diff ttest.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/ttest.xml	Mon Mar 08 22:04:06 2021 +0000
@@ -0,0 +1,125 @@
+<tool id="secimtools_ttest" name="T-Test (Paired or Unpaired)" version="@WRAPPER_VERSION@">
+    <description>on features.</description>
+    <macros>
+        <import>macros.xml</import>
+    </macros>
+    <expand macro="requirements" />
+    <command detect_errors="exit_code"><![CDATA[
+ttest.py
+--input $input
+--design $design
+--uniqueID $uniqueID
+--group $group
+--pairing $pairing
+--summaries $summaries
+--flags $flags
+--volcano $volcano
+#if $order
+    --order $order
+#end if
+    ]]></command>
+    <inputs>
+        <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file is not tab separated see TIP below."/>
+        <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
+        <param name="uniqueID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers."/>
+        <param name="group" type="text" size="30" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
+        <param name="pairing" size="30" display="radio" type="select" value="unpaired" label="Select Test" help="Select either paired (dependent samples) or unpaired (independent samples) tests.">
+           <option value="unpaired"  selected="true">Unpaired (Independent Samples)</option>
+           <option value="paired"    selected="true">Paired (Dependent Samples)</option>
+        </param>
+        <param name="order" type="text" value="" size="30" label="Pairing ID" help="Name of the column in your design file that contains Pairing IDs. Ignored for Unpaired (Independent Samples) test."/>
+    </inputs>
+    <outputs>
+        <data format="tabular" name="summaries" label="${tool.name} on ${on_string}: Summaries that include p-values and mean differences."/>
+        <data format="tabular" name="flags" label="${tool.name} on ${on_string}: Flags that include 0.01,  0.05 and  0.10 significance levels for the differences. "/>
+        <data format="pdf" name="volcano" label="${tool.name} on ${on_string}: Volcano plots for the 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" />
+            <param name="pairing"  value="unpaired" />
+            <output name="summaries" file="ST000006_ttest_select_unpaired_summary.tsv" />
+            <output name="flags"     file="ST000006_ttest_select_unpaired_flags.tsv" />
+            <output name="volcano"   file="ST000006_ttest_select_unpaired_volcano.pdf" compare="sim_size" delta="10000"/>
+        </test>
+    </tests>
+    <help><![CDATA[
+
+@TIP_AND_WARNING@
+
+**Tool Description**
+
+The tool performs a two-sided t-test for two groups of dependent samples (paired or dependent t-test) or multiple (two or more) groups of independent samples (unpaired or independent t-test).
+The user selects which test (paired or unpaired) to perform.
+
+In an unpaired t-test, the samples within and between groups are independent.
+The test is performed for all pairs of conditions specified using the Group/Treatment field.
+For example, if there are three treatment conditions (Control, Time1 and Time2) then t-tests will be performed for: (i) Control vs Time1, (ii) Control vs Time2, and (iii) Time1 vs Time2.
+Note that this will give slightly different results than the contrast in an ANOVA because the ANOVA uses all groups to estimate the error.
+
+A paired t-test can be performed for pairs of treatment conditions where sample pairs are known and specified by the user in the Pairing ID field.
+Here, the difference between the measurements for the pairs is calculated.
+To ensure that the differences are taken in the same order across all pairs, the Group/Treatment variable is required.
+The differences will be calculated beween the groups in the order that the groups appear in the Design File.
+The Pairing ID specifies which samples are paired. A two sided t-test will be performed for the test that the difference is zero.
+
+--------------------------------------------------------------------------------
+
+**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**
+
+        - List with the name of the column the Design File that contains group classifications.
+
+**Pairing ID**
+
+        - Name of the column in your Design File that contains Pairing IDs.  An example is given below:
+
+    +----------+--------+--------+
+    | sampleID | group  | pairID |
+    +==========+========+========+
+    | sample1  | g1     |   p1   |
+    +----------+--------+--------+
+    | sample2  | g1     |   p2   |
+    +----------+--------+--------+
+    | sample3  | g1     |   p3   |
+    +----------+--------+--------+
+    | sample4  | g2     |   p1   |
+    +----------+--------+--------+
+    | sample5  | g2     |   p2   |
+    +----------+--------+--------+
+    | sample6  | g2     |   p3   |
+    +----------+--------+--------+
+    | ...      | ...    |   ...  |
+    +----------+--------+--------+
+
+
+
+--------------------------------------------------------------------------------
+
+**Output**
+
+The tool outputs 3 files:
+
+(1) a TSV file with the results table containing p-values for each test and the corresponding differences between the means for comparisons between the groups.
+(2) a TSV file with an indicator flag = 1 if the difference between the groups is statistically significant using provided α levels.
+(3) a PDF file with volcano plots visual inspection of the differences between group means and p-values. The red dashed line in volcano plot(s) corresponds to a p-value = 0.01 cutoff (2 on the negative log base 10 scale).
+
+    ]]></help>
+    <expand macro="citations"/>
+</tool>