<tool id="rseqc_geneBody_coverage" name="Gene Body Converage (BAM)" version="@WRAPPER_VERSION@">
  <description>
    Read coverage over gene body.
  </description>

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

    <expand macro="requirements" />

  <expand macro="stdio" />

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

  <command><![CDATA[
    #import re
    #set $input_list = []
    #for $i, $input in enumerate($inputs):
        #set $safename = re.sub('[^\w\-_]', '_', $input.element_identifier)
        #if $safename in $input_list:
            #set $safename = str($safename) + "." + str($i)
        #end if
        $input_list.append($safename)
        ln -sf '${input}' '${safename}.bam' &&
        ln -sf '${input.metadata.bam_index}' '${safename}.bam.bai' &&
        echo '${safename}.bam' >> 'input_list.txt' &&
    #end for
    geneBody_coverage.py -i 'input_list.txt' -r '${refgene}' --minimum_length ${minimum_length} -o output
    ]]>
  </command>

  <inputs>
    <param name="inputs" type="data" label="Input .bam file(s)" format="bam" help="(--input-file)" multiple="true"/>
    <expand macro="refgene_param" />
    <param name="minimum_length" type="integer" value="100" label="Minimum mRNA length (default: 100)" help="Minimum mRNA length in bp, mRNA that are shorter than this value will be skipped (--minimum_length)." />
    <expand macro="rscript_output_param" />
  </inputs>

  <outputs>
    <data name="outputcurvespdf" format="pdf" from_work_dir="output.geneBodyCoverage.curves.pdf" label="${tool.name} on ${on_string} (Curves pdf)" />
    <data name="outputheatmappdf" format="pdf" from_work_dir="output.geneBodyCoverage.heatMap.pdf" label="${tool.name} on ${on_string} (HeatMap pdf)">
      <filter>len(inputs) >= 3</filter>
    </data>
    <expand macro="rscript_output_data" filename="output.geneBodyCoverage.r" />
    <data name="outputtxt" format="txt" from_work_dir="output.geneBodyCoverage.txt" label="${tool.name} on ${on_string} (text)" />
  </outputs>

  <!-- PDF Files contain R version, must avoid checking for diff -->
  <tests>
    <test>
      <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
      <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" />
      <param name="rscript_output" value="true" />
      <output name="outputcurvespdf" file="output.geneBodyCoverage.curves.pdf" compare="sim_size" />
      <output name="outputr" file="output.geneBodyCoverage.r" />
      <output name="outputtxt" file="output.geneBodyCoverage.txt" />
    </test>
    <test>
      <param name="inputs" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam,pairend_strandspecific_51mer_hg19_chr1_1-100000.bam" />
      <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" />
      <param name="rscript_output" value="true" />
      <output name="outputcurvespdf" file="output2.geneBodyCoverage.curves.pdf" compare="sim_size" />
      <output name="outputheatmappdf" file="output2.geneBodyCoverage.heatMap.pdf" compare="sim_size" />
      <output name="outputr" file="output2.geneBodyCoverage.r" />
      <output name="outputtxt" file="output2.geneBodyCoverage.txt" />
    </test>

  </tests>

  <help><![CDATA[
## geneBody_coverage.py

Read coverage over gene body. This module is used to check if read coverage is uniform and if there is any 5\'/3\' bias. This module scales all transcripts to 100 nt and calculates the number of reads covering each nucleotide position. Finally, it generates plots illustrating the coverage profile along the gene body.

If 3 or more BAM files were provided. This program generates a lineGraph and a heatmap. If fewer than 3 BAM files were provided, only lineGraph is generated. See below for examples.

When heatmap is generated, samples are ranked by the "skewness" of the coverage: Sample with best (worst) coverage will be displayed at the top (bottom) of the heatmap.
Coverage skewness was measured by `Pearson’s skewness coefficients <http://en.wikipedia.org/wiki/Skewness#Pearson.27s_skewness_coefficients>`_

.. image:: $PATH_TO_IMAGES/geneBody_workflow.png
:width: 800 px
:scale: 80 %


## Inputs

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

Reference gene model
    Gene Model in BED format.

Minimum mRNA length
    Minimum mRNA length (bp). mRNA that are shorter than this value will be skipped (default is 100).

    ## Outputs

Text
    Table that includes the data used to generate the plots

R Script
    R script file that reads the data and generates the plot

PDF
    The final plot, in PDF format

Example plots:
.. image:: $PATH_TO_IMAGES/Aug_26.geneBodyCoverage.curves.png
:height: 600 px
:width: 600 px
:scale: 80 %

.. image:: $PATH_TO_IMAGES/Aug_26.geneBodyCoverage.heatMap.png
:height: 600 px
:width: 600 px
:scale: 80 %

@ABOUT@

    ]]>
  </help>

  <expand macro="citations" />

</tool>