annotate preprocess.xml @ 0:4d539083cf7f draft

planemo upload for repository https://github.com/sblanck/MPAgenomics4Galaxy/tree/master/mpagenomics_wrappers commit 689d0d8dc899a683ee18700ef385753559850233-dirty

<tool id="preprocess" name="Data Normalization" force_history_refresh="True" version="1.1.0">
  	<requirements>
    <!--requirement type="set_environment">R_SCRIPT_PATH</requirement-->
    <requirement type="package" version="1.1.2">mpagenomics</requirement>
   </requirements>
	<!--command interpreter="python"-->
    <command>
    	<![CDATA[ 
        Rscript 
        ${__tool_directory__}/preprocess.R	
		--summary '$summary' 
		--new_file_path '$__new_file_path__'  
		--inputcdffull_name '$inputcdffull.name' 
		--inputufl_name '$inputufl.name' 
		--inputugp_name '$inputugp.name' 
		--inputacs_name '$inputacs.name'
		--inputcdffull '$inputcdffull' 
		--inputufl '$inputufl' 
		--inputugp '$inputugp' 
		--inputacs '$inputacs'
		--dataSetName '$datasetName'
  	#if $settings.settingsType == "tumor":
  	--tumorcsv '$tumorcsv' 
  	#end if
  	#if $settings.settingsType == "standard":
  	--tumorcsv 'none'
  	#end if
  	 --settingsType '$settings.settingsType' 
	 --outputgraph '$outputgraph' 
	 --zipfigures '$zipfigures' 
	 --outputlog '$outputlog' 
	 --log '$log' 
	 --user_id '$__user_id__'
	 --input "#for $input in $inputs# $input;$input.name, #end for#"
    	]]>
     
  </command>
  <inputs>
  	<param name="datasetName" type="text" label="Dataset Name"/>
  	<param name="inputs" type="data" format="cel" multiple="True" label="Cel files dataset" help="Cel files dataset previously uploaded with the Multiple File Datasets tool."/>
    <param name="inputcdffull" type="data" format="cdf" label="cdf file" help=".cdf file name must comply with the following format : &lt; chiptype &gt;,&lt; tag &gt;.cdf (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full.cdf)." />
    <param name="inputufl" type="data" format="ufl" label="ufl file" help=".ufl file name must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full,na31,hg19,HB20110328.ufl)."/>
    <param name="inputugp" type="data" format="ugp" label="ugp file" help=".ugp file name must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full,na31,hg19,HB20110328.ugp)."/>
    <param name="inputacs" type="data" format="acs" label="acs file" help=".acs file name must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,HB20080710.acs)."/>
	<conditional name="settings">
      <param name="settingsType" type="select" label="Reference">
        <option value="standard">Study without reference</option>
        <option value="tumor">Normal-tumor study with TumorBoost</option>
      </param>
      <when value="standard" />
      <when value="tumor">
        <param name="tumorcsv" type="data" format="csv" label="TumorBoost csv file" help="Normal-tumor csv file. See below for more information."/>
      </when>
    </conditional>
    <!--param name="outputgraph" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output figures" /-->
    <!--param name="outputlog" type="boolean" truevalue="TRUE" falsevalue="FALSE" checked="False" label="Output log" /-->
	<param name="outputgraph" type="select" label="Output figures">
        <option value="TRUE">Yes</option>
        <option value="FALSE">No</option>
      </param>
    <param name="outputlog" type="select" label="Output log">
        <option value="TRUE">Yes</option>
        <option value="FALSE">No</option>
    </param>
    <!--param name="chipType" type="text" label="chipType" /-->
    <!--param name="workspace" type="text" label="Workspace"/-->
  </inputs>
  
  <outputs>
  	<!-- Would like to make this hidden or not appear all together, but
  	     variable outputs require a primary dataset. If hidden refresh 
  	     doesn't occur. 
  	-->
    <data format="dsf" name="summary" label="Dataset summary file of ${datasetName}" />
    <data format="zip" name="zipfigures" label="figures of normalization of ${datasetName}">
    	<filter>outputgraph == "TRUE"</filter>	
    </data>    
    <data format="log" name="log" label="log of normalization ${datasetName}">
    	<filter>outputlog == "TRUE"</filter>
    </data>
  </outputs>
  
  <stdio>
    <exit_code range="1:"   level="fatal"   description="See logs for more details" />
   </stdio>
   
     <help>
  
**What it does**
     	
This preprocessing step consists in a correction of biological and technical biaises due to the experiment. Raw data from Affymetrix arrays are provided in different CEL files. These data must be normalized before statistical analysis.
The pre-processing is proposed as a wrapper of aroma.* packages (using CRMAv2 and TumorBoost when appropriate). Note that this implies that the pre-processing step is only available for Affymetrix arrays.

-----
     	
**Chip file naming conventions**
      	
Chip filenames must strictly follow the following rules :
     	
- *.cdf* filename must comply with the following format : &lt; chiptype &gt;,&lt; tag &gt;.cdf (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full.cdf). Note the use of a comma (not a point) between &lt;chiptype&gt; and the tag "Full".

- *.ufl* filename must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full,na31,hg19,HB20110328.ufl).

- *.ugp* filename must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,Full,na31,hg19,HB20110328.ugp).   	

- *.acs* file name must start with  &lt; chiptype &gt;,&lt; tag &gt; (e.g, for a GenomeWideSNP_6 chip: GenomeWideSNP_6,HB20080710.acs).
     	
-----
     	
**Normal-tumor study with TumorBoost**
     	
In cases where normal (control) samples match to tumor samples, normalization can be improved using TumorBoost. In this case, a normal-tumor csv file must be provided :

	- The first column contains the names of the files corresponding to normal samples of the dataset.
     	 
	- The second column contains the names of the tumor samples files. 
     	
	- Column names of these two columns are respectively normal and tumor.
     	
	- Columns are separated by a comma.
     	
	- *Extensions of the files (.CEL for example) should be removed*


     	
**Example** 

Let 6 .cel files in the dataset studied (3 patients, each of them being represented by a couple of normal and tumor cel files.) ::
     	
     	patient1_normal.cel
     	patient1_tumor.cel
     	patient2_normal.cel
     	patient2_tumor.cel
     	patient3_normal.cel 
     	patient3_tumor.cel
      	

The csv file should look like this ::
     	
     	normal,tumor
     	patient1_normal,patient1_tumor
     	patient2_normal,patient2_tumor
     	patient3_normal,patient3_tumor

     	
-----
     	
**Citation**
	
When using this tool, please cite : 

`Q. Grimonprez, A. Celisse, M. Cheok, M. Figeac, and G. Marot. MPAgenomics : An R package for multi-patients analysis of genomic markers, 2014. Preprint &lt;http://fr.arxiv.org/abs/1401.5035&gt;`_
     	
As CRMAv2 normalization is used, please also cite `H. Bengtsson, P. Wirapati, and T. P. Speed. A single-array preprocessing method for estimating full-resolution raw copy numbers from all Affymetrix genotyping arrays including GenomeWideSNP 5 &amp; 6. Bioinformatics, 5(17):2149–2156, 2009. &lt;http://bioinformatics.oxfordjournals.org/content/25/17/2149.short&gt;`_

When using TumorBoost to improve normalization in a normal-tumor study, please cite `H. Bengtsson, P. Neuvial, and T. P. Speed. TumorBoost: Normalization of allele-specific tumor copy numbers from a single pair of tumor-normal genotyping microarrays. BMC Bioinformatics, 11, 2010 &lt;http://www.biomedcentral.com/1471-2105/11/245&gt;`_

  </help>
</tool>