view kc-align.xml @ 0:04b13fc809ac draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/kc-align commit 3b23039a67d8cb2d185c56df50b837e5601a95bf"
author iuc
date Tue, 17 Mar 2020 15:24:15 -0400
parents
children 60ed1c94f584
line wrap: on
line source

<tool id="kc-align" name="Kc-Align" version="0.1.0" python_template_version="3.5">
    <requirements>
        <requirement type="package" version="0.5">kcalign</requirement>
        <requirement type="package" version="2.04">kalign2</requirement>
    </requirements>
    <command detect_errors="exit_code">
        <![CDATA[
        kc-align
            --mode $position.mode
            --reference '$reference'
            --reads '$reads'
            #if $position.mode == "genome":
                --start $position.start
                --end $position.end
            #end if
    ]]></command>
    <inputs>
        <param name="reference" type="data" format="fasta" label="Reference Sequence" help="Single FASTA reference sequence to be aligned" />
        <param name="reads" type="data" format="fasta" label="Reads" help="Single or multi-FASTA seqeunces to be aligned with the reference" />
        <conditional name="position" >
            <param name="mode" type="select" label="Mode" >
                <option value="genome">Genome</option>
                <option value="gene">Gene</option>
                <option value="mixed">Mixed</option>
            </param>
            <when value="genome" >
                <param name="start" type="integer" value="0" min="0" label="Start Position" help="The 1-indexed start position of the gene of interest in the reference sequence" />
                <param name="end" type="integer" value="0" min="0" label="End Position" help="The 1-indexed end position of the gene of interest in the reference sequence" />
            </when>
            <when value="gene" >
            </when>
            <when value="mixed" >
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data name="fasta" format="fasta" from_work_dir="kc-align.fasta" label="out.fasta" />
        <data name="clustal" format="txt" from_work_dir="kc-align.clustal" label="out.clustal" />
    </outputs>
<tests>
    <test>
        <param name="reference" ftype="fasta" value="MN908947.3.fasta" />
        <param name="reads" ftype="fasta" value="corona.fasta" />
        <param name="mode" value="genome" />
        <param name="start" value="21563" />
        <param name="end" value="25384" />
        <output name="fasta" ftype="fasta" compare="diff" value="kc-align.fasta" />
        <output name="clustal" ftype="txt" compare="diff" value="kc-align.clustal" />
    </test>
</tests>
    <help><![CDATA[

============
Kc-Align
============

Kc-Algin is a codon-aware multiple aligner that uses Kalgin2 to produce in-frame gapped codon alignments for selection analysis of small genomes (mostly viral and some smaller bacterial genomes). Takes nucleotide seqeunces as inputs, converts them to their in-frame amino acid sequences, performs multiple alignment with Kalign, and then converts the alignments back to their original codon sequence while preserving the gaps. Produces two outputs: the gapped nucleotide alignments in FASTA format and in CLUSTAL format.

Kc-Align will also attempt to detect any frameshift mutations in the input reads. If a frameshift is detected, that sequence will not be included in the multiple alignment and its ID will be printed to stdout.

Modes:
------
        
Kc-Align can be run in three different modes, depending on your input data.

* In **genome** mode, the "reference" and "reads" input parameters are all full genome FASTA files. This mode also requires the 1-based start and end position numbers corresponding to the gene you are interested in aligning from the reference input.

* If both the "reference" and "reads" inputs are already in-frame genes, the **gene** mode should be used. This mode does not require start and end position parameters as the reference is already in-frame.

* For the case when your "reference" is an in-frame gene while the "reads" are whole genomes, the **mixed** mode can be used. Like gene mode, this mode does not require the start and end point position parameters.


    ]]></help>
    <citations>
        <citation type="bibtex">
        	@misc{githubkcalign,
            author = {Nicholas Keener, Emil Bouvier},
            year = {2020},
            title = {Kc-Align},
            publisher = {Github},
            journal = {Github repository},
            url = {https://github.com/davebx/kc-align},
        }</citation>
    </citations>
</tool>