annotate computeMatrix.xml @ 30:a60c359ec43c draft default tip

planemo upload for repository https://github.com/deeptools/deepTools/tree/master/galaxy/wrapper/ commit 4a4029b5c2e725b7cebc27217b76d23910508412

<tool id="deeptools_compute_matrix" name="computeMatrix" version="@TOOL_VERSION@+galaxy0" profile="@GALAXY_VERSION@">
    <description>prepares data for plotting a heatmap or a profile of given regions</description>
    <macros>
        <token name="@BINARY@">computeMatrix</token>
        <import>deepTools_macros.xml</import>
    </macros>
    <expand macro="requirements" />
    <command>
<![CDATA[
        @multiple_input_bigwigs@

        #set bed_files=[]
        #for $counter, $rf, in enumerate($regionsFiles):
            #set identifier = re.sub('[^\s\w\-]', '_', str($rf.regionsFile.element_identifier))
            ln -f -s '${rf.regionsFile}' '${identifier}_${counter}.bed' &&
            #silent $bed_files.append('%s_%s.bed' % ($identifier, $counter))
        #end for

        @BINARY@

            $mode.mode_select
            --regionsFileName '#echo "' '".join($bed_files)#'

            --scoreFileName #echo ' '.join($files)#

            --outFileName '$outFileName'
            --samplesLabel #echo ' '.join($labels)#

            @THREADS@

            #if $output.showOutputSettings == "yes"
                #if $output.saveMatrix:
                --outFileNameMatrix '$outFileNameMatrix'
                #end if

                #if $output.saveSortedRegions:
                    --outFileSortedRegions '$outFileSortedRegions'
                #end if
            #end if

            #if $mode.mode_select == "reference-point":
                --referencePoint $mode.referencePoint
                $mode.nanAfterEnd
                --beforeRegionStartLength $mode.beforeRegionStartLength
                --afterRegionStartLength $mode.afterRegionStartLength
            #else
                --regionBodyLength $mode.regionBodyLength
                #if $mode.regionStartLength.regionStartLength_select == "yes":
                    --beforeRegionStartLength $mode.regionStartLength.beforeRegionStartLength
                    --afterRegionStartLength $mode.regionStartLength.afterRegionStartLength

                    --unscaled5prime $mode.regionStartLength.unscaled5prime
                    --unscaled3prime $mode.regionStartLength.unscaled3prime

                #end if

            #end if

            #if $advancedOpt.showAdvancedOpt == "yes":
                --sortRegions '$advancedOpt.sortRegions'
                --sortUsing '$advancedOpt.sortUsing'
                --averageTypeBins '$advancedOpt.averageTypeBins'
                $advancedOpt.skipZeros
                $advancedOpt.missingDataAsZero
                --binSize $advancedOpt.binSize

                #if $advancedOpt.minThreshold is not None and str($advancedOpt.minThreshold) != '':
                    --minThreshold $advancedOpt.minThreshold
                #end if
                #if $advancedOpt.maxThreshold is not None and str($advancedOpt.maxThreshold) != '':
                    --maxThreshold $advancedOpt.maxThreshold
                #end if
                #if $advancedOpt.scale is not None and str($advancedOpt.scale) != '':
                    --scale $advancedOpt.scale
                #end if

                @ADVANCED_OPTS_GTF@

                @blacklist@

            #end if
]]>
    </command>
    <inputs>

        <repeat name="regionsFiles" title="Select regions" min="1">
            <param name="regionsFile" format="bed,gtf" type="data" label="Regions to plot"
                help="File, in BED format, containing the regions to plot."/>
        </repeat>

        <expand macro="multiple_input_bigwigs" MIN="1" LABEL="Score file" TITLE="Score files"/>
        <expand macro="custom_sample_labels" />

        <conditional name="mode" >
            <param name="mode_select" type="select"
                label="computeMatrix has two main output options"
                help="In the scale-regions mode, all regions in the BED file are
                stretched or shrunken to the same length (in bases) that is indicated
                by the user. Reference-point refers to a position within the BED
                regions (start or end of each region). In the reference-point mode only
                those genomic positions before (upstream) and/or after (downstream)
                the reference point will be considered.">
                <option value="scale-regions" selected="true">scale-regions</option>
                <option value="reference-point">reference-point</option>
            </param>

            <when value="scale-regions" >
                <param argument="--regionBodyLength" type="integer" value="500"
                    label="Distance in bases to which all regions are going to be fit" help=""/>
                <conditional name="regionStartLength">
                    <param name="regionStartLength_select" type="select" label="Set distance up- and downstream of the given regions">
                        <option value="no" selected="true">no</option>
                        <option value="yes">yes</option>
                    </param>
                    <when value="no" />
                    <when value="yes">
                        <param argument="--beforeRegionStartLength" type="integer" value="1000" min="1"
                            label="Distance upstream of the region start position"
                            help="If the regions are genes, this would be the
                            distance upstream of the transcription start site."/>
                        <param argument="--afterRegionStartLength" type="integer" value="1000" min="1"
                            label="Distance downstream of the region end position"
                            help="If the regions are genes, this would be the
                            distance downstream of the transcription end site."/>
                        <param argument="--unscaled5prime" type="integer" min="0" value="0"
                            label="Number of bases within the gene body at the 5-prime end to exclude from scaling."
                            help="By default, each region is scaled to a given length (see the --regionBodyLength
                             option). In some cases it is useful to look at unscaled signals around region boundaries, so this
                             setting specifies the number of unscaled bases on the 5-prime end of each boundary." />
                        <param argument="--unscaled3prime" type="integer" min="0" value="0"
                            label="Number of bases within the gene body at the 3-prime end to exclude from scaling."
                            help="As with --unscaled5prime, but for the 3-prime end." />
                    </when>
                </conditional>
            </when>
            <when value="reference-point">
                <param name="referencePoint" type="select" label="The reference point for the plotting">
                    <option value="TSS" selected="true">beginning of region (e.g. TSS)</option>
                    <option	 value="TES">end of region (e.g. TES)</option>
                    <option value="center">center of region</option>
                </param>
                <param name="nanAfterEnd" type="boolean" truevalue="--nanAfterEnd" falsevalue=""
                    label="Discard any values after the region end"
                    help="This is useful to visualize the region end when not using the
                    scale-regions mode and when the reference-point is set to the TSS. (--nanAfterEnd)"/>
                <param name="beforeRegionStartLength" type="integer" value="1000" min="1"
                    label="Distance upstream of the start site of the regions defined in the region file"
                    help="If the regions are genes, this would be the distance upstream of the transcription start site. (--beforeRegionStartLength)"/>
                <param name="afterRegionStartLength" type="integer" value="1000" min="1"
                    label="Distance downstream of the end site of the given regions"
                    help="If the regions are genes, this would be the distance downstream of the transcription end site. (--afterRegionStartLength)"/>
            </when>
        </conditional>

        <expand macro="input_graphic_output_settings">
            <expand macro="input_save_matrix_values" />
        </expand>

        <conditional name="advancedOpt" >
            <param name="showAdvancedOpt" type="select" label="Show advanced options" >
                <option value="no" selected="true">no</option>
                <option value="yes">yes</option>
            </param>
            <when value="no" />
            <when value="yes">
                <param name="binSize" type="integer" value="50" min="1"
                    label="Length, in bases, of non-overlapping bins used for averaging the score over the regions length"
                    help="(--binSize)"/>

                <expand macro="sortRegionsComputeMatrix" />
                <expand macro="sortUsing" />

                <param name="averageTypeBins" type="select"
                    label="Define the type of statistic that should be displayed."
                    help="The value is computed for each bin. (--averageTypeBins)">
                    <option value="mean" selected="true">mean</option>
                    <option value="median">median</option>
                    <option value="min">min</option>
                    <option value="max">max</option>
                    <option value="sum">sum</option>
                    <option value="std">std</option>
                </param>

                <param name="missingDataAsZero" type="boolean" truevalue="--missingDataAsZero" falsevalue="" checked="False"
                    label="Convert missing values to 0?"
                    help="If set to 'yes', missing values (NAs) are converted
                     to 0. If you want to use clustering with plotHeatmap
                     or plotProfile, set this to 'yes'.
                          The default is to ignore missing values, which will be
                          depicted as black areas once a heatmap is created.
                           (--missingDataAsZero)" />

                <expand macro="skipZeros" />

                <param name="minThreshold" type="float" optional="True"
                    label="Minimum threshold"
                    help="Any region containing a value that is equal or less than this numeric
                    value will be skipped. This is useful to skip, for example, genes where the
                    read count is zero for any of the bins which could be the result of
                    unmappable areas and can bias the overall results. (--minThreshold)"/>
                <param name="maxThreshold" type="float" optional="True"
                    label="Maximum threshold"
                    help="Any region containing a value that is equal or higher that this
                    numeric value will be skipped. The max threshold is useful to skip those
                    few regions with very high read counts (e.g. major satellites) that may
                    bias the average values. (--maxThreshold)"/>
                <param name="scale" type="float" optional="True" label="Scaling factor"
                    help="If set, all values are multiplied by this number. (--scale)"/>

                <expand macro="gtf_options" />

                <expand macro="blacklist" />
            </when>
        </conditional>
    </inputs>
    <outputs>
        <data format="deeptools_compute_matrix_archive" name="outFileName" label="${tool.name} on ${on_string}: Matrix" />
        <expand macro="output_graphic_outputs" />
        <expand macro="output_save_matrix_values" />
    </outputs>
    <tests>
        <test>
            <param name="regionsFile" value="computeMatrix1.bed" ftype="bed" />
            <param name="bigwigfiles" value="bamCoverage_result4.bw" ftype="bigwig" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="mode_select" value="reference-point" />
            <param name="binSize" value="10" />
            <param name="sortUsing" value="sum" />
            <param name="averageTypeBins" value="sum" />
            <param name="beforeRegionStartLength" value="10" />
            <param name="afterRegionStartLength" value="10" />
            <output name="outFileName" file="computeMatrix_result1.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
        </test>
        <test>
            <param name="regionsFile" value="computeMatrix2.bed" ftype="bed" />
            <param name="bigwigfiles" value="computeMatrix2.bw" ftype="bigwig" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="mode_select" value="reference-point" />
            <param name="binSize" value="10" />
            <param name="beforeRegionStartLength" value="10" />
            <param name="afterRegionStartLength" value="10" />
            <output name="outFileName" file="computeMatrix_result2.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
        </test>
        <test>
            <param name="regionsFile" value="computeMatrix2.bed" ftype="bed" />
            <param name="bigwigfiles" value="computeMatrix2.bw" ftype="bigwig" />
            <param name="showAdvancedOpt" value="yes" />
            <param name="mode_select" value="scale-regions" />
            <param name="endLabel" value="END" />
            <param name="regionStartLength" value="yes" />
            <output name="outFileName" file="computeMatrix_result3.gz" ftype="deeptools_compute_matrix_archive" compare="sim_size" />
        </test>
    </tests>
  <help>
<![CDATA[

What it does
----------------

This tool prepares an intermediate file (a gzipped table of values)
that contains scores associated with genomic regions.
The regions can either be scaled to the same size (using the ``scale-regions`` mode) or you can choose the start, end, or center of each region as the focus point for the score calculations.
For more details, check out the explanation `here <https://deeptools.readthedocs.io/en/latest/content/tools/computeMatrix.html#details>`_.

The intermediate file produced by ``computeMatrix`` is meant to be used with ``plotHeatmap`` and ``plotProfile``.
See the descriptions of ``plotHeatmap`` and ``plotProfile`` for example plots.

.. image:: $PATH_TO_IMAGES/computeMatrix_overview.png
   :alt: Relationship between computeMatrix, heatmapper and profiler
   :width: 600
   :height: 418

=======

Usage hints
-------------

The supplied genomic regions can really be anything - genes, parts of genes, ChIP-seq peaks, favorite genome regions... as long as you provide a proper file
in BED or INTERVAL format. If you would like to compare different groups of regions (e.g., genes from chromosome 2 and 3), you can supply more than 1 regions file, one for each group by selecting "Insert Select regions".

.. image:: $PATH_TO_IMAGES/computeMatrix_selectRegions.png
   :width: 600
   :height: 150

You can select as many score (bigWig) files as you like. Simply use the Shift and/or Command key while clicking on the files of interest.

.. image:: $PATH_TO_IMAGES/computeMatrix_selectScores.png
   :width: 600
   :height: 136

The multitude of parameters can seem daunting at first - here are the options that we tend to tune most often:

* ``bin Size`` -- The default value works well most of the time, but if you want to have a more finely grained image, decrease the default value (but not smaller than your bigWig file(s)' bin size). If you want to reduce the computation time, increase it.
* ``Skip zeros`` -- useful to avoid completely blank lines in the heatmap.
* ``Convert missing values to 0?`` -- If you want to identify clusters of similar regions in an unsupervised fashion using ``plotHeatmap`` and/or ``plotProfile``, you should definitely set this to 'yes'.


Output files
---------------

The default output is a **gzipped table of values** that is used by both ``plotHeatmap`` and ``plotProfile``.

The optional output files include a) the **regions after sorting and filtering (if selected)** as they were used to calculate the values for the plotting, and b) the uncompressed table that **underlies the heatmap**.

**TIP:** ``computeMatrix`` can also be used to filter and sort regions according to their score by making use of the "advanced output settings".

.. image:: $PATH_TO_IMAGES/computeMatrix_advancedOutput.png
   :width: 600
   :height: 189

.. image:: $PATH_TO_IMAGES/computeMatrix_output.png
   :width: 600
   :height: 297

Note that these advanced output options are available for ``plotHeatmap`` and ``plotProfile``, too.

See the following table for the optional output options:

+-----------------------------------+--------------------+-----------------+-----------------+
|  **optional output type**         |  **computeMatrix** | **plotHeatmap** | **plotProfile** |
+-----------------------------------+--------------------+-----------------+-----------------+
| values underlying the heatmap     |  yes               | yes             | no              |
+-----------------------------------+--------------------+-----------------+-----------------+
| values underlying the profile     | no                 | no              | yes             |
+-----------------------------------+--------------------+-----------------+-----------------+
| sorted and/or filtered regions    | yes                | yes             | yes             |
+-----------------------------------+--------------------+-----------------+-----------------+

**More examples** can be found in our `Gallery <http://deeptools.readthedocs.org/en/latest/content/example_gallery.html#normalized-chip-seq-signals-and-peak-regions>`_.

-----

@REFERENCES@
]]>
    </help>
    <expand macro="citations" />
</tool>