view read_quality.xml @ 62:473382134e56 draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/rseqc commit ccb6f7edba5492f4750ef8a59c4f91eb67fdbbec
author iuc
date Wed, 22 Feb 2023 15:06:01 +0000
parents 5968573462fa
children 27e16a30667a
line wrap: on
line source

<tool id="rseqc_read_quality" name="Read Quality" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@GALAXY_VERSION@">
    <description>determines Phred quality score</description>
    <macros>
        <import>rseqc_macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements">
        <!--
            Required due to conda solver bug: https://github.com/conda/conda/issues/6269
            See: https://github.com/galaxyproject/tools-iuc/pull/1578 for more info
        -->
        <requirement type="package" version="4.2.2">r-base</requirement>
    </expand>

    <expand macro="stdio" />

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

    <command><![CDATA[
        @BAM_SAM_INPUTS@
        read_quality.py
            --input-file 'input.${extension}'
            --out-prefix output
            -r ${reduce}
            --mapq ${mapq}
        ]]>
    </command>

    <inputs>
        <expand macro="bam_sam_param" />
        <param name="reduce" type="integer" label="Ignore Phred scores less than this amount (only applies to 'boxplot', default=1000)" value="1000" help="(--reduce)"/>
        <expand macro="mapq_param" />
        <expand macro="rscript_output_param" />
    </inputs>

    <outputs>
        <data format="pdf" name="outputheatpdf" from_work_dir="output.qual.heatmap.pdf" label="${tool.name} on ${on_string} (Heatmap pdf)" />
        <data format="pdf" name="outputboxpdf" from_work_dir="output.qual.boxplot.pdf" label="${tool.name} on ${on_string} (Boxplot pdf)" />
        <expand macro="rscript_output_data" filename="output.qual.r" />
    </outputs>

    <tests>
        <test>
            <param name="input" value="pairend_strandspecific_51mer_hg19_random.bam"/>
            <param name="rscript_output" value="true" />
            <output name="outputr" file="output.qual_r"/>
            <output name="outputheatpdf" file="output.qual.heatmap.pdf" compare="sim_size" />
            <output name="outputboxpdf" file="output.qual.boxplot.pdf" compare="sim_size" />
        </test>
    </tests>

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

According to SAM specification, if Q is the character to represent "base calling quality"
in SAM file, then Phred Quality Score = ord(Q) - 33. Here ord() is python function that
returns an integer representing the Unicode code point of the character when the argument
is a unicode object, for example, ord('a') returns 97. Phred quality score is widely used
to measure "reliability" of base-calling, for example, phred quality score of 20 means
there is 1/100 chance that the base-calling is wrong, phred quality score of 30 means there
is 1/1000 chance that the base-calling is wrong. In general: Phred quality score = -10xlog(10)P,
here P is probability that base-calling is wrong.

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

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

Ignore phred scores less than this number (default=1000)
    To avoid making huge vector in R, nucleotide with certain phred score represented less than this number will be ignored. Increase this number save more memory while reduce precision. This option only applies to the 'boxplot'.

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

1. output.qual.r
2. output.qual.boxplot.pdf
    .. image:: $PATH_TO_IMAGES/36mer.qual.plot.png
        :height: 600 px
        :width: 600 px
        :scale: 80 %
3. output.qual.heatmap.pdf
    .. image:: $PATH_TO_IMAGES/36mer.qual.heatmap.png
        :height: 600 px
        :width: 600 px
        :scale: 80 %

Heatmap: use different color to represent nucleotide density ("blue"=low density,"orange"=median density,"red"=high density")

@ABOUT@

]]>
    </help>

    <expand macro="citations" />

</tool>