view hal_halLodExtract.xml @ 1:b95d65e23448 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/main/tools/haltools commit 8a310fc0ea4fd4462a744d940c972974341358f8

<tool id="hal_hallodextract" name="halLodExtract" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>generates a new HAL file at a coarser Level of Detail by interpolation</description>
    <macros>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/> 
    <expand macro="stdio"/>
    <command detect_errors="aggressive"><![CDATA[
        halLodExtract
            #if $backend.format == 'mmap':
                --format 'mmap'
                --mmapFileSize $backend.mmapFileSize
            #end if
            #if $root:
                --root '$root'
            #end if
            #if $outTree:
                --outTree '$outTree'
            #end if
            --probeFrac $probeFrac
            --minSeqFrac $minSeqFrac
            $keepSequences
            $allSequences
            '$input_hal' '$output_file' $scale
    ]]></command>
    <inputs>
        <expand macro="input_hal"/>
        <param name="scale" type="float" value="10" min="1" optional="false" label="Scale factor for interpolation"/>
        <expand macro="params_root_optional"/>
        <param argument="--outTree" type="text" value="" optional="true" label="Newick tree for new HAL file" help="Specify the Newick tree for the new HAL file. Must contain only genomes from the input HAL file (input's tree used if empty)">
            <expand macro="sanitizer_default"/>
            <expand macro="validator_newick"/>
        </param>
        <param argument="--probeFrac" type="float" value="0.035" min="0" label="Fraction of bases in step-interval" help="Fraction of bases in step-interval to sample while looking for most aligned column"/>
        <param argument="--minSeqFrac" type="float" value="0.5" min="0" label="Minumum sequence length to sample (as fraction)" help="Minumum sequence length to sample as fraction of step size: i.e. sequences with length &lt;= floor(minSeqFrac * step) are ignored"/>
        <param argument="--keepSequences" type="boolean" truevalue="--keepSequences" falsevalue="" checked="false" label="Keep sequences" help="Write the sequence strings to the output file"/>
        <param argument="--allSequences" type="boolean" truevalue="--allSequences" falsevalue="" checked="false" label="All sequences" help="Sample all sequences (chromsomes / contigs / etc.) no matter how small they are. By default, small sequences may be skipped if they fall within the step size"/>
        <expand macro="hal_backend_format"/>
    </inputs>
    <outputs>
        <data name="output_file" format="hal" label="${tool.name} on ${on_string}: New HAL"/>
    </outputs>
    <tests>
        <test expect_num_outputs="1">
            <param name="input_hal" value="halTest.hal"/>
            <param name="scale" value="10"/>
            <output name="output_file" ftype="hal">
                <assert_contents>
                    <has_size min="40000"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text text="tree ="/>
                <has_text text="Graph:"/>
            </assert_stdout>
        </test>
        <test expect_num_outputs="1">
            <param name="input_hal" value="halTest.hal"/>
            <param name="scale" value="10"/>
            <output name="output_file" ftype="hal">
                <assert_contents>
                    <has_size min="40000"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text text="tree ="/>
                <has_text text="Graph:"/>
            </assert_stdout>
        </test>
        <test expect_num_outputs="1">
            <param name="input_hal" value="halTest.hal"/>
            <param name="scale" value="10"/>
            <param name="root" value="Genome_0"/>
            <param name="outTree" value="(Genome_1:1,Genome_2:1,Genome_3:1)Genome_0;"/>
            <output name="output_file" ftype="hal">
                <assert_contents>
                    <has_size min="40000"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text text="tree ="/>
                <has_text text="Graph:"/>
            </assert_stdout>
        </test>
        <test expect_num_outputs="1">
            <param name="input_hal" value="halTest.hal"/>
            <param name="scale" value="10"/>
            <param name="minSeqFrac" value="1"/>
            <param name="keepSequences" value="true"/>
            <param name="allSequences" value="true"/>
            <output name="output_file" ftype="hal">
                <assert_contents>
                    <has_size min="50000"/>
                </assert_contents>
            </output>
            <assert_stdout>
                <has_text text="tree ="/>
                <has_text text="Graph:"/>
            </assert_stdout>
        </test>
    </tests>
    <help><![CDATA[
halLodExtract generates a reduced resolution HAL file as output from an input HAL file by sampling the alignment at a coarser Level of Detail by interpolation. 
It needs a scale value that controls how the data is downsampled. 
The tool can keep or drop short sequences, adjust how sequences are filtered relative to the step size, and optionally retain sequence strings. 
Choose a different output tree, set a root genome, and tune how many bases are probed when selecting representative columns.

Use it to create a lighter HAL file for visualization, fast browsing, or downstream analyses that do not require full-resolution data.

-----

.. class:: warningmark

Running the tool on a HAL file in mmap format may fail, while the HDF5 format can run successfully. It is recommended to convert the input to HDF5 format first using halExtract.

.. class:: warningmark

At the moment, creating a HAL file in mmap format is disabled. The creation in HDF5 format is enforced.
    ]]></help>
    <expand macro="citation"/>
    <expand macro="creator"/>
</tool>