annotate delta-filter.xml @ 3:fbca557a4847 draft

"planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mummer4 commit bacb32814054404587451948b3a6682cf0d1a33a"

<tool id="mummer_delta_filter" name="Delta-Filter" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>Filters alignment (delta) file from nucmer</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="bio_tools"/>
    <expand macro="requirements" />
    <command detect_errors="exit_code">
        <![CDATA[
        delta-filter
            $alignment
            -i '$min_identity'
            -l '$min_length'
            $overlap
            -u '$min_uniqueness'
            -o '$max_overlap'
            '$delta' > '$output'
        ]]>
    </command>
    <inputs>
        <param name="delta" type="data" format="tabular" label="Match file from nucmer" />
        <param name="alignment" type="select" label="Alignment Strategy" >
            <option value="-m">Use default [Many-to-many alignment allowing for rearrangements] (-m)</option>
            <option value="-1">1-to-1 alignment allowing for rearrangements (-1)</option>
            <option value="-g">1-to-1 global alignment not allowing rearrangements (-g)</option>
        </param>
        <param name="min_identity" type="float" argument="-i" value="0" min="0" max="100" label="Minimum Identity" help="Set the minimum alignment identity. (-i)" />
        <param name="min_length" type="integer" argument="-l" value="0" label="Minumum Legnth" help="Set the minimum alignment length. (-l)" />
        <param name="overlap" type="select" label="Overlaps"
            help=" Maps each position of each query/reference to its best hit in the reference/query, allowing for reference/query overlaps." >
            <option value="-q">Reference overlaps (-q)</option>
            <option value="-r">Query overlaps (-r)</option>
        </param>
        <param name="min_uniqueness" type="float" argument="-u" value="0" min="0" max="100" label="Minimum Alignment Uniqueness"
            help="Set the minimum alignment uniqueness, i.e. percent of the alignment matching to unique reference AND query sequence. (-u)" />
        <param name="max_overlap" type="float" argument="-o" value="100" min="0" max="100" label="Maximum Alignment Overlap"
            help="Set the maximum alignment overlap for overlap options as a percent of the alignment length. (-o)" />
    </inputs>
    <outputs>
        <data name="output" format="tabular" from_work_dir="delta-filter.txt"/>
    </outputs>
    <tests>
        <test>
            <param name="delta" ftype="tabular" value="nucmer.txt" />
            <output name="output" ftype="tabular" compare="diff" lines_diff="2" value="delta-filter.txt" />
        </test>
    </tests>
    <help><![CDATA[
        This program filters the alignment file produced by nucmer, leaving only the desired alignments. Its primary function is the LIS algorithm which calculates the longest increasing subset of alignments. This allows for the calculation of a global set of alignments (i.e. 1-to-1 and mutually consistent order) with the 1-1 global option or locally consistent with 1-1 with rearrangements or many-to-many alignment. Reference sequences can be mapped to query sequences with the reference option of the Overlaps parameter, or queries to references with the Query option. This allows the user to exclude chance and repeat induced alignments, leaving only the "best" alignments between the two data sets. Filtering can also be performed on length, identity, and uniqueness.

        An important distinction between the alignment options is that 1-1 global requires the alignments to be mutually consistent in their order, while the other options are not required to be mutually consistent and therefore tolerate translocations, inversions, etc.

        In general cases, the many-to-many option is the best choice, however 1-1 alignment allowing for rearrangements can be handy for applications such as SNP finding which require a 1-to-1 mapping. 

        Finally, for mapping query contigs, or sequencing reads, to a reference genome, use the query option for the Overlaps parameter.

**Options**::

    -m      Many-to-many alignment allowing for rearrangements

    -1      1-to-1 alignment allowing for rearrangements

    -g      1-to-1 global alignment not allowing rearrangements

    -i      Set the minimum alignment identity [0, 100], default 0

    -l      Set the minimum alignment length, default 0

    -q      Maps each position of each query to its best hit in the reference, allowing for reference 
            overlaps

    -r      Maps each position of each reference to its best hit in the query, allowing for query overlaps

    -u      Set the minimum alignment uniqueness, i.e. percent of the alignment matching to unique reference 
            AND query sequence [0,100], default 0

    -o      Set the maximum alignment overlap for -r and -q options as a percent of the alignment length 
            [0, 100], default 100

    ]]></help>
    <expand macro="citation" />
</tool>