view secimtools/log_and_glog_transformation.xml @ 0:b54326490b4d draft

Upload 21.3.4.2 release
author malex
date Mon, 08 Mar 2021 20:55:03 +0000
parents
children
line wrap: on
line source

<tool id="secimtools_log_and_glog_transformation" name="Log and Generalized Log (G-Log) Transformation." version="@WRAPPER_VERSION@">
    <description></description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command><![CDATA[
log_and_glog_transformation.py
--input $input
--design $design
--uniqID $uniqID
--transformation $transformation
--log_base $log_base
--lambda_value $lambda_value
--oname $oname
    ]]></command>
    <inputs>
        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
        <param name="uniqID" size="30" type="text" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers.."/>
        <param name="transformation" size="30" display="radio" type="select" value="log" label="Select Transformation" help="Select log or G-log.">
            <option value="log"  selected="true">Logarithm</option>
            <option value="glog" selected="true">Generalized Logarithm (G-Log)</option>
        </param>
        <param name="log_base" size="30" type="select" display="radio" value="log" label="Logarithm Base" help="Select logarithm base.">
            <option value="log" selected="true">Logarithm base e (natural)</option>
            <option value="log2" selected="true">Logarithm base 2</option>
            <option value="log10" selected="true">Logarithm base 10</option>
        </param>
         <param name="lambda_value" size="30" type="text" value="100" label="Regularization Parameter Lambda" help='Regularization parameter lambda is used only for G-log transformation and is ignored for log transformation. Lambda must be non-negative.'/>
    </inputs>
    <outputs>
        <data format="tabular" name="oname" label="${tool.name} on ${on_string}" />
    </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="transformation" value="glog" />
            <param name="log_base"       value="log" />
            <param name="lambda_value"   value="1000000" />
            <output name="oname"         file="ST000006_log_and_glog_transformation_glog_lambda_1000000.tsv" />
        </test>
        <test>
            <param name="input"          value="ST000006_data.tsv"/>
            <param name="design"         value="ST000006_design.tsv"/>
            <param name="uniqID"         value="Retention_Index" />
            <param name="transformation" value="log" />
            <param name="log_base"       value="log" />
            <param name="lambda_value"   value="0" />
            <output name="oname"         file="ST000006_log_and_glog_transformation_log.tsv" />
        </test>
    </tests>
    <help><![CDATA[

@TIP_AND_WARNING@

**Tool Description**

***NOTE: Zero or negative values in the original dataset will be replaced with missing values after log transformation since logarithms are not defined for non-positive values.***

This tool carries out either log or generalized log (G-log) transformation of values in a Wide Format dataset using the base specified by the user.

The logarithmic transformation has the formula: log(data).

The generalized logarithmic transformation has the formula: log(data + sqrt(data^2 + lambda)).

The generalized version becomes the standard logarithmic transformation re-scaled by sqrt(2) if the lambda value is 0.

Three bases are available for both logarithmic transformations:

base e (natural), base 2, and base 10.



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

**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@

**Transformation Choice**

    - User has to choose between logarithmic and generalized logarithmic (G-log) transformation.

**Logarithm Base**

    - Select base of the logarithm.

**Regularization Parameter Lambda**

    - Enter a value for regularization parameter lambda. The value must to be non-negative and is used only for G-log transformation. Default = 100.

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

**Output**

A TSV file containing the same column names as the original Wide Dataset where the values in each cell correspond to the values obtained by the selected log transformation procedure.

***NOTE:*** If the original dataset contains 0 or negative values, they will be replaced with missing values after log transformation since logarithms are not defined for non-positive values.
Any values missing in the original dataset will remain missing.

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