comparison hicBuildMatrixMicroC.xml @ 0:0c22e9361298 draft default tip

planemo upload for repository https://github.com/galaxyproject/tools-iuc/tree/master/tools/hicexplorer commit 63179f3d35e5dec09cdd01c07c6a4e8af3da777d

0:0c22e9361298

<tool id="hicexplorer_hicbuildmatrixmicroc" name="@BINARY@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@" profile="@PROFILE@">
    <description>create a contact matrix</description>
    <macros>
        <token name="@BINARY@">hicBuildMatrixMicroC</token>
        <import>macros.xml</import>
    </macros>
    <expand macro="requirements"/>
    <command detect_errors="exit_code"><![CDATA[

        mkdir ./QCfolder &&
        mkdir '$qc.files_path' &&
        @BINARY@
            --samFiles
            #for $repeat in $samFiles:
                '${repeat.samFile}'
            #end for

            #if $maxLibraryInsertSize:
                --maxLibraryInsertSize $maxLibraryInsertSize
            #end if

            #if $binSizes:
                --binSize
                #for $repeat in $binSizes
                    '${repeat.binSize}'
                #end for
            #end if

            #if $chromosomeSizes:
                --chromosomeSizes '$chromosomeSizes'
            #end if
            #if $dbKey:
                --genomeAssembly '$dbKey'
            #else
                --genomeAssembly '$samFiles[0].samFile.metadata.dbkey'
            #end if

            #if $region:
                --region '$region'
            #end if

            --outFileName 'matrix.$outputFormat'

            #if $outBam:
                $outBam ./unsorted.bam
            #end if

            $keepSelfCircles
            $skipDuplicationCheck

            #if $minMappingQuality and $minMappingQuality is not None:
                --minMappingQuality $minMappingQuality
            #end if

            --threads @THREADS@

            --QCfolder ./QCfolder
        &&
        mv ./QCfolder/* $qc.files_path/
        &&
        mv '$qc.files_path/hicQC.html' '$qc'
        && mv "$qc.files_path"/*.log raw_qc
        && mv matrix.$outputFormat matrix
        #if $outBam:
            && samtools sort -@ @THREADS@ -T "\${TMPDIR:-.}" ./unsorted.bam -o sorted.bam
        #end if
]]>
    </command>
    <inputs>
        <!-- can we use multiple=True here with min="2" and max="2" ? -->
        <repeat max="2" min="2" name="samFiles" title="Sam/Bam files to process (forward/reverse)" help="Please use the special BAM datatype: qname_input_sorted.bam and use for 'bowtie2' the '--reorder' option to create a BAM file.">
            <param name="samFile" type="data" format="sam,qname_input_sorted.bam">
            </param>
        </repeat>

        <param argument="--maxLibraryInsertSize" type="integer" optional="true" value="" label="Maximum library insert size defines different cut offs based on the maximum expected library size" help="*This is not the average fragment size* but the higher end of the fragment size distribution (obtained using for example Fragment Analyzer)
                        which usually is between 800 to 1500 bp. If this value if not known use the default of 1000. The insert value is used to decide if two mates
                        belong to the same fragment (by checking if they are within this max insert size) and to decide if a mate
                        is too far away from the nearest restriction site." />

        <repeat name="binSizes" title="Bin size in bp" min="1" help="If used, the restriction cut places (if given) are used to only consider reads that are in the vicinity of the resctriction sites.
                Otherwise all reads in the interval are considered. Use multiple ones to create a mcool file.">
            <param argument="--binSize" type="integer" optional="true" value="" label="Bin size in bp" />
        </repeat>

        <expand macro="region" />
        <param argument="--keepSelfCircles" type="boolean" truevalue="--keepSelfCircles" falsevalue="" label="Keep self circles" help="If set, outward facing reads without any restriction fragment (self circles) are kept. They will be counted and shown in the QC plots." />
        <expand macro="minMappingQuality" />
        <param argument="--skipDuplicationCheck" type="boolean" truevalue="--skipDuplicationCheck" falsevalue="" label="Skip duplication check" help="Identification of duplicated read pairs is memory consuming. Thus, in case of memory errors this check can be skipped." />
        <param argument="--chromosomeSizes" type="data" format="tabular" optional="true" label="Chromosome sizes for your genome" help="File with the chromosome sizes for your genome. A tab-delimited two column layout 'chr_name size' is expected
                    Usually the sizes can be determined from the SAM/BAM input files, however,
                    for cHi-C or scHi-C it can be that at the start or end no data is present.
                    Please consider that this option causes that only reads are considered which are on the listed chromosomes.
                    Use this option to guarantee fixed sizes. An example file is available via UCSC:
                    http://hgdownload.soe.ucsc.edu/goldenPath/dm3/bigZips/dm3.chrom.sizes" />
        <param name="dbKey" type="text" optional="true" label="Use this dbkey for your history genome"
        help="You can set the reference genome in your history as metadata. In case you have not you can specify it here." />

        <param argument="--outBam" type="boolean" truevalue="--outBam" falsevalue="" checked="false" label="Save valid Hi-C reads in BAM file" help="A bam
                    file containing all valid Hi-C reads can be created
                    using this option. This bam file could be useful to
                    inspect the distribution of valid Hi-C reads pairs or
                    for other downstream analyses, but is not used by any
                    HiCExplorer tool. Computation will be significantly
                    longer if this option is set." />

        <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="outfileBam" from_work_dir="sorted.bam" format="bam" label="${tool.name} BAM file on ${on_string}">
            <filter>outBam</filter>
        </data>
        <data name="outFileName" from_work_dir="matrix" format="h5" label="${tool.name} MATRIX on ${on_string}">
            <change_format>
                <when input="outputFormat" value="cool" format="cool" />
            </change_format>
        </data>
        <data name="qc" format="html" label="${tool.name} QC on ${on_string}" />
        <data name="raw_qc" from_work_dir="raw_qc" format="txt" label="${tool.name} raw QC on ${on_string}" />
    </outputs>
    <tests>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <param name="outputFormat" value="h5" />
            <repeat name="binSizes">
                <param name="binSize" value="5000" />
            </repeat>
            <param name="outBam" value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted_microc.bam" compare="diff" lines_diff="2" ftype="bam" />
            <output name="outFileName" ftype="h5">
                <assert_contents>
                    <has_h5_keys keys="intervals,matrix" />
                </assert_contents>
            </output>
            <output name="raw_qc" file="raw_qc_report_micro-c" compare="diff" lines_diff="2" />
        </test>
        <test expect_num_outputs="4">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" dbkey="hg38" />
            </repeat>
            <repeat name="binSizes">
                <param name="binSize" value="5000" />
            </repeat>
            <param name="outputFormat" value="cool" />
            <param name="outBam" value="True" />
            <output name="outfileBam" file="small_test_matrix_result_sorted_microc.bam" compare="diff" lines_diff="2" ftype="bam" />
            <output name="outFileName" ftype="cool">
                <assert_contents>
                    <has_h5_keys keys="bins,chroms,indexes,pixels" />
                </assert_contents>
            </output>
            <output name="raw_qc" file="raw_qc_report_micro-c" compare="diff" lines_diff="2" />
        </test>
    </tests>
    <help><![CDATA[

Creation of the contact matrix
===============================


**hicBuildMatrixMicroC** generates a contact matrix from Micro-C read pairs, using paired-end Hi-C reads mapped to a reference genome. This process requires two SAM or BAM files: one for the first mate and one for the second mate of the paired-end reads. These files must be unaligned by position (i.e., not sorted). Unlike traditional Hi-C data, where restriction enzyme cut sites determine resolution, Micro-C does not rely on such sites. Instead, the contact matrix is created using a fixed bin size (e.g., 10,000 bp). 

Additionally, **hicBuildMatrixMicroC** produces a quality control report to evaluate the quality of the Hi-C reads, aiding in determining the success of both the experimental protocol and sequencing process.


_________________


Usage
-----


This tool is designed to work with paired SAM/BAM files generated by alignment software supporting local alignment, such as Bowtie2, using the `--local` alignment option for paired-end reads. Both files should represent properly mapped reads.

_________________


Output
------

**hicBuildMatrixMicroC** generates the following outputs:

- **Contact Matrix**: A matrix compatible with HiCExplorer for downstream analyses.
- **Accepted Alignments BAM File**: This file includes valid Hi-C read pairs. While not directly used by HiCExplorer, it is valuable for inspecting the distribution of valid reads, such as around restriction enzyme sites, or for other analyses.
- **Quality Control Report**: This report provides an evaluation of the Hi-C data, helping to determine whether the library preparation and experimental workflow were successful.


Example plot
++++++++++++

.. image:: hicPlotMatrix.png
   :width: 50%

*Contact matrix of *Drosophila melanogaster* embryos built using **hicBuildMatrix**. The example shows Micro-C data, visualized with `hicPlotMatrix`. Bins were merged to a 25 kb resolution using `hicMergeMatrixBins` before plotting.*




Quality report
++++++++++++++

A detailed quality control report accompanies the contact matrix. This report is similar to the one generated by **hicBuildMatrix**, but excludes information specific to restriction cut sites, such as dangling ends and self-circles, as these features are not applicable to Micro-C data.


_________________

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

.. _readthedocs.io: http://hicexplorer.readthedocs.io/en/latest/index.html
]]>    </help>
    <expand macro="citations" />
</tool>