--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/mahalanobis_distance.xml	Mon Mar 08 22:04:06 2021 +0000
@@ -0,0 +1,136 @@
+<tool id="secimtools_mahalanobis_distance" name="Penalized Mahalanobis Distance (PMD)" version="@WRAPPER_VERSION@">
+    <description>to compare groups</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <stdio>
+        <exit_code range="1:" level="warning" description="RuntimeWarning"/>
+    </stdio>
+    <command detect_errors="exit_code"><![CDATA[
+mahalanobis_distance.py
+--input $input
+--design $design
+--ID $uniqID
+--figure $plot
+--distanceToMean $out1
+--distancePairwise $out2
+
+#if $group
+    --group $group
+#end if
+
+#if $levels
+    --levels $levels
+#end if
+
+#if $p
+    --per $p
+#end if
+
+#if $order
+    --order $order
+#end if
+
+#if $penalty
+    --penalty $penalty
+#end if
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file not tab separated see TIP below."/>
+        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
+        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers.."/>
+        <param name="group" type="text" size="30" label="Group/Treatment [Optional]" help="Name of the column in your design file that contains group classifications." />
+        <param name="order" type="text" size="30" label="Input Run Order Name [Optional]" help="Enter the name of the column containing the order samples were run. Spelling and capitalization must be exact." />
+        <param name="levels" type="text" size="30" label="Additional groups to separate by [Optional]" help="Enter additional group(s) name(s) to include. Spelling and capitalization must be exact. If more than one group separate with ','." />
+        <param name="p" type="float" value= ".95" size="6" label="Threshold" help="Threshold for standard distribution, specified as a percentile. Default = 0.95." />
+        <param name="penalty" type="float" value= "0.5" size="6" label="λ Penalty" help="λ Penalty to use in the distance. The default is λ=0.5." />
+    </inputs>
+    <outputs>
+        <data format="pdf" name="plot" label="${tool.name} on ${on_string}: plot" />
+        <data format="tabular" name="out1" label="${tool.name} on ${on_string}: toMean" />
+        <data format="tabular" name="out2" label="${tool.name} on ${on_string}: pairwise" />
+    </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="penalty" value="0.5" />
+            <output name="plot"   file="ST000006_mahalanobis_distance_figure.pdf" compare="sim_size" delta="10000" />
+            <output name="out1"   file="ST000006_mahalanobis_distance_to_mean.tsv" />
+            <output name="out2"   file="ST000006_mahalanobis_distance_pairwise.tsv" />
+        </test>
+    </tests>
+    <help><![CDATA[
+
+@TIP_AND_WARNING@
+
+**Tool Description**
+
+The Penalized Mahalanobis distance (PMD) tool can be used to compare samples within a group and accounts for the correlation structure between metabolites.
+In contrast, Standardized Euclidian distance (SED) relies solely on geometric distance and ignores any dependency structures between features.
+PMD incorporates the correlation structure inside the distance measurement.
+
+When correlation structure and dependency between metabolites is ignored, the features inverse variance-covariance matrix simplifies to a diagonal matrix with diagonal values - in this case, MD simplifies to SED.
+When the number of features is greater than the number of samples, the inverse of the features variance-covariance matrix does not exist.
+This is the case for most -omic data. Here, the inverse is estimated using a regularization method (Archambeau et al. 2004).
+The details of the regularization algorithm can be found in Supplementary file 3 in Kirpich et al. 2017.
+
+Archambeau C, Vrins F, Verleysen M. Flexible and Robust Bayesian Classification by Finite Mixture Models. InESANN 2004 (pp. 75-80).​
+
+**NOTE:** Because of the nature of the tool, groups with less than 3 samples will be discarded 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_OPTIONAL@
+
+    - **Warning:** All groups must contain 3 or more samples.
+
+
+@RUNORDER_OPTIONAL@
+
+**Additional groups to separate by [Optional]**
+
+    - Enter additional group(s) name(s) to include. Spelling and capitalization must be exact. If more than one group, separate them with a comma
+    - **Warning:** All groups must contain 3 or more samples.
+
+
+**Percentile cutoff**
+
+- The percentile cutoff for standard distributions. The default is 0.95.
+
+**λ Penalty**
+
+- λ Penalty to use in the distance. The default is λ=0.5.
+
+--------------------------------------------------------------------------------
+
+**Output**
+
+The tool outputs three different files:
+
+(1) a PDF file containing 2D scatter plots and boxplots for the distances 
+
+(2) a TSV file containing distances from the sample to the estimated mean 
+
+(3) a TSV file containing distances from the sample to other samples.
+
+If the grouping variable is specified by the user, the distances are computed both within the groups and for the entire dataset.
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>