annotate inner_distance.xml @ 59:dbedfc5f5a3c draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit 247059e2527b66f1dbecf1e61496daef921040c3"

<tool id="rseqc_inner_distance" name="Inner Distance" version="@TOOL_VERSION@.1">
    <description>calculate the inner distance (or insert size) between two paired RNA reads</description>
    <expand macro="bio_tools"/>
    <macros>
        <import>rseqc_macros.xml</import>
    </macros>

    <expand macro="requirements" />

    <expand macro="stdio" />

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

    <command><![CDATA[
        inner_distance.py -i '${input}' -o output -r '${refgene}'
            --sample-size ${sample_size}
            --lower-bound ${lowerBound}
            --upper-bound ${upperBound}
            --step ${step}
            --mapq ${mapq}
        ]]>
    </command>

    <inputs>
        <expand macro="bam_sam_param" />
        <expand macro="refgene_param" />
        <expand macro="sample_size_param" />
        <param name="lowerBound" type="integer" value="-250" label="Lower bound (bp, default=-250)" help="Used for plotting histogram (--lower-bound)"/>
        <param name="upperBound" type="integer" value="250" label="Upper bound (bp, default=250)" help="Used for plotting histogram (--upper-bound)"/>
        <param name="step" type="integer" value="5" label="Step size of histogram (bp, default=5)" help="(--step)"/>
        <expand macro="mapq_param" />
        <expand macro="rscript_output_param" />
    </inputs>

    <outputs>
        <expand macro="pdf_output_data" filename="output.inner_distance_plot.pdf" />
        <data format="txt" name="outputtxt" from_work_dir="output.inner_distance.txt" label="${tool.name} on ${on_string} (text)"/>
        <data format="txt" name="outputfreqtxt" from_work_dir="output.inner_distance_freq.txt" label="${tool.name} on ${on_string} (frequency text)" />
        <expand macro="rscript_output_data" filename="output.inner_distance_plot.r" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_chr1_1-100000.bam"/>
            <param name="refgene" value="hg19_RefSeq_chr1_1-100000.bed" ftype="bed12"/>
            <param name="rscript_output" value="true" />
            <output name="outputtxt" file="output.inner_distance.txt" />
            <output name="outputfreqtxt" file="output.inner_distance_freq.txt" />
            <output name="outputpdf" file="output.inner_distance_plot.pdf" compare="sim_size"/>
            <output name="outputr" file="output.inner_distance_plot_r" />
        </test>
    </tests>

    <help><![CDATA[
inner_distance.py
+++++++++++++++++

This module is used to calculate the inner distance (or insert size) between two paired RNA
reads. The distance is the mRNA length between two paired fragments. We first determine the
genomic (DNA) size between two paired reads: D_size = read2_start - read1_end, then

* if two paired reads map to the same exon: inner distance = D_size
* if two paired reads map to different exons:inner distance = D_size - intron_size
* if two paired reads map non-exonic region (such as intron and intergenic region): inner distance = D_size
* The inner_distance might be a negative value if two fragments were overlapped.

NOTE: Not all read pairs were used to estimate the inner distance distribution. Those low
quality, PCR duplication, multiple mapped reads were skipped.

Inputs
++++++++++++++

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

Reference gene model
    Gene model in BED format.

Estimated Upper/Lower Bounds (defaults=250 and -250)
    Estimated upper/lower bounds of inner distance (bp).

Step size (default=5)
    Step size of histogram


Output
++++++++++++++

1. output.inner_distance.txt:
    - first column is read ID
    - second column is inner distance. Could be negative value if PE reads were overlapped or mapping error (e.g. Read1_start &lt; Read2_start, while Read1_end >> Read2_end due to spliced mapping of read1)
    - third column indicates how paired reads were mapped: PE_within_same_exon, PE_within_diff_exon,PE_reads_overlap
2. output..inner_distance_freq.txt:
    - inner distance starts
    - inner distance ends
    - number of read pairs
    - note the first 2 columns are left side half open interval
3. output.inner_distance_plot.r: R script to generate histogram
4. output.inner_distance_plot.pdf: histogram plot

.. image:: $PATH_TO_IMAGES/inner_distance.png
   :height: 600 px
   :width: 600 px
   :scale: 80 %

@ABOUT@

]]>
    </help>

    <expand macro="citations" />

</tool>