annotate macros.xml @ 14:cb34f00cc10f draft

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/medaka commit 8051b858e0f5c6d7c1092754df02ed8303a53054

<macros>
    <token name="@TOOL_VERSION@">1.4.4</token>
    <token name="@VERSION_SUFFIX@">1</token>
    <token name="@PROFILE@">21.01</token>
    <xml name="bio_tools">
        <xrefs>
            <xref type="bio.tools">medaka</xref>
        </xrefs>
    </xml>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@TOOL_VERSION@">medaka</requirement>
            <yield />
        </requirements>
    </xml>
    <xml name="version_command">
        <version_command>medaka --version</version_command>
    </xml>
    <xml name="citations">
        <citations>
            <citation type="bibtex">@online{medaka,
              author = {Oxford Nanopore Technologies Ltd.},
              title = {medaka},
              year = 2020,
              url = {https://github.com/nanoporetech/medaka},
              urldate = {2020-05-06}
            }</citation>
        </citations>
    </xml>

    <!--
        command
    -->

    <token name="@REF_FASTA@"><![CDATA[
        #if $reference_source.reference_source_selector == 'history':
            #if $reference_source.ref_file.ext.endswith(".gz")
                gunzip -c '$reference_source.ref_file' > reference.fa &&
            #else
                ln -f -s '$reference_source.ref_file' reference.fa &&
            #end if
        #else:
            ln -f -s '$reference_source.ref_file.fields.path' reference.fa &&
        #end if
    ]]></token>

    <!--
        input
    -->

    <xml name="b" token_argument="-b">
        <param argument="@ARGUMENT@" type="integer" value="100" min="1" label="Set inference batch size"/>
    </xml>
    <xml name="model" token_argument="-m" token_label="Select model">
        <param argument="@ARGUMENT@" type="select" label="@LABEL@" help="For best results it is important to specify the correct model, 
            according to the basecaller used. Medaka models are named to indicate i) the pore type, ii) the sequencing device (MinION 
            or PromethION), iii) the basecaller variant, and iv) the basecaller version">
            <option value="r103_fast_g507">r103_fast_g507</option>
            <option value="r103_fast_snp_g507">r103_fast_snp_g507</option>
            <option value="r103_fast_variant_g507">r103_fast_variant_g507</option>
            <option value="r103_hac_g507">r103_hac_g507</option>
            <option value="r103_hac_snp_g507">r103_hac_snp_g507</option>
            <option value="r103_hac_variant_g507">r103_hac_variant_g507</option>
            <option value="r103_min_high_g345">r103_min_high_g345</option>
            <option value="r103_min_high_g360">r103_min_high_g360</option>
            <option value="r103_prom_high_g360">r103_prom_high_g360</option>
            <option value="r103_prom_snp_g3210">r103_prom_snp_g3210</option>
            <option value="r103_prom_variant_g3210">r103_prom_variant_g3210</option>
            <option value="r103_sup_g507">r103_sup_g507</option>
            <option value="r103_sup_snp_g507">r103_sup_snp_g507</option>
            <option value="r103_sup_variant_g507">r103_sup_variant_g507</option>
            <option value="r104_e81_fast_g5015">r104_e81_fast_g5015</option>
            <option value="r104_e81_hac_g5015">r104_e81_hac_g5015</option>
            <option value="r104_e81_sup_g5015">r104_e81_sup_g5015</option>
            <option value="r10_min_high_g303">r10_min_high_g303</option>
            <option value="r10_min_high_g340">r10_min_high_g340</option>
            <option value="r941_min_fast_g303">r941_min_fast_g303</option>
            <option value="r941_min_fast_g507">r941_min_fast_g507</option>
            <option value="r941_min_fast_snp_g507">r941_min_fast_snp_g507</option>
            <option value="r941_min_fast_variant_g507">r941_min_fast_variant_g507</option>
            <option value="r941_min_hac_g507">r941_min_hac_g507</option>
            <option value="r941_min_hac_snp_g507">r941_min_hac_snp_g507</option>
            <option value="r941_min_hac_variant_g507">r941_min_hac_variant_g507</option>
            <option value="r941_min_high_g303">r941_min_high_g303</option>
            <option value="r941_min_high_g330">r941_min_high_g330</option>
            <option value="r941_min_high_g340_rle">r941_min_high_g340_rle</option>
            <option value="r941_min_high_g344">r941_min_high_g344</option>
            <option value="r941_min_high_g351">r941_min_high_g351</option>
            <option value="r941_min_high_g360" selected="true">r941_min_high_g360</option>
            <option value="r941_min_sup_g507">r941_min_sup_g507</option>
            <option value="r941_min_sup_snp_g507">r941_min_sup_snp_g507</option>
            <option value="r941_min_sup_variant_g507">r941_min_sup_variant_g507</option>
            <option value="r941_prom_fast_g303">r941_prom_fast_g303</option>
            <option value="r941_prom_fast_g507">r941_prom_fast_g507</option>
            <option value="r941_prom_fast_snp_g507">r941_prom_fast_snp_g507</option>
            <option value="r941_prom_fast_variant_g507">r941_prom_fast_variant_g507</option>
            <option value="r941_prom_hac_g507">r941_prom_hac_g507</option>
            <option value="r941_prom_hac_snp_g507">r941_prom_hac_snp_g507</option>
            <option value="r941_prom_hac_variant_g507">r941_prom_hac_variant_g507</option>
            <option value="r941_prom_high_g303">r941_prom_high_g303</option>
            <option value="r941_prom_high_g330">r941_prom_high_g330</option>
            <option value="r941_prom_high_g344">r941_prom_high_g344</option>
            <option value="r941_prom_high_g360">r941_prom_high_g360</option>
            <option value="r941_prom_high_g4011">r941_prom_high_g4011</option>
            <option value="r941_prom_snp_g303">r941_prom_snp_g303</option>
            <option value="r941_prom_snp_g322">r941_prom_snp_g322</option>
            <option value="r941_prom_snp_g360">r941_prom_snp_g360</option>
            <option value="r941_prom_sup_g507">r941_prom_sup_g507</option>
            <option value="r941_prom_sup_snp_g507">r941_prom_sup_snp_g507</option>
            <option value="r941_prom_sup_variant_g507">r941_prom_sup_variant_g507</option>
            <option value="r941_prom_variant_g303">r941_prom_variant_g303</option>
            <option value="r941_prom_variant_g322">r941_prom_variant_g322</option>
            <option value="r941_prom_variant_g360">r941_prom_variant_g360</option>
        </param>
    </xml>
    <xml name="reference">
        <conditional name="reference_source">
            <param name="reference_source_selector" type="select" label="Choose the source for the reference genome">
                <option value="cached">Use a built-in genome</option>
                <option value="history">Use a genome from history</option>
            </param>
            <when value="cached">
                <param name="ref_file" type="select" label="Using reference genome" help="Select genome from the list">
                    <options from_data_table="all_fasta">
                        <filter type="sort_by" column="2"/>
                        <validator type="no_options" message="No reference genomes are available"/>
                    </options>
                    <validator type="no_options" message="A built-in reference genome is not available for the build associated with the selected input file"/>
                </param>
            </when>
            <when value="history">
                <param name="ref_file" type="data" format="fasta,fasta.gz" label="Use the following dataset as the reference sequence" help="You can upload a FASTA or FASTQ sequence to the history and use it as reference"/>
            </when>
        </conditional>
    </xml>

    <!--
        Help
    -->

    <token name="@WID@"><![CDATA[
*medaka* is a tool suite to create a consensus sequence from nanopore sequencing data.

This task is performed using neural networks applied from a pileup of individual sequencing reads against a draft assembly. It outperforms graph-based methods operating on basecalled data, and can be competitive with state-of-the-art signal-based methods, whilst being much faster.
    ]]></token>

    <token name="@MODELS@"><![CDATA[

----

.. class:: infomark

**Models**

For best results it is important to specify the correct model, -m in the above, according to the basecaller used. Allowed values can be found by running medaka tools list\_models.

Medaka models are named to indicate i) the pore type, ii) the sequencing device (MinION or PromethION), iii) the basecaller variant, and iv) the basecaller version, with the format:

    ::

        {pore}_{device}_{caller variant}_{caller version}

For example the model named r941_min_fast_g303 should be used with data from MinION (or GridION) R9.4.1 flowcells using the fast Guppy basecaller version 3.0.3. By contrast the model 
r941_prom_hac_g303 should be used with PromethION data and the high accuracy basecaller (termed "hac" in Guppy configuration files). Where a version of Guppy has been used without an exactly corresponding medaka model, the medaka model with the highest version equal to or less than the guppy version should be selected.
          
    ]]></token>

    <token name="@REFERENCES@"><![CDATA[
More information are available in the `manual <https://github.com/nanoporetech/medaka/tree/master/docs>`_ and `github <https://github.com/nanoporetech/medaka>`_.
    ]]></token>
</macros>