Mercurial > repos > proteore > proteore_topgo

comparison topGO.xml @ 0:92dfcfb03add draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit 2e441b4969ae7cf9aeb227a1d47c43ef7268a5e6-dirty
author proteore
date Wed, 22 Aug 2018 10:39:30 -0400
parents
children 5569a3f066cf
comparison
equal deleted inserted replaced
-1:000000000000 0:92dfcfb03add
1 <tool id="topGO" name="topGO" version="2018.08.22">
2 <description>
3 Enrichment analysis for Gene Ontology
4 </description>
5 <requirements>
6 <requirement type="package" version="3.4.1">R</requirement>
7 <requirement type="package" version="2.2.1">r-ggplot2</requirement>
8 <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
9 <requirement type="package" version="1.56.0">bioconductor-graph</requirement>
10 <requirement type="package" version="1.40.0">bioconductor-annotationdbi</requirement>
11 <requirement type="package" version="3.5.0">bioconductor-go.db</requirement>
12 <requirement type="package" version="2.30.0">bioconductor-topgo</requirement>
13 </requirements>
14 <stdio>
15 <exit_code range="1:" />
16 </stdio>
17 <command><![CDATA[
18
19 #if $inputtype.filetype == "file_all":
20 Rscript --vanilla $__tool_directory__/enrichment_v3.R
21 --inputtype tabfile
22 --input '$inputtype.genelist'
23 --ontology '$ontocat'
24 --option '$option'
25 --threshold '$threshold'
26 --correction '$correction'
27 --textoutput '$condtext.textoutput'
28 --barplotoutput '$condbar.barplotoutput'
29 --dotplotoutput '$conddot.dotplotoutput'
30 --column '$inputtype.column'
31 --geneuniverse '$geneuniverse'
32 --header '$inputtype.header'
33 #end if
34
35
36 #if $inputtype.filetype == "copy_paste":
37 Rscript --vanilla $__tool_directory__/enrichment_v3.R
38 --inputtype copypaste
39 --input '$inputtype.genelist'
40 --ontology '$ontocat'
41 --option '$option'
42 --threshold '$threshold'
43 --correction '$correction'
44 --textoutput '$condtext.textoutput'
45 --barplotoutput '$condbar.barplotoutput'
46 --dotplotoutput '$conddot.dotplotoutput'
47 --column c1
48 --geneuniverse '$geneuniverse'
49 --header None
50 #end if
51
52
53
54 ]]></command>
55
56 <inputs>
57 <conditional name="inputtype">
58 <param name="filetype" type="select" label="Select your type of input file" help="The identifiers must be Ensembl gene IDs (e.g : ENSG00000139618). If it is not the case, please use the ID Mapping tool.">
59 <option value="file_all" selected="true">Input file containing your identifiers</option>
60 <option value="copy_paste">Copy/paste your list of IDs</option>
61 </param>
62 <when value="copy_paste">
63 <param name="genelist" type="text" label="Enter a list of identifiers">
64 <sanitizer>
65 <valid initial="string.printable">
66 <remove value="&apos;"/>
67 </valid>
68 <mapping initial="none">
69 <add source="&apos;" target="__sq__"/>
70 </mapping>
71 </sanitizer>
72 </param>
73 </when>
74 <when value="file_all">
75 <param name="genelist" type="data" format="txt,tabular" label="Choose an input file" help="This file must imperatively have 1 column filled with IDs consistent with the database that will be used. Please use the MappingIDs component if this is not the case."/>
76 <param name="column" type="text" label="Please specify the column where you would like to apply the comparison (e.g : Enter c1)" value="c1"/>
77
78 <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false">
79 <option value="TRUE" selected="true">Yes</option>
80 <option value="FALSE" selected="false">No</option>
81 </param>
82 </when>
83 </conditional>
84 <param name="geneuniverse" type="select" label="Select a specie">
85 <option value="org.At.tair.db" >Arabidopsis</option>
86 <option value="org.Ce.eg.db" >C.elegans</option>
87 <option value="org.Dm.eg.db" >Fly</option>
88 <option value="org.Hs.eg.db" selected="true">Human</option>
89 <option value="org.Mm.eg.db" >Mouse</option>
90 <option value="org.Sc.sqd.db" >Yeast</option>
91 </param>
92
93 <param name="ontocat" type="select" label="Ontology category">
94 <option value="BP" >Biological Process</option>
95 <option value="CC" >Cellular Component</option>
96 <option value="MF" >Molecular Function</option>
97 </param>
98
99 <param name="option" type="select" label="Choose the topGO option for your analysis">
100 <option value="classic" >Classic fisher test</option>
101 <option value="elim" selected="true">Elim</option>
102 <option value="weight01" >Weight01</option>
103 <option value="parentchild" >ParentChild</option>
104 </param>
105 <param name="threshold" type="text" label="Enter the p-value threshold level under the form 1e-level wanted (e.g : 1e-3)" value="1e-3"/>
106 <param name="correction" label="Choose a correction for multiple testing" type="select">
107 <option value="none" >None</option>
108 <option value="holm">Holm correction</option>
109 <option value="hochberg" >Hochberg correction</option>
110 <option value="hommel" >Hommel correction</option>
111 <option value="bonferroni" >Bonferroni correction</option>
112 <option value="BH" selected="true">Benjamini and Hochberg</option>
113 <option value="BY" >Benjamini and Yekutieli</option>
114 <option value="fdr" >FDR</option>
115 </param>
116 <conditional name="condtext">
117 <param name="textoutput" type="select" label="Generate a text file for results">
118 <option value="TRUE">Yes</option>
119 <option value="FALSE">No</option>
120 </param>
121 <when value="TRUE"/>
122 <when value="FALSE"/>
123 </conditional>
124 <conditional name="condbar">
125 <param name="barplotoutput" type="select" label="Generate a barplot of over-represented GO terms">
126 <option value="TRUE">Yes</option>
127 <option value="FALSE">No</option>
128 </param>
129 <when value="TRUE"/>
130 <when value="FALSE"/>
131 </conditional>
132 <conditional name="conddot">
133 <param name="dotplotoutput" type="select" label="Generate a dotplot of over-represented GO terms">
134 <option value="TRUE">Yes</option>
135 <option value="FALSE">No</option>
136 </param>
137 <when value="TRUE"/>
138 <when value="FALSE"/>
139 </conditional>
140 </inputs>
141 <outputs>
142
143 <data name="outputtext" format="tabular" label="Text output for topGO analysis $ontocat category" from_work_dir="result.csv">
144 <filter>condtext['textoutput']=="TRUE"</filter>
145 </data>
146
147 <data name="outputbarplot" format="png" label="Barplot output for topGO analysis $ontocat category" from_work_dir="barplot.png">
148 <filter>condbar['barplotoutput']=="TRUE"</filter>
149 </data>
150
151 <data name="outputdotplot" format="png" label="Dotplot output for topGO analysis $ontocat category" from_work_dir="dotplot.png">
152 <filter>conddot['dotplotoutput']=="TRUE"</filter>
153 </data>
154
155 </outputs>
156 <tests>
157 <test>
158 <conditional name="inputtype">
159 <param name="filetype " value="tabfile"/>
160 <param name="genelist" value="ID_Converter_FKW_Lacombe_et_al_2017_OK.txt"/>
161 <param name="column" value="c8"/>
162 <param name="header" value="TRUE"/>
163 </conditional>
164 <param name="ontocat" value="BP"/>
165 <param name="option" value="elim"/>
166 <param name="threshold" value="1e-3"/>
167 <param name="correction" value="BH"/>
168 <conditional name="condtext">
169 <param name="textoutput" value="TRUE"/>
170 </conditional>
171 <conditional name="condbar">
172 <param name="barplotoutput" value="TRUE"/>
173 </conditional>
174 <conditional name="conddot">
175 <param name="dotoutput" value="TRUE"/>
176 </conditional>
177 <param name="geneuniverse" value="org.Hs.eg.db"/>
178 <output name="outputtext" file="Text_output_for_topGO_analysis_BP_category.tabular"/>
179 <output name="outputbarplot" file="Barplot_output_for_topGO_analysis_BP_category.png"/>
180 <output name="outputdotplot" file="Dotplot_output_for_topGO_analysis_BP_category.png"/>
181 </test>
182 </tests>
183 <help><![CDATA[
184
185
186 **Galaxy component based on R package topGO.**
187
188 **Input required**
189
190 This component works with Ensembl gene ids (e.g : ENSG0000013618). You can
191 copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab)
192 where there are contained.
193
194 **Principle**
195
196 This component provides the GO terms representativity of a gene list in one ontology category (Biological Process "BP", Cellular Component "CC", Molecular Function "MF"). This representativity is evaluated in comparison to the background list of all human genes associated associated with GO terms of the chosen category (BP,CC,MF). This background is given by the R package "org.Hs.eg.db", which is a genome wide association package for **human**.
197
198 **Output**
199
200 Three kind of outputs are available : a textual output, a barplot output and
201 a dotplot output.
202
203 *Textual output* :
204 The text output lists all the GO-terms that were found significant under the specified threshold.
205
206
207 The different fields are as follow :
208
209 - Annotated : number of genes in org.Hs.eg.db which are annotated with the GO-term.
210
211 - Significant : number of genes belonging to your input which are annotated with the GO-term.
212
213 - Expected : show an estimate of the number of genes a node of size Annotated would have if the significant genes were to be randomly selected from the gene universe.
214
215 - pvalues : pvalue obtained after the test
216
217 - ( qvalues : additional column with adjusted pvalues )
218
219
220 **Tests**
221
222 topGO provides a classic fisher test for evaluating if some GO terms are over-represented in your gene list, but other options are also provided (elim, weight01,parentchild). For the merits of each option and their algorithmic descriptions, please refer to topGO manual :
223 https://bioconductor.org/packages/release/bioc/vignettes/topGO/inst/doc/topGO.pdf
224
225 **Multiple testing corrections**
226
227 Furthermore, the following corrections for multiple testing can also be applied :
228
229 - holm
230
231 - hochberg
232
233 - hommel
234
235 - bonferroni
236
237 - BH
238
239 - BY
240
241 - fdr
242
243 -----
244
245 .. class:: infomark
246
247 **Authors**
248
249 Alexa A and Rahnenfuhrer J (2016). topGO: Enrichment Analysis for Gene Ontology. R package version 2.30.0.
250
251 **Galaxy integration**
252
253 Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
254
255 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform
256
257 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
258
259 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
260
261 ]]></help>
262 <citations>
263 </citations>
264
265 </tool>