comparison topGO.xml @ 10:e3430084c996 draft

planemo upload commit ad5f1c5a1a71d7fa2bc8bac408856aa80b0fc2a3

9:70c0c8757f5f

<tool id="topGO" name="topGO" version="2018.09.21">
    <description>
    Enrichment analysis for Gene Ontology
    </description>
    <requirements>
        <requirement type="package" version="3.4.1">R</requirement>
        <requirement type="package" version="3.0.0">r-ggplot2</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.ce.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.dm.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.sc.sgd.db</requirement>
        <!--requirement type="package" version="3.5.0">bioconductor-org.at.tair.db</requirement-->
        <requirement type="package" version="1.56.0">bioconductor-graph</requirement>
        <requirement type="package" version="1.40.0">bioconductor-annotationdbi</requirement>
        <requirement type="package" version="3.5.0">bioconductor-go.db</requirement>
        <requirement type="package" version="2.30.0">bioconductor-topgo</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
    
  #if $inputtype.filetype == "file_all": 
  Rscript --vanilla $__tool_directory__/enrichment_v3.R 
  --inputtype tabfile 
  --input '$inputtype.genelist' 
  --ontology '$ontocat' 
  --option '$option' 
  --threshold '$threshold' 
  --correction '$correction' 
  --textoutput '$condtext.textoutput' 
  --barplotoutput '$condbar.barplotoutput' 
  --dotplotoutput '$conddot.dotplotoutput' 
  --column '$inputtype.column' 
  --geneuniverse '$geneuniverse' 
  --header '$inputtype.header'
  #end if
    
    
  #if $inputtype.filetype == "copy_paste": 
  Rscript --vanilla $__tool_directory__/enrichment_v3.R 
  --inputtype copypaste 
  --input '$inputtype.genelist' 
  --ontology '$ontocat' 
  --option '$option' 
  --threshold '$threshold' 
  --correction '$correction' 
  --textoutput '$condtext.textoutput' 
  --barplotoutput '$condbar.barplotoutput' 
  --dotplotoutput '$conddot.dotplotoutput' 
  --column c1 
  --geneuniverse '$geneuniverse' 
  --header None
  #end if



    ]]></command>

    <inputs>
  <conditional name="inputtype">
    <param name="filetype" type="select" label="Select your type of input file" help="The identifiers must be Ensembl gene IDs (e.g : ENSG00000139618). If it is not the case, please use the ID Mapping tool.">
      <option value="file_all" selected="true">Input file containing your identifiers</option>
      <option value="copy_paste">Copy/paste your list of IDs</option> 
    </param>
    <when value="copy_paste">
      <param name="genelist" type="text" label="Enter a list of identifiers">
        <sanitizer>
            <valid initial="string.printable">
                <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
                <add source="&apos;" target="__sq__"/>
            </mapping>
        </sanitizer>
      </param>
    </when>
    <when value="file_all">
      <param name="genelist" type="data" format="txt,tabular" label="Choose an input file" help="This file must imperatively have 1 column filled with IDs consistent with the database that will be used. Please use the MappingIDs component if this is not the case."/>
      <param name="column" type="text" label="Please specify the column where your Ensembl IDs are (e.g : Enter 'c1' for column n°1..)" value="c1"/> 
    
      <param name="header" type="select" label="Does your file have a header?" multiple="false" optional="false"> 
 	<option value="TRUE" selected="true">Yes</option>
        <option value="FALSE" selected="false">No</option>
      </param>
    </when>
  </conditional>
      <param name="geneuniverse" type="select" label="Select a specie">
        <!--option value="org.At.tair.db" >Arabidopsis</option-->
        <option value="org.Ce.eg.db" >Worm (C. elegans)</option>
        <option value="org.Dm.eg.db" >Fly (D. melanogaster)</option>
        <option value="org.Hs.eg.db" selected="true">Human (H. sapiens)</option>
        <option value="org.Mm.eg.db" >Mouse (M. musculus)</option>
        <option value="org.Sc.sgd.db" >Yeast (S. cerevisiae)</option>
      </param>

      <param name="ontocat" type="select" label="Ontology category">
              <option value="BP" >Biological Process</option>
              <option value="CC" >Cellular Component</option>
              <option value="MF" >Molecular Function</option>
        </param>

        <param name="option" type="select" label="Choose the topGO option for your analysis">
                <option value="classic" >Classic fisher test</option>
                <option value="elim" selected="true">Elim</option>
                <option value="weight01" >Weight01</option>
                <option value="parentchild" >ParentChild</option>
          </param>
        <param name="threshold" type="text" label="Enter the p-value threshold level under the form 1e-level wanted (e.g : 1e-3)" value="1e-3"/>
	<param name="correction" label="Choose a correction for multiple testing" type="select">
             <option value="none" >None</option>
             <option value="holm">Holm correction</option>
             <option value="hochberg" >Hochberg correction</option>
             <option value="hommel" >Hommel correction</option>
             <option value="bonferroni" >Bonferroni correction</option>
             <option value="BH" selected="true">Benjamini and Hochberg</option>
             <option value="BY" >Benjamini and Yekutieli</option>
             <option value="fdr" >FDR</option>
           </param>
            <conditional name="condtext">
            <param name="textoutput" type="select" label="Generate a text file for results">
              <option value="TRUE">Yes</option>
              <option value="FALSE">No</option>
            </param>
            <when value="TRUE"/>
            <when value="FALSE"/>
          </conditional>
          <conditional name="condbar">
            <param name="barplotoutput" type="select" label="Generate a barplot of over-represented GO terms">
              <option value="TRUE">Yes</option>
              <option value="FALSE">No</option>
            </param>
            <when value="TRUE"/>
            <when value="FALSE"/>
          </conditional>
          <conditional name="conddot">
              <param name="dotplotoutput" type="select" label="Generate a dotplot of over-represented GO terms">
              <option value="TRUE">Yes</option>
              <option value="FALSE">No</option>
            </param>
            <when value="TRUE"/>
            <when value="FALSE"/>
          </conditional>
    </inputs>
    <outputs>

      <data name="outputtext" format="tabular" label="Text output for topGO analysis $ontocat category" from_work_dir="result.csv">
        <filter>condtext['textoutput']=="TRUE"</filter>
      </data>

      <data name="outputbarplot" format="png" label="Barplot output for topGO analysis $ontocat category" from_work_dir="barplot.png">
        <filter>condbar['barplotoutput']=="TRUE"</filter>
      </data>
      
      <data name="outputdotplot" format="png" label="Dotplot output for topGO analysis $ontocat category" from_work_dir="dotplot.png">
        <filter>conddot['dotplotoutput']=="TRUE"</filter>
      </data>
      
   </outputs>
   <tests>
     <test>

     </test>
   </tests>
   <help><![CDATA[
      
      
**Galaxy component based on R package topGO.** 

**Input required**

This component works with Ensembl gene ids (e.g : ENSG0000013618). You can
copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab)
where there are contained. 

**Principle**

This component provides the GO terms representativity of a gene list in one ontology category (Biological Process "BP", Cellular Component "CC", Molecular Function "MF"). This representativity is evaluated in comparison to the background list of all human genes associated associated with GO terms of the chosen category (BP,CC,MF). This background is given by the R package "org.Hs.eg.db", which is a genome wide association package for **human**.

**Output**

Three kind of outputs are available : a textual output, a barplot output and
a dotplot output. 

*Textual output* :
The text output lists all the GO-terms that were found significant under the specified threshold.    


The different fields are as follow :

- Annotated : number of genes in org.Hs.eg.db which are annotated with the GO-term.

- Significant : number of genes belonging to your input which are annotated with the GO-term. 

- Expected : show an estimate of the number of genes a node of size Annotated would have if the significant genes were to be randomly selected from the gene universe.  

- pvalues : pvalue obtained after the test 

- ( qvalues  : additional column with adjusted pvalues ) 

 
**Tests**

topGO provides a classic fisher test for evaluating if some GO terms are over-represented in your gene list, but other options are also provided (elim, weight01,parentchild). For the merits of each option and their algorithmic descriptions, please refer to topGO manual : 
https://bioconductor.org/packages/release/bioc/vignettes/topGO/inst/doc/topGO.pdf

**Multiple testing corrections**
    
Furthermore, the following corrections for multiple testing can also be applied : 

- holm

- hochberg

- hommel

- bonferroni

- BH

- BY

- fdr

-----

.. class:: infomark

**Authors**

Alexa A and Rahnenfuhrer J (2016). topGO: Enrichment Analysis for Gene Ontology. R package version 2.30.0.

**Galaxy integration**

Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR

Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform

This work has been partially funded through the French National Agency for Research (ANR) IFB project.

Contact [e-mail] for any questions or concerns about the Galaxy implementation of this tool.

10:e3430084c996

<tool id="topGO" name="Enrichment analysis for Gene Ontology" version="2018.12.17">
    <description>(Human, Mouse, Rat)[topGO]</description>
    <requirements>
        <requirement type="package" version="3.4.1">R</requirement>
        <requirement type="package" version="3.0.0">r-ggplot2</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.mm.eg.db</requirement>
        <requirement type="package" version="3.5.0">bioconductor-org.rn.eg.db</requirement>
        <!--requirement type="package" version="3.6.0">bioconductor-org.ce.eg.db</requirement-->
        <!--requirement type="package" version="3.6.0">bioconductor-org.dm.eg.db</requirement-->
        <!--requirement type="package" version="3.6.0">bioconductor-org.sc.sgd.db</requirement-->
        <!--requirement type="package" version="3.5.0">bioconductor-org.at.tair.db</requirement-->
        <requirement type="package" version="1.56.0">bioconductor-graph</requirement>
        <requirement type="package" version="1.40.0">bioconductor-annotationdbi</requirement>
        <requirement type="package" version="3.5.0">bioconductor-go.db</requirement>
        <requirement type="package" version="2.30.0">bioconductor-topgo</requirement>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command><![CDATA[
       
  Rscript --vanilla $__tool_directory__/topGO_enrichment.R 
  --inputtype="$inputtype.filetype"
  --input='$inputtype.genelist'

  #if $inputtype.filetype == "file"
    --column='$inputtype.column'
    --header='$inputtype.header'
  #end if

  --ontology='$ontocat'
  --option='$option'
  --threshold='$threshold'
  --correction='$correction'
  --textoutput='true'
  --plot='$plot'
  --geneuniverse='$geneuniverse' 
  --background="$background_genes.background"

  #if $background_genes.background == "true"
    --background_genes="$background_genes.inputtype.genelist"
    --background_input_type="$background_genes.inputtype.filetype"
    #if $background_genes.inputtype.filetype == "file"
      --background_header="$background_genes.inputtype.header"
      --background_column="$background_genes.inputtype.column"
    #end if
  #end if

    ]]></command>

    <inputs>
  <conditional name="inputtype">
    <param name="filetype" type="select" label="Enter your IDs (Ensembl Gene only)" help="Copy/paste or from a file">
      <option value="file" selected="true">Input file containing your IDs</option>
      <option value="copy_paste">Copy/paste your list of IDs</option> 
    </param>
    <when value="copy_paste">
      <param name="genelist" type="text" label="Enter a list of IDs">
        <sanitizer>
            <valid initial="string.printable">
                <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
                <add source="&apos;" target="__sq__"/>
            </mapping>
        </sanitizer>
      </param>
    </when>
    <when value="file">
      <param name="genelist" type="data" format="txt,tabular" label="Select your file" help=""/>
      <param name="column" type="text" 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"/> 
      <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" /> 
    </when>
  </conditional>
  <conditional name="background_genes">
    <param name="background" type="boolean" checked="false" truevalue="true" falsevalue="false" label="Define your own background IDs ?"/>
    <when value="true">
      <conditional name="inputtype">
        <param name="filetype" type="select" label="Enter your background IDs (Ensembl gene IDs)" help="(e.g : ENSG00000139618)">
          <option value="file" selected="true">Input file containing your background IDs</option>
          <option value="copy_paste">Copy/paste your background IDs</option> 
        </param>
        <when value="copy_paste">
          <param name="genelist" type="text" label="Copy/paste your background IDs" help="IDs must be separated by spaces into the form field, for example: ENSG00000139618 ENSG00000007350">
            <sanitizer>
            <valid initial="string.printable">
                <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
                <add source="&apos;" target="__sq__"/>
            </mapping>
            </sanitizer>
          </param>
        </when>
        <when value="file">
          <param name="genelist" type="data" format="txt,tabular" label="Select file that contains your background IDs list" help=""/>
          <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header ?" /> 
          <param name="column" type="text" label="Column number of IDs" value="c1" help="For example, fill in 'c1' if it is the first column, 'c2' if it is the second column and so on"/> 
        </when>
      </conditional>
    </when>
    <when value="false"/>
  </conditional>
    <param name="geneuniverse" type="select" label="Species">
      <!--option value="org.At.tair.db" >Arabidopsis</option-->
      <!--option value="org.Ce.eg.db" >Worm (C. elegans)</option-->
      <!--option value="org.Dm.eg.db" >Fly (D. melanogaster)</option-->
      <option value="org.Hs.eg.db" selected="true">Human (Homo sapiens)</option>
      <option value="org.Mm.eg.db" >Mouse (Mouse musculus)</option>
      <option value="org.Rn.eg.db" >Rat (Rattus norvegicus)</option>
      <!--option value="org.Sc.sgd.db" >Yeast (S. cerevisiae)</option-->
    </param>
    <param name="ontocat" type="select" label="GO terms category">
      <option value="BP" >Biological Process</option>
      <option value="CC" >Cellular Component</option>
      <option value="MF" >Molecular Function</option>
    </param>
    <param name="option" type="select" label="Select the topGO parameter (see user doc)">
      <option value="classic" >Classic Fisher test</option>
      <option value="elim" selected="true">Elim</option>
      <option value="weight01" >Weight01</option>
      <option value="parentchild" >ParentChild</option>
    </param>
    <param name="threshold" type="text" label="p-value threshold (e.g : 1e-3)" value="1e-3"/>
	  <param name="correction" label="Multiple testing procedure (p-value adjustment)" type="select">
      <option value="none" >None</option>
      <option value="holm">Holm correction</option>
      <option value="hochberg" >Hochberg correction</option>
      <option value="hommel" >Hommel correction</option>
      <option value="bonferroni" >Bonferroni correction</option>
      <option value="BH" selected="true">Benjamini and Hochberg</option>
      <option value="BY" >Benjamini and Yekutieli</option>
      <option value="fdr" >FDR</option>
    </param>
    <!--param name="textoutput" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Generate a text file for results" /-->
    <param name="plot" type="select" display="checkboxes" multiple="true" label="Graphical display" optional="false">
      <option selected = "true" value="dotplot">dot-plot</option>
      <option value="barplot">bar-plot</option>
    </param>
    </inputs>
    <outputs>

      <data name="outputtext" format="tsv" label="Text output for topGO analysis $ontocat category" from_work_dir="result">
        <filter>textoutput</filter>
      </data>

      <data name="outputbarplot" format="png" label="Barplot output for topGO analysis $ontocat category" from_work_dir="barplot.png">
        <filter>barplot</filter>
      </data>
      
      <data name="outputdotplot" format="png" label="Dotplot output for topGO analysis $ontocat category" from_work_dir="dotplot.png">
        <filter>dotplot</filter>
      </data>
      
   </outputs>
   <tests>
     <test>

     </test>
   </tests>
   <help><![CDATA[
      
      
**Description**

This tool is based on R package topGO. topGO package provides tools for testing GO terms while accounting for the topology of the GO graph. Different test statistics and different methods for eliminating local similarities and dependencies between GO terms can be applied.

This component computes the GO terms representativity of a gene list in one ontology category (Biological Process "BP", Cellular Component "CC", Molecular Function "MF"). This representativity is evaluated in comparison to the background list of all genes/proteins (of the selected species) associated associated with GO terms of the chosen category (BP,CC,MF).

-----

**Input required**

This component works with Ensembl gene IDs (e.g : ENSG0000013618). You can copy/paste these identifiers or supply a tabular file (.csv, .tsv, .txt, .tab)
and then specifying the column number that contains the ENSG IDs. 

-----

**Parameters**

"Species": "Species": the three available species are Homo sapiens, Mus musculus and Rattus norvegicus 
 
"GO terms category": select either Biogical Process (BP)(by default), Cellular Component (CC) or Molecular Function (MF)
 
"Select the topGO parameter (see user doc)": topGO provides a classic Fisher test for evaluating which GO terms are over-represented in your gene/protein list; other methodologies are also provided (Elim, Weight01, Parentchild). For the merits of each option and their algorithmic descriptions, please refer to topGO manual: 
https://bioconductor.org/packages/release/bioc/vignettes/topGO/inst/doc/topGO.pdf

"p-value threshold (e.g : 1e-3)": must be in the form of "1e-5" (i.e. 0.00001)

"Multiple testing procedure (p-value adjustment): several FDR procedure for multiple testing and p-value adjustment are available: Holm, Hochberg
Hommel, Bonferroni, BH (Benjamini-Hochberg), BY (Benjamini-Yekutieli), FDR. Default is BH (most commonly used)

-----

**Output**

Three outputs are available : a textual output, a barplot and/or a dotplot (set by default) graphical outputs. 

*Textual output*

The text output lists all the GO-terms that were found significantly enriched according to the specified threshold (p-value).    

The different fields are as follow:

- Annotated : number of genes in the selected species that are annotated with the GO-term.

- Significant : number of genes belonging to your input annotated with the GO-term. 

- Expected : represents the expected number of interesting genes mapped to the GO term if the interesting genes were randomly distributed over all GO terms.

- p-values : p-value obtained after the test 

- ( q-values  : additional column with adjusted pvalues ) 

-----

.. class:: infomark

**Authors**

Alexa A, Rahnenführer J, Lengauer T. Improved scoring of functional groups from gene expression data by decorrelating GO graph structure. Bioinformatics. 2006. 22(13):1600-7. PubMed PMID: 16606683.

-----

.. class:: infomark

**Galaxy integration**

Lisa Perus, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck - CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR

Sandra Dérozier, Olivier Rué, Christophe Caron, Valentin Loux - INRA, Paris-Saclay University, MAIAGE Unit, Migale Bioinformatics platform, FR

This work has been partially funded through the French National Agency for Research (ANR) IFB project.

Contact [e-mail] for any questions or concerns about the Galaxy implementation of this tool.