view ttest_single_group.xml @ 1:2e7d47c0b027 draft

"planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
author malex
date Mon, 08 Mar 2021 22:04:06 +0000
parents
children
line wrap: on
line source

<tool id="secimtools_ttest_single_group" name="T-Test (Single Group)" version="@WRAPPER_VERSION@">
    <description>for the specified mean.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
ttest_single_group.py
--input $input
--design $design
--uniqueID $uniqueID
--mu $mu
--summaries $summaries
--flags $flags
--volcano $volcano
#if $group
    --group $group
#end if
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
        <param name="uniqueID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/>
        <param name="mu" type="text" size="30" value = "0" label="Mu" help="The value of the mean under the null hypothesis. Default = 0. "/>
        <param name="group" type="text" size="30" label="Group/Treatment [Optional]" help="Name of the column in your design file that contains group classifications."/>
    </inputs>
    <outputs>
        <data format="tabular" name="summaries" label="${tool.name} on ${on_string}: Summaries that include p-values and mean differences."/>
        <data format="tabular" name="flags" label="${tool.name} on ${on_string}: Flags that include 0.01, 0.05 and 0.10 significance levels for the differences. "/>
        <data format="pdf" name="volcano" label="${tool.name} on ${on_string}: Volcano plots for the differences."/>
    </outputs>
    <tests>
        <test>
            <param name="input"      value="ST000006_data.tsv"/>
            <param name="design"     value="ST000006_design.tsv"/>
            <param name="uniqueID"   value="Retention_Index" />
            <param name="mu"         value="0" />
            <output name="summaries" file="ST000006_ttest_single_group_no_group_summary.tsv" />
            <output name="flags"     file="ST000006_ttest_single_group_no_group_flags.tsv" />
            <output name="volcano"   file="ST000006_ttest_single_group_no_group_volcano.pdf" compare="sim_size" delta="10000"/>
        </test>
        <test>
            <param name="input"       value="ST000006_data.tsv"/>
            <param name="design"      value="ST000006_design.tsv"/>
            <param name="uniqueID"    value="Retention_Index" />
            <param name="mu"          value="0" />
            <param name="group"       value="White_wine_type_and_source" />
            <output name="summaries"  file="ST000006_ttest_single_group_with_group_summary.tsv" />
            <output name="flags"      file="ST000006_ttest_single_group_with_group_flags.tsv" />
            <output name="volcano"    file="ST000006_ttest_single_group_with_group_volcano.pdf" compare="sim_size" delta="10000"/>
        </test>
    </tests>
    <help><![CDATA[

@TIP_AND_WARNING@

**Tool Description**

The tool performs a one sample t-test for each feature.
Two options are available for the t-test: if the user provides the Group/Treatment variable, then the mean for each treatment condition is compared with Mu, the user-specified value of the true mean under the null hypothesis.
If Group/Treatment is not provided, then the mean across all samples is compared to Mu.

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

**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/Treatment [Optional]**

        - Name of the column the Design File that contains group classifications.

**Mu**

        - The value of the mean under the null hypothesis. Default = 0.


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

**Output**

The tool produces three outputs:

(1)  a TSV file with the results table containing p-values for each test and the corresponding differences between the group means and the mu value under the null.
(2) a TSV file containing indicator flags equal to 1 if the difference between the groups and the mean under the null is statistically significant using the indicated α levels.
(3) a PDF file with volcano plots for visual inspection of the differences between the group means and p-values. The red dashed line in the volcano plot(s) corresponds to a p-value = 0.01 cutoff (2 on the negative log base 10 scale).

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