annotate run_order_regression.xml @ 1:2e7d47c0b027 draft

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

<tool id="secimtools_run_order_regression" name="Run Order Regression (ROR)" version="@WRAPPER_VERSION@">
    <description>using the order samples were run.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
run_order_regression.py
--input $input
--design $design
--ID $uniqID
--group $group
--order $order
--fig $order_plots
--table $order_summary
--flags $flags
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file(tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/>
        <param name="group" type="text" size="30" value="" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
        <param name="order" type="text" size="30" value="" label="Run Order ID" help="The name of the column in your design file that contains the order the samples were run."/>
    </inputs>
    <outputs>
        <data name="order_plots" format="pdf" label="${tool.name} on ${on_string}: Plots" />
        <data name="order_summary" format="tabular" label="${tool.name} on ${on_string}: Summary"/>
        <data name="flags"  format="tabular" label="${tool.name} on ${on_string}: Flags"/>
    </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" />
            <param name="order"  value="run_Order_fake_variable" />
            <output name="order_plots"        file="ST000006_run_order_regression_figure.pdf" compare="sim_size" delta="10000" />
            <output name="order_summary" file="ST000006_run_order_regression_table.tsv" />
            <output name="flags"         file="ST000006_run_order_regression_flags.tsv" />
        </test>
    </tests>
    <help><![CDATA[

@TIP_AND_WARNING@

**Tool Description**

**NOTE:** The tool is intended to evaluate the impact of sample run order on feature (row) values.  Not applicable in the absence of known run order.

It uses linear regression to identify features where the regression slope is not zero for nominal levels of significance.

The tool fits a simple linear regression by feature (row) using values for each feature as a response and sample run order as a linear predictor.
The goal is to identify a linear trend  that changes over time and determine whether the trends are statistically significant.
The tool generates flags if the slope is statistically significant for two different levels of statistical significance ( alpha = 0.05 and alpha = 0.01).

NOTE: Groups with one element are excluded from the analysis.

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

**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@

    - **NOTE:** Groups with one element will be excluded.

@RUNORDER@


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

**Output**

This tool outputs three different files:

(1) a TSV file of regression summaries including the values of the regression slope, corresponding p-value and r-squared value.

(2) a TSV file with the  corresponding flags for two levels of statistical significance (alpha = 0.05 and alpha = 0.01).

(3) and a PDF file with fitted regression plots for each feature. The values of the feature are displayed on the plot together with the regression line, bands, slopes, and corresponding p and r-squared values. The values are colored according to group classification.

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