annotate add_protein_features.xml @ 12:1a4cfa7a3a27 draft

planemo upload commit 77279e994f5751c6cd9aa165aa0604db3d241271-dirty

<tool id="prot_features" name="Add protein features" version="2019.03.11">
<description>[neXtProt]
</description>
<requirements>
  <requirement type="package" version="3.4.1">R</requirement>
</requirements>
<stdio>
  <exit_code range="1:" />
</stdio>
<command><![CDATA[

  Rscript $__tool_directory__/add_protein_features.R 
  --inputtype="$inputtype.filetype"
  --input='$inputtype.genelist'

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

  --type='$idtype'
  --pc_features='$Nextprot_params.pc_features' 
  --localization='$Nextprot_params.localization' 
  --diseases_info='$Nextprot_params.diseases_info'  
  --output='$output'  

  #if 'nextprot_ref' in str($ref_file).split("/")
    --nextprot="$ref_file" 
  #else 
    --nextprot="$__tool_directory__/$ref_file"
  #end if 
    
]]></command>

<inputs>
  <conditional name="inputtype">
    <param name="filetype" type="select" label="Enter your IDs (neXtProt or UniProt)" 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 separated by tab, space or carriage return into the form field" help="for example : A0AVI2 A6NGB0">
        <sanitizer invalid_char="">
            <valid initial="string.printable">
                <remove value="&apos;"/>
            </valid>
            <mapping initial="none">
                <add source="&apos;" target="__sq__"/>
                <add source="&#x20;" target=""/>
                <add source="&#xA;" target=""/>
                <add source="&#xD;" target=""/>
                <add source="&#x9;" target=""/>
            </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 IDs (e.g : Enter c1 for column n°1)" value="c1">
        <validator type="regex" message="Please enter a column number, for example: 'c1' for the first column">[c]{0,1}[0-9]+</validator>
      </param>
      <param name="header" type="boolean" checked="true" truevalue="true" falsevalue="false" label="Does input file have header?" />
    </when>
  </conditional>

      <param name="idtype" type="select" label="Type of IDs" multiple="false" optional="false"> 
 		      <option value="Uniprot_AC" selected="true">Uniprot accession number</option>
          <option value="NextprotID" selected="false">neXtProt IDs</option>
      </param>
      <section name="Nextprot_params" title="Select features" expanded="True">
        <param name="pc_features" type="select" label="Physico-Chemical Features" multiple="true" help="" display="checkboxes" optional="false"> 
          <option value="SeqLength" selected="false">Sequence Length</option>
          <option value="MW" selected="false">Molecular Weight</option>
          <option value="IsoPoint" selected="false">Isoelectric point</option>
          <option value="TMDomains" selected="false">Number of transmembrane domains</option>
          <option value="ProteinExistence" selected="false">Protein Existence (evidence score from 1 to 5)</option>
        </param>

        <param name="localization" type="select" label="Localization" multiple="true" help="" display="checkboxes" optional="true"> 
 		      <option value="Chr" selected="false">Chromosome</option>
 		      <option value="SubcellLocations" selected="false">Subcellular Location</option>
        </param>

        <param name="diseases_info" type="boolean" checked="false" truevalue="true" falsevalue="false" label="Disease information" />

      </section>
      <param name="ref_file" type="select" label="Release of neXtProt reference file to use">
        <options from_data_table="proteore_nextprot_ref"/>
      </param>

</inputs>


<outputs>
  <data name="output" format="tsv" label="Add_information_from_neXtProt on ${inputtype.genelist.name}">
    <filter>inputtype=="file"</filter>
  </data>
  <data name="output" format="tsv" label="Add_information_from_neXtProt"/>
</outputs>

<tests>
  <test>
    <conditional name="inputtype">
      <param name="filetype " value="file"/>
      <param name="genelist" value="FKW_ID_Converter_Lacombe_et_al_2017_OK.tsv"/>
      <param name="column" value="c1"/>
      <param name="header" value="true"/>
    </conditional>

    <param name="idtype" value="uniprot"/> 

    <section name="Nextprot_params">
      <param name="pc_features" value="SeqLength,MW,IsoPoint,TMDomains,ProteinExistence"/> 
      <param name="localization" value="Chr,SubcellLocations"/> 
      <param name="diseases_info" value="true"/> 
    </section>
      
    <output name="output" file="Add_information_from_neXtProt.tsv"/>
  </test>
</tests>

<help><![CDATA[

**Description**

This tool retrieves annotation (protein features) from the neXtProt database (knowledgebase on human proteins) to enrich your protein IDs list.

-----

**Input**

A list of of Uniprot Accession Number (e.g. P05090) or neXtProt IDs (e.g. NX_P05090) entered in a copy/paste mode or a file containing one or multiple columns with **at least one column of Uniprot accession number or neXtProt IDs**. If your input file contains other type of IDs, please use the ID_Converter tool.  

-----

**Parameters**

"Select features": three categories of annotation can be retrieved: physico-chemical features, localisation (chromosome, subcellular) and disease information (set to "Yes" by default). Select each feature according to your interest by clicking the corresponding checkbox. 

-----

**Output**

Output is a tabular file containing both original columns and new columns including the annotation requested.  

-----

**Data source (release date)**

Annotations have been retrieved from the neXtProt released on 21/02/2018 using the latest data from peptideAtlas (release January 2018)

using a REST API (https://academic.oup.com/nar/article/43/D1/D764/2439066#40348985) (Gaudet et  al., 2017)

-----

.. class:: infomark

**Authors**

David Christiany, 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, 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>