|
1
|
1 <tool id="msigdb_kegg_geneSet" name="Get gene sets from Msigdb/KEGG" version="0.1.0">
|
|
|
2 <description>Get a geneSet object from Msigdb or KEGG</description>
|
|
|
3
|
|
|
4 <requirements>
|
|
|
5 <requirement type="package" version="1.30.0">bioconductor-KEGGREST</requirement>
|
|
|
6 <requirement type="package" version="7.2.1">r-msigdbr</requirement>
|
|
|
7 <requirement type="package" version="1.52.1">bioconductor-GSEABase</requirement>
|
|
|
8 <requirement type="package" version="1.20.3">r-getopt</requirement>
|
|
|
9 </requirements>
|
|
|
10
|
|
|
11 <command detect_errors="exit_code"><![CDATA[
|
|
|
12 Rscript '$__tool_directory__/msigdb_kegg_geneSet.R'
|
|
|
13
|
|
|
14 --source '$input_args.source'
|
|
|
15
|
|
|
16 #if str($input_args.source) == 'KEGG':
|
|
|
17 --organism '$input_args.organism'
|
|
|
18 #end if
|
|
|
19
|
|
|
20 #if str($input_args.source) == 'Msigdb':
|
|
|
21 --species '$input_args.species'
|
|
|
22 --category '$input_args.cat.category'
|
|
|
23 --geneIdType '$input_args.geneIdType'
|
|
|
24
|
|
|
25 #if str($input_args.cat.category) == 'C2':
|
|
|
26 --subcategory '$input_args.cat.subcategory'
|
|
|
27 #end if
|
|
|
28
|
|
|
29 #if str($input_args.cat.category) == 'C3':
|
|
|
30 --subcategory '$input_args.cat.subcategory'
|
|
|
31 #end if
|
|
|
32
|
|
|
33 #if str($input_args.cat.category) == 'C4':
|
|
|
34 --subcategory '$input_args.cat.subcategory'
|
|
|
35 #end if
|
|
|
36
|
|
|
37 #if str($input_args.cat.category) == 'C5':
|
|
|
38 --subcategory '$input_args.cat.subcategory'
|
|
|
39 #end if
|
|
|
40
|
|
|
41 #end if
|
|
|
42
|
|
|
43 --outputRData '$outputRData'
|
|
|
44
|
|
|
45 ]]></command>
|
|
|
46
|
|
|
47 <inputs>
|
|
|
48 <conditional name="input_args">
|
|
|
49 <param type="select" name="source" label="KEGG or MSigDB" help="Choose gene set from KEGG or MSigDB.">
|
|
|
50 <option value="KEGG" selected="true">KEGG</option>
|
|
|
51 <option value="Msigdb" >MSigDB</option>
|
|
|
52 </param>
|
|
|
53
|
|
|
54 <when value="KEGG">
|
|
|
55 <param type="text" name="organism" value="hsa" label="organism" help="A KEGG organism code (see https://www.kegg.jp/kegg/catalog/org_list.html). For example, human is `hsa`, Mus musculus is `mmu`."/>
|
|
|
56 </when>
|
|
|
57 <when value="Msigdb">
|
|
|
58 <param type="select" name="species" label="Species" help="Species name, such as Homo sapiens or Mus musculus.">
|
|
|
59 <option value="Homo sapiens" selected="true">human (H sapiens)</option>
|
|
|
60 <option value="Bos taurus">cattle (B taurus)</option>
|
|
|
61 <option value="Caenorhabditis elegans">roundworm (C elegans)</option>
|
|
|
62 <option value="Canis lupus familiaris">dog (C familiaris)</option>
|
|
|
63 <option value="Danio rerio">zebrafish (D rerio)</option>
|
|
|
64 <option value="Drosophila melanogaster">fruit fly (D melanogaster)</option>
|
|
|
65 <option value="Gallus gallus">chicken (G gallus)</option>
|
|
|
66 <option value="Mus musculus">house mouse (M musculus)</option>
|
|
|
67 <option value="Rattus norvegicus">Rat (R norvegicus)</option>
|
|
|
68 <option value="Saccharomyces cerevisiae">baker's or brewer's yeast (S cerevisiae)</option>
|
|
|
69 <option value="Sus scrofa">pig (S scrofa)</option>
|
|
|
70 </param>
|
|
|
71
|
|
|
72 <conditional name="cat">
|
|
|
73 <param type="select" name="category" label="Category" help="MSigDB collection abbreviation, such as H or C1.">
|
|
|
74 <option value="H">h: hallmark gene sets</option>
|
|
|
75 <option value="C1">c1: positional gene sets</option>
|
|
|
76 <option value="C2" selected="true">c2: curated gene sets</option>
|
|
|
77 <option value="C3">c3: regulatory target gene sets</option>
|
|
|
78 <option value="C4">c4: computational gene sets</option>
|
|
|
79 <option value="C5">c5: Ontology gene sets</option>
|
|
|
80 <option value="C6">c6: oncogenic signature gene sets</option>
|
|
|
81 <option value="C7">c7: immunologic signature gene sets</option>
|
|
|
82 <option value="C8">c8: cell type signature gene sets</option>
|
|
|
83 </param>
|
|
|
84 <when value="H"></when>
|
|
|
85 <when value="C1"></when>
|
|
|
86 <when value="C2">
|
|
|
87 <param type="select" name="subcategory" label="Sub Category" multiple="true" display="checkboxes">
|
|
|
88 <option value="CGP">chemical and genetic perturbations</option>
|
|
|
89 <option value="CP">all canonical pathways</option>
|
|
|
90 <option value="CP:BIOCARTA">BioCarta gene sets</option>
|
|
|
91 <option value="CP:KEGG" selected="true">KEGG gene sets</option>
|
|
|
92 <option value="CP:PID">PID gene sets</option>
|
|
|
93 <option value="CP:REACTOME">Reactome gene sets</option>
|
|
|
94 <option value="CP:WIKIPATHWAYS">WikiPathways gene sets</option>
|
|
|
95 </param>
|
|
|
96 </when>
|
|
|
97
|
|
|
98 <when value="C3">
|
|
|
99 <param type="select" name="subcategory" label="Sub Category" multiple="true" display="checkboxes">
|
|
|
100 <option value="MIR:MIR_Legacy">legacy microRNA targets</option>
|
|
|
101 <option value="MIR:MIRDB">MIRDB targets</option>
|
|
|
102 <option value="TFT:GTRD">GTRD targets </option>
|
|
|
103 <option value="TFT:TFT_Legacy">legacy transcription factor targets</option>
|
|
|
104 </param>
|
|
|
105 </when>
|
|
|
106
|
|
|
107 <when value="C4">
|
|
|
108 <param type="select" name="subcategory" label="Sub Category" multiple="true" display="checkboxes">
|
|
|
109 <option value="CGN">cancer gene neighborhoods</option>
|
|
|
110 <option value="CM">cancer modules</option>
|
|
|
111 </param>
|
|
|
112 </when>
|
|
|
113
|
|
|
114 <when value="C5">
|
|
|
115 <param type="select" name="subcategory" label="Sub Category" multiple="true" display="checkboxes">
|
|
|
116 <option value="GO:BP">GO biological processes</option>
|
|
|
117 <option value="GO:CC">GO cellular components</option>
|
|
|
118 <option value="GO:MF">GO molecular functions</option>
|
|
|
119 <option value="HPO">Human Phenotype Ontology</option>
|
|
|
120 </param>
|
|
|
121 </when>
|
|
|
122 <when value="C6"></when>
|
|
|
123 <when value="C7"></when>
|
|
|
124 <when value="C8"></when>
|
|
|
125
|
|
|
126 </conditional>
|
|
|
127 <param type="select" name="geneIdType" label="gene ID type" help="Specify gene ID type in pathway. Default is Entrez ID.">
|
|
|
128 <option value="entrez" selected="true">Entrez</option>
|
|
|
129 <option value="symbol">Symbol</option>
|
|
|
130 </param>
|
|
|
131 </when>
|
|
|
132
|
|
|
133 </conditional>
|
|
|
134
|
|
|
135 <!--<param type="boolean" name="whetherOutputfile" truevalue="True" false="False" checked="False" label="Output GMT file" />-->
|
|
|
136
|
|
|
137 </inputs>
|
|
|
138
|
|
|
139 <outputs>
|
|
|
140 <!--<data name="outputGMTFile" format="gmt" />-->
|
|
|
141 <data name="outputRData" format="rdata" label="GeneSet object from MSigDB/KEGG" />
|
|
|
142 </outputs>
|
|
|
143
|
|
|
144 <tests>
|
|
|
145 <test>
|
|
|
146 <conditional name="input_args">
|
|
|
147 <param name="source" value="KEGG" />
|
|
|
148 <param name="organism" value="hsa" />
|
|
|
149 </conditional>
|
|
|
150 <output name="outputRData" file="geneSet.RData"/>
|
|
|
151 </test>
|
|
|
152 </tests>
|
|
|
153
|
|
|
154 <help><![CDATA[
|
|
|
155
|
|
|
156 .. class:: infomark
|
|
|
157
|
|
|
158 **What it does**
|
|
|
159
|
|
|
160 This is a tool built to get a 'geneSetCollection' R object from the MSigDB or KEGG database.
|
|
|
161
|
|
|
162 If the gene sets source is KEGG_, it will only receive a KEGG organism code and output an Rdata file which has a `geneSet` object containing all KEGG pathways with their Entrez gene ID.
|
|
|
163
|
|
|
164 If the gene sets source is MSigDB_, you must assign specific species and categories to define the Gene Set collection. Again, the output is an Rdata file which has a `geneSet` object.
|
|
|
165
|
|
|
166 -----
|
|
|
167
|
|
|
168 **More Information**
|
|
|
169
|
|
|
170 **MSigDB Gene Set Colletions**
|
|
|
171
|
|
|
172 The MSigDB_ gene sets are divided into 9 major collections:
|
|
|
173
|
|
|
174 * **H: hallmark gene sets** are coherently expressed signatures derived by aggregating many MSigDB gene sets to represent well-defined biological states or processes.
|
|
|
175 * **C1: positional gene sets** for each human chromosome and cytogenetic band.
|
|
|
176 * **C2: curated gene sets** are from online pathway databases, publications in PubMed, and knowledge of domain experts.
|
|
|
177 * **C3: motif gene sets** are based on conserved cis-regulatory motifs from a comparative analysis of the human, mouse, rat, and dog genomes.
|
|
|
178 * **C4: computational gene sets** are defined by mining large collections of cancer-oriented microarray data.
|
|
|
179 * **C5: GO gene sets** consist of genes annotated by the same GO terms.
|
|
|
180 * **C6: oncogenic gene sets** are defined directly from microarray gene expression data from cancer gene perturbations.
|
|
|
181 * **C7: immunologic gene sets** are defined directly from microarray gene expression data from immunologic studies.
|
|
|
182 * **C8: cell type signature gene sets** curated from cluster markers identified in single-cell sequencing studies of human tissue.
|
|
|
183
|
|
|
184 .. _MSigDB: http://software.broadinstitute.org/gsea/msigdb
|
|
|
185 .. _KEGG: http://www.genome.jp/kegg/
|
|
|
186 ]]></help>
|
|
|
187
|
|
|
188 <citations>
|
|
|
189 <citation type="bibtex">@ARTICLE{Kim07aninterior-point,
|
|
|
190 author = {Xiaowei Huang and Songqing Mei and Antonio Mora},
|
|
|
191 title = {Galaxy-GSA –A suite of tools for advanced gene set analysis in Galaxy},
|
|
|
192 journal = {Bioinformatics},
|
|
|
193 year = {2021},
|
|
|
194 volume = {8},
|
|
|
195 pages = {1-3}
|
|
|
196 }</citation>
|
|
|
197 </citations>
|
|
|
198
|
|
|
199 </tool>
|
