view getfastaBed.xml @ 4:607c0576c6ab draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/bedtools commit 6692e3a4fa1bf6e9a407735afdbb2454ed32b316
author iuc
date Wed, 27 Jan 2016 15:15:59 -0500
parents 82aac94b06c3
children c78cf6fe3018
line wrap: on
line source

<tool id="bedtools_getfastabed" name="GetFastaBed" version="@WRAPPER_VERSION@.0">
    <description>use intervals to extract sequences from a FASTA file</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <command>
<![CDATA[
        bedtools getfasta
        $name
        $tab
        $strand
        $split
        -fi $fasta 
        -bed $input
        -fo $output
]]>
    </command>
    <inputs>
        <param format="bed,vcf,gff,gff3" name="input" type="data" label="BED/VCF/GFF file" />
        <param format="fasta" name="fasta" type="data" label="Fasta file" />
        <param name="name" type="boolean" checked="false" truevalue="-name" falsevalue=""
            label="Use the 'name' column in the BED file for the FASTA headers in the output FASTA file"
            help="(-name)" />
        <param name="tab" type="boolean" checked="false" truevalue="-tab" falsevalue=""
            label="Report extract sequences in a tab-delimited format instead of in FASTA format"
            help="(-tab)" />
        <param name="strand" type="boolean" checked="false" truevalue="-s" falsevalue=""
            label="Force strandedness"
            help="If the feature occupies the antisense strand, the sequence will be reverse complemented. (-s)" />
        <expand macro="split" />
    </inputs>
    <outputs>
        <data format="fasta" name="output">
            <change_format>
                <when input="tab" value="-tab" format="tabular" />
            </change_format>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="input" value="nucBed1.bed" ftype="bed" />
            <param name="fasta" value="nucBed1.fasta" ftype="fasta" />
            <param name="tab" value="False" />
            <param name="split" value="False" />
            <output name="output" file="getfastaBed_result1.bed" ftype="fasta" />
        </test>
        <test>
            <param name="input" value="nucBed1.bed" ftype="bed" />
            <param name="fasta" value="nucBed1.fasta" ftype="fasta" />
            <param name="tab" value="True" />
            <param name="split" value="False" />
            <output name="output" file="getfastaBed_result2.tabular" ftype="tabular" />
        </test>
    </tests>
    <help>
<![CDATA[
**What it does**

bedtools getfasta will extract the sequence defined by the coordinates in a BED interval and create a new FASTA entry in the output file for each extracted sequence. By default, the FASTA header for each extracted sequence will be formatted as follows: “>chrom>:&lt;start>-&lt;end>”.

.. image:: $PATH_TO_IMAGES/getfasta-glyph.png

.. class:: warningmark

1. The headers in the input FASTA file must exactly match the chromosome column in the BED file.

2. You can use the UNIX fold command to set the line width of the FASTA output. For example, fold -w 60 will make each line of the FASTA file have at most 60 nucleotides for easy viewing.

@REFERENCES@
]]>
    </help>
    <expand macro="citations" />
</tool>