comparison read2mut.xml @ 55:8fbe6aba07e5 draft

planemo upload for repository https://github.com/Single-Molecule-Genetics/VariantAnalyzerGalaxy/tree/master/tools/variant_analyzer commit ee4a8e6cf290e6c8a4d55f9cd2839d60ab3b11c8

54:95c27bcb1b7a

<?xml version="1.0" encoding="UTF-8"?>
<tool id="read2mut" name="Call specific mutations in reads:" version="2.1.0" profile="19.01">
    <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description>
    <macros>
        <import>va_macros.xml</import>
    </macros>
    <requirements>

        --trim '$trim'
        $chimera_correction
        --softclipping_dist '$softclipping_dist'
        --reads_threshold '$reads_threshold'
        --outputFile '$output_xlsx'
        --outputFile2 '$output_xlsx2'
        --outputFile3 '$output_xlsx3'
    ]]>
    </command>
    <inputs>

        <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"/>
<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."/>
    </inputs>
    <outputs>
        <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/>
        <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/>
        <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/>
    </outputs>
    <tests>
        <test>

            <param name="trim" value="10"/>
            <param name="chimera_correction"/>
            <param name="softclipping_dist" value="15"/>
            <param name="reads_threshold" value="1.0"/>
            <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/>
            <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/>
            <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/>
        </test>
    </tests>
    <help> <![CDATA[

from the raw reads.

**Input** 

**Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 
generated by the `FreeBayes variant caller <https://arxiv.org/abs/1207.3907>`_.

**Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 
tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.

**Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool 

is called in the DCS.

**Output**

The output are three XLSX files containing frequencies stats for DCS mutations based 
on information from the raw reads. In addition to that a tier based 
classification is provided based on the amout of support for a true variant call.

    ]]> 
    </help>
    <expand macro="citation" />
</tool>

55:8fbe6aba07e5

<?xml version="1.0" encoding="UTF-8"?>
<tool id="read2mut" name="Call specific mutations in reads:" version="2.1.1" profile="19.01">
    <description>Looks for reads with mutation at known positions and calculates frequencies and stats.</description>
    <macros>
        <import>va_macros.xml</import>
    </macros>
    <requirements>

        --trim '$trim'
        $chimera_correction
        --softclipping_dist '$softclipping_dist'
        --reads_threshold '$reads_threshold'
        --outputFile '$output_xlsx'
        --outputFile_csv '$outputFile_csv'
        --outputFile2 '$output_xlsx2'
        --outputFile3 '$output_xlsx3'
    ]]>
    </command>
    <inputs>

        <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"/>
<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."/>
    </inputs>
    <outputs>
        <data name="output_xlsx" format="xlsx" label="${tool.name} on ${on_string}: XLSX summary"/>
        <data name="outputFile_csv" format="csv" label="${tool.name} on ${on_string}: CSV summary"/>
        <data name="output_xlsx2" format="xlsx" label="${tool.name} on ${on_string}: XLSX allele frequencies"/>
        <data name="output_xlsx3" format="xlsx" label="${tool.name} on ${on_string}: XLSX tiers"/>
    </outputs>
    <tests>
        <test>

            <param name="trim" value="10"/>
            <param name="chimera_correction"/>
            <param name="softclipping_dist" value="15"/>
            <param name="reads_threshold" value="1.0"/>
            <output name="output_xlsx" file="Variant_Analyzer_summary_test.xlsx" decompress="true" lines_diff="10"/>
            <output name="outputFile_csv" file="Variant_Analyzer_summary_test.csv" decompress="true" lines_diff="10"/>
            <output name="output_xlsx2" file="Variant_Analyzer_allele_frequencies_test.xlsx" decompress="true" lines_diff="10"/>
            <output name="output_xlsx3" file="Variant_Analyzer_tiers_test.xlsx" decompress="true" lines_diff="10"/>
        </test>
    </tests>
    <help> <![CDATA[

from the raw reads.

**Input** 

**Dataset 1:** VCF file with duplex consesus sequence (DCS) mutations. E.g. 
generated by the `FreeBayes <https://arxiv.org/abs/1207.3907>`_ or `LoFreq <https://academic.oup.com/nar/article/40/22/11189/1152727>`_ variant caller.

**Dataset 2:** BAM file of aligned raw reads. This file can be obtained by the 
tool `Map with BWA-MEM <https://arxiv.org/abs/1303.3997>`_.

**Dataset 3:** JSON file generated by the **DCS mutations to tags/reads** tool 

is called in the DCS.

**Output**

The output are three XLSX files containing frequencies stats for DCS mutations based 
on information from the raw reads and a CSV file containing the summary information without color-coding. In addition to that a tier based 
classification is provided based on the amout of support for a true variant call.


    ]]> 
    </help>
    <expand macro="citation" />
</tool>