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

Two strategies were used to determine reads duplication rate:

* Sequence based: reads with exactly the same sequence content are regarded as duplicated reads.
* Mapping based: reads mapped to the same genomic location are regarded as duplicated reads. For splice reads, reads mapped to the same starting position and splice the same way are regarded as duplicated reads.

Inputs
++++++++++++++

Input BAM/SAM file
    Alignment file in BAM/SAM format.

Upper Limit of Plotted Duplicated Times (default=500)
    Only used for plotting.

Output
++++++++++++++

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" />

</tool>