diff add_expression_data.xml @ 5:e919b55188ab draft

planemo upload commit e51bfb0f336c151fefcccf97e0c34be60283fb3b-dirty
author proteore
date Wed, 02 Jan 2019 04:26:18 -0500
parents 3f9057cdfdde
children ea59f5750c51
line wrap: on
line diff
--- a/add_expression_data.xml	Thu Dec 13 03:56:46 2018 -0500
+++ b/add_expression_data.xml	Wed Jan 02 04:26:18 2019 -0500
@@ -1,4 +1,4 @@
-<tool id="rna_abbased_data" name="Add expression data" version="2018.12.12">
+<tool id="rna_abbased_data" name="Add expression data" version="2019.01.02">
 <description> (RNAseq or Immuno-assays)[Human Protein Atlas]
 </description>
 <requirements>
@@ -24,12 +24,12 @@
 
 <inputs>
   <conditional name="inputtype">
-    <param name="filetype" type="select" label="Enter your list of Ensembl gene ID"> 
+    <param name="filetype" type="select" label="Enter your IDs (Ensembl gene ENSG IDs only)" help="Copy/paste or from a file (e.g. table)"> 
       <option value="file_all" 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 identifiers">
+      <param name="genelist" type="text" label="Enter a list of IDs">
         <sanitizer>
             <valid initial="string.printable">
                 <remove value="&apos;"/>
@@ -41,22 +41,22 @@
       </param>
     </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"> 
+      <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 if ENSG ID are in column n°1)" value="c1"/> 
+      <param name="header" type="select" label="Does file contain 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"> 
+      <param name="hpaparams" type="select" label="Select information to add to your list" multiple="True" display="checkboxes" optional="false" > 
           <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 (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>
@@ -77,28 +77,31 @@
       <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"/>
+      <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"/>
+      <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[
+**Description**
 
-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.
+This tool adds expression annotation (RNAseq- or antibody-based experimental data - see "Parameters" below) from the Human Protein Atlas (HPA) database (https://www.proteinatlas.org/) to your gene/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.  
+Input can be either a list of Ensembl gene (ENSG) IDsds (copy/paste mode) or a file containing multiple fields 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 (Human Protein Atlas version 18):  http://www.proteinatlas.org/download/proteinatlas.tab.gz
+**Parameters** 
 
-**Annotation**
+"Select information to add to your list": choose by clicking the following information: 
 
 - Gene name: according to the HGNC (Hugo Gene Nomenclature Committee) 
 
@@ -120,9 +123,17 @@
 
 - RNA non-specific tissue abundance in 'Transcript Per Million': please refer to http://www.proteinatlas.org/about/assays+annotation#rna.
 
-**Outputs**
+-----
+
+**Output**
+
+The output is a tabular file containing original columns and new columns including selected annotation.  
 
-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.  
+-----
+
+**Data sources (release date)**
+
+HPA source file (Human Protein Atlas version 18):  http://www.proteinatlas.org/download/proteinatlas.tab.gz
 
 -----
 
@@ -130,9 +141,9 @@
 
 **Authors**
 
-Lisa Peru, T.P. Lien Nguyen, Florence Combes, Yves Vandenbrouck CEA, INSERM, CNRS, Grenoble-Alpes University, BIG Institute, FR
+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
+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.