annotate small_rna_maps.xml @ 12:d33263e6e812 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_maps commit b0676fd329c2ca50002f9f2fede531d8e550569f

<tool id="small_rna_maps" name="small_rna_maps" version="2.5.0">
  <description></description>
  <requirements>
        <requirement type="package" version="1.11.2=py27_0">numpy</requirement>
        <requirement type="package" version="0.11.2.1=py27_0">pysam</requirement>
        <requirement type="package" version="1.3.2=r3.3.2_0">r-optparse</requirement>
        <requirement type="package" version="0.6_28=r3.3.2_0">r-latticeextra</requirement>
        <requirement type="package" version="2.2.1=r3.3.2_0">r-gridextra</requirement>
        <requirement type="package" version="1.4.2=r3.3.2_0">r-reshape2</requirement>
        
  </requirements>
  <stdio>
      <exit_code range="1:" level="fatal" description="Tool exception" />
  </stdio>
  <command detect_errors="exit_code"><![CDATA[
      #if $inputs_cond.normalize == "no":
          #for $file in $inputs_cond.inputs
              samtools index '$file';
          #end for
          python '$__tool_directory__'/small_rna_maps.py 
              --inputs
          #for $file in $inputs_cond.inputs
              '$file'
          #end for
              --sample_names
          #for $sample in $inputs_cond.inputs
              '$sample.name'
          #end for
      #else if $inputs_cond.normalize == "yes":
          #for $file in $inputs_cond.series
              samtools index '$file.inputs';
          #end for
          python '$__tool_directory__'/small_rna_maps.py 
              --inputs
          #for $file in $inputs_cond.series
              '$file.inputs'
          #end for
              --sample_names
          #for $sample in $inputs_cond.series
              '$sample.inputs.name'
          #end for
      #end if
          --minsize $minsize
          --maxsize $maxsize
          --cluster $cluster
      #if str($plots_options.plots_options_selector ) == "two_plot":
          --plot_methods '${plots_options.first_plot}' '${plots_options.extra_plot}'
          --outputs '$output_tab' '$extra_output_tab';
      #elif str($plots_options.plots_options_selector ) == "global":
          --plot_methods 'Size'
          --outputs '$output_tab';
      #else:
          --plot_methods '${plots_options.first_plot}'
          --outputs '$output_tab' ;
      #end if
      Rscript '$__tool_directory__'/small_rna_maps.r
          --first_dataframe '$output_tab' 
          --extra_dataframe '$extra_output_tab'
          --normalization 
          #if $inputs_cond.normalize == "no":
              ''
          #else if $inputs_cond.normalize == "yes":
              #set $norm = ""
              #for $file in $inputs_cond.series
                     #set $norm += str($file.normalization)+' '
              #end for
              #set $norm = $norm[:-1]
              '$norm'
          #end if
          #if $ylimits_cond.ylimits == "no":
              --ymin '' --ymax ''
          #else:
              --ymin '${ylimits_cond.ymin}' --ymax '${ylimits_cond.ymax}'
          #end if
          #if str($plots_options.plots_options_selector ) == "two_plot":
              --first_plot_method '${plots_options.first_plot}'
              --extra_plot_method '${plots_options.extra_plot}'
          #elif str($plots_options.plots_options_selector ) == "global":
              --first_plot_method 'Size'
              --extra_plot_method ''
              --global '${plots_options.mergestrands}'
          #else:
              --first_plot_method '${plots_options.first_plot}'
              --extra_plot_method ''
          #end if
              --output_pdf '$output_pdf'
  ]]></command>
 <inputs>
    <conditional name="inputs_cond">
        <param name="normalize" type="boolean" label="Will there be normalization?" truevalue="yes" falsevalue="no" checked="false"/>
        <when value="no">
            <param name="inputs" type="data" format="bam" label="Select multiple alignments to parse" multiple="True"/>
        </when>
        <when value="yes">
            <repeat name="series" title="Normalization factors" min="1">
                <param name="inputs" type="data" format="bam" label="Select multiple alignments to parse" />
                <param name="normalization" type="float" label="Enter size/normalization factors."
                       help="e.g. '0.75' '1.23'" value="1.0"/>
            </repeat>
        </when>
    </conditional>
    <param name="minsize" type="integer" label="Minimal size of reads for inclusion in analysis"
           value="0" help="default value: 0" />
    <param name="maxsize" type="integer" label="Maximal size of reads for inclusion in analysis"
           value="10000" help="default value: 10000" />
    <param name="cluster" type="integer" label="Aggregation distance in nucleotides"
           value="0" help="If not 0, sets the distance (in nt) below which data are clustered to a single median position" />
    <conditional name="plots_options">
        <param name="plots_options_selector" type="select" display="radio" label="Plot Options">
            <option value="one_plot">Just one plot per chromosome</option>
            <option value="two_plot" selected="True">Two plots per chromosome</option>
            <option value="global">Global read size distributions of aligned reads</option> 
        </param>
        <when value="two_plot">
            <param name="first_plot" type="select" display="radio" label="Select the type of the top plot">
                <option value="Counts">Counts</option> 
                <option value="Coverage">Coverage</option> 
                <option value="Mean">Mean Sizes</option> 
                <option value="Median">Median Sizes</option>
                <option value="Size">Size Distributions</option>
            </param>
            <param name="extra_plot" type="select" display="radio" label="Select the type of the bottom plot">
                <option value="Counts">Counts</option> 
                <option value="Coverage">Coverage</option> 
                <option value="Mean">Mean Sizes</option> 
                <option value="Median">Median Sizes</option>
                <option value="Size">Size Distributions</option>
            </param>
        </when>
        <when value="one_plot">
            <param name="first_plot" type="select" display="radio" label="select the type of plot">
                <option value="Counts">Counts</option> 
                <option value="Coverage">Coverage</option> 
                <option value="Mean">Mean Sizes</option> 
                <option value="Median">Median Sizes</option>
                <option value="Size">Size Distributions</option>
            </param>
        </when>
        <when value="global">
            <param name="first_plot" type="hidden" value="Size"/>
            <param name="mergestrands" type="select" display="radio" label="Whether forward and reverse aligned reads should be merged or not in the histogram">
                <option value="nomerge">Do not merge</option>
                <option value="merge">Merge forward and reverse reads</option>
            </param>
        </when>
    </conditional>
    <conditional name="ylimits_cond">
        <param name="ylimits" type="boolean" truevalue="yes" falsevalue="no" checked="false" label="Do you wish to set an y axis limit to the plots?"
               help="This limit won't be applied to size distribution plots"/>
        <when value="yes">
            <param name="ymin" type="float" label="Enter minimum value" value="0.0" help="e.g. '-5.0'"/>
            <param name="ymax" type="float" label="Enter maximum value" value="0.0" help="e.g. '5.0'"/>
        </when>
        <when value="no">
        </when>
    </conditional>
 </inputs>

 <outputs>
    <data format="tabular" name="output_tab" label="$plots_options.first_plot dataframe" />
    <data format="tabular" name="extra_output_tab" label="$plots_options.extra_plot dataframe">
        <filter>plots_options['plots_options_selector'] == 'two_plot'</filter>
    </data> 
    <data format="pdf" name="output_pdf" label="small RNA maps" />
</outputs>

    <tests>
        <test>
            <param name="inputs" value="input1.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="ylimits" value="yes" />
            <param name="ymin" value="-5" />
            <param name="ymax" value="5" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Counts" />
            <output file="input1_counts_yminneg5_5.tab" name="output_tab" />
            <output file="input1_yminneg5_5_single_plot_counts.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="5" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Coverage" />
            <output file="input1_coverage_cluster5.tab" name="output_tab" />
            <output file="input1_cluster5_single_plot_coverage.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam" ftype="bam"/>
            <param name="minsize" value="20" />
            <param name="maxsize" value="30" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Size" />
            <output file="input1_min20_max30_size.tab" name="output_tab" />
            <output file="input1_min20_max30_single_plot_size.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Mean" />
            <output file="input1_mean.tab" name="output_tab" />
            <output file="input1__single_plot_mean.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Median" />
            <output file="input1_median.tab" name="output_tab" />
            <output file="input1_single_plot_median.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="normalize" value="yes" />
            <repeat name="series">
                <param name="inputs" value="input1.bam" ftype="bam" />
                <param name="normalization" value="1.0" />
            </repeat>
            <repeat name="series">
                <param name="inputs" value="input2.bam" ftype="bam" />
                <param name="normalization" value="2.0" />
            </repeat>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Counts" />
            <output file="input1_input2_norm_1_2_counts.tab" name="output_tab" />
            <output file="input1_input2_norm_1_2_single_plot_counts.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="ylimits" value="yes" />
            <param name="ymin" value="-5" />
            <param name="ymax" value="5" />
            <param name="plots_options_selector" value="two_plot" />
            <param name="first_plot" value="Counts" />
            <param name="extra_plot" value="Size" />
            <output file="input1_input2_counts.tab" name="output_tab" />
            <output file="input1_input2_size.tab" name="extra_output_tab" />
            <output file="input1_input2_double_plot_counts_size_ylimneg5_5.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input_single_chr.bam,input_single_chr.bam,input_single_chr.bam,input_single_chr.bam,input_single_chr.bam,input_single_chr.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Coverage" />
            <output file="input_single_chr_x_6_single_plot_coverage.tab" name="output_tab" />
            <output file="input_single_chr_x_6_single_plot_coverage.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="global" />
            <param name="mergestrands" value="nomerge" />
            <param name="first_plot" value="Size" />
            <param name="normalization" value="1 1" />
            <output file="size.tab" name="output_tab" />
            <output file="global_nomerge.pdf" name="output_pdf" />
        </test>
        <test>
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam"/>
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="cluster" value="0" />
            <param name="plots_options_selector" value="global" />
            <param name="mergestrands" value="merge" />
            <param name="first_plot" value="Size" />
            <param name="normalization" value="1 1" />
            <output file="size.tab" name="output_tab" />
            <output file="global_merge.pdf" name="output_pdf" />
        </test>
    </tests>
<help>

**What it does**

Plots mapping statistics of an alignment along the reference chromosomes :

 - counts
 - mean sizes
 - median sizes
 - coverage depth
 - size distribution

Read counts, mean sizes and median sizes are computed by counting the number of 5' end of reads
in each position of a chromosome reference.
Coverage depths are computed from the input bam alignment files using the python pysam module.

The metrics mentioned above can be plotted either separately:

.. image:: one_plot.png

Or in all possible pairwise combinations:

.. image:: two_plot.png

For comparison purposes, values from bam alignment files can be normalized by a size factor
before plotting.

**Inputs**

bam alignment files that must be

  - single-read
  - sorted
  - mapped to the same reference

**Output**

A pdf file generated by the R package lattice and one or two dataframes used to plot the data.

</help>

<citations>
    <citation type="doi">10.1093/bioinformatics/btp352</citation>
     <citation type="bibtex">@Book{,
    title = {Lattice: Multivariate Data Visualization with R},
    author = {Deepayan Sarkar},
    publisher = {Springer},
    address = {New York},
    year = {2008},
    note = {ISBN 978-0-387-75968-5},
    url = {http://lmdvr.r-forge.r-project.org},
  }</citation>
</citations>
</tool>