comparison show-coords.xml @ 6:4c89814871e8 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/mummer4 commit 980f7472892817697208792e4443fa579625b696

5:e832875e5d5a

    <expand macro="requirements" />
    <command detect_errors="exit_code">
        <![CDATA[
        show-coords
            $merge
            -c
            -H
            -I '$identity'
            -l
            -L '$min_alignment_length'
            $annotate
            $sort
            -T
            '${delta}' > '${output}'
        ]]>
    </command>
    <inputs>
        <param name="delta" type="data" format="tabular" label="Match file from Nucmer" />
        <param name="merge" type="boolean" argument="-b" truevalue="-b" falsevalue="" label="Merge"
            help="Merges overlapping alignments regardless of match dir or frame and does not display any idenitity information. (-b)" />
        <param name="identity" type="float" argument="-I" value="75.0" label="Identity" help="Set minimum percent identity to display (-I)" />
        <param name="min_alignment_length" type="integer" argument="-L" value="100" label="Minimum Alignment Length" help="Set minimum alignment length to display (-L)" />
        <param name="annotate" type="boolean" argument="-o" truevalue="-o" falsevalue="" label="Annotate"
            help="Annotate maximal alignments between two sequences, i.e. overlaps between reference and query sequences (-o)" />
        <param name="sort" type="select" label="Sorting strategy for output" >
            <option value="-q">Sort output by query IDs and coordinates (-q)</option>
            <option value="-r">Sort output by reference IDs and coordinates (-r)</option>
        </param>
    </inputs>
    <outputs>
        <data name="output" format="tabular" from_work_dir="show-coords.txt" >
            <actions>
                <action name="column_names" type="metadata" default="[S1], [E1], [S2], [E2], [LEN 1], [LEN 2], [% IDY], [LEN R], [LEN Q], [COV R], [COV Q], [REF TAG], [QUERY TAG]" />
            </actions>
        </data>
    </outputs>
    <tests>
        <test>
            <param name="delta" ftype="tabular" value="nucmer.txt" />
            <output name="output" ftype="tabular" compare="diff" value="show-coords.txt" />
        </test>
    </tests>
    <help><![CDATA[
This program parses the delta alignment output of nucmer and displays the coordinates, and other useful information about the alignments.

Output is tabular. Below is a description of each column:
    * **[S1]** Start of the alignment region in the reference sequence
    * **[E1]** End of the alignment region in the reference sequence
    * **[S2]** Start of the alignment region in the query sequence
    * **[E2]** End of the alignment region in the query sequence
    * **[LEN 1]** Length of the alignment region in the reference sequence, measured in nucleotides

    * **[% IDY]** Percent identity of the alignment, calculated as (number of exact matches) / ([LEN 1] + insertions in the query)
    * **[LEN R]** Length of the reference sequence
    * **[LEN Q]** Length of the query sequence
    * **[COV R]** Percent coverage of the alignment on the reference sequence, calculated as [LEN 1] / [LEN R]
    * **[COV Q]** Percent coverage of the alignment on the query sequence, calculated as [LEN 2] / [LEN Q]
    * **[REF TAG]** The reference FastA ID
    * **[QUERY TAG]** The query FastA ID

There is also an optional final column (turned on with the "Annotate" parameter) that will contain some 'annotations'. The Annotate option will annotate alignments that represent overlaps between two sequences. Sometimes, nucmer will extend adjacent clusters past one another, thus causing a somewhat redundant output, this option will notify users of such rare occurrences.

**Options:**::

    -b      Merges overlapping alignments regardless of match dir or frame and does not display any 
            identity information.

    -I      Set minimum percent identity to display

    -L      Set minimum alignment length to display

    -o      Annotate maximal alignments between two sequences, i.e. overlaps between reference and query 

6:4c89814871e8

    <expand macro="requirements" />
    <command detect_errors="exit_code">
        <![CDATA[
        show-coords
            $merge
            $direction
            -c
            -H
            -I '$identity'
            -l
            -L '$min_alignment_length'
            $annotate
            $sort
            -T
            '${delta}' 
            #if $direction:
                >  '${output_extend}'
            #else:
               >  '${output}'
            #end if
        ]]>
    </command>
    <inputs>
        <param name="delta" type="data" format="tabular" label="Match file from Nucmer" />
        <param name="merge" type="boolean" argument="-b" truevalue="-b" falsevalue="" label="Merge"
            help="Merges overlapping alignments regardless of match dir or frame and does not display any idenitity information. (-b)" />
        <param name="identity" type="float" argument="-I" value="75.0" label="Identity" help="Set minimum percent identity to display (-I)" />
 
        <param name="direction" type="boolean" argument="-d"  truevalue="-d" falsevalue="" label="Direction"  help="Display the alignment direction in the additional FRM columns (-d)" />
        <param name="min_alignment_length" type="integer" argument="-L" value="100" label="Minimum Alignment Length" help="Set minimum alignment length to display (-L)" />
        <param name="annotate" type="boolean" argument="-o" truevalue="-o" falsevalue="" label="Annotate"
            help="Annotate maximal alignments between two sequences, i.e. overlaps between reference and query sequences (-o)" />
        <param name="sort" type="select" label="Sorting strategy for output" >
            <option value="-q">Sort output by query IDs and coordinates (-q)</option>
            <option value="-r">Sort output by reference IDs and coordinates (-r)</option>
        </param>

    </inputs>
    <outputs>
        <data name="output" format="tabular" from_work_dir="show-coords.txt"   label="${tool.name} on ${on_string} default format)">
            <filter>direction is False</filter>
            <actions>
                <action name="column_names" type="metadata" default="[S1], [E1], [S2], [E2], [LEN 1], [LEN 2], [% IDY], [LEN R], [LEN Q], [COV R], [COV Q], [REF TAG], [QUERY TAG]" />
            </actions>
        </data>
        <data name="output_extend" format="tabular" from_work_dir="show-coords_extend.txt"   label="${tool.name} on ${on_string} extend format)" >
            <filter>direction is True</filter>
            <actions>
                <action name="column_names" type="metadata" default="[S1], [E1], [S2], [E2], [LEN 1], [LEN 2], [% IDY], [LEN R], [LEN Q], [COV R], [COV Q], [FRM R], [FRM Q], [REF TAG], [QUERY TAG]" />
            </actions>
        </data>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="delta" ftype="tabular" value="nucmer.txt" />
            <param name="direction" value="False" />
            <output name="output" ftype="tabular" compare="diff" value="show-coords.txt" />
        </test>
        <test expect_num_outputs="1">
            <param name="delta" ftype="tabular" value="nucmer.txt" />
            <param name="direction" value="True" />
            <output name="output_extend" ftype="tabular" compare="diff" value="show-coords_extend.txt" />
        </test>
    </tests>
    <help><![CDATA[
This program parses the delta alignment output of nucmer and displays the coordinates, and other useful information about the alignments.

Output is tabular. Below is a description of each column (Default):
    * **[S1]** Start of the alignment region in the reference sequence
    * **[E1]** End of the alignment region in the reference sequence
    * **[S2]** Start of the alignment region in the query sequence
    * **[E2]** End of the alignment region in the query sequence
    * **[LEN 1]** Length of the alignment region in the reference sequence, measured in nucleotides

    * **[% IDY]** Percent identity of the alignment, calculated as (number of exact matches) / ([LEN 1] + insertions in the query)
    * **[LEN R]** Length of the reference sequence
    * **[LEN Q]** Length of the query sequence
    * **[COV R]** Percent coverage of the alignment on the reference sequence, calculated as [LEN 1] / [LEN R]
    * **[COV Q]** Percent coverage of the alignment on the query sequence, calculated as [LEN 2] / [LEN Q]
    * **[FRM R]** Reading frame for the reference sequence (only with -d)
    * **[FRM Q]** Reading frame for the query sequence (only with -d)
    * **[REF TAG]** The reference FastA ID
    * **[QUERY TAG]** The query FastA ID

There is also an optional final column (turned on with the "Annotate" parameter) that will contain some 'annotations'. The Annotate option will annotate alignments that represent overlaps between two sequences. Sometimes, nucmer will extend adjacent clusters past one another, thus causing a somewhat redundant output, this option will notify users of such rare occurrences.

**Options:**::

    -b      Merges overlapping alignments regardless of match dir or frame and does not display any 
            identity information.
    -d      Display the alignment direction in the additional FRM columns
    -I      Set minimum percent identity to display

    -L      Set minimum alignment length to display

    -o      Annotate maximal alignments between two sequences, i.e. overlaps between reference and query