diff multiple_testing_adjustment.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
line wrap: on
line diff
--- /dev/null	Thu Jan 01 00:00:00 1970 +0000
+++ b/multiple_testing_adjustment.xml	Mon Mar 08 22:04:06 2021 +0000
@@ -0,0 +1,86 @@
+<tool id="secimtools_multiple_testing_adjustment" name="Multiple Testing Adjustment (MTA)" version="@WRAPPER_VERSION@">
+    <description>of p-values.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command><![CDATA[
+multiple_testing_adjustment.py
+--input $input
+--uniqID $uniqID
+--pval "$pval"
+--alpha $alpha
+--outadjusted $outadjusted
+--flags $flags
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If not tab separated see TIP below."/>
+        <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your Wide Dataset that has unique identifiers.."/>
+        <param name="pval" type="text" size="30" value="" label="p-value column" help="Name of the column in your wide dataset that contains the p-values."/>
+        <param name="alpha" type="float" size="6" value="0.05" label="α" help="Value of α to be used for multiple correction.  Default α = 0.05."/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="outadjusted" label="${tool.name} on ${on_string}: Adjusted pval."/>
+        <data format="tabular" name="flags" label="${tool.name} on ${on_string}: Flags."/>
+    </outputs>
+    <tests>
+        <test>
+            <param name="input"  value="ST000006_anova_fixed_with_group_summary.tsv"/>
+            <param name="uniqID" value="Retention_Index" />
+            <param name="pval"   value="prob_greater_than_t_for_diff_Chardonnay, Carneros, CA 2003 (CH01)-Chardonnay, Carneros, CA 2003 (CH02)" />
+            <param name="alpha"  value="0.05" />
+            <output name="outadjusted" file="ST000006_multiple_testing_adjustment_outadjusted.tsv" />
+            <output name="flags"       file="ST000006_multiple_testing_adjustment_flags.tsv" />
+        </test>
+    </tests>
+    <help><![CDATA[
+
+@TIP_AND_WARNING@
+
+**Tool Description**
+
+The tool is designed to adjust p-values for multiple comparisons using three different methods:
+
+(1) The Bonferroni method and two false discovery rate (FDR) methods, (2) the Benjamini-Hochberg method (BH) and (3) the Benjamini-Yekutieli method (BY).
+The p-value correction can be carried out on p-values generated from the following tools: Analysis of Variance (ANOVA) Fixed Effects Model, Kruskal-Wallis Non-Parametric Test, T-test (Single Group) and T-test (Paired and/or Unpaired) in addition to p-values generated outside of these tools.
+The user can specify the total type I error α value.
+
+More details about the PH and BY methods are available in the papers:
+
+Benjamini, Y., and Hochberg, Y. (1995). Controlling the false discovery rate: a practical and powerful approach to multiple testing. Journal of the royal statistical society. Series B (Methodological), 289-300.
+
+Benjamini, Y., and Yekutieli, D. (2001). The control of the false discovery rate in multiple testing under dependency. Annals of statistics, 1165-1188.
+
+-------------------------------------------------------------------------------------------
+
+**Input**
+
+    - Two input datasets are required.
+
+@WIDE@
+
+@UNIQID@
+
+**Name for p-value column**
+
+    - Name of the column in your Wide Dataset that contains the p-values.
+
+**α**
+
+    - Value of α to be used for multiple correction.  Default α = 0.05.
+
+-------------------------------------------------------------------------------------------
+
+**Output**
+
+The tool produces two TSV files:
+
+(1) One TSV that contains the following five columns:
+	a column with unique feature IDs,
+	a column of the original p-values and
+	the last three columns contain the p-values adjusted using the 3 methods described above which are reflected in the column name.
+(2) The second TSV file contains flags where all significant values are flagged as 1 and non-significant values are flagged as 0.
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>