Mercurial > repos > proteore > proteore_topgo

comparison topGO.xml @ 10:e3430084c996 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit ad5f1c5a1a71d7fa2bc8bac408856aa80b0fc2a3
author proteore
date Tue, 18 Dec 2018 10:06:00 -0500
parents 70c0c8757f5f
children fa2e27165d5d
comparison
equal deleted inserted replaced
9:70c0c8757f5f 10:e3430084c996
1 <tool id="topGO" name="topGO" version="2018.09.21"> 1 <tool id="topGO" name="Enrichment analysis for Gene Ontology" version="2018.12.17">
2 <description> 2 <description>(Human, Mouse, Rat)[topGO]</description>
3 Enrichment analysis for Gene Ontology
4 </description>
5 <requirements> 3 <requirements>
6 <requirement type="package" version="3.4.1">R</requirement> 4 <requirement type="package" version="3.4.1">R</requirement>
7 <requirement type="package" version="3.0.0">r-ggplot2</requirement> 5 <requirement type="package" version="3.0.0">r-ggplot2</requirement>
8 <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement> 6 <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
9 <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement> 7 <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>
10 <requirement type="package" version="3.5.0">bioconductor-org.ce.eg.db</requirement> 8 <requirement type="package" version="3.5.0">bioconductor-org.rn.eg.db</requirement>
11 <requirement type="package" version="3.5.0">bioconductor-org.dm.eg.db</requirement> 9 <!--requirement type="package" version="3.6.0">bioconductor-org.ce.eg.db</requirement-->
12 <requirement type="package" version="3.5.0">bioconductor-org.sc.sgd.db</requirement> 10 <!--requirement type="package" version="3.6.0">bioconductor-org.dm.eg.db</requirement-->
11 <!--requirement type="package" version="3.6.0">bioconductor-org.sc.sgd.db</requirement-->
13 <!--requirement type="package" version="3.5.0">bioconductor-org.at.tair.db</requirement--> 12 <!--requirement type="package" version="3.5.0">bioconductor-org.at.tair.db</requirement-->
14 <requirement type="package" version="1.56.0">bioconductor-graph</requirement> 13 <requirement type="package" version="1.56.0">bioconductor-graph</requirement>
15 <requirement type="package" version="1.40.0">bioconductor-annotationdbi</requirement> 14 <requirement type="package" version="1.40.0">bioconductor-annotationdbi</requirement>
16 <requirement type="package" version="3.5.0">bioconductor-go.db</requirement> 15 <requirement type="package" version="3.5.0">bioconductor-go.db</requirement>
17 <requirement type="package" version="2.30.0">bioconductor-topgo</requirement> 16 <requirement type="package" version="2.30.0">bioconductor-topgo</requirement>
18 </requirements> 17 </requirements>
19 <stdio> 18 <stdio>
20 <exit_code range="1:" /> 19 <exit_code range="1:" />
21 </stdio> 20 </stdio>
22 <command><![CDATA[ 21 <command><![CDATA[
23 22
24 #if $inputtype.filetype == "file_all": 23 Rscript --vanilla $__tool_directory__/topGO_enrichment.R
25 Rscript --vanilla $__tool_directory__/enrichment_v3.R 24 --inputtype="$inputtype.filetype"
26 --inputtype tabfile 25 --input='$inputtype.genelist'
27 --input '$inputtype.genelist' 26
28 --ontology '$ontocat' 27 #if $inputtype.filetype == "file"
29 --option '$option' 28 --column='$inputtype.column'
30 --threshold '$threshold' 29 --header='$inputtype.header'
31 --correction '$correction'
32 --textoutput '$condtext.textoutput'
33 --barplotoutput '$condbar.barplotoutput'
34 --dotplotoutput '$conddot.dotplotoutput'
35 --column '$inputtype.column'
36 --geneuniverse '$geneuniverse'
37 --header '$inputtype.header'
38 #end if 30 #end if
39 31
40 32 --ontology='$ontocat'
41 #if $inputtype.filetype == "copy_paste": 33 --option='$option'
42 Rscript --vanilla $__tool_directory__/enrichment_v3.R 34 --threshold='$threshold'
43 --inputtype copypaste 35 --correction='$correction'
44 --input '$inputtype.genelist' 36 --textoutput='true'
45 --ontology '$ontocat' 37 --plot='$plot'
46 --option '$option' 38 --geneuniverse='$geneuniverse'
47 --threshold '$threshold' 39 --background="$background_genes.background"
48 --correction '$correction' 40
49 --textoutput '$condtext.textoutput' 41 #if $background_genes.background == "true"
50 --barplotoutput '$condbar.barplotoutput' 42 --background_genes="$background_genes.inputtype.genelist"
51 --dotplotoutput '$conddot.dotplotoutput' 43 --background_input_type="$background_genes.inputtype.filetype"
52 --column c1 44 #if $background_genes.inputtype.filetype == "file"
53 --geneuniverse '$geneuniverse' 45 --background_header="$background_genes.inputtype.header"
54 --header None 46 --background_column="$background_genes.inputtype.column"
47 #end if
55 #end if 48 #end if
56
57
58 49
59 ]]></command> 50 ]]></command>
60 51
61 <inputs> 52 <inputs>
62 <conditional name="inputtype"> 53 <conditional name="inputtype">
63 <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."> 54 <param name="filetype" type="select" label="Enter your IDs (Ensembl Gene only)" help="Copy/paste or from a file">
64 <option value="file_all" selected="true">Input file containing your identifiers</option> 55 <option value="file" selected="true">Input file containing your IDs</option>
65 <option value="copy_paste">Copy/paste your list of IDs</option> 56 <option value="copy_paste">Copy/paste your list of IDs</option>
66 </param> 57 </param>
67 <when value="copy_paste"> 58 <when value="copy_paste">
68 <param name="genelist" type="text" label="Enter a list of identifiers"> 59 <param name="genelist" type="text" label="Enter a list of IDs">
69 <sanitizer> 60 <sanitizer>
70 <valid initial="string.printable"> 61 <valid initial="string.printable">
71 <remove value="&apos;"/> 62 <remove value="&apos;"/>
72 </valid> 63 </valid>
73 <mapping initial="none"> 64 <mapping initial="none">
74 <add source="&apos;" target="__sq__"/> 65 <add source="&apos;" target="__sq__"/>
75 </mapping> 66 </mapping>
76 </sanitizer> 67 </sanitizer>
77 </param> 68 </param>
78 </when> 69 </when>
79 <when value="file_all"> 70 <when value="file">
80 <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."/> 71 <param name="genelist" type="data" format="txt,tabular" label="Select your file" help=""/>
81 <param name="column" type="text" label="Please specify the column where your Ensembl IDs are (e.g : Enter 'c1' for column n°1..)" value="c1"/> 72 <param name="column" type="text" label="Column number of IDs" help="For example, fill in 'c1' if it is the first column, 'c2' if it is the second column and so on"/>
82 73 <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
83 <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false">
84 <option value="TRUE" selected="true">Yes</option>
85 <option value="FALSE" selected="false">No</option>
86 </param>
87 </when> 74 </when>
88 </conditional> 75 </conditional>
89 <param name="geneuniverse" type="select" label="Select a specie"> 76 <conditional name="background_genes">
90 <!--option value="org.At.tair.db" >Arabidopsis</option--> 77 <param name="background" type="boolean" checked="false" truevalue="true" falsevalue="false" label="Define your own background IDs ?"/>
91 <option value="org.Ce.eg.db" >Worm (C. elegans)</option> 78 <when value="true">
92 <option value="org.Dm.eg.db" >Fly (D. melanogaster)</option> 79 <conditional name="inputtype">
93 <option value="org.Hs.eg.db" selected="true">Human (H. sapiens)</option> 80 <param name="filetype" type="select" label="Enter your background IDs (Ensembl gene IDs)" help="(e.g : ENSG00000139618)">
94 <option value="org.Mm.eg.db" >Mouse (M. musculus)</option> 81 <option value="file" selected="true">Input file containing your background IDs</option>
95 <option value="org.Sc.sgd.db" >Yeast (S. cerevisiae)</option> 82 <option value="copy_paste">Copy/paste your background IDs</option>
96 </param>
97
98 <param name="ontocat" type="select" label="Ontology category">
99 <option value="BP" >Biological Process</option>
100 <option value="CC" >Cellular Component</option>
101 <option value="MF" >Molecular Function</option>
102 </param> 83 </param>
103 84 <when value="copy_paste">
104 <param name="option" type="select" label="Choose the topGO option for your analysis"> 85 <param name="genelist" type="text" label="Copy/paste your background IDs" help="IDs must be separated by spaces into the form field, for example: ENSG00000139618 ENSG00000007350">
105 <option value="classic" >Classic fisher test</option> 86 <sanitizer>
106 <option value="elim" selected="true">Elim</option> 87 <valid initial="string.printable">
107 <option value="weight01" >Weight01</option> 88 <remove value="&apos;"/>
108 <option value="parentchild" >ParentChild</option> 89 </valid>
90 <mapping initial="none">
91 <add source="&apos;" target="__sq__"/>
92 </mapping>
93 </sanitizer>
109 </param> 94 </param>
110 <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"/> 95 </when>
111 <param name="correction" label="Choose a correction for multiple testing" type="select"> 96 <when value="file">
112 <option value="none" >None</option> 97 <param name="genelist" type="data" format="txt,tabular" label="Select file that contains your background IDs list" help=""/>
113 <option value="holm">Holm correction</option> 98 <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header ?" />
114 <option value="hochberg" >Hochberg correction</option> 99 <param name="column" type="text" label="Column number of IDs" value="c1" help="For example, fill in 'c1' if it is the first column, 'c2' if it is the second column and so on"/>
115 <option value="hommel" >Hommel correction</option> 100 </when>
116 <option value="bonferroni" >Bonferroni correction</option> 101 </conditional>
117 <option value="BH" selected="true">Benjamini and Hochberg</option> 102 </when>
118 <option value="BY" >Benjamini and Yekutieli</option> 103 <when value="false"/>
119 <option value="fdr" >FDR</option> 104 </conditional>
120 </param> 105 <param name="geneuniverse" type="select" label="Species">
121 <conditional name="condtext"> 106 <!--option value="org.At.tair.db" >Arabidopsis</option-->
122 <param name="textoutput" type="select" label="Generate a text file for results"> 107 <!--option value="org.Ce.eg.db" >Worm (C. elegans)</option-->
123 <option value="TRUE">Yes</option> 108 <!--option value="org.Dm.eg.db" >Fly (D. melanogaster)</option-->
124 <option value="FALSE">No</option> 109 <option value="org.Hs.eg.db" selected="true">Human (Homo sapiens)</option>
125 </param> 110 <option value="org.Mm.eg.db" >Mouse (Mouse musculus)</option>
126 <when value="TRUE"/> 111 <option value="org.Rn.eg.db" >Rat (Rattus norvegicus)</option>
127 <when value="FALSE"/> 112 <!--option value="org.Sc.sgd.db" >Yeast (S. cerevisiae)</option-->
128 </conditional> 113 </param>
129 <conditional name="condbar"> 114 <param name="ontocat" type="select" label="GO terms category">
130 <param name="barplotoutput" type="select" label="Generate a barplot of over-represented GO terms"> 115 <option value="BP" >Biological Process</option>
131 <option value="TRUE">Yes</option> 116 <option value="CC" >Cellular Component</option>
132 <option value="FALSE">No</option> 117 <option value="MF" >Molecular Function</option>
133 </param> 118 </param>
134 <when value="TRUE"/> 119 <param name="option" type="select" label="Select the topGO parameter (see user doc)">
135 <when value="FALSE"/> 120 <option value="classic" >Classic Fisher test</option>
136 </conditional> 121 <option value="elim" selected="true">Elim</option>
137 <conditional name="conddot"> 122 <option value="weight01" >Weight01</option>
138 <param name="dotplotoutput" type="select" label="Generate a dotplot of over-represented GO terms"> 123 <option value="parentchild" >ParentChild</option>
139 <option value="TRUE">Yes</option> 124 </param>
140 <option value="FALSE">No</option> 125 <param name="threshold" type="text" label="p-value threshold (e.g : 1e-3)" value="1e-3"/>
141 </param> 126 <param name="correction" label="Multiple testing procedure (p-value adjustment)" type="select">
142 <when value="TRUE"/> 127 <option value="none" >None</option>
143 <when value="FALSE"/> 128 <option value="holm">Holm correction</option>
144 </conditional> 129 <option value="hochberg" >Hochberg correction</option>
130 <option value="hommel" >Hommel correction</option>
131 <option value="bonferroni" >Bonferroni correction</option>
132 <option value="BH" selected="true">Benjamini and Hochberg</option>
133 <option value="BY" >Benjamini and Yekutieli</option>
134 <option value="fdr" >FDR</option>
135 </param>
136 <!--param name="textoutput" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Generate a text file for results" /-->
137 <param name="plot" type="select" display="checkboxes" multiple="true" label="Graphical display" optional="false">
138 <option selected = "true" value="dotplot">dot-plot</option>
139 <option value="barplot">bar-plot</option>
140 </param>
145 </inputs> 141 </inputs>
146 <outputs> 142 <outputs>
147 143
148 <data name="outputtext" format="tabular" label="Text output for topGO analysis $ontocat category" from_work_dir="result.csv"> 144 <data name="outputtext" format="tsv" label="Text output for topGO analysis $ontocat category" from_work_dir="result">
149 <filter>condtext['textoutput']=="TRUE"</filter> 145 <filter>textoutput</filter>
150 </data> 146 </data>
151 147
152 <data name="outputbarplot" format="png" label="Barplot output for topGO analysis $ontocat category" from_work_dir="barplot.png"> 148 <data name="outputbarplot" format="png" label="Barplot output for topGO analysis $ontocat category" from_work_dir="barplot.png">
153 <filter>condbar['barplotoutput']=="TRUE"</filter> 149 <filter>barplot</filter>
154 </data> 150 </data>
155 151
156 <data name="outputdotplot" format="png" label="Dotplot output for topGO analysis $ontocat category" from_work_dir="dotplot.png"> 152 <data name="outputdotplot" format="png" label="Dotplot output for topGO analysis $ontocat category" from_work_dir="dotplot.png">
157 <filter>conddot['dotplotoutput']=="TRUE"</filter> 153 <filter>dotplot</filter>
158 </data> 154 </data>
159 155
160 </outputs> 156 </outputs>
161 <tests> 157 <tests>
162 <test> 158 <test>
186 </test> 182 </test>
187 </tests> 183 </tests>
188 <help><![CDATA[ 184 <help><![CDATA[
189 185
190 186
191 **Galaxy component based on R package topGO.** 187 **Description**
188
189 This tool is based on R package topGO. topGO package provides tools for testing GO terms while accounting for the topology of the GO graph. Different test statistics and different methods for eliminating local similarities and dependencies between GO terms can be applied.
190
191 This component computes 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 genes/proteins (of the selected species) associated associated with GO terms of the chosen category (BP,CC,MF).
192
193 -----
192 194
193 **Input required** 195 **Input required**
194 196
195 This component works with Ensembl gene ids (e.g : ENSG0000013618). You can 197 This component works with Ensembl gene IDs (e.g : ENSG0000013618). You can copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab)
196 copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab) 198 and then specifying the column number that contains the ENSG IDs.
197 where there are contained. 199
198 200 -----
199 **Principle** 201
200 202 **Parameters**
201 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**. 203
204 "Species": "Species": the three available species are Homo sapiens, Mus musculus and Rattus norvegicus
205
206 "GO terms category": select either Biogical Process (BP)(by default), Cellular Component (CC) or Molecular Function (MF)
207
208 "Select the topGO parameter (see user doc)": topGO provides a classic Fisher test for evaluating which GO terms are over-represented in your gene/protein list; other methodologies are also provided (Elim, Weight01, Parentchild). For the merits of each option and their algorithmic descriptions, please refer to topGO manual:
209 https://bioconductor.org/packages/release/bioc/vignettes/topGO/inst/doc/topGO.pdf
210
211 "p-value threshold (e.g : 1e-3)": must be in the form of "1e-5" (i.e. 0.00001)
212
213 "Multiple testing procedure (p-value adjustment): several FDR procedure for multiple testing and p-value adjustment are available: Holm, Hochberg
214 Hommel, Bonferroni, BH (Benjamini-Hochberg), BY (Benjamini-Yekutieli), FDR. Default is BH (most commonly used)
215
216 -----
202 217
203 **Output** 218 **Output**
204 219
205 Three kind of outputs are available : a textual output, a barplot output and 220 Three outputs are available : a textual output, a barplot and/or a dotplot (set by default) graphical outputs.
206 a dotplot output. 221
207 222 *Textual output*
208 *Textual output* : 223
209 The text output lists all the GO-terms that were found significant under the specified threshold. 224 The text output lists all the GO-terms that were found significantly enriched according to the specified threshold (p-value).
210 225
211 226 The different fields are as follow:
212 The different fields are as follow : 227
213 228 - Annotated : number of genes in the selected species that are annotated with the GO-term.
214 - Annotated : number of genes in org.Hs.eg.db which are annotated with the GO-term. 229
215 230 - Significant : number of genes belonging to your input annotated with the GO-term.
216 - Significant : number of genes belonging to your input which are annotated with the GO-term. 231
217 232 - Expected : represents the expected number of interesting genes mapped to the GO term if the interesting genes were randomly distributed over all GO terms.
218 - 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. 233
219 234 - p-values : p-value obtained after the test
220 - pvalues : pvalue obtained after the test 235
221 236 - ( q-values : additional column with adjusted pvalues )
222 - ( qvalues : additional column with adjusted pvalues )
223
224
225 **Tests**
226
227 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 :
228 https://bioconductor.org/packages/release/bioc/vignettes/topGO/inst/doc/topGO.pdf
229
230 **Multiple testing corrections**
231
232 Furthermore, the following corrections for multiple testing can also be applied :
233
234 - holm
235
236 - hochberg
237
238 - hommel
239
240 - bonferroni
241
242 - BH
243
244 - BY
245
246 - fdr
247 237
248 ----- 238 -----
249 239
250 .. class:: infomark 240 .. class:: infomark
251 241
252 **Authors** 242 **Authors**
253 243
254 Alexa A and Rahnenfuhrer J (2016). topGO: Enrichment Analysis for Gene Ontology. R package version 2.30.0. 244 Alexa A, Rahnenführer J, Lengauer T. Improved scoring of functional groups from gene expression data by decorrelating GO graph structure. Bioinformatics. 2006. 22(13):1600-7. PubMed PMID: 16606683.
245
246 -----
247
248 .. class:: infomark
255 249
256 **Galaxy integration** 250 **Galaxy integration**
257 251
258 Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR 252 Lisa Perus, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
259 253
260 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform 254 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
261 255
262 This work has been partially funded through the French National Agency for Research (ANR) IFB project. 256 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
263 257
264 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool. 258 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
265 259