Mercurial > repos > malex > secimtools

annotate data_normalization_and_rescaling.xml @ 1:2e7d47c0b027 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
"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_data_normalization_and_rescaling" name="Normalization and Re-Scaling" version="@WRAPPER_VERSION@">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
2 <description>of data.</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><![CDATA[
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
8 data_normalization_and_rescaling.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 --uniqID $uniqID
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
12 --method $method
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
13 --out $out
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
14 ]]></command>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
15 <inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
16 <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input tab-separated wide format dataset. 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
17 <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
18 <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."/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
19 <param name="method" size="30" type="select" value="" display="radio" label="Normalization Method" help="Method to be used for normalization and re-scaling of the data.">
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
20 <option value="mean" selected="true">Mean (samples)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
21 <option value="sum" selected="true">Sum (samples)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
22 <option value="median" selected="true">Median (samples)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
23 <option value="centering" selected="true">Centering (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
24 <option value="auto" selected="true">Autoscaling (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
25 <option value="pareto" selected="true">Pareto (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
26 <option value="range" selected="true">Range (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
27 <option value="level" selected="true">Level (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
28 <option value="vast" selected="true">VAST (features)</option>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
29 </param>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
30 </inputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
31 <outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
32 <data format="tabular" name="out" label="${tool.name} on ${on_string}: Normalized data"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
33 </outputs>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
34 <tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
35 <test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
36 <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
37 <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
38 <param name="uniqID" value="Retention_Index" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
39 <param name="method" value="mean" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
40 <output name="out" file="ST000006_data_normalization_and_rescaling_mean_output.tsv" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
41 </test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
42 <test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
43 <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
44 <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
45 <param name="uniqID" value="Retention_Index" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
46 <param name="method" value="vast" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
47 <output name="out" file="ST000006_data_normalization_and_rescaling_vast_output.tsv" />
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
48 </test>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
49 </tests>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
50 <help><![CDATA[
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 @TIP_AND_WARNING@
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 **Tool Description**
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 The first three normalization methods (Mean, Sum and Median) perform re-scaling of the data by sample.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
57 Each individual sample (column) in the wide dataset is re-scaled by dividing all feature values within that column by the mean, median or sum of those feature values.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
58 Each sample (column) is re-scaled independently from other samples (columns).
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 The last six normalization methods (Centering, Pareto, Autoscaling, Range, Level, and Variable Stability (VAST)) perform scaling of the data by features.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
61 Each feature (row) is re-scaled independently from other features.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
62 Each individual feature (row) in the wide dataset is centered by subtraction of the mean of that feature and is re-scaled by dividing all the feature values within that row by the scaling factor.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
63 The scaling factor is computed from the feature values in the current row and depends on the selected method.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
64 Centering does not have a scaling factor and does not perform division, Autoscaling uses standard deviation, Pareto scaling uses the square root of the standard deviation, Range uses the difference between the max and min values, and Level uses the mean.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
65 VAST scaling is performed in two steps. The first step is Autoscaling, followed by division of the resulting feature values in each row by the coefficient of variation for that feature.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
66
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
67 More information on the scaling methods are available from the literature:
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
68
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
69 Keun, Hector C., Timothy MD Ebbels, Henrik Antti, Mary E. Bollard, Olaf Beckonert, Elaine Holmes, John C. Lindon, and Jeremy K. Nicholson. "Improved analysis of multivariate data by variable stability scaling: application to NMR-based metabolic profiling." Analytica chimica acta 490, no. 1 (2003): 265-276.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
70 van den Berg, Robert A., Huub CJ Hoefsloot, Johan A. Westerhuis, Age K. Smilde, and Mariët J. van der Werf. "Centering, scaling, and transformations: improving the biological information content of metabolomics data." BMC genomics 7, no. 1 (2006): 142
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
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 **Input Files**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
76
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
77 - Two input datasets are required.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
78
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
79 @WIDE@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
80
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
81 **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
82 (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
83
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
84 @METADATA@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
85
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
86 @UNIQID@
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
87
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
88 **Normalization Method**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
89
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
90 - Method to be used for normalization and re-scaling of the data. The parenthesis indicates whether the method will be applied to samples or features.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
91
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
92 --------------------------------------------------------------------------------
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
93
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
94 **Output**
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
95
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
96 TSV file containing the same column names as in the original Wide Dataset where the values in each cell correspond to the values after normalization/re-scaling.
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
97
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
98 ]]></help>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
99 <expand macro="citations"/>
2e7d47c0b027 "planemo upload for repository https://malex@toolshed.g2.bx.psu.edu/repos/malex/secimtools"
malex
parents:
diff changeset
100 </tool>