Mercurial > repos > proteore > proteore_clusterprofiler
comparison cluster_profiler.xml @ 11:cc2bd0d2afa2 draft
planemo upload commit 9664cb97c1ab9d21af2b302eb976015178089a72
author | proteore |
---|---|
date | Fri, 27 Sep 2019 05:48:17 -0400 |
parents | d951677a50d4 |
children | 85f039f53414 |
comparison
equal
deleted
inserted
replaced
10:d951677a50d4 | 11:cc2bd0d2afa2 |
---|---|
1 <tool id="cluter_profiler" name="GO terms classification and enrichment analysis" version="2019.06.27.1"> | 1 <tool id="cluter_profiler" name="GO terms classification and enrichment analysis" version="2019.09.26"> |
2 <description>(Human, Mouse, Rat)[clusterProfiler]</description> | 2 <description>(Human, Mouse, Rat)[clusterProfiler]</description> |
3 <requirements> | 3 <requirements> |
4 <requirement type="package" version="3.4.1">R</requirement> | 4 <requirement type="package">R</requirement> |
5 <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement> | 5 <requirement type="package" version="3.8.2">bioconductor-org.hs.eg.db</requirement> |
6 <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement> | 6 <requirement type="package" version="3.8.2">bioconductor-org.mm.eg.db</requirement> |
7 <requirement type="package" version="3.5.0">bioconductor-org.Rn.eg.db</requirement> | 7 <requirement type="package" version="3.8.2">bioconductor-org.Rn.eg.db</requirement> |
8 <requirement type="package" version="3.2.0">bioconductor-dose</requirement> | 8 <requirement type="package" version="3.10.2">bioconductor-dose</requirement> |
9 <requirement type="package" version="3.4.4">bioconductor-clusterprofiler</requirement> | 9 <requirement type="package" version="3.12.0">bioconductor-clusterprofiler</requirement> |
10 </requirements> | 10 </requirements> |
11 <command detect_errors="exit_code"><![CDATA[ | 11 <command detect_errors="exit_code"><![CDATA[ |
12 Rscript "$__tool_directory__/GO-enrich.R" | 12 Rscript "$__tool_directory__/GO-enrich.R" |
13 #if $input.ids == "text" | 13 #if $input.ids == "text" |
14 --input_type="text" | 14 --input_type="text" |
17 --input_type="file" | 17 --input_type="file" |
18 --input="$input.file" | 18 --input="$input.file" |
19 --ncol="$input.ncol" | 19 --ncol="$input.ncol" |
20 --header="$input.header" | 20 --header="$input.header" |
21 #end if | 21 #end if |
22 | 22 |
23 --id_type="$idti.idtypein" | 23 --id_type="$idti.idtypein" |
24 | 24 |
25 --species="$species" | 25 --species="$species" |
26 | 26 |
27 #if $ggo.go_represent == "true" | 27 #if $ggo.go_represent == "true" |
30 #else | 30 #else |
31 --go_represent="false" | 31 --go_represent="false" |
32 #end if | 32 #end if |
33 | 33 |
34 #if $ego.go_enrich == "true" | 34 #if $ego.go_enrich == "true" |
35 --plot="$ego.plot" | 35 --plot="$ego.plot" |
36 --go_enrich="true" | 36 --go_enrich="true" |
37 --pval_cutoff="$ego.pval" | 37 --pval_cutoff="$ego.pval" |
38 --qval_cutoff="$ego.qval" | 38 --qval_cutoff="$ego.qval" |
39 #if $ego.universe.universe_option == "true" | 39 #if $ego.universe.universe_option == "true" |
40 #if $ego.universe.universe_input.universe_ids == "text" | 40 #if $ego.universe.universe_input.universe_ids == "text" |
49 --universe_id_type="$ego.universe.universe_idti.universe_idtypein" | 49 --universe_id_type="$ego.universe.universe_idti.universe_idtypein" |
50 #end if | 50 #end if |
51 #else | 51 #else |
52 --go_enrich="false" | 52 --go_enrich="false" |
53 #end if | 53 #end if |
54 | 54 |
55 --onto_opt="$ontology" > $log | 55 --onto_opt="$ontology" > $log |
56 ]]></command> | 56 ]]></command> |
57 <inputs> | 57 <inputs> |
58 <conditional name="input" > | 58 <conditional name="input" > |
59 <param name="ids" type="select" label="Enter your IDs (UniProt Accession number or Gene ID)" help="Copy/paste or from a file (e.g. table)" > | 59 <param name="ids" type="select" label="Enter your IDs (UniProt Accession number or Gene ID)" help="Copy/paste or from a file (e.g. table)" > |
85 <option value="Uniprot">UniProt accession number (e.g. P31946)</option> | 85 <option value="Uniprot">UniProt accession number (e.g. P31946)</option> |
86 <option value="Entrez">Entrez Gene ID (e.g. 4151)</option> | 86 <option value="Entrez">Entrez Gene ID (e.g. 4151)</option> |
87 </param> | 87 </param> |
88 <when value="Uniprot"/> | 88 <when value="Uniprot"/> |
89 <when value="Entrez"/> | 89 <when value="Entrez"/> |
90 </conditional> | 90 </conditional> |
91 <param name="species" type="select" label="Species" > | 91 <param name="species" type="select" label="Species" > |
92 <option value="org.Hs.eg.db">Human (Homo sapiens) </option> | 92 <option value="org.Hs.eg.db">Human (Homo sapiens) </option> |
93 <option value="org.Mm.eg.db">Mouse (Mus musculus) </option> | 93 <option value="org.Mm.eg.db">Mouse (Mus musculus) </option> |
94 <option value="org.Rn.eg.db">Rat (Rattus norvegicus)</option> | 94 <option value="org.Rn.eg.db">Rat (Rattus norvegicus)</option> |
95 </param> | 95 </param> |
224 | 224 |
225 **Description** | 225 **Description** |
226 | 226 |
227 This tool is based on R package clusterProfiler and allows to perform GO terms classification and enrichment analyses on gene/protein sets (e.g. given a set of genes that are up-regulated under certain conditions, an enrichment analysis will find which GO terms are over-represented (or under-represented) using annotations for that gene/protein set). | 227 This tool is based on R package clusterProfiler and allows to perform GO terms classification and enrichment analyses on gene/protein sets (e.g. given a set of genes that are up-regulated under certain conditions, an enrichment analysis will find which GO terms are over-represented (or under-represented) using annotations for that gene/protein set). |
228 | 228 |
229 Given a list of IDs, this tool: | 229 Given a list of IDs, this tool: |
230 | 230 |
231 (i) performs gene classification based on GO distribution at a specific level, | 231 (i) performs gene classification based on GO distribution at a specific level, |
232 | 232 |
233 (ii) calculates GO categories enrichment (over- or under-representation) for the IDs of the input list, compared to a background. User has the possibility to use background corresponding to the whole organism or to a user-defined list. In this latter case, we recommand to use the "Build tissue-specific expression dataset" ProteoRE tool to create this list according to your need. | 233 (ii) calculates GO categories enrichment (over- or under-representation) for the IDs of the input list, compared to a background. User has the possibility to use background corresponding to the whole organism or to a user-defined list. In this latter case, we recommand to use the "Build tissue-specific expression dataset" ProteoRE tool to create this list according to your need. |
234 | 234 |
235 ----- | 235 ----- |
236 | 236 |
237 **Input** | 237 **Input** |
238 | 238 |
239 Two modes are allowed: either by supplying a tabular file (.csv, .tsv, .txt, .tab) including your IDs (identifiers) or by copy/pasting your IDs (separated by a space). | 239 Two modes are allowed: either by supplying a tabular file (.csv, .tsv, .txt, .tab) including your IDs (identifiers) or by copy/pasting your IDs (separated by a space). |
240 | 240 |
241 "Select type/source of IDs": only entrez gene ID (e.g. 4151, 7412) or Uniprot accession number (e.g. P31946) are allowed. If your list is not in this form, please use the ID_Converter tool of ProteoRE. | 241 "Select type/source of IDs": only entrez gene ID (e.g. 4151, 7412) or Uniprot accession number (e.g. P31946) are allowed. If your list is not in this form, please use the ID_Converter tool of ProteoRE. |
242 | 242 |
243 .. class:: warningmark | 243 .. class:: warningmark |
244 | 244 |
245 In copy/paste mode, the number of IDs considered in input is limited to 5000. | 245 In copy/paste mode, the number of IDs considered in input is limited to 5000. |
246 | 246 |
247 ----- | 247 ----- |
248 | 248 |
249 **Parameters** | 249 **Parameters** |
250 | 250 |
251 "Species": the three supported species are Homo sapiens, Mus musculus and Rattus norvegicus | 251 "Species": the three supported species are Homo sapiens, Mus musculus and Rattus norvegicus |
252 | 252 |
253 "Perform GO categories representation analysis?": classify genes based on their projection at a specific level of the GO corpus (see parameter below), and provides functions (set to "Yes") | 253 "Perform GO categories representation analysis?": classify genes based on their projection at a specific level of the GO corpus (see parameter below), and provides functions (set to "Yes") |
254 | 254 |
255 "Ontology level (the higher this number, the deeper the GO level)": correspond to the level of GO hierarchy (from 1 to 3) (set to level "2" by default). In general the higher the level, the more semantically specific the term is. | 255 "Ontology level (the higher this number, the deeper the GO level)": correspond to the level of GO hierarchy (from 1 to 3) (set to level "2" by default). In general the higher the level, the more semantically specific the term is. |
256 | 256 |
258 | 258 |
259 "P-value cut off": P-value threshold value for the declaration of significance (default is < 0.01) | 259 "P-value cut off": P-value threshold value for the declaration of significance (default is < 0.01) |
260 | 260 |
261 "Q-value cut off": to prevent high false discovery rate (FDR) in multiple testing, Q-values (adjusted P-values) are estimated for FDR control. (default is < 0.05) | 261 "Q-value cut off": to prevent high false discovery rate (FDR) in multiple testing, Q-values (adjusted P-values) are estimated for FDR control. (default is < 0.05) |
262 | 262 |
263 "Define your own background IDs?": by default the whole genome/proteome is used as a reference background to compute the enrichment. As this reference set should normally only include genes/proteins that were monitored during your analysis, this option allows to provide your own background; this could be for instance, the total number of genes/proteins expressed in the tissue/sample under study. | 263 "Define your own background IDs?": by default the whole genome/proteome is used as a reference background to compute the enrichment. As this reference set should normally only include genes/proteins that were monitored during your analysis, this option allows to provide your own background; this could be for instance, the total number of genes/proteins expressed in the tissue/sample under study. |
264 | 264 |
265 If you want to use your own background, click on the "Yes" button. Your gene/protein set must be a list of Entrez gene ID or Uniprot accession number (otherwise, use the ID-Converter tool of ProteoRE). Select the file containing your list of ID (as background), then specify the column number which contains IDs and the type of IDs (gene Entrez or Uniprot Accession number) as requested. | 265 If you want to use your own background, click on the "Yes" button. Your gene/protein set must be a list of Entrez gene ID or Uniprot accession number (otherwise, use the ID-Converter tool of ProteoRE). Select the file containing your list of ID (as background), then specify the column number which contains IDs and the type of IDs (gene Entrez or Uniprot Accession number) as requested. |
266 | 266 |
267 Of note: for Human species, you can build your own background by using the "Build tissue-specific expression dataset" tool of ProteoRE. | 267 Of note: for Human species, you can build your own background by using the "Build tissue-specific expression dataset" tool of ProteoRE. |
268 | 268 |
269 ----- | 269 ----- |
270 | 270 |
271 **Output** | 271 **Output** |
272 | 272 |
273 Diagram output: graphical output in the form of bar-plot or dot-plot (png, jpeg or pdf format), one figure for each GO category. | 273 Diagram output: graphical output in the form of bar-plot or dot-plot (png, jpeg or pdf format), one figure for each GO category. |
274 Text tables: with the following information GO category description (e.g.BP.Description), GO term identifier (e.g. BP.GOID) and GO term frequency (e.g. BP.Frequency)d graphics representing the repartition and/or enrichment of GO categories. One table and one graphic will be produced for each GO catagory. | 274 Text tables: with the following information GO category description (e.g.BP.Description), GO term identifier (e.g. BP.GOID) and GO term frequency (e.g. BP.Frequency)d graphics representing the repartition and/or enrichment of GO categories. One table and one graphic will be produced for each GO catagory. |
275 | 275 |
276 ----- | 276 ----- |
277 | 277 |
278 **Authors** | 278 **Authors** |
279 | 279 |
280 G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters. | 280 G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters. |
281 OMICS: A Journal of Integrative Biology 2012, 16(5):284-287. doi:[10.1089/omi.2011.0118](http://dx.doi.org/10.1089/omi.2011.0118) | 281 OMICS: A Journal of Integrative Biology 2012, 16(5):284-287. doi:[10.1089/omi.2011.0118](http://dx.doi.org/10.1089/omi.2011.0118) |
282 | 282 |
283 User manual / Documentation of the clusterProfiler R package (functions and parameters): | 283 User manual / Documentation of the clusterProfiler R package (functions and parameters): |
284 https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html | 284 https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html |
285 | 285 |
286 ----- | 286 ----- |
287 | 287 |
288 .. class:: infomark | 288 .. class:: infomark |
289 | 289 |
290 Bioconductor Packages used: | 290 Bioconductor Packages used: |
291 | 291 |
292 - bioconductor-org.hs.eg.db v3.5.0 | 292 - bioconductor-org.hs.eg.db v3.8.2 |
293 - bioconductor-org.mm.eg.db v3.5.0 | 293 - bioconductor-org.mm.eg.db v3.8.2 |
294 - bioconductor-org.rn.eg.db v3.5.0 | 294 - bioconductor-org.rn.eg.db v3.8.2 |
295 - dose v3.2.0 | 295 - dose v3.10.2 |
296 - clusterprofiler v 3.4.4 | 296 - clusterprofiler v 3.12.0 |
297 | 297 |
298 .. class:: infomark | 298 .. class:: infomark |
299 | 299 |
300 **Galaxy integration** | 300 **Galaxy integration** |
301 | 301 |