0
|
1 <tool id="MaREA_cluester" name="MaREA cluster analysis">
|
|
2 <description>of Reaction Activity Scores</description>
|
1
|
3 <macros>
|
|
4 <import>marea_macros.xml</import>
|
|
5 </macros>
|
|
6 <expand macro="requirements" />
|
0
|
7 <requirements>
|
|
8 <requirement type="package">scikit-learn</requirement>
|
|
9 <requirement type="package">matplotlib</requirement>
|
|
10 </requirements>
|
|
11 <command>
|
|
12 <![CDATA[
|
|
13 python $__tool_directory__/marea_cluster.py
|
|
14 --rules_selector $cond_rule.rules_selector
|
|
15 #if $cond_rule.rules_selector == 'Custom':
|
|
16 --custom ${cond_rule.Custom_rules}
|
|
17 #end if
|
|
18 --cond_hier $cond_hier.hier
|
|
19 #if $cond_hier.hier == 'yes':
|
|
20 --linkage ${cond_hier.linkage}
|
|
21 --dendro $dendrogram
|
|
22 #end if
|
|
23 --k_max $k_max
|
|
24 --k_min $k_min
|
|
25 --data $input
|
|
26 --name $name
|
|
27 --none $None
|
|
28 --tool_dir $__tool_directory__
|
|
29 --out_log $log
|
|
30 --elbow $elbow
|
|
31 ]]>
|
|
32 </command>
|
|
33 <inputs>
|
|
34 <conditional name="cond_rule">
|
1
|
35 <expand macro="options" />
|
0
|
36 <when value="Custom">
|
1
|
37 <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules" />
|
0
|
38 </when>
|
|
39 </conditional>
|
1
|
40 <param name="input" argument="--data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples" />
|
|
41 <param name="name" argument="--name" type="text" label="Output name prefix" value="dataset" />
|
|
42 <param name="k_min" argument="--k_min" type="integer" size="20" value="3" min="2" max="30" label="Min number of clusters (k) to be tested (k-means)"/>
|
|
43 <param name="k_max" argument="--k_max" type="integer" size="20" value="3" min="2" max="30" label="Max number of clusters (k) to be tested (k-means)"/>
|
|
44 <param name="None" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" help="If NO is selected, (A and NaN) is solved as (NaN)" />
|
0
|
45 <conditional name="cond_hier">
|
1
|
46 <param name="hier" argument="--cond_hier" type="select" label="Produce dendrogram (hierarchical clustering):">
|
0
|
47 <option value="no" selected="true">no</option>
|
|
48 <option value="yes">yes</option>
|
|
49 </param>
|
|
50 <when value="yes">
|
1
|
51 <param name="linkage" argument="--linkage" type="select" label="Linkage type:">
|
0
|
52 <option value="single" selected="true">Single: minimum distance between all observations of two sets</option>
|
|
53 <option value="complete">Complete: maximum distance between all observations of two sets</option>
|
|
54 <option value="average">Average: average distance between all observations of two sets</option>
|
|
55 </param>
|
|
56 </when>
|
|
57 </conditional>
|
|
58 </inputs>
|
1
|
59
|
0
|
60 <outputs>
|
1
|
61 <data format="txt" name="log" label="Log" />
|
0
|
62 <data format="pdf" name="dendrogram" label="$name dendrogram">
|
|
63 <filter>cond_hier['hier'] == 'yes'</filter>
|
|
64 </data>
|
1
|
65 <data format="pdf" name="elbow" label="$name elbow evaluation method" />
|
0
|
66 <collection name="cluster_out" type="list" label="Clusters $k_min - $k_max">
|
1
|
67 <discover_datasets pattern="__name_and_ext__" directory="cluster_out" />
|
0
|
68 </collection>
|
|
69 </outputs>
|
1
|
70
|
0
|
71 <help>
|
1
|
72 <![CDATA[
|
|
73
|
|
74 What it does
|
|
75 -------------
|
|
76
|
|
77 This tool performs cluster analysis of RNA-seq dataset(s) based of Graudenzi et al."`MaREA`_: Metabolic feature extraction, enrichment and visualization of RNAseq data" bioRxiv (2018): 248724.
|
|
78
|
|
79 Accepted files are:
|
|
80 1) For "Recon 2.2 rules" or "HMRcore rules" options: RNA-seq dataset. The user can specify a label of output prefix (as e.g. "K=3 *dataset*" and "K=4 *MyDataset*");
|
|
81 2) For "Custom rules" option: custom rules dataset, custom map (.svg) and RNA-seq dataset. The user can specify a label of output prefix (as e.g. "K=3 *dataset*" and "K=4 *MyDataset*").
|
|
82
|
|
83 Optional files:
|
|
84 - custom GPR (Gene-Protein-Reaction) rules. Two accepted formats:
|
|
85
|
|
86 * (Cobra Toolbox and CobraPy compliant) xml of metabolic model;
|
|
87 * .csv file specifyig for each reaction ID (column 1) the corresponding GPR rule (column 2).
|
|
88 - custom svg map. Graphical elements must have the same IDs of reactions. See HmrCore svg map for an example.
|
0
|
89
|
1
|
90 The tool generates:
|
|
91 1) Clusters n1 - n2 (n1 and n2 refer to min and max number of clusters): class-files (as many files as the chosen different number of clusters k to be tested) specifying the class/condition each sample belongs to;
|
|
92 2) Log: a log file (.txt);
|
|
93 3) *dataset* elbow evaluation method: diagram (.pdf) of elbow evaluation method;
|
|
94 4) *dataset* dendrogram (optional): dendrogram (.pdf) if the user chooses to produce a dendrogram (hierachical clustering).
|
|
95
|
|
96 RNA-seq datasets format: tab-separated text files, reporting the expression level (e.g., TPM, RPKM, ...) of each gene (row) for a given sample (column). Header: sample ID.
|
|
97
|
|
98
|
|
99 Example input
|
|
100 -------------
|
0
|
101
|
1
|
102 **RNA-seq dataset**:
|
|
103
|
|
104 @DATASET_EXEMPLE@
|
|
105
|
|
106 **Custom Rules Dataset**:
|
|
107
|
|
108 @CUSTOM_RULES_EXEMPLE@
|
|
109
|
|
110 **Custom Map**:
|
|
111
|
|
112 *see the generated HMRcore .svg map for example*
|
|
113
|
|
114
|
0
|
115
|
|
116 .. class:: infomark
|
|
117
|
1
|
118 **TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_.
|
|
119
|
|
120 .. class:: warningmark
|
|
121
|
|
122 If dendrogram it's too populated, each path and label can be not clear.
|
|
123
|
|
124 @REFERENCE@
|
0
|
125
|
1
|
126 .. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724
|
|
127 .. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj
|
|
128
|
|
129
|
|
130 ]]>
|
0
|
131 </help>
|
1
|
132 <expand macro="citations" />
|
0
|
133 </tool>
|
|
134
|
|
135
|