annotate SNP_density/calculateSlidingWindowsSNPdensitiesFromVCF_wrapper.xml @ 11:15b23cdde685 draft

planemo upload commit 305985afd3b7c3d47f531149c2f1a279af2d12aa-dirty

<tool id="sniplay_density" name="SNP density" version="2.0.0">
    
    <!-- [REQUIRED] Tool description displayed after the tool name -->
    <description> Calculate SNP densities along chromosome from a VCF input</description>

    <!-- [OPTIONAL] 3rd party tools, binaries, modules... required for the tool to work -->
    <requirements>
        <requirement type="binary">perl</requirement>
        <requirement type="package" version="1.6.924">perl-bioperl</requirement>
        <requirement type="package" version="0.1.14">vcftools</requirement>
        <requirement type="package" version="0.1.14">perl-vcftools-vcf</requirement>
    </requirements>
    
    <!-- [STRONGLY RECOMMANDED] Exit code rules -->
    <stdio>
        <!-- [HELP] If no exit code rule is defined, the tool will stop if anything is written to STDERR -->
      <exit_code range="1:" level="fatal" />
    </stdio>

    <!-- [OPTIONAL] Command to be executed to get the tool's version string -->
    <version_command>
<!--
        tool_binary -v
-->
    </version_command>
    
    <!-- [REQUIRED] The command to execute -->
    <command interpreter="bash">
	calculateSlidingWindowsSNPdensitiesFromVCF.sh $filein $fileout $fileout_bysample $step
    </command>

    <!-- [REQUIRED] Input files and tool parameters -->
    <inputs>
	<param name="filein" type="data" format="vcf" optional="false" label="VCF input" />
	<param name="step" type="integer" value="200000" label="Step" help="Step in bp"/>
	<param name="fileout_label" type="text" value="densities" label="Output name" help="Output name for tabular files" />
    </inputs>
    
    <!-- [REQUIRED] Output files -->
    <outputs>
	<data name="fileout" format="txt" label="${fileout_label}" />
	<data name="fileout_bysample" format="txt" label="${fileout_label}.by_sample" />
    </outputs>

    <tests>
        <test> 
         <param name="filein" value="vcf2fastaAndHapmap-sample.vcf" />
         <param name="step" value="20000" />
         <output name="fileout" file="SNPden-result.txt" />
         <output name="fileout_bysample" file="SNPden-result_bysample.txt" />
        </test>
        <!-- [HELP] Multiple tests can be defined with different parameters -->
<!--
        <test>
        </test>
-->
    </tests>
    
    <!-- [OPTIONAL] Help displayed in Galaxy -->
    <help><![CDATA[

.. class:: infomark

**Authors** Dereeper Alexis ([e-mail]), IRD, South Green platform 

 | **Please cite** "SNiPlay3: a web-based application for exploration and large scale analyses of genomic variations", **Dereeper A. et al.**, Nucl. Acids Res. (1 july 2015) 43 (W1).

.. class:: infomark

**Galaxy integration** Provided by Southgreen & Andres Gwendoline (Institut Français de Bioinformatique) & Marcon Valentin (IFB & INRA)

.. class:: infomark

**Support** For any questions about Galaxy integration, please send an e-mail to [e-mail]

---------------------------------------------------

=============
SNP densities
=============

-----------
Description
-----------

  Calculate SNP densities along chromosome from a VCF file

------------
Dependencies
------------
VCFtools
        vcftools_ 0.1.14, Conda version
VCFtools Perl libraries
	perl-vcftools-vcf_ 0.1.14, Conda version
Bioperl
	perl-bioperl_ 1.6.924, Conda version

.. _vcftools: https://anaconda.org/bioconda/vcftools
.. _perl-vcftools-vcf: https://anaconda.org/bioconda/perl-vcftools-vcf
.. _perl-bioperl: https://anaconda.org/bioconda/perl-bioperl

----------
Input file
----------	

VCF file
	File with SNPs

----------
Parameters
----------

Step
        Step in bp for the window to calculate SNP density

Output name
        Output base name for the two ouput files

------------
Output files
------------

Output_name
	Tabular file with SNP density in each postion 

Output_name.by_sample
	Tabular file with SNP density for each sample
	
---------------------------------------------------

---------------
Working example
---------------

Input file
==========

vcf file
-----------

::

	#fileformat=VCFv4.1
	#FILTER=&lt;ID=LowQual,Description="Low quality">
	#FORMAT=&lt;ID=AD,Number=.,Type=Integer,Description="Allelic depths for the ref and alt alleles in the order listed">
	[...]
	CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO	FORMAT	CATB1
	chr1	2209	.	G	T	213.84	.	AC=2;AF=1.00;AN=2;DP=7;Dels=0.00;FS=0.000;HaplotypeScore=0.0000;MLEAC=2;MLEAF=1.00;MQ=41.50;MQ0=0;QD=30.55;EFF=DOWNSTREAM(MODIFIER||||Cc01g00020|mRNA||GSCOCT00012438001|),UPSTREAM(MODIFIER||||Cc01g00010|mRNA||GSCOCT00012439001|)	GT:AD:DP:GQ:PL	1/1:0,7:7:18:242,18,0

Parameters
==========

Step -> 200000

Output name -> densities


Output files
============

densities
---------

::

	Chromosome Position SNPs
	chr1       200000   355
	chr1       400000   228
	chr1       600000   63
	chr1       800000   191


densities.by_sample
-------------------

::

	Chromosome BA58 BA59 BD54
	chr1       220  197  225
	chr1       130  119  133
	chr1       43   43   40
	chr1       139  167  141

    ]]></help>
    <citations>
        <!-- [HELP] As DOI or BibTex entry -->
    	<citation type="bibtex">@article{Dereeper03062015,
author = {Dereeper, Alexis and Homa, Felix and Andres, Gwendoline and Sempere, Guilhem and Sarah, Gautier and Hueber, Yann and Dufayard, Jean-François and Ruiz, Manuel}, 
title = {SNiPlay3: a web-based application for exploration and large scale analyses of genomic variations},
year = {2015}, 
doi = {10.1093/nar/gkv351}, 
abstract ={SNiPlay is a web-based tool for detection, management and analysis of genetic variants including both single nucleotide polymorphisms (SNPs) and InDels. Version 3 now extends functionalities in order to easily manage and exploit SNPs derived from next generation sequencing technologies, such as GBS (genotyping by sequencing), WGRS (whole gre-sequencing) and RNA-Seq technologies. Based on the standard VCF (variant call format) format, the application offers an intuitive interface for filtering and comparing polymorphisms using user-defined sets of individuals and then establishing a reliable genotyping data matrix for further analyses. Namely, in addition to the various scaled-up analyses allowed by the application (genomic annotation of SNP, diversity analysis, haplotype reconstruction and network, linkage disequilibrium), SNiPlay3 proposes new modules for GWAS (genome-wide association studies), population stratification, distance tree analysis and visualization of SNP density. Additionally, we developed a suite of Galaxy wrappers for each step of the SNiPlay3 process, so that the complete pipeline can also be deployed on a Galaxy instance using the Galaxy ToolShed procedure and then be computed as a Galaxy workflow. SNiPlay is accessible at http://sniplay.southgreen.fr.}, 
URL = {http://nar.oxfordjournals.org/content/early/2015/06/03/nar.gkv351.abstract}, 
eprint = {http://nar.oxfordjournals.org/content/early/2015/06/03/nar.gkv351.full.pdf+html}, 
journal = {Nucleic Acids Research} 
}

    	</citation>

    </citations>    
</tool>