annotate ribocount.xml @ 31:69f43f4144df

Use latest version of riboplot from PyPI (0.2.2)

<tool id="ribocount" name="ribocount" version="0.2.0">
    <description>Get read counts for all transcripts in an alignment (BAM)
    </description>
    <requirements>
        <requirement type="package" version="0.2.2">riboplot</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:"  level="fatal" description="Error" />
    </stdio>
    <command>python \${RIBOPLOT_PATH}/ribocount
    --ribo_file "${ribo_file}"
    --transcriptome_fasta "${transcriptome_fasta}"
    --read_length "${read_length}"
    --read_offset "${read_offset}"
    #if (str($region_select) == 'five_prime'):
    --count_five
    #elif (str($region_select) == 'three_prime'):
    --count_three
    #end if
    --html_file "${html_file}"
    --output_path "${html_file.files_path}"
    ## --debug
    </command>
    <inputs>
        <param name="ribo_file" type="data" format="bam" label="Ribo-Seq alignment file in BAM format"/>
        <param name="transcriptome_fasta" type="data" format="fasta" label="FASTA format file of the transcriptome"/>
        <param name="read_length" type="integer" label="Read length to consider" value="28" help="If specified, only reads of this length will be considered.
            A read length of 0 will output counts for all reads"/>
        <param name="read_offset" type="integer" label="Offset" value="0"/>
        <param name="region_select" type="select" label="Which read counts to output?"
            help="Output read counts for the entire transcript or restrict read counts to the region 5' or 3' of the longest ORF">
            <option value="all_reads">All reads</option>
            <option value="five_prime">5' of the longest ORF</option>
            <option value="three_prime">3' of the longest ORF</option>
        </param>
    </inputs>
    <outputs>
        <data format="html" name="html_file" label="ribocount on ${ribo_file.name} ($region_select.value_label)"/>
    </outputs>
    <help>
**RiboCount**

Output read counts for all transcripts in an alignment.

----

**Parameters**

1. Ribo-Seq alignment file (Sorted BAM file)

   A Bowtie 1 output (BAM) from an alignment of Ribo-Seq data to the transcriptome. This BAM
   file should be sorted. This can be done using one of the following methods.

   1. RiboGalaxy -> Sort Data -> Sort BAM dataset.
   2. ``samtools sort input.bam inputsorted``

2. Transcriptome (FASTA)

   A FASTA format file with sequences of the transcripts.

3. Read lengths to consider [optional] (Integer - 0 or greater)

   If this option is provided, only Ribo-Seq data of the given length is considered.

4. Offset [optional] (Integer - 0 or greater)

   If this option is provided, this offset is added to the read alignment positions.

5. Restrict read counts

   Choose whether to output read counts for the entire transcript or restrict read counts to the 5' or 3' region of the longest ORF.
   Default start (ATG) and stop codons ('TAG', 'TGA', 'TAA') are used to identify the longest ORF in 3 frames.

----

**Output**

Read counts for all transcripts in the alignment (ZIP)

The output file ``ribocount_output.zip`` should first be uncompressed. This will generate
a folder called ``ribocount_output``. Open ``index.html`` in a web browser to view the results of ribocount.

Total reads for each transcript will be displayed in a table along with the name of the transcript and a link
to the CSV file containing the read counts in 3 frames for each position in the transcript.

.. image:: images/ribocount.png

    </help>
</tool>