diff kruskal_wallis.xml @ 1:2e7d47c0b027 draft

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

--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/kruskal_wallis.xml	Mon Mar 08 22:04:06 2021 +0000
@@ -0,0 +1,86 @@
+<tool id="secimtools_kruskal_wallis" name="Kruskal-Wallis Non-Parametric Test" version="@WRAPPER_VERSION@">
+    <description>on features (rows).</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+kruskal_wallis.py
+--input $input
+--design $design
+--uniqueID $uniqueID
+--group $group
+--summaries $summaries
+--flags $flags
+--volcano $volcano
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
+        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
+        <param name="uniqueID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/>
+        <param name="group" type="text" size="30" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="summaries" label="${tool.name} on ${on_string}: Summaries that include p-values and mean differences."/>
+        <data format="tabular" name="flags" label="${tool.name} on ${on_string}: Flags that include 0.01,  0.05 and  0.10 significance levels for the pairwise differences. "/>
+        <data format="pdf" name="volcano" label="${tool.name} on ${on_string}: Volcano plots for the pairwise 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="group"    value="White_wine_type_and_source" />
+            <output name="summaries" file="ST000006_kruskal_wallis_with_group_summary.tsv" />
+            <output name="flags"     file="ST000006_kruskal_wallis_with_group_flags.tsv" />
+            <output name="volcano"   file="ST000006_kruskal_wallis_with_group_volcano.pdf" compare="sim_size" delta="10000" />
+        </test>
+    </tests>
+    <help><![CDATA[
+
+@TIP_AND_WARNING@
+
+**Tool Description**
+
+The tool performs Kruskal-Wallis non-parametric test, an analog of the one-way ANOVA F-test that does not rely on the normality assumption of the distribution.
+Unlike t-tests or an ANOVA F-test, a Kruskal-Wallis test is based on ranks where ranks are compared between groups.
+The test is performed (1) for samples from all groups together and (2) for the samples belonging to each group.
+The user is referred to the literature for more details on the Kruskal-Wallis test and the computation/approximation of corresponding p-values.
+
+Kruskal, William H., and W. Allen Wallis. "Use of ranks in one-criterion variance analysis." Journal of the American statistical Association 47, no. 260 (1952): 583-621.
+
+Meyer, J. Patrick, and Michael A. Seaman. "A comparison of the exact Kruskal-Wallis distribution to asymptotic approximations for all sample sizes up to 105." The Journal of Experimental Education 81, no. 2 (2013): 139-156.
+
+--------------------------------------------------------------------------------
+
+**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**
+
+        - Name of the column the Design File that contain group classifications.
+
+--------------------------------------------------------------------------------
+
+**Output**
+
+Three different outputs are generated:
+
+(1) a TSV file with the results, including p-values for each test and the corresponding differences between the means for comparisons between the groups.
+(2) a TSV file containing indicator flags.  A flag = 1 if the difference between the groups is statistically significant.
+(3) a PDF file with volcano plots for visual inspection of the differences between the treatment groups. The red dashed line in the volcano plot(s) corresponds to a 0.01 cutoff for p-values (2 on the negative log base 10 scale).
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>