view dante_ltr_search.xml @ 8:9de392f2fc02 draft

"planemo upload commit d6433b48c9bae079edb06364147f19500501c986"
author petr-novak
date Tue, 28 Jun 2022 12:33:22 +0000
parents c33d6583e548
children ff01d4263391
line wrap: on
line source

<tool id="dante_ltr_search" name="DANTE_LTR retrotransposon identification" version="0.1.6.1" 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">bioconductor-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' -M $max_missing --output output --cpu 32
        &&
        mv output.gff3 $te_ltr_gff
        &&
        mv output_statistics.csv $statistics
    ]]></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" />
        <param type="integer" name="max_missing" min="0" max="3" value="1" label="Maximum number of missing protein domains to tolerate in full length retrotransposon" />
    </inputs>
    <outputs>
        <data name="te_ltr_gff" format="gff3" label="LTR retrotransposons annotation (GFF3)
        based on DANTE annotation $dante.hid and reference $reference.hid" />
        <data name="statistics" format="tabular" label="LTR retrotransposons detection
        summary based on $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' Long Terminal Repeats, Target Site Duplication (TSD) and primer binding site (PBS).

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

        - elements with domains, 5'LTR, 3'LTR, TSD and PBS - rank DLTP
        - elements with domains, 5'LTR, 3'LTR and PBS (TSD was not found) rank DLP
        - elements with domains, 5' LTR, 3'LTR, TSD (PBS was not found) - rank DTL
        - elements with protein domains, 5'LTR and 3'LTR (PBS and LDS were not found)  - rank DL
        - elements as cluster of proteins domains with same classification, no LTRs - rank D

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

    ]]></help>
</tool>