view AnnotationStatsFromVCF/annotationStatsFromVCF_wrapper.xml @ 10:c6640c49fd01 draft

planemo upload commit 475f4d7d8442a0d75e103af326ae5881c4d2a4ac
author dereeper
date Mon, 16 Apr 2018 09:00:24 -0400
parents 98c37a5d67f4
children
line wrap: on
line source

<tool id="annotationStatsFromVCF" name="Get VCF annotation statistics" version="2.0.0">
    <description>Get annotation fromi a VCF file annotated by snpeff</description>
    <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>
    </requirements>
    <stdio>
        <exit_code range="1:" />
    </stdio>
    <command interpreter="perl">
        AnnotationStatsFromVCF.pl -v $input -o $output_label -s $step &amp;&amp; mv ${output_label} $output_count &amp;&amp; mv ${output_label}.effect $output_stats_effect &amp;&amp; mv ${output_label}.location $output_stats_location 
    </command>
    <inputs>
        <param type="data" name="input" format="vcf" label="VCF file" />
        <param name="step" type="integer" value="200000" label="Step" help="Step in bp"/>
        <param type="text" name="output_label" label="Output_label" value='VCF_stats' optional='false' />
    </inputs>
    <outputs>
        <data name="output_count" format="txt" label="${output_label}"/>
	<data name="output_stats_effect" format="txt" label="${output_label}.effect"/>
	<data name="output_stats_location" format="txt" label="${output_label}.location"/>
    </outputs>
    <tests>
        <test>
            <param name="input" value="annotationStatsFromVCF.vcf"/>
            <param name="step" value="50000"/>
            <output name="output_count" file="annotationStatsFromVCF.txt"/>
            <output name="output_stats_effect" file="annotationStatsFromVCF.effect"/>
	    <output name="output_stats_location" file="annotationStatsFromVCF.location"/>
        </test>
    </tests>
    <help><![CDATA[

.. class:: infomark

**Authors** Dereeper Alexis (alexis.dereeper@ird.fr), 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 alexis.dereeper@ird.fr

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

=========================
Get annotation statistics
=========================

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

    | Get annotation statistics from VCF

------------
Dependencies
------------
VCFtools
        vcftools_ 0.1.14, Conda version
Bioperl
        perl-bioperl_ 1.6.924, Conda version

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

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

VCF file
        VCF file

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

Step
        Step in bp 

Output label
        Prefix for the ouput files

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

Output_name

Output_name.effect file

Output_name.location file

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

---------------
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  AZUCENA
	Chr1    4299    .       G       A       .       PASS    AR2=1;DR2=1;AF=0.168    GT:DS:GP        0|0:0:1,0,0    

                              
Parameters
==========

Step -> 50000
Output label -> VCF_stats


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

VCF_stats
----------------------------------

::

        Chrom	Bin	dN/dS ratio
        chr1	50000	0.791666666666667
        chr1	100000	0.981132075471698
        chr1	150000	2.08333333333333


VCF_stats.effect
--------------------

::

        Intron	960	Intron:960
        UTR	281	UTR:281
        Exon	3248	Synonym:124	Non-syn:120

VCF_stats.location
--------------------

::

        Intergenic	466	Intergenic:466
        Genic	4489	Exon:3248	Intron:960	UTR:281


    ]]></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>