Mercurial > repos > sigven > oncoenrichr

changeset 3:2f22b3924572 draft

Find changesets by keywords (author, files, the commit message), revision number or hash, or revset expression.
Uploaded
author sigven
date Tue, 21 Feb 2023 14:47:45 +0000
parents 3c61ef74a176
children 781e1a7160d8
files oncoenrichr_wrapper.xml
diffstat 1 files changed, 83 insertions(+), 67 deletions(-) [+]
line wrap: on
line diff
--- a/oncoenrichr_wrapper.xml	Tue Sep 27 15:31:59 2022 +0000
+++ b/oncoenrichr_wrapper.xml	Tue Feb 21 14:47:45 2023 +0000
@@ -1,7 +1,7 @@
-<tool id="oncoenrichr_wrapper" name="oncoEnrichR" version="1.3.2">
+<tool id="oncoenrichr_wrapper" name="oncoEnrichR" version="1.4.0">
   <description>Cancer-dedicated gene set interpretation</description>
     <requirements>
-        <container type="docker">sigven/oncoenrichr:1.3.2</container>
+        <container type="docker">sigven/oncoenrichr:1.4.0</container>
   </requirements>
   <command detect_errors="aggressive"><![CDATA[
       #if $query_set.query_choice.query_input == "text"
@@ -27,7 +27,7 @@
 
       R -e 'suppressPackageStartupMessages(library(oncoEnrichR));
       suppressWarnings(load(system.file("internal_db", "oedb.rda", package = "oncoEnrichR")));
-      gene_data <- read.csv("$input_file", stringsAsFactors = F, header = F);
+      gene_data <- read.csv("$input_file", strip.white = TRUE);
       oe_report <- oncoEnrichR::onco_enrich(
         query = gene_data[[1]],
         oeDB = oedb,
@@ -55,17 +55,17 @@
       show_coexpression = $modules.show_coexpression,
       show_subcell_comp = $modules.show_subcell_comp,
       show_complex = $modules.show_complex,
-	 show_domain = $modules.show_domain,
+	  show_domain = $modules.show_domain,
       show_fitness = $modules.show_fitness,
-	 show_cell_tissue = $modules.show_cell_tissue,
+	  show_cell_tissue = $modules.show_cell_tissue,
       show_ligand_receptor = $modules.show_ligand_receptor,
       show_regulatory = $modules.show_regulatory,
-	 show_prognostic = $modules.show_prognostic,
-	 show_unknown_function = $modules.show_unknown_function,
+	  show_prognostic = $modules.show_prognostic,
+	  show_unknown_function = $modules.show_unknown_function,
       show_synleth = $modules.show_synleth,
 
       #if $background_file
-          bgset = read.csv("$background_file", stringsAsFactors = F, header = F)[[1]],
+          bgset = read.csv("$background_file", strip.white = TRUE)[[1]],
 		#if $fun_enrich.custom_bgset.bg_enrich_id_type
             bgset_id_type = "$fun_enrich.custom_bgset.bg_enrich_id_type",
           #end if
@@ -76,45 +76,54 @@
           bgset = NULL,
       #end if
 
-      #if $fun_enrich.p_value_cutoff_enrichment
-          p_value_cutoff_enrichment = $fun_enrich.p_value_cutoff_enrichment,
+      #if $fun_enrich.enrichment_p_value_cutoff
+          enrichment_p_value_cutoff = $fun_enrich.enrichment_p_value_cutoff,
       #end if
-      #if $fun_enrich.p_value_adjustment_method
-          p_value_adjustment_method = "$fun_enrich.p_value_adjustment_method",
+      #if $fun_enrich.enrichment_p_value_adj
+          enrichment_p_value_adj = "$fun_enrich.enrichment_p_value_adj",
+      #end if
+      #if $fun_enrich.enrichment_q_value_cutoff
+          enrichment_q_value_cutoff = $fun_enrich.enrichment_q_value_cutoff,
       #end if
-      #if $fun_enrich.q_value_cutoff_enrichment
-          q_value_cutoff_enrichment = $fun_enrich.q_value_cutoff_enrichment,
+      #if $fun_enrich.enrichment_min_geneset_size
+          enrichment_min_geneset_size = $fun_enrich.enrichment_min_geneset_size,
       #end if
-      #if $fun_enrich.min_geneset_size
-          min_geneset_size = $fun_enrich.min_geneset_size,
+      #if $fun_enrich.enrichment_max_geneset_size
+          enrichment_max_geneset_size = $fun_enrich.enrichment_max_geneset_size,
       #end if
-      #if $fun_enrich.max_geneset_size
-          max_geneset_size = $fun_enrich.max_geneset_size,
-      #end if
+      enrichment_plot_num_terms = $fun_enrich.enrichment_plot_num_terms,
+      enrichment_simplify_go = $fun_enrich.enrichment_simplify_go,
+
 
       #if $protein_interactions.ppi_add_nodes
           ppi_add_nodes = $protein_interactions.ppi_add_nodes,
       #end if
-      #if $protein_interactions.ppi_score_threshold
-          ppi_score_threshold = $protein_interactions.ppi_score_threshold,
+      #if $protein_interactions.ppi_string_min_score
+          ppi_string_min_score = $protein_interactions.ppi_string_min_score,
       #end if
-      show_drugs_in_ppi = $protein_interactions.show_drugs_in_ppi,
-	 ppi_node_shadow = $protein_interactions.ppi_node_shadow,
+      #if $protein_interactions.ppi_biogrid_min_evidence
+          ppi_biogrid_min_evidence = $protein_interactions.ppi_biogrid_min_evidence,
+      #end if
+      ppi_show_drugs = $protein_interactions.ppi_show_drugs,
+      ppi_show_isolated_nodes = $protein_interactions.ppi_show_isolated_nodes,
+	  ppi_node_shadow = $protein_interactions.ppi_node_shadow,
 
-	 #if $subcellular_compartments.min_subcellcomp_confidence
-          min_subcellcomp_confidence = $subcellular_compartments.min_subcellcomp_confidence,
+	  #if $subcellular_compartments.subcellcomp_min_confidence
+          subcellcomp_min_confidence = $subcellular_compartments.subcellcomp_min_confidence,
       #end if
-      #if $fitness.max_fitness_score
-          max_fitness_score = $fitness.max_fitness_score,
+      #if $subcellular_compartments.subcellcomp_min_channels
+          subcellcomp_min_channels = $subcellular_compartments.subcellcomp_min_channels,
       #end if
-      subcellcomp_show_cytosol = $subcellular_compartments.show_cytosol,
+      #if $fitness.fitness_max_score
+          fitness_max_score = $fitness.fitness_max_score,
+      #end if
+      subcellcomp_show_cytosol = $subcellular_compartments.subcellcomp_show_cytosol,
       #if $disease.show_top_diseases_only
           show_top_diseases_only = $disease.show_top_diseases_only,
       #end if
 
-      min_confidence_reg_interaction = "$regulatory.min_confidence_reg_interaction",
-      num_terms_enrichment_plot = $fun_enrich.num_terms_enrichment_plot,
-      simplify_go = $fun_enrich.simplify_go,
+      regulatory_min_confidence = "$regulatory.regulatory_min_confidence",
+      
       html_floating_toc = $report_metadata.html_floating_toc,
       html_report_theme = "$report_metadata.html_report_theme",
       galaxy = TRUE
@@ -160,7 +169,7 @@
           <param type="text" name="project_owner" label="Project owner" />
           <param type="text" name="project_description" label="Project description" area="true"/>
           <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"/>
-          <param name="html_report_theme" type="select" label="HTML report - bootswatch theme" expanded="true">
+          <param name="html_report_theme" type="select" label="HTML report - bootswatch theme">
               <option value="default">default</option>
               <option value="cerulean">cerulean</option>
               <option value="cosmo">cosmo</option>
@@ -177,9 +186,9 @@
 
       <section title="" name=""/>
       <section name="modules" title="Analysis modules included in the report" expanded="true">
-		<param name="show_disease" type="boolean" label="Gene-cancer associations" truevalue="T" falsevalue="F" checked="true"/>
+		  <param name="show_disease" type="boolean" label="Gene-cancer associations" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_enrichment" type="boolean" label="Gene functional enrichment" truevalue="T" falsevalue="F" checked="true"/>
-		<param name="show_cell_tissue" type="boolean" label="Tissue/cell-type enrichment" truevalue="T" falsevalue="F" checked="false"/>
+		  <param name="show_cell_tissue" type="boolean" label="Tissue/cell-type enrichment" truevalue="T" falsevalue="F" checked="false"/>
           <param name="show_ppi" type="boolean" label="Protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_regulatory" type="boolean" label="Regulatory (TF-target) interactions" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_ligand_receptor" type="boolean" label="Ligand-receptor interactions" truevalue="T" falsevalue="F" checked="true"/>
@@ -189,15 +198,15 @@
           <param name="show_coexpression" type="boolean" label="Tumor co-expression patterns" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_subcell_comp" type="boolean" label="Subcellular localizations" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_complex" type="boolean" label="Protein complex memberships" truevalue="T" falsevalue="F" checked="true"/>
-		<param name="show_domain" type="boolean" label="Protein domain frequencies" truevalue="T" falsevalue="F" checked="false"/>
+		  <param name="show_domain" type="boolean" label="Protein domain frequencies" truevalue="T" falsevalue="F" checked="false"/>
           <param name="show_fitness" type="boolean" label="Gene fitness effects" truevalue="T" falsevalue="F" checked="true"/>
           <param name="show_synleth" type="boolean" label="Predicted synthetic lethality interactions" truevalue="T" falsevalue="F" checked="true"/>
-		<param name="show_unknown_function" type="boolean" label="Genes of poorly defined function" truevalue="T" falsevalue="F" checked="true"/>
-		<param name="show_prognostic" type="boolean" label="Prognostic cancer associations" truevalue="T" falsevalue="F" checked="true"/>
+		  <param name="show_unknown_function" type="boolean" label="Genes of poorly defined function" truevalue="T" falsevalue="F" checked="true"/>
+		  <param name="show_prognostic" type="boolean" label="Prognostic cancer associations" truevalue="T" falsevalue="F" checked="true"/>
       </section>
 
       <section title="" name=""/>
-      <section name="fun_enrich" title="Options - gene functional enrichment" expanded="true">
+      <section name="fun_enrich" title="Options - gene functional enrichment">
 		 <conditional name="custom_bgset">
 			 <param name="def_background" type="boolean" label="Define custom background set (all annotated protein-coding genes by default)" truevalue="T" falsevalue="F" checked="false"/>
 			 <when value="T">
@@ -230,38 +239,44 @@
 			</when>
 		</conditional>
 
-          <param type="float" name="p_value_cutoff_enrichment" label="P-value cutoff for enrichment tests (clusterProfiler)" value="0.05"/>
-          <param type="select" name="p_value_adjustment_method" label="P-value adjustment method (clusterProfiler)">
-              <option value="holm">holm</option>
-              <option value="hochberg">hochberg</option>
-              <option value="hommel">hommel</option>
-              <option value="bonferroni">bonferroni</option>
-              <option value="BH">BH</option>
-              <option value="BY">BY</option>
+          <param name="enrichment_p_value_cutoff" type="float" label="P-value cutoff for enrichment tests (clusterProfiler)" value="0.05"/>
+          <param name="enrichment_p_value_adj" type="select" label="P-value adjustment method (clusterProfiler)">
+              <option value="BH">Benjamini-Hochberg</option>
+              <option value="holm">Holm</option>
+              <option value="hochberg">Hochberg</option>
+              <option value="hommel">Hommel</option>
+              <option value="bonferroni">Bonferroni</option>
+              <option value="BY">Benjamini-Yekutieli</option>
               <option value="fdr">fdr</option>
               <option value="none">none</option>
           </param>
-          <param type="float" name="q_value_cutoff_enrichment" label="Q-value cutoff for enrichment tests to report as significant (clusterProfiler)" value="0.2"/>
-          <param type="integer" name="min_geneset_size" label="Minimum number of genes annotated by ontology term for testing (clusterProfiler)" value="10"/>
-          <param type="integer" name="max_geneset_size" label="Maximum number of genes annotated by ontology term for testing (clusterProfiler)" value="500"/>
-          <param name="simplify_go" type="boolean" label="Simplify GO enrichment results by removal of redundant terms (recommended)" truevalue="T" falsevalue="F" checked="true"/>
-          <param type="integer" name="num_terms_enrichment_plot" label="Number of top enriched Gene Ontology terms (max) to show in enrichment barplot" min="10" max="30" value="20"/>
+          <param name="enrichment_q_value_cutoff" type="float" label="Q-value cutoff for enrichment tests to report as significant (clusterProfiler)" value="0.2"/>
+          <param name="enrichment_min_geneset_size" type="integer" label="Minimum number of genes annotated by ontology term for testing (clusterProfiler)" value="10"/>
+          <param name="enrichment_max_geneset_size" type="integer" label="Maximum number of genes annotated by ontology term for testing (clusterProfiler)" value="500"/>
+          <param name="enrichment_simplify_go" type="boolean" label="Simplify GO enrichment results by removal of redundant terms (recommended)" truevalue="T" falsevalue="F" checked="true"/>
+          <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"/>
       </section>
 
       <section title="" name=""/>
-      <section name="fitness" title="Options - gene fitness scores" expanded="true">
-          <param type="float" name="max_fitness_score" label="Maximum loss-of-fitness score (Bayes Factor from BAGEL) for genes retrieved from Project Score" value="-2" min="-5" max="0"/>
+      <section name="fitness" title="Options - gene fitness scores">
+          <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"/>
       </section>
       <section title="" name=""/>
-      <section name="protein_interactions" title="Options - protein-protein interaction network" expanded="true">
-          <param type="integer" name="ppi_add_nodes" label="Addition of interacting non-queryset proteins to the protein-protein interaction network (maximum number)" value="50" min="0" max="50"/>
-          <param type="integer" name="ppi_score_threshold" label="Minimum confidence score for interactions to be included in the network (STRING confidence: 0-1000)" value="900" min="400" max="1000"/>
-          <param name="show_drugs_in_ppi" type="boolean" label="Show anti-cancer drugs in protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
-		<param name="ppi_node_shadow" type="boolean" label="Add shadow to nodes in protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
+      <section name="protein_interactions" title="Options - protein-protein interaction network">
+          <param name="ppi_network_type" type = "select" label="STRING: type of retrieved network interactions">
+              <option value="functional">functional</option>
+              <option value="physical">physical</option>
+          </param>
+          <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"/>
+          <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"/>
+          <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"/>
+          <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"/>
+          <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"/>
+		  <param name="ppi_node_shadow" type="boolean" label="Add shadow to nodes in protein-protein interaction network" truevalue="T" falsevalue="F" checked="true"/>
       </section>
       <section title="" name=""/>
-      <section name="regulatory" title="Options - regulatory interactions" expanded="true">
-         <param type="select" name="min_confidence_reg_interaction" label = "Minimum confidence level of regulatory interactions included (DoRothEA - A:highest, D:lowest)">
+      <section name="regulatory" title="Options - regulatory interactions">
+         <param name="regulatory_min_confidence" type="select" label = "Minimum confidence level of regulatory interactions included (DoRothEA - A:highest, D:lowest)">
             <option value="D">D</option>
             <option value="C">C</option>
             <option value="B">B</option>
@@ -270,13 +285,14 @@
       </section>
      <section title="" name=""/>
 
-	 <section name="subcellular_compartments" title="Options - Subcellular localizations" expanded="true">
-           <param type="integer" name="min_subcellcomp_confidence" label="Minimum confidence level for subcellular localization annotations" value="1" min="1" max="6"/>
-          <param name="show_cytosol" type="boolean" label="Show cytosol annotations (very common localization) in subcellular heatmap " truevalue="T" falsevalue="F" checked="false"/>
+	 <section name="subcellular_compartments" title="Options - Subcellular compartment annotations">
+        <param name="subcellcomp_min_confidence" type="integer" label="Minimum confidence level for subcellular compartment annotations" value="3" min="3" max="5"/>
+        <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"/>
+        <param name="subcellcomp_show_cytosol" type="boolean" label="Show cytosol annotations (very common localization) in subcellular heatmap " truevalue="T" falsevalue="F" checked="false"/>
       </section>
       <section title="" name=""/>
 
-      <section name="disease" title="Options - Disease associations" expanded="true">
+      <section name="disease" title="Options - Disease associations">
           <param type="boolean" name="show_top_diseases_only" label="Show top disease assocations only" truevalue="T" falsevalue="F" checked="true"/>
       </section>
 
@@ -290,7 +306,7 @@
   <help><![CDATA[
 .. class:: infomark
 
-The query gene set is limited to n = 500 identifiers. A limited query gene set (e.g. n < 5) will in general reduce the relevance and significance of many oncoEnrichR report modules.
+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.
 
 -----
 
@@ -333,7 +349,7 @@
 
 -  `hu.MAP2 <http://humap2.proteincomplexes.org/>`_ - human protein complex map
 
--  `ComPPI <http://comppi.linkgroup.hu/>`_ - subcellular compartment database
+-  `COMPARTMENTS <https://compartments.jensenlab.org/Search/>`_ - subcellular compartment annotation database
 
 -  `CancerMine <http://bionlp.bcgsc.ca/cancermine/>`_ - literature-mined resource on cancer drivers, oncogenes and tumor suppressor genes
 
@@ -347,7 +363,7 @@
 
 The contents of the gene set analysis report attempt to answer the following questions related to the query set:
 
--  Which diseases/tumor types are known to be associated with genes in the query set, and to what extent? Which genes are a classified as proto-oncogenes, tumor suppressors or cancer driver genes?
+-  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?
 
 -  Which query genes have been linked (through literature) to the various hallmarks of cancer?