Mercurial > repos > recetox > waveica

comparison waveica.xml @ 5:fba892edb9d9 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"planemo upload for repository https://github.com/RECETOX/galaxytools/tree/master/tools/waveica commit 98e541a75678eee749261630610b946c258fd5f3"
author recetox
date Wed, 23 Mar 2022 11:35:00 +0000
parents 8b55efc7d117
children cf3f2f964d80
comparison
equal deleted inserted replaced
4:8b55efc7d117 5:fba892edb9d9
1 <tool id="waveica" name="WaveICA" version="@TOOL_VERSION@+galaxy0" python_template_version="3.5"> 1 <tool id="waveica" name="WaveICA" version="@TOOL_VERSION@+galaxy1" python_template_version="3.5">
2 <description>removal of batch effects for untargeted metabolomics data</description> 2 <description>removal of batch effects for untargeted metabolomics data</description>
3 <macros> 3 <macros>
4 <import>waveica_macros.xml</import> 4 <import>macros.xml</import>
5 </macros> 5 </macros>
6 <expand macro="creator" /> 6 <expand macro="creator"/>
7 7
8 <requirements> 8 <requirements>
9 <requirement type="package" version="@TOOL_VERSION@">r-recetox-waveica</requirement> 9 <requirement type="package" version="@TOOL_VERSION@">r-recetox-waveica</requirement>
10 </requirements> 10 </requirements>
11 <command detect_errors="aggressive"><![CDATA[ 11 <command detect_errors="aggressive"><![CDATA[
12 Rscript 12 Rscript
13 -e 'source("${__tool_directory__}/waveica_wrapper.R")' 13 -e 'source("${__tool_directory__}/waveica_wrapper.R")'
14 14
37 37
38 -e 'store_data(normalized_data,"$normalized_data")' 38 -e 'store_data(normalized_data,"$normalized_data")'
39 ]]></command> 39 ]]></command>
40 40
41 <inputs> 41 <inputs>
42 <expand macro="general_parameters" /> 42 <expand macro="general_parameters"/>
43 <expand macro="wf" /> 43 <expand macro="wf"/>
44 <conditional name="batch_correction"> 44 <conditional name="batch_correction">
45 <param name="mode" type="select" label="Batch correction mode" help="'multiple batches' takes into account inter- and intrabatch intensity drift; 'single batch' relies only on the injection order of the samples and requires no batch information [2]"> 45 <param name="mode" type="select" label="Batch correction mode" help="'multiple batches' takes into account
46 inter- and intrabatch intensity drift; 'single batch' relies only on the injection order of the samples and
47 requires no batch information [2]">
46 <option value="batchwise" selected="true">Multiple batches</option> 48 <option value="batchwise" selected="true">Multiple batches</option>
47 <option value="single_batch">Single batch (or no batch information)</option> 49 <option value="single_batch">Single batch (or no batch information)</option>
48 </param> 50 </param>
49 <when value="batchwise"> 51 <when value="batchwise">
50 <expand macro="batchwise_parameters" /> 52 <expand macro="batchwise_parameters"/>
51 </when> 53 </when>
52 <when value="single_batch"> 54 <when value="single_batch">
53 <expand macro="singlebatch_parameters" /> 55 <expand macro="singlebatch_parameters"/>
54 </when> 56 </when>
55 </conditional> 57 </conditional>
56 <expand macro="exclude_blanks" /> 58 <expand macro="exclude_blanks"/>
57 </inputs> 59 </inputs>
58 60
59 <expand macro="outputs" /> 61 <expand macro="outputs"/>
60 62
61 <tests> 63 <tests>
62 <test> 64 <test>
63 <param name="data" value="input_data.csv" ftype="csv" /> 65 <param name="data" value="input_data.csv" ftype="csv"/>
64 <param name="mode" value="batchwise" /> 66 <param name="mode" value="batchwise"/>
65 <param name="wavelet_filter" value="d" /> 67 <param name="wavelet_filter" value="d"/>
66 <param name="filter_length" value="2" /> 68 <param name="filter_length" value="2"/>
67 <param name="k" value="20" /> 69 <param name="k" value="20"/>
68 <param name="t" value="0.05" /> 70 <param name="t" value="0.05"/>
69 <param name="t2" value="0.05" /> 71 <param name="t2" value="0.05"/>
70 <param name="alpha" value="0" /> 72 <param name="alpha" value="0"/>
71 <output name="normalized_data" file="normalized_data.tsv" /> 73 <output name="normalized_data" file="normalized_data.tsv"/>
72 </test> 74 </test>
73 <test> 75 <!-- The following test has different results on three platform I've tried -->
74 <param name="data" value="input_data_nobatch.csv" ftype="csv" /> 76 <!-- <test>
75 <param name="mode" value="single_batch" /> 77 <param name="data" value="input_data_nobatch.csv" ftype="csv"/>
76 <param name="wavelet_filter" value="d" /> 78 <param name="mode" value="single_batch"/>
77 <param name="filter_length" value="2" /> 79 <param name="wavelet_filter" value="d"/>
78 <param name="k" value="20" /> 80 <param name="filter_length" value="2"/>
79 <param name="alpha" value="0" /> 81 <param name="k" value="20"/>
80 <param name="cutoff" value="0" /> 82 <param name="alpha" value="0"/>
81 <output name="normalized_data" file="normalized_data_nobatch.tsv" /> 83 <param name="cutoff" value="0"/>
84 <output name="normalized_data" file="normalized_data_nobatch.tsv"/>
85 </test> -->
86 <test expect_failure="true">
87 <param name="data" value="na_data.csv" ftype="csv"/>
82 </test> 88 </test>
83 <test expect_failure="true"> 89 <test expect_failure="true">
84 <param name="data" value="na_data.csv" ftype="csv" /> 90 <param name="data" value="incomplete_metadata_data.csv" ftype="csv"/>
85 </test>
86 <test expect_failure="true">
87 <param name="data" value="incomplete_metadata_data.csv" ftype="csv" />
88 </test> 91 </test>
89 </tests> 92 </tests>
90 93
91 <help><![CDATA[ 94 <help>
92 **Description** 95 <![CDATA[
93 96 @HELP@
94 Removal of batch effects for large-scale untargeted metabolomics data based on wavelet analysis and independent component analysis. 97 ]]>
95 The WaveICA method uses the time trend of samples over the injection order, decomposes the original data into new multi-scale features, extracts and removes the batch effect resulting in normalized intensities across samples. 98 </help>
96
97 The input is an intensity-by-feature table with metadata in the following format:
98
99 +---------------+--------+------------+----------------+-------+------------+--------------+-------------+-------------+-----+
100 | sampleName | class | sampleType | injectionOrder | batch | M85T34 | M86T41 | M86T518 | M86T539 | ... |
101 +===============+========+============+================+=======+============+==============+=============+=============+=====+
102 | VT_160120_002 | sample | sample | 1 | 1 | 228520.064 | 35646729.215 | 2386896.979 | 1026645.836 | ... |
103 +---------------+--------+------------+----------------+-------+------------+--------------+-------------+-------------+-----+
104 | QC1 | sample | QC | 2 | 1 | 90217.384 | 35735702.457 | 2456290.696 | 1089246.460 | ... |
105 +---------------+--------+------------+----------------+-------+------------+--------------+-------------+-------------+-----+
106 | ... | ... | ... | ... | ... | ... | ... | ... | ... | ... |
107 +---------------+--------+------------+----------------+-------+------------+--------------+-------------+-------------+-----+
108
109
110 + The required columns are **sampleName**, **class**, **sampleType**, **injectionOrder**, and the **features** that you want to normalize.
111 + The **batch** column is required if batch correction mode is **Multiple batches** and optional otherwise.
112 + The presence of any additional columns (except features) will result in incorrect batch correction or job failure.
113 + the input table must not contain missing values. Missing intensities must be filled with 0.
114 + **sampleType** column accepts three possible values: [QC, sample, blank] (case insensitive).
115 + **class** column is used to denote a biological group of a sample (e.g., positive/negative species). The column accepts any values.
116 + the **output** is the same table with corrected feature intensities.
117
118 .. rubric:: **Footnotes**
119 .. [1] for details on wavelet-filter parameters refer to R `wavelets::wt.filter <https://www.rdocumentation.org/packages/wavelets/versions/0.3-0.2/topics/wt.filter>`_;
120 .. [2] when using 'Multiple batches', please cite the WaveICA (2019) paper; else, cite WaveICA 2.0 (2021) paper;
121
122
123 ]]></help>
124 99
125 <citations> 100 <citations>
126 <citation type="doi">10.1016/j.aca.2019.02.010</citation> 101 <citation type="doi">10.1016/j.aca.2019.02.010</citation>
127 <citation type="doi">10.1007/s11306-021-01839-7</citation> 102 <citation type="doi">10.1007/s11306-021-01839-7</citation>
128 </citations> 103 </citations>