comparison read_duplication.xml @ 51:09846d5169fa draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit 37fb1988971807c6a072e1afd98eeea02329ee83

50:f242ee103277

<tool id="rseqc_read_duplication" name="Read Duplication" version="2.4galaxy1">
    <description>determines reads duplication rate with sequence-based and mapping-based strategies</description>

    <macros>
        <import>rseqc_macros.xml</import>
    </macros>

    <requirements>
        <expand macro="requirement_package_r" />
        <expand macro="requirement_package_numpy" />
        <expand macro="requirement_package_rseqc" />
    </requirements>

    <expand macro="stdio" />

    <version_command><![CDATA[read_duplication.py --version]]></version_command>

    <command><![CDATA[
        read_duplication.py -i $input -o output -u $upLimit
        ]]>
    </command>

    <inputs>
        <param name="input" type="data" format="bam,sam" label="input bam/sam file" help="(--input-file)"/>
        <param name="upLimit" type="integer" label="Upper Limit of Plotted Duplicated Times (default=500)" value="500" help="(--up-limit)"/>
    </inputs>

    <outputs>
        <data format="xls" name="outputxls" from_work_dir="output.pos.DupRate.xls" label="${tool.name} on ${on_string} (Position XLS)"/>
        <data format="xls" name="outputseqxls" from_work_dir="output.seq.DupRate.xls" label="${tool.name} on ${on_string} (Sequence XLS)"/>
        <data format="txt" name="outputr" from_work_dir="output.DupRate_plot.r" label="${tool.name} on ${on_string} (R Script)" />
        <data format="pdf" name="outputpdf" from_work_dir="output.DupRate_plot.pdf" label="${tool.name} on ${on_string} (PDF)" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            <output name="outputxls" file="output.pos.DupRate.xls"/>
            <output name="outputseqxls" file="output.seq.DupRate.xls"/>
            <output name="outputr" file="output.DupRate_plot.r"/>
        </test>
    </tests>

    <help><![CDATA[
read_duplication.py

1. output.dup.pos.DupRate.xls: Read duplication rate determined from mapping position of read. First column is "occurrence" or duplication times, second column is number of uniquely mapped reads.
2. output.dup.seq.DupRate.xls: Read duplication rate determined from sequence of read. First column is "occurrence" or duplication times, second column is number of uniquely mapped reads.
3. output.DupRate_plot.r: R script to generate pdf file
4. output.DupRate_plot.pdf: graphical output generated from R script

.. image:: http://rseqc.sourceforge.net/_images/duplicate.png
   :height: 600 px
   :width: 600 px
   :scale: 80 %

-----

About RSeQC
+++++++++++

The RSeQC_ package provides a number of useful modules that can comprehensively evaluate high throughput sequence data especially RNA-seq data. "Basic modules" quickly inspect sequence quality, nucleotide composition bias, PCR bias and GC bias, while "RNA-seq specific modules" investigate sequencing saturation status of both splicing junction detection and expression estimation, mapped reads clipping profile, mapped reads distribution, coverage uniformity over gene body, reproducibility, strand specificity and splice junction annotation.

The RSeQC package is licensed under the GNU GPL v3 license.

.. image:: http://rseqc.sourceforge.net/_static/logo.png

.. _RSeQC: http://rseqc.sourceforge.net/
]]>
    </help>

    <expand macro="citations" />

51:09846d5169fa

<tool id="rseqc_read_duplication" name="Read Duplication" version="@WRAPPER_VERSION@">
    <description>determines reads duplication rate with sequence-based and mapping-based strategies</description>

    <macros>
        <import>rseqc_macros.xml</import>
    </macros>

    <expand macro="requirements" />

    <expand macro="stdio" />

    <version_command><![CDATA[read_duplication.py --version]]></version_command>

    <command><![CDATA[
        read_duplication.py -i '${input}' -o output -u ${upLimit} -q ${mapq}
        ]]>
    </command>

    <inputs>
        <expand macro="bam_sam_param" />
        <param name="upLimit" type="integer" label="Upper Limit of Plotted Duplicated Times (default=500)" value="500" help="(--up-limit)"/>
        <expand macro="mapq_param" />
        <expand macro="rscript_output_param" />
    </inputs>

    <outputs>
        <expand macro="pdf_output_data" filename="output.DupRate_plot.pdf" />
        <data format="xls" name="outputxls" from_work_dir="output.pos.DupRate.xls" label="${tool.name} on ${on_string} (Position xls)"/>
        <data format="xls" name="outputseqxls" from_work_dir="output.seq.DupRate.xls" label="${tool.name} on ${on_string} (Sequence xls)"/>
        <expand macro="rscript_output_data" filename="output.DupRate_plot.r" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
            <param name="rscript_output" value="true" />
            <output name="outputxls" file="output.pos.DupRate.xls" />
            <output name="outputseqxls" file="output.seq.DupRate.xls" />
            <output name="outputr" file="output.DupRate_plot.r" />
            <output name="outputpdf" file="output.DupRate_plot.pdf" compare="sim_size" />
        </test>
    </tests>

    <help><![CDATA[
read_duplication.py

1. output.dup.pos.DupRate.xls: Read duplication rate determined from mapping position of read. First column is "occurrence" or duplication times, second column is number of uniquely mapped reads.
2. output.dup.seq.DupRate.xls: Read duplication rate determined from sequence of read. First column is "occurrence" or duplication times, second column is number of uniquely mapped reads.
3. output.DupRate_plot.r: R script to generate pdf file
4. output.DupRate_plot.pdf: graphical output generated from R script

.. image:: $PATH_TO_IMAGES/duplicate.png
   :height: 600 px
   :width: 600 px
   :scale: 80 %

@ABOUT@

]]>
    </help>

    <expand macro="citations" />