annotate expression_rnaseq_abbased.xml @ 1:8dd24f13f923 draft

planemo upload commit 5774fd6a5a746f36f6bf4671a51a39ea2b978300-dirty

<tool id="rna_abbased_data" name="Get annotation from RNAseq/Ab-based experiments (Human species)" version="0.1.0">
<description>
</description>
<requirements>
</requirements>
<stdio>
  <exit_code range="1:" />
</stdio>
<command><![CDATA[

  #if $inputtype.filetype == "copy_paste": 
  
    Rscript --vanilla $__tool_directory__/get_data_HPA_v2.R --inputtype copypaste --input '$inputtype.genelist' --header FALSE --proteinatlas $__tool_directory__/proteinatlas.csv --column c1 --select '$options.hpaparams' --output '$output'  

  #else 
  
    Rscript --vanilla $__tool_directory__/get_data_HPA_v2.R --inputtype tabfile --input '$inputtype.genelist' --header '$inputtype.header' --proteinatlas $__tool_directory__/proteinatlas.csv --column '$inputtype.column' --select '$options.hpaparams' --output '$output'  

  #end if
   

]]></command>

<inputs>
  <conditional name="inputtype">
    <param name="filetype" type="select" label="Enter your list of Ensembl gene ID"> 
      <option value="file_all">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 identifiers"/>
    </when>
    <when value="file_all">
      <param name="genelist" type="data" format="txt,tabular" label="Choose your file" help="This file must imperatively have 1 column filled with Ensembl Gene IDs (ENSG). Please use the ID_Converter tool if this is not the case."/>
      <param name="column" type="text" label="Please specify the column where are your Ensembl gene IDs (e.g : Enter c1 if ENSG ID are in 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>
  <section name="options" title="RNAseq/Ab-based expression data" expanded="True">   
      <param name="hpaparams" type="select" label="Choose the information from RNAseq/ab-based data you want to add to your list (see below for details)" multiple="True" display="checkboxes"> 
          <option value="Gene" selected="true">Gene name</option>
          <option value="Gene.description" selected="false">Gene description</option>
          <option value="Evidence">Evidence (at protein level, at transcript level or no evidence)</option>
          <option value="Antibody">Antibody reference</option>
          <option value="RNA.tissue.category">RNA tissue category</option>
 		  <option value="Reliability.IH">IH detection level</option>
          <option value="Reliability.IF">IF detection level</option>
          <option value="Subcellular.location">Subcellular location</option>
          <option value="RNA.TS.TPM">RNA tissue specificity abundance in 'Transcript Per Million'</option>
          <option value="TPM.max.in.non.specific">RNA non-specific tissue abundance in 'Transcript Per Million'</option>
    </param>
  </section>

</inputs>


<outputs>
  <data name="output" format="tabular" label=""/>
</outputs>

<tests>
  <test>
    <conditional name="inputtype">
      <param name="filetype " value="file_all"/>
      <param name="genelist" value="ID_Converter_Lacombe_et_al_2017_OK.txt"/>
      <param name="column" value="c8"/>
      <param name="header" value="TRUE"/>
    </conditional>
    <section name="options">
      <param name="hpaparams" value="Gene,Gene.description,Evidence,Antibody,RNA.tissue.category,Reliability.IH,Reliability.IF,Subcellular.location,RNA.TS.TPM,TPM.max.in.non.specific"/>
    </section>
    <output name="output" file="Get_annotation_RNAseq.txt"/>
  </test>
</tests>

<help><![CDATA[

This tool adds expression information (RNAseq- or antibody-based experiments) from the Human Protein Atlas (HPA) database (https://www.proteinatlas.org/) to your protein list.

**Input**

Input can be either a list of Ensembl gene ids (copy/paste) or a file containing multiple fields but with **at least one column of Ensembl gene IDs**. If your input file contains other type of IDs, please use the ID_Converter tool to create a column of Ensembl gene IDs.  

**Databases**

HPA source file:  http://www.proteinatlas.org/download/proteinatlas.tab.gz

**Annotation**

- Gene name: according to the HGNC (Hugo Gene Nomenclature Committee) 

- Gene description: entry description (full text)  

- Evidence: at protein level, at transcript level or no evidence

- Antibody reference: reference of the HPA antibody used for immunohistochemistry and immunocytochemistry/IF

- RNA tissue category: categories based on RNA-Seq data to estimate the transcript abundance of each protein-coding gene in tissues. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#rna .

- IH detection level: level of detection of the protein associated to the coding gene tissues based on immunofluorescency. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#if .

- IF detection level:level of detection of the protein associated to the coding gene tissues based on immunohistochemistry. For more information, please refer to http://www.proteinatlas.org/about/assays+annotation#ih .

- Subcellular location:according to HPA data. For more information, please refer to https://www.proteinatlas.org/about/assays+annotation#ifa

- RNA tissue specificity abundance in 'Transcript Per Million': For each gene is reported the tissue specificity abundance in 'Transcript Per Million' (TPM) as the sum of the TPM values of all its protein-coding transcripts.

- RNA non-specific tissue abundance in 'Transcript Per Million': please refer to http://www.proteinatlas.org/about/assays+annotation#rna.

**Outputs**

The output is a tabular file. The initial columns are kept and new columns are added according to what type of annotation data you chose.  

-----

.. class:: infomark

**Authors**

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.

]]></help>

<citations>
</citations>

</tool>