annotate helixer.xml @ 0:1b08e39cc52d draft

planemo upload for repository https://github.com/genouest/galaxy-tools/tree/master/tools/helixer commit 8f0b5d30f8f5daea0f6c03293c8593ac24d9e1b7

<?xml version="1.0"?>
<tool id="helixer" name="Helixer" version="@TOOL_VERSION@" profile="21.05">
    <description>gene calling</description>
    <macros>
        <import>macros.xml</import>
    </macros>

    <requirements>
        <expand macro="requirements" />
    </requirements>

    <command detect_errors="exit_code"><![CDATA[
        ## Not in $PATH in the docker image
        ## Manage models with a data manager?
        /usr/local/bin/fetch_helixer_models.py

        &&

        Helixer.py
        --fasta-path '$input'
        --species '$species'
        --lineage $lineage.lineages
        --gff-output-path '$output'

        --temporary-dir ./

        --subsequence-length $lineage.subsequence_length
        #if str($lineage.option_overlap.use_overlap) == "true":
            --overlap-offset $lineage.option_overlap.overlap_offset
            --overlap-core-length $lineage.option_overlap.overlap_core_length
        #else:
            --no-overlap
        #end if

        --window-size $post_processing.window_size
        --min-coding-length $post_processing.min_coding_length
        --edge-threshold $post_processing.edge_threshold
        --peak-threshold $post_processing.peak_threshold
    ]]></command>

    <inputs>
        <param argument="--fasta-path" name="input" type="data" format="fasta,fasta.gz" label="Genomic sequence"></param>
        <conditional name="lineage">
            <param argument="--lineage" name="lineages" type="select" label="Available lineages" help="Choose the model to use for the annotation">
                <option value="land_plant">land plant</option>
                <option value="vertebrate">vertebrate</option>
                <option value="invertebrate">invertebrate</option>
                <option value="fungi">fungi</option>
            </param>
            <when value="land_plant">
                <expand macro="subseq" length="106920" offset="53460" offsetlen="80190" />
            </when>
            <when value="vertebrate">
                <expand macro="subseq" length="213840" offset="106920" offsetlen="160380" />
            </when>
            <when value="invertebrate">
                <expand macro="subseq" length="213840" offset="106920" offsetlen="160380" />
            </when>
            <when value="fungi">
                <expand macro="subseq" length="21384" offset="10692" offsetlen="16038" />
            </when>
        </conditional>
        <param argument="--species" type="text" optional="true" label="Species name">
            <sanitizer invalid_char="">
                <valid initial="string.letters,string.digits">
                    <add value="_" />
                </valid>
            </sanitizer>
            <validator type="regex">[0-9a-zA-Z_]+</validator>
        </param>

        <section name="post_processing" title="Post-processing">
            <param argument="--window-size" type="integer" min="0" value="100" label="Window size" help="This determines the number of bases averaged during the sliding window approach"/>
            <param argument="--edge-threshold" type="float" min="0" max="1" value="0.1" label="Edge threshold" help="This threshold specifies the genic score which defines the start / end boundaries of each candidate region"/>
            <param argument="--peak-threshold" type="float" min="0" max="1" value="0.8" label="Peak threshold" help="This threshold specifies the minimum peak genic score required to accept the candidate region"/>
            <param argument="--min-coding-length" type="integer"  min="0" value="100" label="Minimum coding length"/>
        </section>
    </inputs>

    <outputs>
        <data name="output" format="gff3">
        </data>
    </outputs>
    <tests>
        <!-- Test for land_plant -->
        <test expect_num_outputs="1">
            <param name="input" value="sequence.fasta"/>
            <conditional name="lineage">
                <param name="lineages" value="land_plant"/>
            </conditional>
            <output name="output" value="output.gff3" ftype="gff3" lines_diff="2" />
        </test>
        <test expect_num_outputs="1">
            <!-- Test for species -->
            <param name="input" value="sequence.fasta"/>
            <param name="species" value="Arabidopsis"/>
            <conditional name="lineage">
                <param name="lineages" value="land_plant"/>
            </conditional>
            <output name="output" value="ouput_species.gff3" ftype="gff3" lines_diff="2" />
        </test>
    </tests>


    <help><![CDATA[
        Helixer_: Gene calling with Deep Neural Networks.

        .. _Helixer: https://github.com/weberlab-hhu/Helixer
    ]]></help>
    <expand macro="citation"></expand>
</tool>