view repeat_annotate_custom.xml @ 1:814cba36e435 draft

Uploaded
author mvdbeek
date Mon, 21 Feb 2022 10:21:39 +0000
parents ea6a3059a6af
children 7f1032da7a0a
line wrap: on
line source

<tool id="repeat_annotate" name="RepeatExplorer Based Assembly Annotation" version="0.1.1" python_template_version="3.5">
    <requirements>
        <requirement type="package">repeatmasker</requirement>
        <requirement type="package">bioconductor-rtracklayer</requirement>
    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        RepeatMasker -dir \$(pwd) '$input' -pa 32 -lib '$repeat_library' -xsmall -nolow -no_is -e ncbi -s
        &&
        ls -l * >&2 &&
        cp `basename $input`.out  $output2
        &&
        Rscript ${__tool_directory__}/clean_rm_output.R $output2 $output1

        ]]></command>
    <inputs>
        <param type="data" name="input" format="fasta" label="Genome/ Assembly to annotate" />
        <param type="data" name="repeat_library" format="fasta" label="RepeatExplorer based Library of Repetitive Sequences"
               help="custom database of repetitive sequences should be provided in fasta format. Sequence header should specify repeat class:
                     >sequence_id#classification_level1/classification_level2/..." />
    </inputs>
    <outputs>
        <data name="output1" format="gff3"  label="Repeat Annotation on ${on_string}, cleaned gff"/>
        <data name="output2" format="tabular" label="Raw output from RepeatMasker on ${on_string}" />
    </outputs>
    <help><![CDATA[
        This tools uses RepeatMasker to annotate repetitive sequences in the genome assemblie using custom library of repeats created from RepeatExplorer output.
        Library of repeats can be created from RepeatExplorer ouputt from contigs and TAREAN consensus sequences. Fasta formated library of repeats must contain header containg information about classification of repeats as **>sequence_id#classification_level1/classification_level2/...**

        Classification in RepeatExplorer based library follows predetermined classification levels. User can however specify additional classification levels or completelly custom classifications. Conflicts in annotations are resolved based on classification hierarchy.
    ]]></help>
</tool>