|
0
|
1 <tool id="MaREA" name="Metabolic Enrichment Analysis">
|
|
|
2 <description>for Galaxy</description>
|
|
|
3 <requirements>
|
|
|
4 <requirement type="package">pandas</requirement>
|
|
|
5 <requirement type="package">scipy</requirement>
|
|
|
6 <requirement type="package">lxml</requirement>
|
|
|
7 <requirement type="package">svglib</requirement>
|
|
|
8 <requirement type="package">reportlab</requirement>
|
|
|
9 <requirement type="package">cobrapy</requirement>
|
|
|
10 <requirement type="package">python-libsbml</requirement>
|
|
|
11 </requirements>
|
|
|
12 <command>
|
|
|
13 <![CDATA[
|
|
|
14 python $__tool_directory__/marea.py
|
|
|
15 --rules_selector $cond_rule.rules_selector
|
|
|
16 #if $cond_rule.rules_selector == 'Custom':
|
|
|
17 --custom ${cond_rule.Custom_rules}
|
|
|
18 --yes_no ${cond_rule.cond_map.yes_no}
|
|
|
19 #if $cond_rule.cond_map.yes_no == 'yes':
|
|
|
20 --custom_map $cond_rule.cond_map.Custom_map
|
|
|
21 #end if
|
|
|
22 #end if
|
|
|
23 --none $None
|
|
|
24 --pValue $pValue
|
|
|
25 --fChange $fChange
|
|
|
26 --tool_dir $__tool_directory__
|
|
|
27 --option $cond.type_selector
|
|
|
28 --out_log $log
|
|
|
29 #if $cond.type_selector == 'datasets':
|
|
|
30 --input_datas
|
|
|
31 #for $data in $cond.input_Datasets:
|
|
|
32 ${data.input}
|
|
|
33 #end for
|
|
|
34 --names
|
|
|
35 #for $data in $cond.input_Datasets:
|
|
|
36 ${data.input_name}
|
|
|
37 #end for
|
|
|
38 #elif $cond.type_selector == 'dataset_class':
|
|
|
39 --input_data ${input_data}
|
|
|
40 --input_class ${input_class}
|
|
|
41 #end if
|
|
|
42 ]]>
|
|
|
43 </command>
|
|
|
44 <inputs>
|
|
|
45 <conditional name="cond_rule">
|
|
|
46 <param name="rules_selector" type="select" label="Gene-Protein-Reaction rules:">
|
|
|
47 <option value="HMRcore" selected="true">HMRcore rules</option>
|
|
|
48 <option value="Recon">Recon 2.2 rules</option>
|
|
|
49 <option value="Custom">Custom rules</option>
|
|
|
50 </param>
|
|
|
51 <when value="Custom">
|
|
|
52 <param name="Custom_rules" type="data" format="tabular, csv, tsv, xml" label="Custom rules"/>
|
|
|
53 <conditional name="cond_map">
|
|
|
54 <param name="yes_no" type="select" label="Custom map? (optional)">
|
|
|
55 <option value="no" selected="true">no</option>
|
|
|
56 <option value="yes">yes</option>
|
|
|
57 </param>
|
|
|
58 <when value="yes">
|
|
|
59 <param name="Custom_map" type="data" format="xml, svg" label="custom-map.svg"/>
|
|
|
60 </when>
|
|
|
61 </conditional>
|
|
|
62 </when>
|
|
|
63 </conditional>
|
|
|
64 <conditional name="cond">
|
|
|
65 <param name="type_selector" type="select" label="Input format:">
|
|
|
66 <option value="datasets" selected="true">RNAseq of group 1 + RNAseq of group 2 + … + RNAseq of group N</option>
|
|
|
67 <option value="dataset_class">RNAseq of all samples + sample group specification</option>
|
|
|
68 </param>
|
|
|
69 <when value="datasets">
|
|
|
70 <repeat name="input_Datasets" title="RNAseq" type="data" min="2">
|
|
|
71 <param name="input" type="data" format="tabular, csv, tsv" label="add dataset"/>
|
|
|
72 <param name="input_name" type="text" label="Dataset's name:" value="Dataset" help="Defalut: Dataset"/>
|
|
|
73 </repeat>
|
|
|
74 </when>
|
|
|
75 <when value="dataset_class">
|
|
|
76 <param name="input_data" type="data" format="tabular, csv, tsv" label="RNAseq of all samples"/>
|
|
|
77 <param name="input_class" type="data" format="tabular, csv, tsv" label="Sample group specification"/>
|
|
|
78 </when>
|
|
|
79 </conditional>
|
|
|
80 <param name="None" type="boolean" truevalue="true" falsevalue="false" checked="true" label="(A and NaN) solved as (A)?"/>
|
|
|
81 <param name="pValue" type="float" size="20" value="0.05" max="1" min="0" label="P-value threshold" help="min value 0"/>
|
|
|
82 <param name="fChange" type="float" size="20" value="1.5" min="1" label="Fold-Cahnge threshold" help="min value 1"/>
|
|
|
83 </inputs>
|
|
|
84 <outputs>
|
|
|
85 <data format="txt" name="log" label="Log"/>
|
|
|
86 <collection name="map_svg" type="list" label="file svg">
|
|
|
87 <filter>(cond_rule['rules_selector'] == 'HMRcore') or ((cond_rule['rules_selector'] == 'Custom') and (cond_rule['cond_map']['yes_no'] == 'yes'))</filter>
|
|
|
88 <discover_datasets pattern="__name_and_ext__" directory="map_svg"/>
|
|
|
89 </collection>
|
|
|
90 <collection name="map_pdf" type="list" label="file pdf">
|
|
|
91 <filter>(cond_rule['rules_selector'] == 'HMRcore') or ((cond_rule['rules_selector'] == 'Custom') and (cond_rule['cond_map']['yes_no'] == 'yes'))</filter>
|
|
|
92 <discover_datasets pattern="__name_and_ext__" directory="map_pdf"/>
|
|
|
93 </collection>
|
|
|
94 <collection name="table_out" type="list" label="file table">
|
|
|
95 <discover_datasets pattern="__name_and_ext__" directory="table_out"/>
|
|
|
96 </collection>
|
|
|
97 </outputs>
|
|
|
98 <help>
|
|
|
99 <![CDATA[
|
|
|
100
|
|
|
101 What it does
|
|
|
102 -------------
|
|
|
103
|
|
|
104 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.
|
|
|
105
|
|
|
106 The tool can be used to generate:
|
|
|
107 1) a tab-separated file: reporting fold-change and p-values of reaction activity scores (RASs) between a pair of conditions/classes
|
|
|
108 2) a metabolic map file (downlodable as .svg): visualizing up- and down-regulated reactions between a pair of conditions/classes
|
|
|
109 3) a log file (.txt)
|
|
|
110
|
|
|
111 Accepted files are:
|
|
|
112 1) or 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”).
|
|
|
113 2) or one RNA dataset and one class-file specifying the class/condition each sample belongs to.
|
|
|
114
|
|
|
115
|
|
|
116 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.
|
|
|
117
|
|
|
118 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).
|
|
|
119
|
|
|
120 To calculate P-Values and Fold-Changes and to generate maps, comparisons are performed for each possible pair of classes.
|
|
|
121
|
|
|
122 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”.
|
|
|
123
|
|
|
124 .. _MaREA: https://www.biorxiv.org/content/early/2018/01/16/248724
|
|
|
125
|
|
|
126
|
|
|
127 Example input
|
|
|
128 -------------
|
|
|
129
|
|
|
130 **"RNAseq of group 1 + RNAseq of group 2 + ... + RNAseq of group N" exemple input"** option:
|
|
|
131
|
|
|
132 Dataset 1:
|
|
|
133
|
|
|
134 +------------+------------+------------+------------+
|
|
|
135 | Hugo_ID | TCGAA62670 | TCGAA62671 | TCGAA62672 |
|
|
|
136 +============+============+============+============+
|
|
|
137 | HGNC:24086 | 0.523167 | 0.371355 | 0.925661 |
|
|
|
138 +------------+------------+------------+------------+
|
|
|
139 | HGNC:24086 | 0.568765 | 0.765567 | 0.456789 |
|
|
|
140 +------------+------------+------------+------------+
|
|
|
141 | HGNC:9876 | 0.876545 | 0.768933 | 0.987654 |
|
|
|
142 +------------+------------+------------+------------+
|
|
|
143 | HGNC:9 | 0.456788 | 0.876543 | 0.876542 |
|
|
|
144 +------------+------------+------------+------------+
|
|
|
145 | HGNC:23 | 0.876543 | 0.786543 | 0.897654 |
|
|
|
146 +------------+------------+------------+------------+
|
|
|
147
|
|
|
148 |
|
|
|
149
|
|
|
150 Dataset 2:
|
|
|
151
|
|
|
152 +-------------+------------+------------+------------+
|
|
|
153 | Hugo_Symbol | TCGAA62670 | TCGAA62671 | TCGAA62672 |
|
|
|
154 +=============+============+============+============+
|
|
|
155 | A1BG | 0.523167 | 0.371355 | 0.925661 |
|
|
|
156 +-------------+------------+------------+------------+
|
|
|
157 | A1CF | 0.568765 | 0.765567 | 0.456789 |
|
|
|
158 +-------------+------------+------------+------------+
|
|
|
159 | A2M | 0.876545 | 0.768933 | 0.987654 |
|
|
|
160 +-------------+------------+------------+------------+
|
|
|
161 | A4GALT | 0.456788 | 0.876543 | 0.876542 |
|
|
|
162 +-------------+------------+------------+------------+
|
|
|
163 | M664Y65 | 0.876543 | 0.786543 | 0.897654 |
|
|
|
164 +-------------+------------+------------+------------+
|
|
|
165
|
|
|
166 |
|
|
|
167
|
|
|
168 **"RNAseq of all samples + sample group specification"** option:
|
|
|
169
|
|
|
170 Dataset:
|
|
|
171
|
|
|
172 +------------+------------+------------+------------+
|
|
|
173 | Hugo_ID | TCGAA62670 | TCGAA62671 | TCGAA62672 |
|
|
|
174 +============+============+============+============+
|
|
|
175 | HGNC:24086 | 0.523167 | 0.371355 | 0.925661 |
|
|
|
176 +------------+------------+------------+------------+
|
|
|
177 | HGNC:24086 | 0.568765 | 0.765567 | 0.456789 |
|
|
|
178 +------------+------------+------------+------------+
|
|
|
179 | HGNC:9876 | 0.876545 | 0.768933 | 0.987654 |
|
|
|
180 +------------+------------+------------+------------+
|
|
|
181 | HGNC:9 | 0.456788 | 0.876543 | 0.876542 |
|
|
|
182 +------------+------------+------------+------------+
|
|
|
183 | HGNC:23 | 0.876543 | 0.786543 | 0.897654 |
|
|
|
184 +------------+------------+------------+------------+
|
|
|
185
|
|
|
186 |
|
|
|
187
|
|
|
188 Class-file:
|
|
|
189
|
|
|
190 +------------+------------+
|
|
|
191 | Patient_ID | class |
|
|
|
192 +============+============+
|
|
|
193 | TCGAAA3529 | MSI |
|
|
|
194 +------------+------------+
|
|
|
195 | TCGAA62671 | MSS |
|
|
|
196 +------------+------------+
|
|
|
197 | TCGAA62672 | MSI |
|
|
|
198 +------------+------------+
|
|
|
199
|
|
|
200 |
|
|
|
201
|
|
|
202
|
|
|
203
|
|
|
204 .. class:: warningmark
|
|
|
205
|
|
|
206 This tool expects input datasets consisting of tab-delimited columns.
|
|
|
207
|
|
|
208
|
|
|
209 .. class:: infomark
|
|
|
210
|
|
|
211 TIP: If your data is not TAB delimited, use `Convert delimiters to TAB`_.
|
|
|
212
|
|
|
213 .. class:: infomark
|
|
|
214
|
|
|
215 TIP: If your dataset is not split into classes, use `Cluster for MaREA`_.
|
|
|
216
|
|
|
217 This tool is developed by the `nome del gruppo di bioinformatica`_ at the `dipartimento di informatica disco`_.
|
|
|
218
|
|
|
219
|
|
|
220 .. _Convert delimiters to TAB: https://usegalaxy.org/?tool_id=Convert+characters1&version=1.0.0&__identifer=6t22teyofhj
|
|
|
221 .. _Cluster for MaREA: http://link del tool di cluster.org/
|
|
|
222 .. _nome del gruppo di bioinformatica: http://sito di bio.org
|
|
|
223 .. _dipartimento di informatica disco : http://www.disco.unimib.it/go/Home/English
|
|
|
224
|
|
|
225 ]]>
|
|
|
226 </help>
|
|
|
227 </tool>
|
|
|
228
|
|
|
229
|
|
|
230
|
|
|
231
|
|
|
232
|
|
|
233
|
|
|
234
|
|
|
235
|
|
|
236
|
|
|
237
|
|
|
238
|
|
|
239
|
|
|
240
|
