0
|
1 <tool id="secimtools_mahalanobis_distance" name="Penalized Mahalanobis Distance (PMD)" version="@WRAPPER_VERSION@">
|
|
2 <description>to compare groups</description>
|
|
3 <macros>
|
|
4 <import>macros.xml</import>
|
|
5 </macros>
|
|
6 <expand macro="requirements" />
|
|
7 <stdio>
|
|
8 <exit_code range="1:" level="warning" description="RuntimeWarning"/>
|
|
9 </stdio>
|
|
10 <command detect_errors="exit_code"><![CDATA[
|
|
11 mahalanobis_distance.py
|
|
12 --input $input
|
|
13 --design $design
|
|
14 --ID $uniqID
|
|
15 --figure $plot
|
|
16 --distanceToMean $out1
|
|
17 --distancePairwise $out2
|
|
18
|
|
19 #if $group
|
|
20 --group $group
|
|
21 #end if
|
|
22
|
|
23 #if $levels
|
|
24 --levels $levels
|
|
25 #end if
|
|
26
|
|
27 #if $p
|
|
28 --per $p
|
|
29 #end if
|
|
30
|
|
31 #if $order
|
|
32 --order $order
|
|
33 #end if
|
|
34
|
|
35 #if $penalty
|
|
36 --penalty $penalty
|
|
37 #end if
|
|
38 ]]></command>
|
|
39 <inputs>
|
|
40 <param name="input" type="data" format="tabular" label="Wide Dataset" help="Input your tab-separated wide format dataset. If file not tab separated see TIP below."/>
|
|
41 <param name="design" type="data" format="tabular" label="Design File" help="Input your design file (tab-separated). Note you need a 'sampleID' column. If not tab separated see TIP below."/>
|
|
42 <param name="uniqID" type="text" size="30" value="" label="Unique Feature ID" help="Name of the column in your wide dataset that has unique identifiers.."/>
|
|
43 <param name="group" type="text" size="30" label="Group/Treatment [Optional]" help="Name of the column in your design file that contains group classifications." />
|
|
44 <param name="order" type="text" size="30" label="Input Run Order Name [Optional]" help="Enter the name of the column containing the order samples were run. Spelling and capitalization must be exact." />
|
|
45 <param name="levels" type="text" size="30" label="Additional groups to separate by [Optional]" help="Enter additional group(s) name(s) to include. Spelling and capitalization must be exact. If more than one group separate with ','." />
|
|
46 <param name="p" type="float" value= ".95" size="6" label="Threshold" help="Threshold for standard distribution, specified as a percentile. Default = 0.95." />
|
|
47 <param name="penalty" type="float" value= "0.5" size="6" label="λ Penalty" help="λ Penalty to use in the distance. The default is λ=0.5." />
|
|
48 </inputs>
|
|
49 <outputs>
|
|
50 <data format="pdf" name="plot" label="${tool.name} on ${on_string}: plot" />
|
|
51 <data format="tabular" name="out1" label="${tool.name} on ${on_string}: toMean" />
|
|
52 <data format="tabular" name="out2" label="${tool.name} on ${on_string}: pairwise" />
|
|
53 </outputs>
|
|
54 <tests>
|
|
55 <test>
|
|
56 <param name="input" value="ST000006_data.tsv"/>
|
|
57 <param name="design" value="ST000006_design.tsv"/>
|
|
58 <param name="uniqID" value="Retention_Index" />
|
|
59 <param name="group" value="White_wine_type_and_source" />
|
|
60 <param name="penalty" value="0.5" />
|
|
61 <output name="plot" file="ST000006_mahalanobis_distance_figure.pdf" compare="sim_size" delta="10000" />
|
|
62 <output name="out1" file="ST000006_mahalanobis_distance_to_mean.tsv" />
|
|
63 <output name="out2" file="ST000006_mahalanobis_distance_pairwise.tsv" />
|
|
64 </test>
|
|
65 </tests>
|
|
66 <help><![CDATA[
|
|
67
|
|
68 @TIP_AND_WARNING@
|
|
69
|
|
70 **Tool Description**
|
|
71
|
|
72 The Penalized Mahalanobis distance (PMD) tool can be used to compare samples within a group and accounts for the correlation structure between metabolites.
|
|
73 In contrast, Standardized Euclidian distance (SED) relies solely on geometric distance and ignores any dependency structures between features.
|
|
74 PMD incorporates the correlation structure inside the distance measurement.
|
|
75
|
|
76 When correlation structure and dependency between metabolites is ignored, the features inverse variance-covariance matrix simplifies to a diagonal matrix with diagonal values - in this case, MD simplifies to SED.
|
|
77 When the number of features is greater than the number of samples, the inverse of the features variance-covariance matrix does not exist.
|
|
78 This is the case for most -omic data. Here, the inverse is estimated using a regularization method (Archambeau et al. 2004).
|
|
79 The details of the regularization algorithm can be found in Supplementary file 3 in Kirpich et al. 2017.
|
|
80
|
|
81 Archambeau C, Vrins F, Verleysen M. Flexible and Robust Bayesian Classification by Finite Mixture Models. InESANN 2004 (pp. 75-80).
|
|
82
|
|
83 **NOTE:** Because of the nature of the tool, groups with less than 3 samples will be discarded from the analysis.
|
|
84
|
|
85
|
|
86 **Input**
|
|
87
|
|
88 - Two input datasets are required.
|
|
89
|
|
90 @WIDE@
|
|
91
|
|
92 **NOTE:** The sample IDs must match the sample IDs in the Design File
|
|
93 (below). Extra columns will automatically be ignored.
|
|
94
|
|
95 @METADATA@
|
|
96
|
|
97 @UNIQID@
|
|
98
|
|
99 @GROUP_OPTIONAL@
|
|
100
|
|
101 - **Warning:** All groups must contain 3 or more samples.
|
|
102
|
|
103
|
|
104 @RUNORDER_OPTIONAL@
|
|
105
|
|
106 **Additional groups to separate by [Optional]**
|
|
107
|
|
108 - Enter additional group(s) name(s) to include. Spelling and capitalization must be exact. If more than one group, separate them with a comma
|
|
109 - **Warning:** All groups must contain 3 or more samples.
|
|
110
|
|
111
|
|
112 **Percentile cutoff**
|
|
113
|
|
114 - The percentile cutoff for standard distributions. The default is 0.95.
|
|
115
|
|
116 **λ Penalty**
|
|
117
|
|
118 - λ Penalty to use in the distance. The default is λ=0.5.
|
|
119
|
|
120 --------------------------------------------------------------------------------
|
|
121
|
|
122 **Output**
|
|
123
|
|
124 The tool outputs three different files:
|
|
125
|
|
126 (1) a PDF file containing 2D scatter plots and boxplots for the distances
|
|
127
|
|
128 (2) a TSV file containing distances from the sample to the estimated mean
|
|
129
|
|
130 (3) a TSV file containing distances from the sample to other samples.
|
|
131
|
|
132 If the grouping variable is specified by the user, the distances are computed both within the groups and for the entire dataset.
|
|
133
|
|
134 ]]></help>
|
|
135 <expand macro="citations"/>
|
|
136 </tool>
|