view hicQuickQC.xml @ 6:9c5078f3926b draft default tip

"planemo upload for repository commit 2a0943e78bdc8ebb13f181399206a9eea37ed78f"
author iuc
date Tue, 16 Mar 2021 15:08:31 +0000
parents 909125ec301f
line wrap: on
line source

<tool id="hicexplorer_hicquickqc" name="@BINARY@" version="@TOOL_VERSION@+galaxy@VERSION_SUFFIX@">
    <description>get a first quality estimate of Hi-C data</description>
        <token name="@BINARY@">hicQuickQC</token>
    <expand macro="requirements" />
    <command detect_errors="exit_code"><![CDATA[

        mkdir ./QCfolder &&
        mkdir $qc.files_path &&

            #for $repeat in $samFiles:
            #end for

            --restrictionCutFile '$restrictionCutFile'
            #if $restrictionSequence:
                --restrictionSequence '$restrictionSequence'
            #end if

            #if $danglingSequence:
                --danglingSequence '$danglingSequence'
            #end if
            --QCfolder ./QCfolder

            --lines $lines

        && mv ./QCfolder/* $qc.files_path/
        && mv $qc.files_path/hicQC.html $qc
        && mv $qc.files_path/*.log raw_qc
    ]]>    </command>
        <!-- can we use multiple="true" 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" />
        <expand macro="restrictionCutFile" />
        <expand macro="restrictionSequence" />
        <expand macro="danglingSequence" />

        <param argument="--lines" optional='true' type="integer" label="Lines to analyze for the QC report" help= "Number of lines to consider for the qc test run." value='1000000' />

        <data name="qc" format="html" label="${} QC on ${on_string}" />
        <data name="raw_qc" from_work_dir='raw_qc' format='txt' label="${} raw QC on ${on_string}" />
        <test expect_num_outputs="2">
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R1_unsorted.sam" />
            <repeat name="samFiles">
                <param name="samFile" value="small_test_R2_unsorted.sam" />
            <param name='restrictionCutFile' value='DpnII_10k.bed' />
            <param name='restrictionSequence' value='GATC' />
            <param name='danglingSequence' value='GATC' />

            <param name="lines" value='1000' />
            <output name="raw_qc" file='hicQuickQC/QC.log' compare='diff' lines_diff='2' />

Quick QC

Get a quick impression on the quality of your Hi-C data. hicQuickQC considers the first n lines of two bam/sam files to get a first estimate of the quality of the data. It is highly recommended to set the restriction enzyme and dangling end parameter to get a good quality report.

The default is to read the first 1,000,000 reads of the mapped bam files to get a quality estimate of the Hi-C data.

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

]]>    </help>
    <expand macro="citations" />