <help> <![CDATA[ 67 <help> <![CDATA[
52 **What it does** 68 **What it does**
53 69
54 Takes a tabular file with mutations, a BAM file of aligned raw reads, and JSON files 70 Takes a VCF file with mutations, a BAM file of aligned raw reads, and JSON files
55 created by the tools **DCS mutations to tags/reads** and **DCS mutations to SSCS stats** 71 created by the tools **DCS mutations to tags/reads** and **DCS mutations to SSCS stats**
56 as input and calculates frequencies and stats for DCS mutations based on information 72 as input and calculates frequencies and stats for DCS mutations based on information
57 from the raw reads. 73 from the raw reads.
58 74
59 **Input** 75 **Input**
60 76
61 **Dataset 1:** Tabular file with duplex consesus sequence (DCS) mutations as 77 **Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g.
62 generated by the **Variant Annotator** tool. 78 generated by the `FreeBayes variant caller <https://arxiv.org/abs/1207.3907>`_.
63 79
64 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 80 **Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the
65 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_. 81 tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.
66 82
67 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool 83 **Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool
72 stats of tags that carry a mutation in the SSCS at the same position a mutation 88 stats of tags that carry a mutation in the SSCS at the same position a mutation
73 is called in the DCS. 89 is called in the DCS.
74 90
75 **Output** 91 **Output**
76 92
77 The output is an XLSX file containing frequencies stats for DCS mutations based 93 The output are three XLSX files containing frequencies stats for DCS mutations based
78 on information from the raw reads. In addition to that a tier based 94 on information from the raw reads. In addition to that a tier based
79 classification is provided based on the amout of support for a true variant call. 95 classification is provided based on the amout of support for a true variant call.
80 96
81 ]]> 97 ]]>
82 </help> 98 </help>