annotate mash_sketch.xml @ 0:68084b06ae83 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mash commit 24f4271bd62a3d96fec812eae2ad607f6a7f723c"

<tool id="mash_sketch" name="mash sketch" version="@TOOL_VERSION@+galaxy0" profile="19.01">
    <description>
        Create a reduced representation of a sequence or set of sequences, based on min-hashes
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
        mash sketch
            -s '${sketch_size}'
            -k '${kmer_size}'
            #if str ( $reads_assembly.reads_assembly_selector ) == "reads"
              -m '${reads_assembly.minimum_kmer_copies}'
              -r
              #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired"
                '$reads_assembly.reads_input.reads_1' '$reads_assembly.reads_input.reads_2'
              #end if
              #if str( $reads_assembly.reads_input.reads_input_selector ) == "paired_collection"
                '$reads_assembly.reads_input.reads.forward' '$reads_assembly.reads_input.reads.reverse'
              #end if
              #if str( $reads_assembly.reads_input.reads_input_selector ) == "single"
                '$reads_assembly.reads_input.reads'
              #end if
            #elif str ( $reads_assembly.reads_assembly_selector ) == "assembly"
              -p \${GALAXY_SLOTS:-1}
              '${assembly}'
              ${reads_assembly.individual_sequences}
            #end if
            -o 'sketch'
    ]]></command>
    <inputs>
        <conditional name="reads_assembly">
            <param name="reads_assembly_selector" type="select" label="Input: Reads or Assemblies">
                <option selected="True" value="reads">Reads</option>
                <option value="assembly">Assembly</option>
            </param>
            <when value="reads">
                <conditional name="reads_input">
                    <param name="reads_input_selector" type="select" label="Single or Paired-end reads" help="Select between paired and single end data">
                        <option value="paired">Paired</option>
                        <option value="single">Single</option>
                        <option value="paired_collection">Paired Collection</option>
                    </param>
                    <when value="paired">
                        <param name="reads_1" type="data" format="@INTYPES@" label="Select first set of reads" help="Specify dataset with forward reads"/>
                        <param name="reads_2" type="data" format="@INTYPES@" label="Select second set of reads" help="Specify dataset with reverse reads"/>
                    </when>
                    <when value="single">
                        <param name="reads" type="data" format="@INTYPES@" label="Select fastq dataset" help="Specify dataset with single reads"/>
                    </when>
                    <when value="paired_collection">
                        <param name="reads" format="@INTYPES@" type="data_collection" collection_type="paired" label="Select a paired collection" help="See help section for an explanation of dataset collections"/>
                    </when>
                </conditional>
                <param type="integer" name="minimum_kmer_copies" argument="-m" value="1" min="1" max="1000" label="Minimum copies of each k-mer required to pass noise filter"/>
            </when>
            <when value="assembly">
                <param name="assembly" type="data" format="fasta,fasta.gz" label="Assembly"/>
                <param type="boolean" name="individual_sequences" truevalue="-i" falsevalue="" label="Sketch individual Sequences"/>
            </when>
        </conditional>
        <param type="integer" name="sketch_size" argument="-s" value="1000" min="10" max="1000000" label="Sketch size" />
        <param type="integer" name="kmer_size" argument="-k" value="21" min="1" max="32" label="kmer size" />
    </inputs>
    <outputs>
        <data name="sketch" format="msh" from_work_dir="sketch.msh"/>
    </outputs>
    <tests>
        <test>
            <param name="reads_assembly_selector" value="reads" />
            <param name="reads_input_selector" value="single"/>
            <param name="reads" value="ERR024951_seqtk_sample_1000_1.fastq"/>
            <output name="sketch" file="ERR024951_seqtk_sample_1000_1.sketch.msh" compare="sim_size" />
        </test>
        <test>
            <param name="reads_assembly_selector" value="assembly" />
            <param name="assembly" value="test_assembly.fasta"/>
            <output name="sketch" file="test_assembly.sketch.msh" compare="sim_size" />
        </test>
    </tests>
    <help><![CDATA[

**What it does**

  Create a sketch file, which is a reduced representation of a sequence or set
  of sequences (based on min-hashes) that can be used for fast distance
  estimations. Inputs can be fasta or fastq files (gzipped or not), and "-" can
  be given to read from standard input. Input files can also be files of file
  names (see -l). For output, one sketch file will be generated, but it can have
  multiple sketches within it, divided by sequences or files (see -i). By
  default, the output file name will be the first input file with a '.msh'
  extension, or 'stdin.msh' if standard input is used (see -o).
  ]]></help>
    <expand macro="citations"/>
</tool>