annotate macros.xml @ 8:c0caca5af183 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/khmer commit 14ea2dc5ef36219c908ed64b256794711ce7b902"

<macros>
    <token name="@TOOL_VERSION@">3.0.0a3</token>
    <token name="@VERSION_SUFFIX@">2</token>
    <token name="@PROFILE@">20.01</token>
    <xml name="requirements">
        <requirements>
            <requirement type="package" version="@TOOL_VERSION@">khmer</requirement>
            <yield/>
        </requirements>
    </xml>
    <xml name="version">
        <version_command><![CDATA[@BINARY@ --version 2>&1 | tail -n 1 | cut -d ' ' -f 2]]></version_command>
    </xml>
    <xml name="stdio">
        <stdio>
            <exit_code range="1:" level="fatal" />
        </stdio>
    </xml>
    <token name="@TABLEPARAMS@">
<![CDATA[
#if $parameters.type == "simple"
  --ksize=20
  --n_tables=4
  --max-tablesize=$parameters.tablesize
#else
  --ksize=$parameters.ksize
  --n_tables=$parameters.n_tables
  --max-tablesize="$parameters.tablesize_specific"
#end if
]]>
    </token>
    <token name="@THREADS@">--threads \${GALAXY_SLOTS:-4}</token>
    <xml name="tableinputs">
        <conditional name="parameters">
            <param name="type" type="select" label="Advanced Parameters"
                help="ksize, n_tables, a specific tablesize" >
                <option value="simple" selected="true">Hide</option>
                <option value="specific">Show</option>
            </param>
            <when value="simple">
                <param argument="" name="tablesize" type="select" label="Sample Type" display="radio">
                    <option value="1e9" selected="true">Microbial Genome</option>
                    <option value="2e9">Animal Transcriptome</option>
                    <option value="4e9">Small Animal Genome or Low-Diversity Metagenome</option>
                    <option value="16e9">Large Animal Genome</option>
                </param>
            </when>
            <when value="specific">
                <param argument="--ksize" name="ksize" type="integer" value="20" label="k-mer size" help="k-mer size to use" />
                <param argument="--n_tables" name="n_tables" type="integer" min="1" value="4" label="n_tables" help="number of tables to use" />
                <param argument="--max-tablesize" name="tablesize_specific" type="text" value="1000000.0"
                    label="tablesize" help="(--max-tablesize) upper bound on the tablesize to use" />
            </when>
        </conditional>
    </xml>
    <token name="@LINK_SEQUENCES@">
<![CDATA[
#import re
mkdir input/ &&
#set gzip=""
#for $num, $input in enumerate($inputs)
    ln -s '${input}' 'input/$re.sub("[^\w\-_.]", "_", $input.element_identifier).$input.ext' &&
    #if str($input).endswith(".gz"):
        #set gzip="--gzip"
    #end if
#end for]]></token>
    <token name="@USE_SEQUENCES@">
<![CDATA[
#for $num, $input in enumerate($inputs)
    '../input/$re.sub("[^\w\-_.]", "_", $input.element_identifier).$input.ext'
#end for]]></token>

    <xml name="input_sequences_filenames">
        <param  name="inputs" multiple="true" type="data" format="fasta,fastq,fasta.gz,fastq.gz"
            label="Sequences in FASTA or FASTQ format"
            help="Put in order of precedence such as longest reads first." />
    </xml>
    <xml name="input_sequence_filename">
        <param  name="input_sequence_filename" type="data" format="fasta,fastq,fasta.gz,fastq.gz"
            label="Sequence in FASTA or FASTQ format" />
    </xml>
    <xml name="input_countgraph_filename">
        <param  name="input_countgraph_filename" type="data" format="oxlicg"
            label="the k-mer countgraph to query"
            help="The abundances of the k-mers in the input nucleotide sequence file will be calculated using the kmer counts in this k-mer countgraph." />
    </xml>
    <xml name="abundance-histogram-output">
        <data name="output_histogram_filename" format="txt"
            label="${tool.name} on ${on_string}: k-mer abundance histogram. The
                columns are: (1) k-mer abundance, (2) k-mer count, (3)
                cumulative count, (4) fraction of total distinct k-mers." />
    </xml>
    <xml name="output_sequences" token_extension="">
        <collection name="sequences" type="list">
            <discover_datasets pattern="(?P&lt;name&gt;.*)\.(?P&lt;ext&gt;fast[aq](\.gz)?)\.@EXTENSION@" directory="output" />
        </collection>
    </xml>
    <xml name="output_sequences_single">
        <data name="output" format_source="input_sequence_filename"
            label="${tool.name} on ${on_string}: processed nucleotide sequence file" />
    </xml>
    <xml name="input_zero">
        <param argument="--no-zero" name="zero" type="boolean" truevalue="" falsevalue="--no-zero" checked="true"
            help="Output zero count bins" />
    </xml>
    <xml name="input_bigcount">
        <param  argument="--no-bigcount" name="bigcount" type="boolean" truevalue="" falsevalue="--no-bigcount"
            checked="true" help="Count k-mers past 255 occurences" />
    </xml>
    <token name="@HELP_FOOTER@"><![CDATA[
(from the khmer project: http://khmer.readthedocs.org/en/v2.0/ )]]></token>
    <xml name="software-citation">
        <citation type="doi">10.12688/f1000research.6924.1</citation>
    </xml>
    <xml name="diginorm-citation">
        <citation type="bibtex">@unpublished{diginorm,
    author = "Brown, C Titus and Howe, Adina and Zhang, Qingpeng and Pyrkosz,
Alexis B and Brom, Timothy H",
    title = "A Reference-Free Algorithm for Computational Normalization of
Shotgun Sequencing Data",
    year = "2012",
    eprint = "arXiv:1203.4802",
    url = "http://arxiv.org/abs/1203.4802",
}</citation></xml>
    <xml name="graph-citation">
        <citation type="doi">10.1073/pnas.1121464109</citation>
    </xml>
    <xml name="counting-citation">
        <citation type="doi">10.1371/journal.pone.0101271</citation>
    </xml>
</macros>