annotate compute_kegg_pathways.xml @ 0:42d0805353b6 draft

planemo upload commit 0ce4c81e6d2f7af8c9b52f6c07e83b0319c2adb1-dirty

<tool id="compute_kegg_pathways" name="KEGG pathways coverage" version="2018.09.18">
    <requirements>
        <requirement type="package" version="1.18.0">bioconductor-keggrest</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        Rscript $__tool_directory__/compute_kegg_pathways.R  
        
        #if $input.ids == "text"
            --id_list="$input.txt"
        #else
            --input="$input.file"
            --id_column="$input.ncol"
            --header="$input.header"  
        #end if
        
        --id_type="$ref_ids.id_type"
        --output="$output1" 
        --nb_pathways="$nb_pathways"
        --ref="$__tool_directory__/$ref_ids.ref_file"

    ]]></command>
    <inputs>
        <conditional name="input" >
            <param name="ids" type="select" label="Provide your identifiers (Uniprot or Entrez gene)" help="Copy/paste or ID list from a file (e.g. table)" >
                <option value="text">Copy/paste your identifiers</option>
                <option value="file" selected="true">Input file containing your identifiers</option>
            </param>
            <when value="text" >
                <param name="txt" type="text" label="Copy/paste your identifiers" help='IDs must be separated by "," into the form field, for example: P31946,P62258' >
                    <sanitizer invalid_char=''>
                        <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="Select a file that contains your list of IDs" help="" />
                <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does your input file contain header?" />
                <param name="ncol" type="text" value="c1" label="The column number of IDs to map" help='For example, fill in "c1" if it is the first column, "c2" if it is the second column and so on' />
            </when>
        </conditional>
        <conditional name="ref_ids">
            <param name="id_type" type="select" label="select your identifiers type :">
                <option value="uniprot">Uniprot Accession number</option>
                <option value="geneID">Entrez gene ID</option>
            </param>
            <when value="uniprot">
                <param name="ref_file" type="select" label="Select species" >
                    <options from_data_table="uniprot_kegg_list"/>
                        <option>Human (Homo sapiens)</option>
                        <option>Mouse (Mus musculus)</option>
                </param>
            </when>
            <when value="geneID">
                <param name="ref_file" type="select" label="Select species" >
                    <options from_data_table="entrez_kegg_list"/>
                        <option>Human (Homo sapiens)</option>
                        <option>Mouse (Mus musculus)</option>
                </param>
            </when>
        </conditional>
        <param type="integer" name="nb_pathways" label="Set the number of pathways to be displayed in the output" value="10" help="pathways are sorted by percent of mapping gene by pathway in descending order"/>
    </inputs>
    <outputs>
        <data name="output1" format="tsv" />
    </outputs>
    <help><![CDATA[

This tool computes the number of proteins from your list divided by the total number of protein of each KEGG pathway. 

it allows you to identify the signaling pathways that are the most covered by your proteomics dataset. 

By default the number of pathway to be displayed is set to 10 and sorted in descending order. 

At the moment two species are supported: Human (Homo sapiens) and Mouse (Mus musculus)

**Input:**

Input can be either a list of Uniprot accession number or Entrez gene IDs (copy/paste mode) or a file containing multiple columns but with at least one column Uniprot accession number or Entrez gene IDs. If your input file contains other type of IDs, please use the ID_Converter tool.

**Output:**

The output is a tabular file (.tsv) with the following columns:

* **Pathway_ID:** KEGG pathway identifier (e.g. hsa04970)
* **Description:** name of the pathway as in KEGG
* **Ratio IDs mapped/total IDs (%):** percentage of pathway coverage
* **nb genes mapped in the pathway:** number of genes/proteins of your list mapped on the KEGG pathway
* **nb total genes present in the pathway:** total number of genes/proteins present in the KEGG pathway

-----

.. class:: infomark

**Database:**

Pathways and associated Uniprot Accession Number or Gene IDs are collected from KEGGREST package 

User manual / Documentation: KEGGREST Bioconductor package https://bioconductor.org/packages/3.1/bioc/html/KEGGREST.html


-----

.. class:: infomark

**Galaxy integration**

David Christiany, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR

Sandra Dérozier, Olivier Rué, 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.

-----

compute_KEGG_pathways R script

| Arguments:
| --**help**                  Print this test
| --**input**                 tab file
| --**id_list**               id list ',' separated
| --**id_type**               type of input ids (uniprot_AC or geneID)
| --**id_column**             number og column containg ids of interest
| --**org**                   organism : Hs , Mm, ...
| --**nb_pathways**           number of pathways to return
| --**header**                boolean
| --**output**                output path
| --**ref**                   ref file (l.hsa.gene.RData, l.hsa.up.RData)
|
| Example:
| Rscript compute_KEGG_pathways.R --input='P31946,P62258' --id_type='uniprot' --id_column 'c1' --header TRUE
|

    ]]></help>
    <citations>
        <citation type="bibtex">
@misc{githubKEGGREST,
  title = {KEGGREST: Client-side REST access to KEGG},
  author = {Dan Tenenbaum},
  year = {2018},
  note = {R package version 1.18.1},
  publisher = {GitHub},
  journal = {GitHub repository},
  url = {https://github.com/Bioconductor/KEGGREST},
}</citation>
    </citations>
</tool>