diff partial_least_squares.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 caba07f41453
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/partial_least_squares.xml	Mon Mar 08 22:04:06 2021 +0000
@@ -0,0 +1,145 @@
+<tool id="secimtools_partial_least_squares" name="Partial Least Squares Discriminant Analysis (PLS-DA)" version="@WRAPPER_VERSION@">
+    <description></description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+partial_least_squares.py
+--input $input
+--design $design
+--ID $uniqID
+--group $group
+--toCompare "$toCompare"
+--cross_validation $cross_validation
+--nComp $nComp
+--outScores $outScores
+--outWeights $outWeights
+--outClassification $outClassification
+--outClassificationAccuracy $outClassificationAccuracy
+--figure $figures
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
+        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
+        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/>
+        <param name="group" type="text" size="30" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
+        <param name="toCompare" type="text" size="30" label="Names of the Groups to Compare" help="Names of the two groups to compare. The user should insure that group names do not contain commas. The separator for the two groups should only include commas (no spaces)."/>
+        <param name="cross_validation" type="select" size="30" display="radio" value="double" label="Cross-Validation Options">
+            <option value="none">None</option>
+            <option value="single">Single</option>
+            <option value="double">Double</option>
+        </param>
+        <param name="nComp" type="text" size="30" value="2" label="Number of Components" help="Number of components for the analysis to use (default = 2). This field is used only when the cross validation field is set to none."/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="outScores" label="${tool.name} on ${on_string}: Scores"/>
+        <data format="tabular" name="outWeights" label="${tool.name} on ${on_string}: Weights"/>
+        <data format="tabular" name="outClassification" label="${tool.name} on ${on_string}: Classification of Samples"/>
+        <data format='tabular' name="outClassificationAccuracy" label="${tool.name} on ${on_string}: Classification Accuracy of Samples"/>
+        <data format="pdf" name="figures" label="${tool.name} on ${on_string}: Scatter Plots"/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input"             value="ST000006_data.tsv"/>
+            <param name="design"            value="ST000006_design_group_name_underscore.tsv"/>
+            <param name="uniqID"            value="Retention_Index" />
+            <param name="group"             value="White_wine_type_and_source" />
+            <param name="toCompare"         value="Chardonnay_ Napa_ CA 2003,Riesling_ CA 2004" />
+            <param name="cross_validation"  value="none"/>
+            <param name="nComp"             value="2"/>
+            <output name="outScores"                 file="ST000006_partial_least_squares_none_scores.tsv" />
+            <output name="outWeights"                file="ST000006_partial_least_squares_none_weights.tsv" />
+            <output name="outClassification"         file="ST000006_partial_least_squares_none_classification.tsv" />
+            <output name="outClassificationAccuracy" file="ST000006_partial_least_squares_none_classification_accuracy.tsv" />
+            <output name="figures"                   file="ST000006_partial_least_squares_none_figure.pdf" compare="sim_size" delta="10000"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+@TIP_AND_WARNING@
+
+**Tool Description**
+
+The tool performs partial least square discriminant analysis (PLS-DA) for two treatment groups selected by the user.
+
+**NOTE: A minimum of 100 samples is required by the tool for single or double cross validation**
+
+The subspace dimension defines the number of components that will be used to describe the variability within the data.
+The user can specify subspace dimension in the range of two to the sample number.
+The user has the option to specify the dimension of the subspace directly (Default =2) or to perform single or double cross-validation to determine the dimension of the subspace.
+
+For single and double cross-validation: the data set is split differently when the model fit is performed.
+
+For double cross-validation: the data set is split into pieces and the model fit is performed on one piece using cross-validation and evaluated on the other pieces.
+
+For single cross-validation: the same data are used to fit the model and to evaluate the model using three-fold cross validation.
+
+More details can be found in:
+
+Geladi, Paul, and Bruce R. Kowalski. "Partial least-squares regression: a tutorial." Analytica chimica acta 185 (1986): 1-17.
+
+
+--------------------------------------------------------------------------------
+
+**Note**
+
+- This tool currently treats all variables as continuous numeric
+  variables. Running the tool on categorical variables may result in
+  incorrect results.
+- Rows containing non-numeric (or missing) data in any
+  of the chosen columns will be skipped 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@
+
+
+**Names of the Groups to Compare**
+
+    - Comma separated names of the two groups in your Group/Treatment column that you want to compare. The user should ensure that group names do not contain commas. The separator for the two groups should only include commas (no spaces).
+
+**Cross-Validation Options**
+
+    - The choice of cross-validation options available for the user. None corresponds to no cross-validation when the user specifies the number of components manually.
+
+**Number of Components**
+
+    - The parameter is used only when the "None" cross-validation option is selected. If the field is left blank, the number of components is set to the default value (2).
+--------------------------------------------------------------------------------
+
+**Output**
+
+
+Three different files are generated:
+
+(1) a TSV file containing the scores produced by the model for each sample
+
+(2) a TSV file containing the weights produced by the model for each feature.
+
+(3) a TSV file containing the classification produced by the model for each sample.
+
+(4) a TSV file containing the algorithm classification accuracy (in percent).
+
+(5) a PDF file containing the 2D plots for all pairwise comparisons of components between the two treatment groups.
+
+**NOTE:** Regardless how many components are selected for the algorithm, pairwise 2D plots are produced for the pairs of components.
+Increasing the number of components will increase the number of plots produced.
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>