annotate kruskal_wallis.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
Ignore whitespace changes - Everywhere: Within whitespace: At end of lines:
rev   line source
1
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
1 <tool id="secimtools_kruskal_wallis" name="Kruskal-Wallis Non-Parametric Test" version="@WRAPPER_VERSION@">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
2 <description>on features (rows).</description>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
3 <macros>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
4 <import>macros.xml</import>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
5 </macros>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
6 <expand macro="requirements" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
7 <command detect_errors="exit_code"><![CDATA[
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
8 kruskal_wallis.py
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
9 --input $input
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
10 --design $design
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
11 --uniqueID $uniqueID
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
12 --group $group
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
13 --summaries $summaries
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
14 --flags $flags
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
15 --volcano $volcano
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
16 ]]></command>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
17 <inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
18 <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."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
19 <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."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
20 <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."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
21 <param name="group" type="text" size="30" label="Group/Treatment" help="Name of the column in your design file that contains group classifications."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
22 </inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
23 <outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
24 <data format="tabular" name="summaries" label="${tool.name} on ${on_string}: Summaries that include p-values and mean differences."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
25 <data format="tabular" name="flags" label="${tool.name} on ${on_string}: Flags that include 0.01, 0.05 and 0.10 significance levels for the pairwise differences. "/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
26 <data format="pdf" name="volcano" label="${tool.name} on ${on_string}: Volcano plots for the pairwise differences."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
27 </outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
28 <tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
29 <test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
30 <param name="input" value="ST000006_data.tsv"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
31 <param name="design" value="ST000006_design.tsv"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
32 <param name="uniqueID" value="Retention_Index" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
33 <param name="group" value="White_wine_type_and_source" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
34 <output name="summaries" file="ST000006_kruskal_wallis_with_group_summary.tsv" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
35 <output name="flags" file="ST000006_kruskal_wallis_with_group_flags.tsv" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
36 <output name="volcano" file="ST000006_kruskal_wallis_with_group_volcano.pdf" compare="sim_size" delta="10000" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
37 </test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
38 </tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
39 <help><![CDATA[
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
40
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
41 @TIP_AND_WARNING@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
42
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
43 **Tool Description**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
44
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
45 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.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
46 Unlike t-tests or an ANOVA F-test, a Kruskal-Wallis test is based on ranks where ranks are compared between groups.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
47 The test is performed (1) for samples from all groups together and (2) for the samples belonging to each group.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
48 The user is referred to the literature for more details on the Kruskal-Wallis test and the computation/approximation of corresponding p-values.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
49
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
50 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.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
51
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
52 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.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
53
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
54 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
55
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
56 **Input**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
57
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
58 - Two input datasets are required.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
59
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
60
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
61 @WIDE@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
62
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
63 **NOTE:** The sample IDs must match the sample IDs in the Design File
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
64 (below). Extra columns will automatically be ignored.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
65
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
66 @METADATA@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
67
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
68 @UNIQID@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
69
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
70 **Group/Treatment**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
71
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
72 - Name of the column the Design File that contain group classifications.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
73
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
74 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
75
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
76 **Output**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
77
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
78 Three different outputs are generated:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
79
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
80 (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.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
81 (2) a TSV file containing indicator flags. A flag = 1 if the difference between the groups is statistically significant.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
82 (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).
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
83
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
84 ]]></help>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
85 <expand macro="citations"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
86 </tool>