|
3
|
1 <tool id="oncoenrichr_wrapper" name="oncoEnrichR" version="1.4.0">
|
|
2
|
2 <description>Cancer-dedicated gene set interpretation</description>
|
|
|
3 <requirements>
|
|
3
|
4 <container type="docker">sigven/oncoenrichr:1.4.0</container>
|
|
2
|
5 </requirements>
|
|
|
6 <command detect_errors="aggressive"><![CDATA[
|
|
|
7 #if $query_set.query_choice.query_input == "text"
|
|
|
8 echo $query_set.query_choice.query_text | sed 's/__cn__/\n/g' > query_text.csv &&
|
|
|
9 #set input_file = './query_text.csv'
|
|
|
10 #else if $query_set.query_choice.query_input == "file"
|
|
|
11 ln -s $query_set.query_choice.query_file "$query_set.query_choice.query_file.element_identifier" &&
|
|
|
12 #set input_file = './' + str($query_set.query_choice.query_file.element_identifier)
|
|
|
13 #end if
|
|
|
14
|
|
|
15 #set background_file = ''
|
|
|
16 #if $fun_enrich.custom_bgset.def_background
|
|
|
17 #if $fun_enrich.custom_bgset.bg_choice.bg_source == "text"
|
|
|
18 echo $fun_enrich.custom_bgset.bg_choice.bg_enrich_text | sed 's/__cn__/\n/g' > custom_bgset.csv &&
|
|
|
19 #set background_file = './custom_bgset.csv'
|
|
|
20 #else if $fun_enrich.custom_bgset.bg_choice.bg_source == "file" and $fun_enrich.custom_bgset.bg_choice.bg_enrich_file
|
|
|
21 ln -s $fun_enrich.custom_bgset.bg_choice.bg_enrich_file background_text.csv &&
|
|
|
22 #set background_file = './custom_bgset.csv'
|
|
|
23 #else
|
|
|
24 #set background_file = ''
|
|
|
25 #end if
|
|
|
26 #end if
|
|
|
27
|
|
|
28 R -e 'suppressPackageStartupMessages(library(oncoEnrichR));
|
|
|
29 suppressWarnings(load(system.file("internal_db", "oedb.rda", package = "oncoEnrichR")));
|
|
3
|
30 gene_data <- read.csv("$input_file", strip.white = TRUE);
|
|
2
|
31 oe_report <- oncoEnrichR::onco_enrich(
|
|
|
32 query = gene_data[[1]],
|
|
|
33 oeDB = oedb,
|
|
|
34 #if $query_set.query_id_type
|
|
|
35 query_id_type = "$query_set.query_id_type",
|
|
|
36 #end if
|
|
|
37 ignore_id_err = $query_set.ignore_id_err,
|
|
|
38
|
|
|
39 #if $report_metadata.project_title
|
|
|
40 project_title = "$report_metadata.project_title",
|
|
|
41 #end if
|
|
|
42 #if $report_metadata.project_owner
|
|
|
43 project_owner = "$report_metadata.project_owner",
|
|
|
44 #end if
|
|
|
45 #if $report_metadata.project_description
|
|
|
46 project_description = "$report_metadata.project_description",
|
|
|
47 #end if
|
|
|
48
|
|
|
49 show_enrichment = $modules.show_enrichment,
|
|
|
50 show_ppi = $modules.show_ppi,
|
|
|
51 show_disease = $modules.show_disease,
|
|
|
52 show_cancer_hallmarks = $modules.show_cancer_hallmarks,
|
|
|
53 show_drug = $modules.show_drug,
|
|
|
54 show_aberration = $modules.show_aberration,
|
|
|
55 show_coexpression = $modules.show_coexpression,
|
|
|
56 show_subcell_comp = $modules.show_subcell_comp,
|
|
|
57 show_complex = $modules.show_complex,
|
|
3
|
58 show_domain = $modules.show_domain,
|
|
2
|
59 show_fitness = $modules.show_fitness,
|
|
3
|
60 show_cell_tissue = $modules.show_cell_tissue,
|
|
2
|
61 show_ligand_receptor = $modules.show_ligand_receptor,
|
|
|
62 show_regulatory = $modules.show_regulatory,
|
|
3
|
63 show_prognostic = $modules.show_prognostic,
|
|
|
64 show_unknown_function = $modules.show_unknown_function,
|
|
2
|
65 show_synleth = $modules.show_synleth,
|
|
|
66
|
|
|
67 #if $background_file
|
|
3
|
68 bgset = read.csv("$background_file", strip.white = TRUE)[[1]],
|
|
2
|
69 #if $fun_enrich.custom_bgset.bg_enrich_id_type
|
|
|
70 bgset_id_type = "$fun_enrich.custom_bgset.bg_enrich_id_type",
|
|
|
71 #end if
|
|
|
72 #if $fun_enrich.custom_bgset.bg_enrich_description
|
|
|
73 bgset_description = "$fun_enrich.custom_bgset.bg_enrich_description",
|
|
|
74 #end if
|
|
|
75 #else
|
|
|
76 bgset = NULL,
|
|
|
77 #end if
|
|
|
78
|
|
3
|
79 #if $fun_enrich.enrichment_p_value_cutoff
|
|
|
80 enrichment_p_value_cutoff = $fun_enrich.enrichment_p_value_cutoff,
|
|
2
|
81 #end if
|
|
3
|
82 #if $fun_enrich.enrichment_p_value_adj
|
|
|
83 enrichment_p_value_adj = "$fun_enrich.enrichment_p_value_adj",
|
|
|
84 #end if
|
|
|
85 #if $fun_enrich.enrichment_q_value_cutoff
|
|
|
86 enrichment_q_value_cutoff = $fun_enrich.enrichment_q_value_cutoff,
|
|
2
|
87 #end if
|
|
3
|
88 #if $fun_enrich.enrichment_min_geneset_size
|
|
|
89 enrichment_min_geneset_size = $fun_enrich.enrichment_min_geneset_size,
|
|
2
|
90 #end if
|
|
3
|
91 #if $fun_enrich.enrichment_max_geneset_size
|
|
|
92 enrichment_max_geneset_size = $fun_enrich.enrichment_max_geneset_size,
|
|
2
|
93 #end if
|
|
3
|
94 enrichment_plot_num_terms = $fun_enrich.enrichment_plot_num_terms,
|
|
|
95 enrichment_simplify_go = $fun_enrich.enrichment_simplify_go,
|
|
|
96
|
|
2
|
97
|
|
|
98 #if $protein_interactions.ppi_add_nodes
|
|
|
99 ppi_add_nodes = $protein_interactions.ppi_add_nodes,
|
|
|
100 #end if
|
|
3
|
101 #if $protein_interactions.ppi_string_min_score
|
|
|
102 ppi_string_min_score = $protein_interactions.ppi_string_min_score,
|
|
2
|
103 #end if
|
|
3
|
104 #if $protein_interactions.ppi_biogrid_min_evidence
|
|
|
105 ppi_biogrid_min_evidence = $protein_interactions.ppi_biogrid_min_evidence,
|
|
|
106 #end if
|
|
|
107 ppi_show_drugs = $protein_interactions.ppi_show_drugs,
|
|
|
108 ppi_show_isolated_nodes = $protein_interactions.ppi_show_isolated_nodes,
|
|
|
109 ppi_node_shadow = $protein_interactions.ppi_node_shadow,
|
|
2
|
110
|
|
3
|
111 #if $subcellular_compartments.subcellcomp_min_confidence
|
|
|
112 subcellcomp_min_confidence = $subcellular_compartments.subcellcomp_min_confidence,
|
|
2
|
113 #end if
|
|
3
|
114 #if $subcellular_compartments.subcellcomp_min_channels
|
|
|
115 subcellcomp_min_channels = $subcellular_compartments.subcellcomp_min_channels,
|
|
2
|
116 #end if
|
|
3
|
117 #if $fitness.fitness_max_score
|
|
|
118 fitness_max_score = $fitness.fitness_max_score,
|
|
|
119 #end if
|
|
|
120 subcellcomp_show_cytosol = $subcellular_compartments.subcellcomp_show_cytosol,
|
|
2
|
121 #if $disease.show_top_diseases_only
|
|
|
122 show_top_diseases_only = $disease.show_top_diseases_only,
|
|
|
123 #end if
|
|
|
124
|
|
3
|
125 regulatory_min_confidence = "$regulatory.regulatory_min_confidence",
|
|
4
|
126
|
|
2
|
127 html_floating_toc = $report_metadata.html_floating_toc,
|
|
|
128 html_report_theme = "$report_metadata.html_report_theme",
|
|
|
129 galaxy = TRUE
|
|
|
130 );
|
|
|
131
|
|
|
132 oncoEnrichR::write(report = oe_report, oeDB = oedb, file = "$report1", format = "html", selfcontained_html = F, extra_files_path = "$report1.extra_files_path", overwrite = T, ignore_file_extension = T);
|
|
|
133 oncoEnrichR::write(report = oe_report, oeDB = oedb, file = "$report2", format = "excel", overwrite = T, ignore_file_extension = T)' 2>&1
|
|
|
134
|
|
|
135 ]]></command>
|
|
|
136 <inputs>
|
|
|
137 <section title="" name=""/>
|
|
|
138 <section name="query_set" title="Query gene set" expanded="true">
|
|
|
139 <conditional name="query_choice">
|
|
|
140 <param name="query_input" type="select" multiple="false" display="radio"
|
|
|
141 label="Query gene set: do you want to upload a file OR paste into a text box?">
|
|
|
142 <option value="text">Text field</option>
|
|
|
143 <option value="file">From file</option>
|
|
|
144 </param>
|
|
|
145 <when value="text">
|
|
|
146 <param type="text" name="query_text" label="Query gene set identifiers (one per line)" area="true"/>
|
|
|
147 </when>
|
|
|
148 <when value="file">
|
|
|
149 <param name="query_file" type="data" format="txt" label="Query gene set identifiers" multiple="false"/>
|
|
|
150 </when>
|
|
|
151 </conditional>
|
|
|
152 <param name="query_id_type" type="select" label="Query identifier type" display="radio" multiple="false">
|
|
|
153 <option value="symbol">Primary gene symbol (HGNC) - e.g. KRAS</option>
|
|
|
154 <option value="uniprot_acc">UniProt accession - e.g. P01116</option>
|
|
|
155 <option value="entrezgene">NCBI Entrez gene identifier - e.g. 3845</option>
|
|
|
156 <option value="ensembl_gene">Ensembl gene identifier - e.g. ENSG00000133703</option>
|
|
|
157 <option value="ensembl_mrna">Ensembl transcript identifier - e.g. ENST00000311936</option>
|
|
|
158 <option value="ensembl_protein">Ensembl protein identifier - e.g. ENSP00000308495</option>
|
|
|
159 <option value="refseq_mrna">RefSeq mRNA identifier - e.g. NM_004985</option>
|
|
|
160 <option value="refseq_protein">RefSeq protein identifier - e.g. NP_004976</option>
|
|
|
161 </param>
|
|
|
162 <param name="ignore_id_err" type="boolean" label="Ignore erroneous idenfiers" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
163 </section>
|
|
|
164
|
|
|
165 <section title="" name=""/>
|
|
|
166 <section name="report_metadata" title="Project metadata and output settings" expanded="true">
|
|
|
167 <param type="text" name="report_name" label="Output filename (prefix)" value="Report"/>
|
|
|
168 <param type="text" name="project_title" label="Project title" />
|
|
|
169 <param type="text" name="project_owner" label="Project owner" />
|
|
|
170 <param type="text" name="project_description" label="Project description" area="true"/>
|
|
|
171 <param name="html_floating_toc" type="boolean" label="HTML report - float the table of contents to the left of the main document content (always visible during scrolling)" truevalue="T" falsevalue="F" checked="true"/>
|
|
3
|
172 <param name="html_report_theme" type="select" label="HTML report - bootswatch theme">
|
|
2
|
173 <option value="default">default</option>
|
|
|
174 <option value="cerulean">cerulean</option>
|
|
|
175 <option value="cosmo">cosmo</option>
|
|
|
176 <option value="journal">journal</option>
|
|
|
177 <option value="lumen">lumen</option>
|
|
|
178 <option value="paper">paper</option>
|
|
|
179 <option value="sandstone">sandstone</option>
|
|
|
180 <option value="simplex">simplex</option>
|
|
|
181 <option value="spacelab">spacelab</option>
|
|
|
182 <option value="united">united</option>
|
|
|
183 <option value="yeti">yeti</option>
|
|
|
184 </param>
|
|
|
185 </section>
|
|
|
186
|
|
|
187 <section title="" name=""/>
|
|
|
188 <section name="modules" title="Analysis modules included in the report" expanded="true">
|
|
3
|
189 <param name="show_disease" type="boolean" label="Gene-cancer associations" truevalue="T" falsevalue="F" checked="true"/>
|
|
2
|
190 <param name="show_enrichment" type="boolean" label="Gene functional enrichment" truevalue="T" falsevalue="F" checked="true"/>
|
|
3
|
191 <param name="show_cell_tissue" type="boolean" label="Tissue/cell-type enrichment" truevalue="T" falsevalue="F" checked="false"/>
|
|
2
|
192 <param name="show_ppi" type="boolean" label="Protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
193 <param name="show_regulatory" type="boolean" label="Regulatory (TF-target) interactions" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
194 <param name="show_ligand_receptor" type="boolean" label="Ligand-receptor interactions" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
195 <param name="show_cancer_hallmarks" type="boolean" label="Cancer hallmark associations" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
196 <param name="show_drug" type="boolean" label="Drug-target associations" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
197 <param name="show_aberration" type="boolean" label="Tumor aberration frequencies" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
198 <param name="show_coexpression" type="boolean" label="Tumor co-expression patterns" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
199 <param name="show_subcell_comp" type="boolean" label="Subcellular localizations" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
200 <param name="show_complex" type="boolean" label="Protein complex memberships" truevalue="T" falsevalue="F" checked="true"/>
|
|
3
|
201 <param name="show_domain" type="boolean" label="Protein domain frequencies" truevalue="T" falsevalue="F" checked="false"/>
|
|
2
|
202 <param name="show_fitness" type="boolean" label="Gene fitness effects" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
203 <param name="show_synleth" type="boolean" label="Predicted synthetic lethality interactions" truevalue="T" falsevalue="F" checked="true"/>
|
|
3
|
204 <param name="show_unknown_function" type="boolean" label="Genes of poorly defined function" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
205 <param name="show_prognostic" type="boolean" label="Prognostic cancer associations" truevalue="T" falsevalue="F" checked="true"/>
|
|
2
|
206 </section>
|
|
|
207
|
|
|
208 <section title="" name=""/>
|
|
3
|
209 <section name="fun_enrich" title="Options - gene functional enrichment">
|
|
2
|
210 <conditional name="custom_bgset">
|
|
|
211 <param name="def_background" type="boolean" label="Define custom background set (all annotated protein-coding genes by default)" truevalue="T" falsevalue="F" checked="false"/>
|
|
|
212 <when value="T">
|
|
|
213 <conditional name="bg_choice">
|
|
|
214 <param name="bg_source" type="select" display="radio"
|
|
|
215 label="Custom background gene set: do you want to upload a file OR paste into a text box?">
|
|
|
216 <option value="text">Text field</option>
|
|
|
217 <option value="file">From file</option>
|
|
|
218
|
|
|
219 </param>
|
|
|
220 <when value="file">
|
|
|
221 <param type="data" format="txt" name="bg_enrich_file" label="Custom background gene set" optional="true" multiple="false"/>
|
|
|
222 </when>
|
|
|
223 <when value="text">
|
|
|
224 <param type="text" name="bg_enrich_text" label="Custom background gene set identifiers (one per line):" area="true"/>
|
|
|
225 </when>
|
|
|
226 </conditional>
|
|
|
227
|
|
|
228 <param type="select" name="bg_enrich_id_type" label="Custom background identifier type" display="radio" multiple="false">
|
|
|
229 <option value="symbol">Primary gene symbol (HGNC) - e.g. KRAS</option>
|
|
|
230 <option value="uniprot_acc">UniProt accession - e.g. P01116</option>
|
|
|
231 <option value="entrezgene">NCBI Entrez gene identifier - e.g. 3845</option>
|
|
|
232 <option value="ensembl_gene">Ensembl gene identifier - e.g. ENSG00000133703</option>
|
|
|
233 <option value="ensembl_mrna">Ensembl transcript identifier - e.g. ENST00000311936</option>
|
|
|
234 <option value="ensembl_protein">Ensembl protein identifier - e.g. ENSP00000308495</option>
|
|
|
235 <option value="refseq_mrna">RefSeq mRNA identifier - e.g. NM_004985</option>
|
|
|
236 <option value="refseq_protein">RefSeq protein identifier - e.g. NP_004976</option>
|
|
|
237 </param>
|
|
|
238 <param type="text" name="bg_enrich_description" label="Custom background gene set description" value="Custom background description"/>
|
|
|
239 </when>
|
|
|
240 </conditional>
|
|
|
241
|
|
3
|
242 <param name="enrichment_p_value_cutoff" type="float" label="P-value cutoff for enrichment tests (clusterProfiler)" value="0.05"/>
|
|
|
243 <param name="enrichment_p_value_adj" type="select" label="P-value adjustment method (clusterProfiler)">
|
|
|
244 <option value="BH">Benjamini-Hochberg</option>
|
|
|
245 <option value="holm">Holm</option>
|
|
|
246 <option value="hochberg">Hochberg</option>
|
|
|
247 <option value="hommel">Hommel</option>
|
|
|
248 <option value="bonferroni">Bonferroni</option>
|
|
|
249 <option value="BY">Benjamini-Yekutieli</option>
|
|
2
|
250 <option value="fdr">fdr</option>
|
|
|
251 <option value="none">none</option>
|
|
|
252 </param>
|
|
3
|
253 <param name="enrichment_q_value_cutoff" type="float" label="Q-value cutoff for enrichment tests to report as significant (clusterProfiler)" value="0.2"/>
|
|
|
254 <param name="enrichment_min_geneset_size" type="integer" label="Minimum number of genes annotated by ontology term for testing (clusterProfiler)" value="10"/>
|
|
|
255 <param name="enrichment_max_geneset_size" type="integer" label="Maximum number of genes annotated by ontology term for testing (clusterProfiler)" value="500"/>
|
|
|
256 <param name="enrichment_simplify_go" type="boolean" label="Simplify GO enrichment results by removal of redundant terms (recommended)" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
257 <param name="enrichment_plot_num_terms" type="integer" label="Number of top enriched Gene Ontology terms (max) to show in enrichment barplot" min="10" max="30" value="20"/>
|
|
2
|
258 </section>
|
|
|
259
|
|
|
260 <section title="" name=""/>
|
|
3
|
261 <section name="fitness" title="Options - gene fitness scores">
|
|
|
262 <param name="fitness_max_score" type="float" label="Maximum loss-of-fitness score (Bayes Factor from BAGEL) for genes retrieved from Project Score" value="-2" min="-5" max="0"/>
|
|
2
|
263 </section>
|
|
|
264 <section title="" name=""/>
|
|
3
|
265 <section name="protein_interactions" title="Options - protein-protein interaction network">
|
|
|
266 <param name="ppi_network_type" type = "select" label="STRING: type of retrieved network interactions">
|
|
|
267 <option value="functional">functional</option>
|
|
|
268 <option value="physical">physical</option>
|
|
|
269 </param>
|
|
|
270 <param name="ppi_string_min_score" type="float" label="STRING: minimum confidence score for interactions to be included in network" value="0.9" min="0.4" max="1"/>
|
|
|
271 <param name="ppi_biogrid_min_evidence" type="integer" label="BioGRID: Minimum number of evidence support for interactions to be included in network" value="3" min="2" max="10"/>
|
|
|
272 <param name="ppi_add_nodes" type="integer" label="Addition of interacting non-queryset proteins to the protein-protein interaction network (STRING/BioGRID)" value="30" min="0" max="50"/>
|
|
|
273 <param name="ppi_show_drugs" type="boolean" label="Attach anti-cancer drugs in protein-protein interaction network (STRING/BioGRID)" truevalue="T" falsevalue="F" checked="false"/>
|
|
|
274 <param name="ppi_show_isolated_nodes" type="boolean" label="Show isolated nodes in protein-protein interaction network (STRING/BioGRID)" truevalue="T" falsevalue="F" checked="false"/>
|
|
|
275 <param name="ppi_node_shadow" type="boolean" label="Add shadow to nodes in protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
|
|
2
|
276 </section>
|
|
|
277 <section title="" name=""/>
|
|
3
|
278 <section name="regulatory" title="Options - regulatory interactions">
|
|
|
279 <param name="regulatory_min_confidence" type="select" label = "Minimum confidence level of regulatory interactions included (DoRothEA - A:highest, D:lowest)">
|
|
2
|
280 <option value="D">D</option>
|
|
|
281 <option value="C">C</option>
|
|
|
282 <option value="B">B</option>
|
|
|
283 <option value="A">A</option>
|
|
|
284 </param>
|
|
|
285 </section>
|
|
|
286 <section title="" name=""/>
|
|
|
287
|
|
3
|
288 <section name="subcellular_compartments" title="Options - Subcellular compartment annotations">
|
|
|
289 <param name="subcellcomp_min_confidence" type="integer" label="Minimum confidence level for subcellular compartment annotations" value="3" min="3" max="5"/>
|
|
|
290 <param name="subcellcomp_min_channels" type="integer" label="Minimum number of channel (Text Mining, Experimental, Knowledge) support for annotations" value="1" min="1" max="3"/>
|
|
|
291 <param name="subcellcomp_show_cytosol" type="boolean" label="Show cytosol annotations (very common localization) in subcellular heatmap " truevalue="T" falsevalue="F" checked="false"/>
|
|
2
|
292 </section>
|
|
|
293 <section title="" name=""/>
|
|
|
294
|
|
3
|
295 <section name="disease" title="Options - Disease associations">
|
|
2
|
296 <param type="boolean" name="show_top_diseases_only" label="Show top disease assocations only" truevalue="T" falsevalue="F" checked="true"/>
|
|
|
297 </section>
|
|
|
298
|
|
|
299 </inputs>
|
|
|
300 <outputs>
|
|
|
301 <data format="xlsx" name="report2" label="$report_metadata.report_name - xlsx"/>
|
|
|
302 <data format="html" name="report1" label="$report_metadata.report_name - html"/>
|
|
|
303 </outputs>
|
|
|
304
|
|
|
305
|
|
|
306 <help><![CDATA[
|
|
|
307 .. class:: infomark
|
|
|
308
|
|
3
|
309 The query gene set is limited to n = 1000 identifiers. A limited query gene set (e.g. n < 5) will in general reduce the relevance and significance of many oncoEnrichR report modules.
|
|
2
|
310
|
|
|
311 -----
|
|
|
312
|
|
|
313 **Dataset formats**
|
|
|
314
|
|
|
315 The input dataset is in tabular_ format. The two output datasets are html_ and xlsx.
|
|
|
316
|
|
|
317 .. _tabular: ${static_path}/formatHelp.html#tab
|
|
|
318 .. _html: ${static_path}/formatHelp.html#html
|
|
|
319
|
|
|
320 -----
|
|
|
321
|
|
|
322 **What it does**
|
|
|
323
|
|
|
324 *OncoEnrichR* is intended for exploratory analysis and prioritization of a candidate hits (referred to as *query set* below) from high-throughput cancer biology experiments. The tool queries a number of high-quality data resources in order to interpret the query gene set along various dimensions, examples being cancer aberration frequencies, protein-protein interactions, pathway enrichment, subcellular compartment localization, target druggability, gene fitness scores, and tissue/cell-type specificity.
|
|
|
325
|
|
|
326 The results from the various analysis modules are provided in an interactive HTML report where the user can interrogate the results further. A multisheet Excel workbook is also provided for convience. The following resources are currently utilized for annotation and analysis:
|
|
|
327
|
|
|
328 - `Open Targets Platform <https://targetvalidation.org/>`_ - disease associations, drug-target associations, cancer hallmarks, and druggability/tractability rankings
|
|
|
329
|
|
|
330 - `The Cancer Genome Atlas <https://portal.gdc.cancer.gov/>`_ - gene aberration frequencies and co-expression patterns in approximately 10,000 primary tumor samples
|
|
|
331
|
|
|
332 - `The Human Protein Atlas <https://www.proteinatlas.org/>`_ - expression data for healthy human tissues (`GTex <https://gtexportal.org/home/>`_)/cell types, and prognostic gene expression associations in cancer (`The Pathology Atlas <https://www.proteinatlas.org/humanproteome/pathology/>`_)
|
|
|
333
|
|
|
334 - `Molecular Signatures Database (MSigDB) <http://software.broadinstitute.org/gsea/msigdb/index.jsp/>`_ - collection of annotated (e.g. towards pathways) gene sets for enrichment/overrepresentation analysis. This includes gene sets from `Gene Ontology <http://geneontology.org/>`_, `Reactome <https://reactome.org/>`_, `KEGG <https://www.genome.jp/kegg/pathway.html/>`_, `WikiPathways <https://www.wikipathways.org/index.php/WikiPathways/>`_, `BIOCARTA <https://maayanlab.cloud/Harmonizome/dataset/Biocarta+Pathways/>`_, as well as curated `immunologic <https://www.gsea-msigdb.org/gsea/msigdb/collections.jsp#C7/>`_ and `cancer-specific <https://www.gsea-msigdb.org/gsea/msigdb/collections.jsp#C6/>`_ signatures.
|
|
|
335
|
|
|
336 - `NetPath <http://www.netpath.org/>`_ - manually curated resource of signal transduction pathways in humans
|
|
|
337
|
|
4
|
338 - `UniProt <https://uniprot.org>`_ - Comprehensive resource of protein sequence and functional information
|
|
|
339
|
|
2
|
340 - `STRING <https://string-db.org/>`_ - protein-protein interaction database
|
|
|
341
|
|
4
|
342 - `InterPro/PFAM <https://www.ebi.ac.uk/interpro/>`_ - Collection of protein families/domains`
|
|
|
343
|
|
|
344 - `BIOGRID <http://thebiogrid.org>`_ - Database of Protein, Genetic and Chemical Interactions
|
|
|
345
|
|
2
|
346 - `CellChatDB <http://www.cellchat.org/>`_ - database on ligand-receptor interactions
|
|
|
347
|
|
|
348 - `DoRothEA <https://saezlab.github.io/dorothea/>`_ - gene set resource containing signed transcription factor (TF) - target interactions
|
|
|
349
|
|
|
350 - `CORUM <https://mips.helmholtz-muenchen.de/corum/>`_ - protein complex database
|
|
|
351
|
|
|
352 - `Compleat <https://fgr.hms.harvard.edu/compleat>`_ - protein complex resource
|
|
|
353
|
|
|
354 - `ComplexPortal <https://www.ebi.ac.uk/complexportal/home/>`_ - manually curated, encyclopaedic resource of macromolecular complexes
|
|
|
355
|
|
|
356 - `hu.MAP2 <http://humap2.proteincomplexes.org/>`_ - human protein complex map
|
|
|
357
|
|
3
|
358 - `COMPARTMENTS <https://compartments.jensenlab.org/Search/>`_ - subcellular compartment annotation database
|
|
2
|
359
|
|
|
360 - `CancerMine <http://bionlp.bcgsc.ca/cancermine/>`_ - literature-mined resource on cancer drivers, oncogenes and tumor suppressor genes
|
|
|
361
|
|
4
|
362 - `Cancer Gene Census <https://cancer.sanger.ac.uk/census/>`_ - Curated high-confidence list of genes with substantial published evidence in oncology
|
|
|
363
|
|
2
|
364 - `Network of Cancer Genes <http://ncg.kcl.ac.uk/>`_ - manually curated collection of cancer genes, healthy drivers and their properties
|
|
|
365
|
|
4
|
366 - `DepMap/Project Score <https://score.depmap.sanger.ac.uk/>`_ - database on the effects on cancer cell line viability elicited by CRISPR-Cas9 mediated gene activation
|
|
2
|
367
|
|
|
368 - `Genetic determinants of survival in cancer <http://survival.cshl.edu/>`_ - resource on the prognostic impact of genetic aberrations (methylation, CNA, mutation, expression) in human cancers (TCGA)
|
|
|
369
|
|
|
370 - `Predicted synthetic lethality interactions <https://pubmed.ncbi.nlm.nih.gov/34529928/>`_ - comprehensive prediction of synthetic lethality interactions in human cancer cell lines
|
|
|
371
|
|
|
372 The contents of the gene set analysis report attempt to answer the following questions related to the query set:
|
|
|
373
|
|
3
|
374 - Which diseases/tumor types are known to be associated with genes in the query set, and to what extent? Which genes show evidence of oncogenic and/or tumor suppressive roles?
|
|
2
|
375
|
|
|
376 - Which query genes have been linked (through literature) to the various hallmarks of cancer?
|
|
|
377
|
|
|
378 - Which genes in the query set are poorly characterized or have an unknown function?
|
|
|
379
|
|
|
380 - Which proteins in the query set can be targeted by inhibitors for diffferent cancer conditions (early and late clinical development phases)? What is the tractability/druggability status for other targets in the query set?
|
|
|
381
|
|
|
382 - Which cancer-relevant protein complexes are involved for proteins in the query set?
|
|
|
383
|
|
|
384 - Are there known cancer-relevant regulatory interactions (transcription factor (TF) - target) found in the query set?
|
|
|
385
|
|
|
386 - Are there known ligand-receptor interactions in the query set?
|
|
|
387
|
|
|
388 - Which subcellular compartments (nucleus, cytosol, plasma membrane etc.) are dominant localizations for members of the query set?
|
|
|
389
|
|
|
390 - Are specific tissues or cell types enriched in the query set, considering healthy tissue/cell-type specific expression patterns (GTex/Human Protein Atlas) of query genes?
|
|
|
391
|
|
|
392 - Which protein-protein interactions are known within the query set? Are there interactions between members of the query set and other cancer-relevant proteins (e.g. proto-oncogenes, tumor-suppressors or predicted cancer drivers)? Which proteins constitute hubs in the protein-protein interaction network?
|
|
|
393
|
|
|
394 - Are there specific pathways, biological processes or molecular functions that are enriched within the query set, as compared to a reference/background set?
|
|
|
395
|
|
|
396 - Which members of the query set are frequently mutated in tumor sample cohorts (TCGA - SNVs/InDels / homozygous deletions / copy number amplifications)? What are the most frequent recurrent somatic variants (SNVs/InDels) in the query set genes?
|
|
|
397
|
|
|
398 - Which members of the query set are co-expressed (strong negative or positive correlations) with cancer-relevant genes (i.e. proto-oncogenes or tumor suppressors) in tumor sample cohorts (TCGA)?
|
|
|
399
|
|
|
400 - Which members of the query set are associated with better/worse survival in different cancers, considering mutation, expression, methylation or copy number levels in tumors?
|
|
|
401
|
|
|
402 - Which members of the query set are predicted as partners of synthetic lethality interactions?
|
|
|
403
|
|
|
404 - Which members of the query set are associated with cellular loss-of-fitness in CRISPR/Cas9 whole-genome drop out screens of cancer cell lines (i.e. reduction of cell viability elicited by a gene inactivation)? Which genes should be prioritized considering genomic biomarkers and fitness scores in combination?
|
|
|
405
|
|
|
406
|
|
|
407 ]]>
|
|
|
408 </help>
|
|
|
409
|
|
|
410 <citations>
|
|
|
411 <!-- Example of annotating a citation using a DOI. -->
|
|
|
412 <citation type="doi">10.48550/arXiv.2107.13247</citation>
|
|
|
413 <!-- Example of annotating a citation using a BibTex entry. -->
|
|
|
414 </citations>
|
|
|
415 </tool>
|
