Mercurial > repos > proteore > proteore_go_terms_profiles_comparison

comparison GO_prof_comp.xml @ 0:fe80e3b6b5c2 draft default tip

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
planemo upload commit b8671ffe2e12dc6612b971a3e6e1dc71496aefd0-dirty
author proteore
date Fri, 24 Jan 2020 10:34:33 -0500
parents
children
comparison
equal deleted inserted replaced
-1:000000000000 0:fe80e3b6b5c2
1 <tool id="go_terms_profiles_comparison" name="Classification and enrichment analysis" version="2020.01.24">
2 <description>(Human, Mouse, Rat)[clusterProfiler]</description>
3 <requirements>
4 <requirement type="package">R</requirement>
5 <requirement type="package" version="3.8.2">bioconductor-org.hs.eg.db</requirement>
6 <requirement type="package" version="3.8.2">bioconductor-org.mm.eg.db</requirement>
7 <requirement type="package" version="3.8.2">bioconductor-org.rn.eg.db</requirement>
8 <requirement type="package" version="3.10.2">bioconductor-dose</requirement>
9 <requirement type="package" version="3.12.0">bioconductor-clusterprofiler</requirement>
10 </requirements>
11 <command detect_errors="exit_code"><![CDATA[
12
13 Rscript $__tool_directory__/GO_prof_comp.R
14 --inputtype1="$input1.ids1"
15 --inputtype2="$input2.ids2"
16
17 #if $input1.ids1 == "text"
18 --input1="$input1.txt1"
19 #else if $input1.ids1 == "file"
20 --input1="$input1.file1"
21 --header1="$input1.header1"
22 --column1="$input1.ncol1"
23 #end if
24
25 --list_name1="$list_name1"
26
27 #if $input2.ids2 == "text"
28 --input2="$input2.txt2"
29 #else if $input2.ids2 == "file"
30 --input2="$input2.file2"
31 --header2="$input2.header2"
32 --column2="$input2.ncol2"
33 #end if
34
35 --list_name2="$list_name2"
36 --org="$species"
37 --ont="$ontology"
38 --lev="$level"
39
40 > $log
41
42 ]]></command>
43 <inputs>
44 <conditional name="input1" >
45 <param name="ids1" type="select" label="Enter your Gene ID list" help="Copy/paste or from a file (e.g. table)" >
46 <option value="text">Copy/paste your IDs</option>
47 <option value="file" selected="true">Input file containing your IDs</option>
48 </param>
49 <when value="text" >
50 <param name="txt1" type="text" label="Copy/paste your identifiers" help='IDs must be separated by spaces into the form field, for example: 2810 7534' >
51 <sanitizer>
52 <valid initial="string.printable">
53 <remove value="&apos;"/>
54 </valid>
55 <mapping initial="none">
56 <add source="&apos;" target="__sq__"/>
57 </mapping>
58 </sanitizer>
59 </param>
60 </when>
61 <when value="file" >
62 <param name="file1" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" />
63 <param name="header1" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
64 <param name="ncol1" type="text" value="c1" 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'>
65 <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
66 </param>
67 </when>
68 </conditional>
69 <param name="list_name1" type="text" label="name of your first ids list" value="list1" optional="false">
70 <sanitizer>
71 <valid initial="string.printable">
72 <remove value="&apos;"/>
73 </valid>
74 <mapping initial="none">
75 <add source="&apos;" target="__sq__"/>
76 </mapping>
77 </sanitizer>
78 <validator type="regex" message="Please enter a list name">[a-zA-Z0-9._-]+</validator>
79 </param>
80 <conditional name="input2" >
81 <param name="ids2" type="select" label="Enter your Gene ID list" help="Copy/paste or from a file (e.g. table)" >
82 <option value="text">Copy/paste your IDs</option>
83 <option value="file" selected="true">Input file containing your IDs</option>
84 </param>
85 <when value="text" >
86 <param name="txt2" type="text" label="Copy/paste your identifiers" help='IDs must be separated by spaces into the form field, for example: 2810 7534' >
87 <sanitizer>
88 <valid initial="string.printable">
89 <remove value="&apos;"/>
90 </valid>
91 <mapping initial="none">
92 <add source="&apos;" target="__sq__"/>
93 </mapping>
94 </sanitizer>
95 </param>
96 </when>
97 <when value="file" >
98 <param name="file2" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" />
99 <param name="header2" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
100 <param name="ncol2" type="text" value="c1" 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'>
101 <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
102 </param>
103 </when>
104 </conditional>
105 <param name="list_name2" type="text" label="name of your second ids list" value="list2">
106 <sanitizer>
107 <valid initial="string.printable">
108 <remove value="&apos;"/>
109 </valid>
110 <mapping initial="none">
111 <add source="&apos;" target="__sq__"/>
112 </mapping>
113 </sanitizer>
114 <validator type="regex" message="Please enter a list name">[a-zA-Z0-9._-]+</validator>
115 </param>
116 <param name="species" type="select" label="Species" >
117 <option value="org.Hs.eg.db">Human (Homo sapiens) </option>
118 <option value="org.Mm.eg.db">Mouse (Mus musculus) </option>
119 <option value="org.Rn.eg.db">Rat (Rattus norvegicus)</option>
120 </param>
121 <param name="ontology" type="select" display="checkboxes" multiple="true" label="Select GO terms category" optional="false" >
122 <option value="CC">Cellular Component</option>
123 <option value="BP">Biological Process</option>
124 <option value="MF">Molecular Function</option>
125 </param>
126 <param name="level" type="select" label="Ontology level (the higher this number, the deeper the GO level)">
127 <option value="1">1</option>
128 <option value="2" >2</option>
129 <option value="3" selected="True">3</option>
130 <option value="4">4</option>
131 <option value="5">5</option>
132 </param>
133 </inputs>
134 <outputs>
135 <data name="log" format="txt" label="GO terms profiles comparison" />
136 <collection type="list" label="GO terms profiles comparison files" name="text_output">
137 <discover_datasets pattern="(?P&lt;designation&gt;.+\.tsv)" ext="tsv"/>
138 </collection>
139 <collection type="list" label="GO terms profiles diagram outputs" name="graph_output" >
140 <discover_datasets pattern="(?P&lt;designation&gt;.+.png)" ext="png" />
141 </collection>
142 </outputs>
143 <tests>
144 <test>
145 <conditional name="input1">
146 <param name="ids1" value="file"/>
147 <param name="file1" value="Bred.tsv"/>
148 <param name="header1" value="true"/>
149 <param name="ncol1" value="c1"/>
150 </conditional>
151 <conditional name="input2">
152 <param name="ids2" value="file"/>
153 <param name="file2" value="Muc.tsv"/>
154 <param name="header2" value="true"/>
155 <param name="ncol2" value="c1"/>
156 </conditional>
157 <param name="list_name1" value="Bred"/>
158 <param name="list_name2" value="Muc"/>
159 <param name="species" value="org.Hs.eg.db"/>
160 <param name="ontology" value="BP"/>
161 <param name="level" value="3"/>
162 <output name="log" file="log.txt" />
163 <output_collection name="text_output">
164 <element name="GO_profiles_comp_BP.tsv" file="GO_profiles_comp_BP.tsv" ftype="tsv"/>
165 </output_collection>
166 <output_collection name="graph_output">
167 <element name="GO_profiles_comp_BP.png" file="GO_profiles_comp_BP.png" ftype="png"/>
168 </output_collection>
169 </test>
170 </tests>
171 <help><![CDATA[
172
173 **Description**
174
175 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).
176
177 Given a list of IDs, this tool:
178
179 (i) performs gene classification based on GO distribution at a specific level,
180
181 (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.
182
183 -----
184
185 **Input**
186
187 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).
188
189 "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.
190
191 -----
192
193 **Parameters**
194
195 "Species": the three supported species are Homo sapiens, Mus musculus and Rattus norvegicus
196
197 "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")
198
199 "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.
200
201 "Perform GO categories enrichment analysis?": calculate enrichment test for GO terms based on hypergeometric distribution (set to "Yes")
202
203 "P-value cut off": P-value threshold value for the declaration of significance (default is < 0.01)
204
205 "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)
206
207 "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.
208
209 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.
210
211 Of note: for Human species, you can build your own background by using the "Build tissue-specific expression dataset" tool of ProteoRE.
212
213 -----
214
215 **Output**
216
217 Diagram output: graphical output in the form of bar-plot or dot-plot (png, jpeg or pdf format), one figure for each GO category.
218 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.
219
220 -----
221
222 **Authors**
223 G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters.
224 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)
225
226 User manual / Documentation of the clusterProfiler R package (functions and parameters):
227 https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html
228
229 -----
230
231 .. class:: infomark
232
233 **Galaxy integration**
234
235 Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
236
237 Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR
238
239 This work has been partially funded through the French National Agency for Research (ANR) IFB project.
240
241 Contact support@proteore.org for any questions or concerns about the Galaxy implementation of this tool.
242
243
244 ]]></help>
245 <citations>
246 </citations>
247 </tool>