comparison kraken.xml @ 3:7c41dbaa9875 draft

planemo upload for repository https://github.com/galaxyproject/tools-devteam/blob/master/tool_collections/kraken/kraken/ commit 0d8d0e2d94ac0cb08a56d020af26ffcbc33d250d

2:642f30185af2

<?xml version="1.0"?>
<tool id="kraken" name="Kraken" version="1.1.2">
    <description>
        assign taxonomic labels to sequencing reads
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <command>
        <![CDATA[
        @SET_DATABASE_PATH@ &&
        kraken --threads \${GALAXY_SLOTS:-1} @INPUT_DATABASE@ 
        

        #end if

        #if $split_reads:
            --classified-out "${classified_out}" --unclassified-out "${unclassified_out}"
        #end if
        --output "${output}"
        ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}"
        ]]>
    </command>
    <inputs>
        <conditional name="single_paired">
            <param name="single_paired_selector" type="select" label="Single or paired reads" help="--paired">
                <option value="collection">Collection</option>
                <option value="yes">Yes</option>
                <option selected="True" value="no">No</option>
            </param>
            <when value="collection">
                <param format="fasta,fastq" label="Collection of paired reads" name="input_pair" type="data_collection" collection_type="paired" help="FASTA or FASTQ datasets" />
                <param name="check_names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match" help="--check-names" />
            </when>

            <filter>(split_reads)</filter>
        </data>
        <data format="tabular" label="${tool.name} on ${on_string}: Classification" name="output" />
        <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />-->
    </outputs>
    <help>
        <![CDATA[
**What it does**

Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise.

            c) the next 31 k-mers contained an ambiguous nucleotide
            d) the next k-mer was not in the database
            e) the last 3 k-mers mapped to taxonomy ID #562
        ]]>
    </help>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <expand macro="citations" />
</tool>

3:7c41dbaa9875

<?xml version="1.0"?>
<tool id="kraken" name="Kraken" version="1.2.0">
    <description>
        assign taxonomic labels to sequencing reads
    </description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <expand macro="stdio" />
    <expand macro="version_command" />
    <command>
        <![CDATA[
        @SET_DATABASE_PATH@ &&
        kraken --threads \${GALAXY_SLOTS:-1} @INPUT_DATABASE@ 
        

        #end if

        #if $split_reads:
            --classified-out "${classified_out}" --unclassified-out "${unclassified_out}"
        #end if

        ## The --output option was changed to redirect as it does not work properly is some situations. For example, on test database the tool classifies 4 reads but does not write them into a file if --output is specified. It does however print correct output into STDOUT. This behavior can be re-created with test database provided in test-data/test_db/ folder. This is the reason for incrementing version number from 1.1.2 to 1.1.3

        > "${output}"
        ##kraken-translate --db ${kraken_database.fields.name} "${output}" > "${translated}"
        ]]>
    </command>
    <inputs>
        <conditional name="single_paired">
            <param name="single_paired_selector" type="select" label="Single or paired reads" help="--paired">
                <option value="collection">Collection</option>
                <option value="yes">Paired</option>
                <option selected="True" value="no">Single</option>
            </param>
            <when value="collection">
                <param format="fasta,fastq" label="Collection of paired reads" name="input_pair" type="data_collection" collection_type="paired" help="FASTA or FASTQ datasets" />
                <param name="check_names" type="boolean" checked="False" truevalue="--paired --check-names" falsevalue="--paired" label="Verify read names match" help="--check-names" />
            </when>

            <filter>(split_reads)</filter>
        </data>
        <data format="tabular" label="${tool.name} on ${on_string}: Classification" name="output" />
        <!--<data format="tabular" label="${tool.name} on ${on_string}: Translated classification" name="translated" />-->
    </outputs>

    <tests>
        <test>
            <param name="single_paired_selector" value="no"/>
            <param name="input_sequences" value="kraken_test1.fa" ftype="fasta"/>
            <param name="split_reads" value="false"/>
            <param name="quick" value="no"/>
            <param name="only-classified-output" value="false"/>
            <param name="kraken_database" value="test_db"/>
            <output name="output" file="kraken_test1_output.tab" ftype="tabular"/>
        </test>
    </tests>
    <help>
        <![CDATA[
**What it does**

Kraken is a taxonomic sequence classifier that assigns taxonomic labels to short DNA reads. It does this by examining the k-mers within a read and querying a database with those k-mers. This database contains a mapping of every k-mer in Kraken's genomic library to the lowest common ancestor (LCA) in a taxonomic tree of all genomes that contain that k-mer. The set of LCA taxa that correspond to the k-mers in a read are then analyzed to create a single taxonomic label for the read; this label can be any of the nodes in the taxonomic tree. Kraken is designed to be rapid, sensitive, and highly precise.

            c) the next 31 k-mers contained an ambiguous nucleotide
            d) the next k-mer was not in the database
            e) the last 3 k-mers mapped to taxonomy ID #562
        ]]>
    </help>
    <expand macro="citations" />
</tool>