15
|
1 <tool id="MaREA" name="Metabolic Enrichment Analysis" version="1.0.1">
|
|
2 <description>for Galaxy - 1.0.1</description>
|
|
3 <macros>
|
|
4 <import>marea_macros.xml</import>
|
|
5 </macros>
|
|
6 <requirements>
|
|
7 <requirement type="package" version="0.23.0">pandas</requirement>
|
|
8 <requirement type="package" version="1.1.0">scipy</requirement>
|
|
9 <requirement type="package" version="0.10.1">cobra</requirement>
|
|
10 <requirement type="package" version="4.2.1">lxml</requirement>
|
|
11 <requirement type="package" version="0.8.1">svglib</requirement>
|
|
12 <requirement type="package" version="3.4.0">reportlab</requirement>
|
|
13 </requirements>
|
|
14 <command detect_errors="exit_code">
|
|
15 <![CDATA[
|
|
16 python $__tool_directory__/marea.py
|
|
17 --rules_selector $cond_rule.rules_selector
|
|
18 #if $cond_rule.rules_selector == 'Custom':
|
|
19 --custom ${cond_rule.Custom_rules}
|
|
20 --yes_no ${cond_rule.cond_map.yes_no}
|
|
21 #if $cond_rule.cond_map.yes_no == 'yes':
|
|
22 --custom_map $cond_rule.cond_map.Custom_map
|
|
23 #end if
|
|
24 #end if
|
|
25 #if $advanced.choice == 'true':
|
|
26 --none ${advanced.None}
|
|
27 --pValue ${advanced.pValue}
|
|
28 --fChange ${advanced.fChange}
|
|
29 --generate_svg ${advanced.generateSvg}
|
|
30 --generate_pdf ${advanced.generatePdf}
|
|
31 --generate_ras ${advanced.generateRas}
|
|
32 #else
|
|
33 --none true
|
|
34 --pValue 0.05
|
|
35 --fChange 1.5
|
|
36 --generate_svg false
|
|
37 --generate_pdf true
|
|
38 --generate_ras false
|
|
39 #end if
|
|
40 --tool_dir $__tool_directory__
|
|
41 --option $cond.type_selector
|
|
42 --out_log $log
|
|
43
|
|
44 #if $cond.type_selector == 'datasets':
|
|
45 --input_datas
|
|
46 #for $data in $cond.input_Datasets:
|
|
47 ${data.input}
|
|
48 #end for
|
|
49 --names
|
|
50 #for $data in $cond.input_Datasets:
|
|
51 ${data.input_name}
|
|
52 #end for
|
|
53 #elif $cond.type_selector == 'dataset_class':
|
|
54 --input_data ${input_data}
|
|
55 --input_class ${input_class}
|
|
56 #end if
|
|
57 ]]>
|
|
58 </command>
|
|
59
|
|
60 <inputs>
|
|
61 <conditional name="cond_rule">
|
|
62 <expand macro="options"/>
|
|
63 <when value="HMRcore">
|
|
64 </when>
|
|
65 <when value="Recon">
|
|
66 </when>
|
|
67 <when value="Custom">
|
|
68 <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules" />
|
|
69 <conditional name="cond_map">
|
|
70 <param name="yes_no" type="select" label="Custom map? (optional)">
|
|
71 <option value="no" selected="true">no</option>
|
|
72 <option value="yes">yes</option>
|
|
73 </param>
|
|
74 <when value="yes">
|
|
75 <param name="Custom_map" argument="--custom_map" type="data" format="xml, svg" label="custom-map.svg"/>
|
|
76 </when>
|
|
77 <when value="no">
|
|
78 </when>
|
|
79 </conditional>
|
|
80 </when>
|
|
81 </conditional>
|
|
82 <conditional name="cond">
|
|
83 <param name="type_selector" argument="--option" type="select" label="Input format:">
|
|
84 <option value="datasets" selected="true">RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N</option>
|
|
85 <option value="dataset_class">RNAseq of all samples + sample group specification</option>
|
|
86 </param>
|
|
87 <when value="datasets">
|
|
88 <repeat name="input_Datasets" title="RNAseq" min="2">
|
|
89 <param name="input" argument="--input_datas" type="data" format="tabular, csv, tsv" label="add dataset" />
|
|
90 <param name="input_name" argument="--names" type="text" label="Dataset's name:" value="Dataset" help="Default: Dataset" />
|
|
91 </repeat>
|
|
92 </when>
|
|
93 <when value="dataset_class">
|
|
94 <param name="input_data" argument="--input_data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples" />
|
|
95 <param name="input_class" argument="--input_class" type="data" format="tabular, csv, tsv" label="Sample group specification" />
|
|
96 </when>
|
|
97 </conditional>
|
|
98
|
|
99 <conditional name="advanced">
|
|
100 <param name="choice" type="boolean" checked="false" label="Use advanced options?" help="Use this options to choose custom rules for evaluation: pValue, Fold-Change threshold, how to solve (A and NaN) and specify output maps.">
|
|
101 <option value="true" selected="true">No</option>
|
|
102 <option value="false">Yes</option>
|
|
103 </param>
|
|
104 <when value="false">
|
|
105 </when>
|
|
106 <when value="true">
|
|
107 <param name="None" argument="--none" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?" />
|
|
108 <param name="pValue" argument="--pValue" type="float" size="20" value="0.05" max="1" min="0" label="P-value threshold:" help="min value 0" />
|
|
109 <param name="fChange" argument="--fChange" type="float" size="20" value="1.5" min="1" label="Fold-Change threshold:" help="min value 1" />
|
|
110 <param name="generateSvg" argument="--generateSvg" type="boolean" checked="false" label="Generate SVG map" help="should the program generate an editable svg map of the processes?" />
|
|
111 <param name="generatePdf" argument="--generatePdf" type="boolean" checked="true" label="Generate PDF map" help="should the program return a non editable (but displayble) pdf map of the processes?" />
|
|
112 <param name="generateRas" argument="--generateRas" type="boolean" checked="false" label="Generate Reaction Activity Score for each table" help="Generate Reaction Activity Score for each table" />
|
|
113 </when>
|
|
114 </conditional>
|
|
115 </inputs>
|
|
116
|
|
117 <outputs>
|
|
118 <data format="txt" name="log" label="${tool.name} - Log" />
|
|
119 <collection name="results" type="list" label="${tool.name} - Results">
|
|
120 <discover_datasets pattern="__name_and_ext__" directory="result"/>
|
|
121 </collection>
|
|
122 <collection name="ras" type="list" label="${tool.name} - RAS" format_source="tabular">
|
|
123 <filter>advanced['choice'] and advanced['generateRas']</filter>
|
|
124 <discover_datasets pattern="__name_and_ext__" directory="ras" format="tabular"/>
|
|
125 </collection>
|
|
126 </outputs>
|
|
127 <tests>
|
|
128 <test>
|
|
129 <param name="pValue" value="0.56"/>
|
|
130 <output name="log" file="log.txt"/>
|
|
131 </test>
|
|
132 </tests>
|
|
133 <help>
|
|
134 <![CDATA[
|
|
135
|
|
136 What it does
|
|
137 -------------
|
|
138
|
|
139 This tool analyzes RNA-seq dataset(s) as described in Graudenzi et al."`MaREA`_: Metabolic feature extraction, enrichment and visualization of RNAseq data" bioRxiv (2018): 248724.
|
|
140
|
|
141 Accepted files are:
|
|
142 - option 1) two or more RNA-seq datasets, each referring to samples in a given condition/class. The user can specify a label for each class (as e.g. "*classA*" and "*classB*");
|
|
143 - option 2) one RNA dataset and one class-file specifying the class/condition each sample belongs to.
|
|
144
|
|
145 Optional files:
|
|
146 - custom GPR (Gene-Protein-Reaction) rules. Two accepted formats:
|
|
147
|
|
148 * (Cobra Toolbox and CobraPy compliant) xml of metabolic model;
|
|
149 * .csv file specifyig for each reaction ID (column 1) the corresponding GPR rule (column 2).
|
|
150 - custom svg map. Graphical elements must have the same IDs of reactions. See HmrCore svg map for an example.
|
|
151
|
|
152 The tool generates:
|
|
153 1) a tab-separated file: reporting fold-change and p-values of reaction activity scores (RASs) between a pair of conditions/classes;
|
|
154 2) a metabolic map file (downlodable as .svg): visualizing up- and down-regulated reactions between a pair of conditions/classes;
|
|
155 3) a log file (.txt).
|
|
156
|
|
157 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.
|
|
158
|
|
159 Class-file format: each row of the class-file reports the sample ID (column1) and the label of the class/condition the sample belongs to (column 2).
|
|
160
|
|
161 To calculate P-Values and Fold-Changes and to generate maps, comparisons are performed for each possible pair of classes.
|
|
162
|
|
163 Output files will be named as classA_vs_classB. Reactions will conventionally be reported as up-regulated (down-regulated) if they are significantly more (less) active in class having label "classA".
|
|
164
|
|
165
|
|
166 Example input
|
|
167 -------------
|
|
168
|
|
169 **"Custom Rules"** option:
|
|
170
|
|
171 Custom Rules Dastaset:
|
|
172
|
|
173 @CUSTOM_RULES_EXEMPLE@
|
|
174
|
|
175 **"RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N"** option:
|
|
176
|
|
177 RNA-seq Dataset 1:
|
|
178
|
|
179 @DATASET_EXEMPLE1@
|
|
180
|
|
181 RNA-seq Dataset 2:
|
|
182
|
|
183 @DATASET_EXEMPLE2@
|
|
184
|
|
185 **"RNAseq of all samples + sample group specification"** option:
|
|
186
|
|
187 RNA-seq Dataset:
|
|
188
|
|
189 @DATASET_EXEMPLE1@
|
|
190
|
|
191 Class-file:
|
|
192
|
|
193 +------------+------------+
|
|
194 | Patient_ID | class |
|
|
195 +============+============+
|
|
196 | TCGAAA3529 | MSI |
|
|
197 +------------+------------+
|
|
198 | TCGAA62671 | MSS |
|
|
199 +------------+------------+
|
|
200 | TCGAA62672 | MSI |
|
|
201 +------------+------------+
|
|
202
|
|
203 |
|
|
204
|
|
205 .. class:: infomark
|
|
206
|
|
207 **TIP**: If your data is not TAB delimited, use `Convert delimiters to TAB`_.
|
|
208
|
|
209 .. class:: infomark
|
|
210
|
|
211 **TIP**: If your dataset is not split into classes, use `MaREA cluster analysis`_.
|
|
212
|
|
213 @REFERENCE@
|
|
214
|
|
215 .. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724
|
|
216 .. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj
|
|
217 .. _MaREA cluster analysis: http://link del tool di cluster.org
|
|
218
|
|
219 ]]>
|
|
220 </help>
|
|
221 <expand macro="citations" />
|
|
222 </tool>
|
|
223
|