annotate small_rna_maps.xml @ 24:e75a10eba0a6 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_maps commit 0293b0f9b07302ba0b71e7877be1ea7a7ed04718

<tool id="small_rna_maps" name="small_rna_maps" version="2.12.0">
  <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>
        <requirement type="package" version="0.6.6">sambamba</requirement>
  </requirements>
  <stdio>
      <exit_code range="1:" level="fatal" description="Tool exception" />
  </stdio>
  <command detect_errors="exit_code"><![CDATA[
          #import json
          #import os
          #for $file in $inputs
              sambamba view -t \${GALAXY_SLOTS} -F "not unmapped and sequence_length >= ${minsize} and sequence_length <= ${maxsize}" -f bam '$file' -o '$file.element_identifier' &&
              samtools index '$file.element_identifier' &&
          #end for
          python '$__tool_directory__'/small_rna_maps.py
              --inputs ${ ' '.join(['"%s"' % x.element_identifier for x in $inputs]) }
              #set $labels = list()
              #for $file in $inputs:
                  $labels.append(str($file.element_identifier))
              #end for
              --sample_names ${ ' '.join(['"%s"' % x for x in $labels]) }
              --minsize $minsize
              --maxsize $maxsize
              #if str($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' &&
              #elif str($plots_options.plots_options_selector ) == "cluster":
                  --plot_methods 'Counts'
                  --outputs '$output_tab'
                  --cluster ${plots_options.cluster}
                  --bed '$output_bed'
                  --bed_skipsize ${plots_options.skip_size}
                  --bed_skipcounts ${plots_options.skip_counts}
                  --bed_skipdensity ${plots_options.skip_density}
                  ${plots_options.strandness} &&
              #else:
                  --plot_methods '${plots_options.first_plot}'
                  --outputs '$output_tab' &&
              #end if
              

          Rscript '$__tool_directory__'/small_rna_maps.r
              --first_dataframe '$output_tab'
              --extra_dataframe '$extra_output_tab'
              #if len(str($normalization)) != 1:
              --normalization "${ ' '.join( [factor for factor in $normalization.split()]) }"
              #else:
              --normalization "${ ' '.join( ["1" for factor in $inputs] )}"
              #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>
    <param name="inputs" type="data" format="bam" label="Select a alignment files to parse" multiple="true"
           help="maps from these bam inputs will be collected in a single pdf output" />
    <param name="normalization" type="text" label="Enter a size/normalization factor."
        help="Enter normalisation factors separated by space eg [0.75 1.23 1.1], no normalization if no values" value="1"/>
    <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" />
    <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>
            <option value="cluster">Map read clusters</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>
        <when value="cluster">
            <param name="first_plot" type="hidden" value="Counts"/>
            <param name="cluster" type="integer" label="Clustering distance in nucleotides" value="1"
                   help="Sets the distance (in nt) below which reads are clustered to a single median position" />
            <param name="strandness" argument="--nostrand" type="boolean" truevalue="--nostrand" falsevalue="" checked="false"
                   label="Ignore polarity of reads ?" help="Set if you wish to cluster reads regardless of whether they are forward or reverse"/>
            <param name="skip_size" type="integer" label="do not report clusters whose size is less than the specified value" value="1"
                   help="Cluster size threshod (in nucleotides) for reporting. Set to 1 (default) reports all clusters, including singlets" />
            <param name="skip_counts" type="integer" label="do not report cluster with a number of reads lower than the specified value" value="1"
                   help="Number-of-reads threshod (in nucleotides) for cluster reporting. Set to 1 (default) reports all clusters, irrespective of their counts" />
             <param name="skip_density" type="float" label="do not report cluster with density equal or less than the specified value" value="0"
                   help="Density threshod (in reads per nucleotides) for reporting. Set to 0 (default) reports all cluster densities" />
        </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="$plots_options.first_plot dataframe" />
    <data format="bed" name="output_bed" label="bed file for clusters" >
        <filter>plots_options['plots_options_selector'] == 'cluster'</filter>
    </data>
    <data format="tabular" name="extra_output_tab" label="$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> <!-- 0 -->
            <param name="inputs" value="input1.bam,input_new2.bam" ftype="bam" />
            <param name="normalization" value="1 2" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="one_plot" />
            <param name="first_plot" value="Counts" />
            <output file="input1_input2new_norm_1_2_counts.tab" name="output_tab" />
            <output file="input1_input2new_norm_1_2_single_plot_counts.pdf" name="output_pdf" />
        </test>
        <test> <!-- 1 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 2 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="cluster" />
            <param name="first_plot" value="Counts" />
            <param name="cluster" value="5" />
            <param name="skip_size" value="1" />
            <param name="strandness" value="false" />
            <output file="clustering.tab" name="output_tab" />
            <output file="clustering.pdf" name="output_pdf" />
            <output file="bed1.bed" name="output_bed" />
        </test>
        <test> <!-- 3 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="cluster" />
            <param name="first_plot" value="Counts" />
            <param name="cluster" value="5" />
            <param name="skip_size" value="1" />
            <param name="strandness" value="true" />
            <output file="clustering_unstranded.tab" name="output_tab" />
            <output file="clustering_unstranded.pdf" name="output_pdf" />
            <output file="bed2.bed" name="output_bed" />
        </test>
        <test> <!-- 4 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="cluster" />
            <param name="first_plot" value="Counts" />
            <param name="cluster" value="5" />
            <param name="skip_size" value="2" />
            <param name="strandness" value="false" />
            <output file="clustering.tab" name="output_tab" />
            <output file="clustering.pdf" name="output_pdf" />
            <output file="bed3.bed" name="output_bed" />
        </test>
        <test> <!-- 5 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="cluster" />
            <param name="first_plot" value="Counts" />
            <param name="cluster" value="5" />
            <param name="skip_size" value="2" />
            <param name="skip_counts" value="3" />
            <param name="skip_density" value="1.0" />
            <param name="strandness" value="false" />
            <output file="clustering.tab" name="output_tab" />
            <output file="clustering.pdf" name="output_pdf" />
            <output file="bed4.bed" name="output_bed" />
        </test>
        <test> <!-- 6 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="cluster" />
            <param name="first_plot" value="Counts" />
            <param name="cluster" value="5" />
            <param name="skip_size" value="2" />
            <param name="skip_counts" value="2" />
            <param name="skip_density" value="0.4" />
            <param name="strandness" value="true" />
            <output file="clustering_unstranded.tab" name="output_tab" />
            <output file="clustering_unstranded.pdf" name="output_pdf" />
            <output file="bed5.bed" name="output_bed" />
        </test>
        <test> <!-- 7 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="20" />
            <param name="maxsize" value="30" />
            <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> <!-- 8 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 9 -->
            <param name="inputs" value="input1.bam" ftype="bam" />
            <param name="normalization" value="1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 10 -->
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam" />
            <param name="normalization" value="1.0 2.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 11 -->
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam" />
            <param name="normalization" value="1.0 1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 12 -->
            <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="normalization" value="1.0 1.0 1.0 1.0 1.0 1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <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> <!-- 13 -->
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam" />
            <param name="normalization" value="1.0 1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="global" />
            <param name="mergestrands" value="nomerge" />
            <param name="first_plot" value="Size" />
            <output file="size.tab" name="output_tab" />
            <output file="global_nomerge.pdf" name="output_pdf" />
        </test>
        <test> <!-- 14 -->
            <param name="inputs" value="input1.bam,input2.bam" ftype="bam" />
            <param name="normalization" value="1.0 1.0" />
            <param name="minsize" value="0" />
            <param name="maxsize" value="10000" />
            <param name="plots_options_selector" value="global" />
            <param name="mergestrands" value="merge" />
            <param name="first_plot" value="Size" />
            <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 read alignments along reference chromosomes or genes or arbitrary regions :

 - 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 (Normalisation field)

*Cluster mode*

Cluster of read alignments are aggregated along regions of *variable* lengths. The Clustering
algorithm works as follows:

A read is clustered with the following read on the genomic reference if the two reads are
separated by at maximum the clustering distance (set in nucleotides). If clustered, the step is
repeated with the following read until clustering fails. A new cluster is then searched.

For clustering procedure, one has the possibility to consider the polarity of reads (only forward
reads or reverse reads can be clustered separately), or to ignore this polarity.

Cluster reads are plotted as for single reads, their coordinate being the median of extrem coordinates of the cluster.

In addition, cluster are reported in a bed file, where clusters can be filtered out upon various parameters,
cluster size, cluster read number or cluster read density (number of reads divided by the length of the cluster).

**Inputs**

bam alignment files that must be

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

.. class:: warningmark

This tools follows a "map-reduce" procedure: multiple inputs, that can be arranged as a data collection,
are visualised side by side in a single pdf file.
 


**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>