comparison mash_screen.xml @ 2:7f7d8b0c8517 draft

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

1:402b67d1af7d

<tool id="mash_screen" name="mash screen" version="@TOOL_VERSION@+galaxy1" profile="19.01">
    <description>determines how well query sequences are contained within a pool of sequences.</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <requirements>
        <requirement type="package" version="@TOOL_VERSION@">mash</requirement>
    </requirements>
    <version_command>mash --version</version_command>
    <command detect_errors="exit_code"><![CDATA[
        ln -s '$queries' queries.msh &&
        mash screen
             $winner_takes_all
             -i $minimum_identity_to_report

            <when value="paired_collection">
                <param name="pool" 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 name="queries" type="data" format="msh" />
        <param type="boolean" name="winner_takes_all" argument="-w" truevalue="-w" falsevalue=""/>
        <param type="float" name="minimum_identity_to_report" argument="-i" value="0." min="-1." max="1." />
        <param type="float" name="maximum_p_value_to_report" argument="-v" value="1." min="0." max="1."/>
    </inputs>
    <outputs>
        <data name="output" format="tabular" />
    </outputs>
    <tests>

            <param name="pool_2" value="ERR024951_seqtk_sample_1000_2.fastq"/>
            <output name="output" file="mash_screen_NZ_MYON01000010.1_ERR024951_seqtk_sample_1000_1and2.tsv"/>
        </test>
    </tests>
    <help><![CDATA[
Description:

  Determine how well query sequences are contained within a pool of sequences.
  The queries must be formatted as a single Mash sketch file (.msh), created
  with the `mash sketch` command. The <pool> files can be contigs or reads, in
  fasta or fastq, gzipped or not, and "-" can be given for <pool> to read from

  be 6-frame translated if the <queries> are amino acids. The output fields are
  [identity, shared-hashes, median-multiplicity, p-value, query-ID,
  query-comment], where median-multiplicity is computed for shared hashes, based
  on the number of observations of those hashes within the pool.
  ]]></help>
    <citations>
        <citation type="bibtex">
@article{ondov2016mash,
  title={Mash: fast genome and metagenome distance estimation using MinHash},
  author={Ondov, Brian D and Treangen, Todd J and Melsted, P{\'a}ll and Mallonee, Adam B and Bergman, Nicholas H and Koren, Sergey and Phillippy, Adam M},
  journal={Genome biology},
  volume={17},
  number={1},
  pages={132},
  year={2016},
  publisher={BioMed Central}
  }
        </citation>
    </citations>
</tool>

2:7f7d8b0c8517

<tool id="mash_screen" name="mash screen" version="@TOOL_VERSION@+galaxy2" profile="19.01">
    <description>determines how well query sequences are contained within a pool of sequences</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="version_command" />
    <command detect_errors="exit_code"><![CDATA[
        ln -s '$queries' queries.msh &&
        mash screen
             $winner_takes_all
             -i $minimum_identity_to_report

            <when value="paired_collection">
                <param name="pool" 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 name="queries" type="data" format="msh" />
        <param name="winner_takes_all" argument="-w" type="boolean" checked="true" truevalue="-w" falsevalue="" label="'Winner takes all' to remove redundancy in the result"
            help="If this option is not enabled, every matching strain from the same species of the reference database is reported in the result."/>
        <param type="float" name="minimum_identity_to_report" argument="-i" value="0." min="-1." max="1." label="Minimum identity to report" />
        <param type="float" name="maximum_p_value_to_report" argument="-v" value="1." min="0." max="1." label="Maximum p-value to report" />
    </inputs>
    <outputs>
        <data name="output" format="tabular" />
    </outputs>
    <tests>

            <param name="pool_2" value="ERR024951_seqtk_sample_1000_2.fastq"/>
            <output name="output" file="mash_screen_NZ_MYON01000010.1_ERR024951_seqtk_sample_1000_1and2.tsv"/>
        </test>
    </tests>
    <help><![CDATA[

**What it does**

  Determine how well query sequences are contained within a pool of sequences.
  The queries must be formatted as a single Mash sketch file (.msh), created
  with the `mash sketch` command. The <pool> files can be contigs or reads, in
  fasta or fastq, gzipped or not, and "-" can be given for <pool> to read from

  be 6-frame translated if the <queries> are amino acids. The output fields are
  [identity, shared-hashes, median-multiplicity, p-value, query-ID,
  query-comment], where median-multiplicity is computed for shared hashes, based
  on the number of observations of those hashes within the pool.
  ]]></help>
    <expand macro="citations"/>
</tool>