view distribution_samples.xml @ 1:2e7d47c0b027 draft

"planemo upload for repository https://[e-mail]/repos/malex/secimtools"

<tool id="secimtools_distribution_samples" name="Generate Distribution of Features within Samples." version="@WRAPPER_VERSION@">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
distribution_samples.py
--input $input
--design $design
--ID $uniqID
--figure $figure

#if $group
    --group $group
#end if

#if $order
    --order $order
#end if
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If not tab separated see TIP below."/>
        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your Wide Dataset that has unique identifiers."/>
        <param name="group" type="text" size="30" value="" optional="true" label="Group/Treatment [Optional]" help="Name of the column in your design file that contains group classifications."/>
        <param name="order" type="text" size="30" value="" optional="true" label="Run Order [Optional]" help="The column name in your design file that contains the order samples were run."/>
    </inputs>
    <outputs>
        <data format="pdf" name="figure" label="${tool.name} on ${on_string}: Plot"/>
    </outputs>
    <tests>
        <test>
            <param name="input"   value="ST000006_data.tsv"/>
            <param name="design"  value="ST000006_design.tsv"/>
            <param name="uniqID"  value="Retention_Index" />
            <param name="group"   value="White_wine_type_and_source" />
            <output name="figure" file="ST000006_distribution_samples_with_group_figure.pdf" compare="sim_size" delta="10000"/>
        </test>
    </tests>
<help><![CDATA[

@TIP_AND_WARNING@

**Tool Description**

The tool plots the distribution of features within each sample.
All samples are colored by group and are plotted on the same graph for comparison purposes.
The distributions of the features within each sample are presented as estimated densities and box-and-whiskers plots with potential outliers.
If the order samples were run is specified in the input, box plots will be displayed according to the run order.

**NOTE:** This script works best with log transformed data.


--------------------------------------------------------------------------------

**Input**

- Two input datasets are required.

@WIDE@

**NOTE:** The sample IDs must match the sample IDs in the Design File
(below). Extra columns will automatically be ignored.

@METADATA@

@UNIQID@

@GROUP_OPTIONAL@

@RUNORDER_OPTIONAL@

--------------------------------------------------------------------------------

**Output**

PDF file containing two plots:

(1) Density plots illustrating the distribution of features within a given sample
(2) Boxplots of the distribution of features within each sample

]]></help>
    <expand macro="citations"/>
</tool>