annotate GO_terms_enrich_comparison.xml @ 1:528652235016 draft

planemo upload commit c9d70181a2b587e53dcc4b5885b74b625def6b8c-dirty

<tool id="go_terms_enrich_comparison" name="GO terms enrich comparison " version="2019.12.13">
    <description>(Human, Mouse, Rat)[clusterProfiler]</description>
    <requirements>
        <requirement type="package">R</requirement>
        <requirement type="package" version="3.8.2">bioconductor-org.hs.eg.db</requirement>
        <requirement type="package" version="3.8.2">bioconductor-org.mm.eg.db</requirement>
        <requirement type="package" version="3.8.2">bioconductor-org.rn.eg.db</requirement>
        <requirement type="package" version="3.10.2">bioconductor-dose</requirement>
        <requirement type="package" version="3.12.0">bioconductor-clusterprofiler</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[


       Rscript $__tool_directory__/GO_terms_enrich_comparison.R

        --nb=$len($lists)

        #for $index, $list in enumerate($lists)
        		    
            #if $list.input.ids == "file"
		        --input.$index="$list.input.file" --name.$index="$list.list_name" --inputtype.$index="file" --header.$index="$list.input.header" --column.$index="$list.input.ncol" 
            #else
                --input.$index="$list.input.txt" --name.$index="$list.list_name" --inputtype.$index="text"  
 		    #end if
            
        #end for

        --org="$species"
        --ont="$ontology"
       

            > $log


    ]]></command>
    <inputs>

        <repeat name="lists" title="List to compare" min="2" max="5" >

            <conditional name="input" >
                <param name="ids" type="select" label="Enter your Gene ID list" help="Copy/paste or from a file (e.g. table)" >
                    <option value="text">Copy/paste your IDs</option>
                    <option value="file" selected="true">Input file containing your IDs</option>
                </param>
                <when value="text" >
                    <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by spaces into the form field, for example: 2810 7534' >
                        <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="file" type="data" format="txt,tabular" label="Choose a file that contains your list of IDs" help="" />
                    <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does file contain header?" />
                    <param name="ncol" 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'>
                        <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
                    </param>
                </when>
            </conditional>
                
            <param name="list_name" type="text" label="name of your list" value="list" optional="false">
                <sanitizer>
                    <valid initial="string.printable">
                        <remove value="&apos;"/>
                    </valid>
                    <mapping initial="none">
                        <add source="&apos;" target="__sq__"/>
                    </mapping>
                </sanitizer>
                <validator type="regex" message="Please enter a list name">[a-zA-Z0-9._-]+</validator>
            </param>
        
        </repeat>
        
        <param name="species" type="select" label="Species" >
            <option value="org.Hs.eg.db">Human (Homo sapiens) </option>
            <option value="org.Mm.eg.db">Mouse (Mus musculus) </option>
            <option value="org.Rn.eg.db">Rat (Rattus norvegicus)</option>
        </param>
		<param name="ontology" type="select" display="checkboxes" multiple="true" label="Select GO terms category" optional="false" >
            <option value="CC">Cellular Component</option>
            <option value="BP">Biological Process</option>
            <option value="MF">Molecular Function</option>
        </param>
    </inputs>
    
    <outputs>
        <data name="log" format="txt" label="GO enrich comparison" />
        <collection type="list" label="GO enrichComparison results Table" name="text_output">
            <discover_datasets pattern="(?P&lt;designation&gt;.+\.tsv)" ext="tsv"/>
        </collection>
        <collection type="list" label="GO enrichComparison results Diagram" name="graph_output" >
	        <discover_datasets pattern="(?P&lt;designation&gt;.+.png)" ext="png" />
	    </collection>
    </outputs>

    <tests>
        <test>
            <repeat name="lists">
	            <conditional name="input">
	                <param name="ids" value="file" />
	                <param name="file" value="Gene_ID_BreastUp.txt" />
	                <param name="header" value="true" />
	                <param name="ncol" value="c7" />
	                <param name="name" value="UP" />
	            </conditional>
	        </repeat>
            <repeat name="lists">
	            <conditional name="input">
	                <param name="ids" value="file" />
	                <param name="file" value="Gene_ID_BreastDn.txt" />
	                <param name="header" value="true" />
	                <param name="ncol" value="c7" />
	                <param name="name" value="DN" />
	            </conditional>
	        </repeat>

            <param name="species" value="org.Hs.eg.db"/>
            <param name="ontology" value="BP"/>
            <output name="log" file="log.txt" />
            <output_collection name="text_output">
                <element name="GO_enrich_comparison_BP.tsv" file="GO_enrich_comparison_BP.tsv" ftype="tsv"/>
            </output_collection>
            <output_collection name="graph_output">
                <element name="GO_enrich_comparison_BP.png" file="GO_enrich_comparison_BP.png" ftype="png"/>
            </output_collection>
        </test>
    </tests>
    <help><![CDATA[

**Description**

This tool is based on the R package clusterProfiler and allows to compare GO terms enrichment analyses of gene/protein sets. 
Given a list of gene set, this function will compute GO enrichment profiles of each gene list.

This tool 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, user has the possibility to use the "Build tissue-specific expression dataset" ProteoRE tool to create this list according to your need. 

-----

**Input**

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).

"Enter your Gene ID list": only Entrez Gene ID (e.g : 4151, 7412).  
If your IDs are not Entrez Gene IDs, please use the ID_Converter tool of ProteoRE. 

"Does file contain header?": in case of file input, you specify if there is header or not. 

"Column number of IDs": in which column are your IDs. (e.g. for column 2 you write "c2")

"name of your list": write the name for this list

-----

**Parameters**

"Species": the three supported species are Homo sapiens, Mus musculus and Rattus norvegicus 

"Select GO terms category": allows you to perform analysis on one, two or three categories of the Gene Ontology. The categories are 
 Cellular Component (CC), Biological Process (BP) and Molecular Function (MF). 

----- 

**Output**

Diagram output: graphical output in the form of a dot-plot (png, jpeg or pdf format), one figure for each GO category. 
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. 

-----

**Authors**
G Yu, LG Wang, Y Han, QY He. clusterProfiler: an R package for comparing biological themes among gene clusters. 
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)

User manual / Documentation of the clusterProfiler R package (functions and parameters):
https://bioconductor.org/packages/3.7/bioc/vignettes/clusterProfiler/inst/doc/clusterProfiler.html

-----

.. class:: infomark

**Galaxy integration**

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.


    ]]></help>
    <citations>
    </citations>
</tool>