annotate hicTransform.xml @ 4:d5bf6e7d3800 draft

planemo upload for repository https://github.com/maxplanck-ie/HiCExplorer/tree/master/galaxy/wrapper/ commit eec0a4d5a7c5ba4ec0fbd2ead8280c3d143bb9d8

<tool id="hicexplorer_hictransform" name="@BINARY@" version="@WRAPPER_VERSION@.0">
    <description>transform a matrix to obs/exp, pearson and covariance matrices</description>
    <macros>
        <token name="@BINARY@">hicTransform</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[


        hicTransform --matrix '$matrix_h5_cooler'
        --method all
        --outFileName matrix.$outputFormat
        && mv obs_exp_matrix.$outputFormat obs_exp_matrix
        && mv pearson_matrix.$outputFormat pearson_matrix
        && mv covariance_matrix.$outputFormat covariance_matrix
]]>
    </command>
    <inputs>
        <expand macro='matrix_h5_cooler_macro' />
        <param name='outputFormat' type='select' label="Output file format">
            <option value='h5'>HiCExplorer format</option>
            <option value="cool">cool</option>
        </param>

    </inputs>
    <outputs>
        <data name="obs_exp" from_work_dir="obs_exp_matrix" format="h5" label="${tool.name} on ${matrix_h5_cooler.name} [${on_string}]: Observed/Expected matrix">
            <change_format>
                <when input="outputFormat" value="cool" format="cool"/>
            </change_format>
        </data>
        <data name="pearson" from_work_dir="pearson_matrix" format="h5" label="${tool.name}  on ${matrix_h5_cooler.name} [${on_string}]: Pearson matrix">
            <change_format>
                <when input="outputFormat" value="cool" format="cool"/>
            </change_format>
        </data>
        <data name="covariance" from_work_dir="covariance_matrix" format="h5" label="${tool.name} on ${matrix_h5_cooler.name} [${on_string}]: Covariance matrix">
            <change_format>
                <when input="outputFormat" value="cool" format="cool"/>
            </change_format>
        </data>

    </outputs>
    <tests>
        <test>
            <param name="matrix_h5_cooler" value="small_test_matrix_50kb_res.h5"/>
            <param name="outputFormat" value="h5" />
            <output name="obs_exp" file="obs_exp_small_50kb.h5" ftype="h5" compare="sim_size"/>
            <output name="pearson" file="pearson_small_50kb.h5" ftype="h5" compare="sim_size"/>
            <output name="covariance" file="covariance_small_50kb.h5" ftype="h5" compare="sim_size"/>
        </test>
        <test>
            <param name="matrix_h5_cooler" value="small_test_matrix_50kb_res.h5"/>
            <param name="outputFormat" value="cool" />
            <output name="obs_exp" file="obs_exp_small_50kb.cool" ftype="cool" compare="sim_size"/>
            <output name="pearson" file="pearson_small_50kb_transform.cool" ftype="cool" compare="sim_size"/>
            <output name="covariance" file="covariance_small_50kb.cool" ftype="cool" compare="sim_size"/>
        </test>
    </tests>
    <help><![CDATA[
Transformation of matrix for plotting
=====================================

**hicTransform** computes three matrices based on one Hi-C contact matrix as input based on the methods determined by `Lieberman-Aiden et al. (2009)`_:

- An **observed/expected matrix** obtained "by dividing each entry in the contact matrix by the genome-wide average contact probability for loci at that genomic distance" (`Lieberman-Aiden et al. (2009)`_). This transformation allows to better assess long range interactions.
- A **Pearson correlation matrix** obtained by computing the Pearson correlation between each bin based on observed/expected values. This matrix transformation allows to better identify the bins that are entering in contact together, or not, at long ranges, and thus helps defining compartments in the nucleus (``hicPCA``).
- A **covariance matrix**, which is used as a basis for the Principal Component Analysis (PCA) to compute the eigenvectors outputed by **hicTransform**.

These three matrices can be used with ``hicPlotMatrix`` or ``hicPlotTADs`` for a visualization of the A / B compartment analysis.

_________________

Output
------

From one Hi-C contact matrix, **hicTransform** outputs the observed/expected, Pearson correlation and covariance matrices.

_________________

| For more information about HiCExplorer please consider our documentation on readthedocs.io_

.. _readthedocs.io: http://hicexplorer.readthedocs.io/en/latest/index.html
.. _`Lieberman-Aiden et al. (2009)`: https://dx.doi.org/10.1126%2Fscience.1181369
]]></help>
    <expand macro="citations" />
</tool>