view hicAggregateContacts.xml @ 6:f922a8d5e897 draft

"planemo upload for repository commit 5744259254d4254a29cb7a6687fbbfd103301064"
author bgruening
date Wed, 05 Feb 2020 19:45:52 -0500
parents ce16a538ab46
children ee370ade24cd
line wrap: on
line source

<tool id="hicexplorer_hicaggregatecontacts" name="@BINARY@" version="@WRAPPER_VERSION@.0">
    <description>allow plotting of aggregated Hi-C contacts between regions specified in a file</description>
        <token name="@BINARY@">hicAggregateContacts</token>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[
    ln -s '$matrix_h5_cooler' 'matrix.$matrix_h5_cooler.ext' &&
    --matrix 'matrix.$matrix_h5_cooler.ext'
    --BED $BED
    #if $BED2:
        --BED2 $BED2
    #end if

    --range '$range_min:$range_max'

    --numberOfBins '$numberOfBins'

    --transform $transform
    --avgType $avgType

    #if $outputs and 'PrefixMatrix' in $outputs:
        --outFilePrefixMatrix 'matrix_values'
    #end if

    #if $outputs and 'ClusterContactPositions' in $outputs:
        --outFilePrefixClusterContactPositions 'contact_positions'
    #end if

    #if $outputs and 'HeatmapFile' in $outputs:
        --diagnosticHeatmapFile 'heatmap'
    #end if

    #if $clustering:
    #end if

    #if $chromosomes:
        --chromosomes #echo "' '".join([ "'%s'" % $chrom.chromosome for $chrom in $chromosomes ])#
    #end if

    #if $plotType:
        --plotType $plotType
    #end if

    #if $colormap:
        --colorMap $colormap
    #end if

    #if $vMin:
        --vMin $vMin
    #end if

    #if $vMax:
        --vMax $vMax
    #end if

    --outFileName plot.$image_file_format
    && mv plot.$image_file_format plot

        <expand macro='matrix_h5_cooler_macro' />
        <param argument="--BED" type="data" format="bed" label="Interactions between regions in this BED file are plotted"/>
        <param argument="--BED2" type="data" format="bed" optional="true"
            label="Interactions between regions in first and second BED file are plotted"/>

        <expand macro='range' />

        <repeat name="chromosomes" title="List of chromosomes to plot" min="0">
            <param name="chromosome" type="text" label="chromosome (one per field)">
                <validator type="empty_field" />

        <param argument="--numberOfBins" type="integer" optional="true" label="Number of bins to include in the submatrix"
            help="The bed regions will be centered between -half number of bins
            and +half number of bins indicated." />

        <param argument="--transform" type="select" label="Type of transformation for the matrix"
            help="If total counts are selected, then the sub-matrix values
            are divided by the total counts for normalization. If
            z-score or obs/exp are selected, then H-C matrix is
            converted into a z-score or observed / expected matrix.">
            <option value="none" selected="true">none</option>
            <option value="total-counts">total-counts</option>
            <option value="z-score">z-score</option>
            <option value="obs/exp">obs/exp</option>

        <param argument="--avgType" type="select" label="Type of average to compute final matrix">
            <option value="median" selected="true">median</option>
            <option value="mean">mean</option>

        <param name="clustering" type="select" optional="true" label="Number of clusters per chromosome"
            help="When this option is set, then the matrix is split into
                  clusters using the hierarchical clustering algorithm,
                  using 'ward linkage'. hclust could be very slow if
                  you have >1000 submatrices per chromosome. In those
                  cases, you might prefer kmeans.">
            <option value="--kmeans">kmeans</option>
            <option value="--hclust">hclust (#clusters per chromosome)</option>

        <param argument="--clusterOnDiagonal" type="boolean" truevalue="--clusterOnDiagonal" falsevalue=""
            label="Perform clustering on the submatrix diagonal"
            help="Clustering is by default carried out on the whole
                  submatrices. If this parameter is given, the
                  clustering is only carried out based on the submatrix
                  diagonal (representing values at the same distance to each other)." />

        <param argument="--plotType" type="select" optional="true" label="Plot type">
            <option value="2d">2D</option>
            <option value="3d">3D</option>
        <expand macro="colormap" />
        <param argument="--vMin" type="float" optional="true" label="vMin"
            help= "Minimum value of the plotted score." />

        <param argument="--vMax" type="float" optional="true" label="vMax"
            help= "Maximum value of the plotted score." />

        <param name="image_file_format" type="select" label="Image output format">
            <option value="png" selected="True">png</option>
            <option value="svg">svg</option>
            <option value="pdf">pdf</option>


        <param name="outputs" type="select" optional="true" multiple="true" label="Optional output files">
            <option value="PrefixMatrix">Save values underlying the final matrix</option>
            <option value="ClusterContactPositions">Save the position of the contacts</option>
            <option value="HeatmapFile">Heatmap file per chromosome</option>

        <data name="outFileName" from_work_dir="plot" format="png" label="${} on ${on_string}: Plot">
                <when input="image_file_format" value="svg" format="svg" />
                <when input="image_file_format" value="pdf" format="pdf" />

        <collection name="matrix_values" type="list" label="${} on ${on_string}: Matrix values">
            <discover_datasets pattern="matrix_values_(?P&lt;designation&gt;.*)\..*" directory="./" format="tabular" />
        <collection name="contact_positions" type="list" label="${} on ${on_string}: Matrix values">
            <discover_datasets pattern="contact_positions_(?P&lt;designation&gt;.*)\..*" directory="./" format="tabular" />
        <collection name="heatmap" type="list" label="${} on ${on_string}: Matrix values">
            <discover_datasets pattern="heatmap_(?P&lt;designation&gt;.*)\..*" directory="./" format="tabular" />
            <param name="matrix_h5_cooler" value="" ftype="cool"/>
            <param name="BED" value="hicAggregateContacts/test_regions.bed" ftype="bed"/>
            <param name="numberOfBins" value="30" />
            <param name="range_max" value="900000" />
            <param name="range_min" value="50000" />
            <param name="image_file_format" value="png" />
            <output name="outFileName" value="hicAggregateContacts_results1.png" compare="sim_size" delta='35000'/>
Aggregation of Hi-C contacts

**hicAggregateContacts** allows plotting of aggregated Hi-C sub-matrices of a specified list of positions. Positions of interest can for example be binding sites of a specific protein that were determined by ChIP-seq or genetic elements as transcription start sites of active genes.



This tool must be used on Hi-C matrices corrected by ``hicCorrectMatrix``. One should also consider bigger bins than restriction enzyme resolution bins using ``hicMergeMatrixBins``.


Optional parameters

Optional data output can be selected:

    - **Save values underlying the final matrix:** if this option is given, then the values underlying the final matrix will be saved to tab-delimited tables (one per chromosome) using the indicated prefix, for example If clustering is performed, then the values are saved including the cluster_id a in

    - **Save the position of the contacts:** if this option is given, then the position of the contacts is saved as (chrom1, start1, end1, chrom2, start2, end2) where chrom_n, start_n, end_n correspond to the pair of positions used to compute the submatrix. The data is saved per chromosome and per cluster separately (one file each).

    - **Heatmap file per chromosome:** if given, a heatmap file (per chromosome) is saved. Each row in the heatmap contains the diagonal of each of the submatrices centered on the bed file. This file is useful to get an idea of the values that are used for the aggregate matrix and to determine the fraction of submatrices that are aggregated that may have an enrichment at the center.



**hicAggregateContacts** outputs a plot of aggregated contacts.

Below, you can find an example of an aggregate Hi-C matrix obtained from *Drosophila melanogaster* Hi-C data. The interactions are plotted at binding sites of a protein that were determined by ChIP-seq. We plot sub-matrices of 30 bins (1.5 kb bin size, 45 kb in total). The regions specified in the BED file will be centered between half number of bins and the other half number of bins.The considered range is 300-1000 kb. The range should be adjusted and only contain contacts larger than TAD size to reduce background interactions.

.. image:: $PATH_TO_IMAGES/hicAggregateContacts.png
   :width: 80 %

This example was calculated using mean interactions of an observed vs. expected transformed Hi-C matrix. Additional options for the matrix transformation are total-counts or z-score. Aggregate contacts can be plotted in 2D or 3D.


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

.. _Colormaps:
    <expand macro="citations" />