view dante_ltr_search.xml @ 0:7b0bbe7477c4 draft

"planemo upload commit 92c684dff3b377c8c08654c7f3d46a133385e3e0-dirty"
author petr-novak
date Tue, 08 Mar 2022 13:24:33 +0000
parents
children c1498f679b50
line wrap: on
line source

<tool id="dante_ltr_search" name="DANTE_LTR transposable element identification" version="0.1.0" python_template_version="3.5">
    <requirements>
        <requirement type="package">blast</requirement>
        <requirement type="package">r-optparse</requirement>
        <requirement type="package">bioconductor-bsgenome</requirement>
        <requirement type="package">biocondutor-biostrings</requirement>
        <requirement type="package">bioconductor-rtracklayer</requirement>

    </requirements>
    <command detect_errors="exit_code"><![CDATA[
        Rscript ${__tool_directory__}/extract_putative_ltr.R --gff3 '$dante' --reference_sequence '$reference' --output output --cpu 32
        &&
        mv output.gff3 $te_ltr_gff
    ]]></command>
    <inputs>
        <param type="data" name="dante" format="gff3" label="Filtered gff3 output from DANTE pipeline"/>
        <param type="data" name="reference" format="fasta" label="Reference sequence matching DANTE output" />
    </inputs>
    <outputs>
        <data name="te_ltr_gff" format="gff3" label="Annotation of detected LTR transposable elements
         based on the annotation $dante.hid and reference $reference.hid" />
    </outputs>
    <help><![CDATA[
        This tool uses output from DANTE annotation pipeline to identify full length LTR
        transposable elements. Output is in the GFF3 format and include annotation of
        5' and 3' Longe Terminal Repeats, Target Site Duplication (TSD) and primer binding site (PBS).

        All identified elements contains complete set of protein domains as defined in
        REXdb_. Based on the results detection  structural feature,
        elements falls into four categories:

        - elements with domains, 5'LTR, 3'LTR, TSD and PBS
        - elements with domains, 5'LTR, 3'LTR and PBS (TSD was not found)
        - elements with domains, 5' LTR, 3'LTR, TSD (PBS was not found)
        - elements with protein domains, 5'LTR and 3'LTR (PBS and LDS were not found)

       .. _REXdb: https://doi.org/10.1186/s13100-018-0144-1

    ]]></help>
</tool>