view triplet.xml @ 3:d7ce95ccf54f

Change R data file format in xml wrappers (rda -> RData) Add test data, sample workflow. Updated README with instructions on testing.

<tool id="riboseqr_triplet_periodicity" name="Triplet Periodicity"
      version="0.4.0">
    <description>
        (Step 2) Plot triplet periodicity for different read lengths.
    </description>
    <requirements>
        <requirement type="package" version="3.1.2">R</requirement>
        <requirement type="package" version="6.2">readline</requirement>
        <requirement type="package" version="2.3.10">rpy2</requirement>
        <requirement type="package" version="0.4.0">riboseqr_wrapper_deps</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:"  level="fatal" description="Error" />
    </stdio>
    <command interpreter="python">riboseqr/triplet.py
        --rdata_load "$rdata_load"
        --fasta_file "$fasta_file"
        --start_codons "$start_codons"
        --stop_codons "$stop_codons"
        --include_lengths "$include_lengths"
        --analyze_plot_lengths "$analyze_plot_lengths"
        --text_legend "$text_legend"
        --rdata_save "$rdata_save"
        --html_file "$html_file"
        --output_path "$html_file.files_path"
    </command>
    <inputs>
        <param name="rdata_load" type="data" format="RData"
               label="Select prepared riboSeqR input (R data file)"
               multiple="false" optional="false"
               help="&lt;br&gt;&lt;h4&gt;&lt;font color=&quot;#666666&quot;&gt;findCDS
                     parameters&lt;/font&gt;&lt;/h4&gt;">
            <validator type="expression"
                       message="Please check if the correct RDA file is selected">value.name == "Prepare riboSeqR input (R data file)"</validator>
        </param>

        <param format="fasta" name="fasta_file" type="data"
               label="Select FASTA file of the reference transcriptome"
               help="This Fasta file is used to find start (ATG) and
                     stop codons(TAG, TAA, TGA) in frame with one another. If no files
                     are listed, you will need to upload a FASTA file of the reference
                     transcriptome. Please note that the FASTA header of the transcriptome
                     sequences must match the sequence names from the SAM file.">
            <validator type="empty_field" message="Field requires a value"/>
        </param>

        <param name="start_codons" type="text" size="15" value="ATG"
               label="Start codon(s) to use"
               help="Default is ATG. Multiple values must be comma-separated.">
            <validator type="empty_field" message="Field requires a value"/>
        </param>

        <param name="stop_codons" type="text" size="15" value="TAG, TAA, TGA"
               label="Stop codon(s) to use"
               help="Default is TAG, TAA, TGA. Multiple values must be comma-separated.
                     &lt;h4&gt;&lt;font color=&quot;#666666&quot;&gt;frameCounting
                     parameters&lt;/font&gt;&lt;/h4&gt;">
            <validator type="empty_field" message="Field requires a value"/>
        </param>

        <param name="include_lengths" type="text"
               label="Lengths of ribosome footprints
                      to be included"
               help="Here, you can specify the lengths of ribosome footprints to
                     be included in the riboData object. &lt;br&gt;For example 25:30.
                     Range, semi-colon separated. &lt;h4&gt;&lt;font color=&quot;#666666&quot;&gt;readingFrame
                     parameters&lt;/font&gt;&lt;/h4&gt;" value="25:30"/>

        <param name="analyze_plot_lengths" type="text"
               label="Lengths of reads to be analysed for frame-shift, or to be plotted"
               help="[Optional] If omitted, all lengths will be plotted.
                     &lt;br&gt;For example 26:30. Range, semi-colon separated.
                     &lt;h4&gt;&lt;font color=&quot;#666666&quot;&gt;plotFS
                     parameters&lt;/font&gt;&lt;/h4&gt;" value="26:30"/>

        <param name="text_legend" type="text" size="30"
               value='Frame 0, Frame 1, Frame 2'
               label="Text for legend used in the
                      plot" help="Comma-separated values."/>
    </inputs>
    <outputs>
        <data format="RData" name="rdata_save"
              label="Triplet periodicity (R data file)"/>
        <data format="html" name="html_file"
              label="Triplet periodicity (HTML report)"/>
    </outputs>
    <!--<tests>-->
        <!--<test>-->
            <!--<param name="rdata_load" value="Prepare riboSeqR input (R data file)" ftype="RData" />-->
            <!--<param name="fasta_file" value="rsem_chlamy236_deNovo.transcripts.fa" />-->
            <!--<param name="include_lengths" value="25:30" />-->
            <!--<param name="analyze_plot_lengths" value="26:30" />-->
            <!--<output name="rdata_save" file="Triplet periodicity (R data file)" ftype="RData" />-->
            <!--<output name="html_file" file="Triplet_periodicity_(HTML_report).html">-->
                <!--<extra_files type="file" name="Periodicity-plot.png" value="Periodicity-plot.png" ftype="png" />-->
                <!--<extra_files type="file" name="Periodicity-plot.pdf" value="Periodicity-plot.pdf" ftype="pdf" />-->
            <!--</output>-->
        <!--</test>-->
    <!--</tests>-->
    <help>
Triplet Periodicity
-------------------
riboSeqR version: ``1.0.5``.

This tool can be used to plot triplet periodicity for different read lengths.
The inputs for this program are:

#. Prepare riboSeqR input (R data file) from the previous step.
#. FASTA format file of the reference transcriptome.

   .. class:: infomark

        Please note that the FASTA header of the transcriptome sequences must
        match the sequence names from the SAM file.

How to use?
-----------
Inputs
......
Select prepared R data file from the previous step.

Select FASTA format file of the reference transcriptome, review/change other
options if necessary and execute program.

Outputs
.......
The following files will be generated on completion:

#. Triplet periodicity (HTML report)

   A HTML file with results and links to other output files - triplet
   periodicity plot (PDF) and R script used for the session.

#. Triplet periodicity (R data file)

   Used as input for the next step - *Metagene analysis*.

riboSeqR functions used
.......................
``findCDS``, ``frameCounting``, ``readingFrame`` and ``plotFS``.

For detailed description of the functions and the options used, please consult
the riboSeqR documentation.

Links
.....
`riboSeqR &lt;http://bioconductor.org/packages/3.0/bioc/html/riboSeqR.html&gt;`_.

    </help>
    <citations>
        <citation type="bibtex">
            @Manual{,
            title = {riboSeqR: Analysis of sequencing data from ribosome
            profiling experiments.},
            author = {Thomas J. Hardcastle},
            year = {2014},
            note = {R package version 1.0.5},
            }
        </citation>
    </citations>
</tool>