DHSv2.xml

<?xml version="1.0"?>
<?xml-stylesheet type="text/css" href="http://deep.mpi-inf.mpg.de/DAC/files/style/deep_process_style.css"?>
<process>
    <name>DHS</name>
	<version>2</version>
	<author>
		<name>Karl Nordström, Peter Ebert</name>
		<email>karl.nordstroem@uni-saarland.de, pebert@mpi-inf.mpg.de</email>
	</author>
    <description>
		Process DHSv2 has been created to correct a couple of mistakes in the v1 process description and - more importantly - since new software versions have been installed on the DEEP cluster at DAC/MPI-Inf.
        This process takes as input aligned reads coming from the DCC/DKFZ and creates a coverage signal track as well as peak files for a DNase BAM file.
        The last step of this process plots the coverage of the histone signal (and, if available, of the input control) in a few selected control regions.
        Note that these plots are by no means suited to interpret the data or judge the quality of the entire dataset - the plot of the control regions just shows regions with expected high or low signal compared to the input;
        the scaling of the values is performed for layout reasons and independently for each region, i.e. plots of different regions cannot be compared directly.
	</description>
	<inputs>
		<filetype>
			<identifier>ALNvX_dnase.bam</identifier>
			<format></format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>ALNvX.bai</identifier>
			<format></format>
			<quantity>single</quantity>
			<comment>Index files are renamed internally to .bam.bai since deepTools is expecting index naming like this</comment>
		</filetype>
	</inputs>
	<references>
		<filetype>
			<identifier>reference_genome</identifier>
			<format>2bit</format>
			<quantity>single</quantity>
			<comment>The reference genome file; see DCC/download/results/references/genomes</comment>
		</filetype>
		<filetype>
			<identifier>plot_regions</identifier>
			<format>BED</format>
			<quantity>single</quantity>
			<comment>Control regions</comment>
		</filetype>
	</references>
	<outputs>
		<filetype>
			<identifier>samplesID.PROCESS.DATE.fgprplot</identifier>
			<format>deepTools graphics PNG</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>sampleID.PROCESS.DATE.gcbplot</identifier>
			<format>deepTools graphics PNG</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>sampleID.PROCESS.DATE.gcbfreq</identifier>
			<format>tab-separated text file</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>sampleID.PROCESS.DATE.bamcov.seqDepthNorm</identifier>
			<format>bigwig</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>sampleID.PROCESS.DATE.ctrlreg</identifier>
			<format>graphics PNG</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
	</outputs>
	<software>
		<tool>
			<name>bamFingerprint (deepTools)</name>
			<version>1.5.8.1</version>
			<command_line><![CDATA[ bamFingerprint -p {numproc} --bamfiles {ALNvX_dnase.bam} --plotFile {samplesID.PROCESS.DATE.fgpplot} --labels {labels} --fragmentLength {dnase_median_fraglen} --numberOfSamples 500000 ]]></command_line>
            <loop>no looping</loop>
			<comment></comment>
		</tool>
		<tool>
			<name>computeGCBias (deepTools)</name>
			<version>1.5.8.1</version>
			<command_line><![CDATA[ computeGCBias -p {numproc} --bamfile {ALNvX_dnase.bam} --effectiveGenomeSize {genomesize} --genome {reference_genome} --fragmentLength {dnase_median_fraglen} --sampleSize 50000000 --GCbiasFrequenciesFile {sampleID.PROCESS.DATE.gcbfreq} --biasPlot {sampleID.PROCESS.DATE.gcbplot} ]]></command_line>
            <loop>no looping</loop>
			<comment></comment>
		</tool>
		<tool>
			<name>MACS2</name>
			<version>macs2 2.1.0.20140616</version>
			<command_line><![CDATA[ macs2 callpeak -t {ALNvX_dnase.bam} -f BAM --broad --gsize {genomesize} --keep-dup all --name {dnase_name_prefix} --nomodel --extsize {dnase_median_fraglen} --qvalue 0.05 {broad} ]]></command_line>
            <loop>no looping</loop>
			<comment>we consider DNase to give broad enriched regions, thus parameter "--broad" by default; default q-value cutoff of 0.05 is recommended by MACS2 author for broad marks</comment>
		</tool>
		<tool>
			<name>bamCoverage (deepTools)</name>
			<version>1.5.8.1</version>
			<command_line><![CDATA[ bamCoverage -p {numproc} --bam {ALNvX_dnase.bam} --outFileName {sampleID.PROCESS.DATE.bamcov.seqDepthNorm} --outFileFormat bigwig --normalizeTo1x {genomesize} --fragmentLength {dnase_median_fraglen} ]]></command_line>
            <loop>no looping</loop>
			<comment>report read coverage normalized to 1x sequencing depth</comment>
		</tool>
		<tool>
			<name>signal_plotter.py</name>
			<version>0.1</version>
			<command_line><![CDATA[ signal_plotter.py --signal {sampleID_histone.PROCESS.DATE.bamcov.seqDepthNorm} --regions {plot_regions} --outfile {sampleID.PROCESS.DATE.ctrlreg} ]]></command_line>
            <loop>no looping</loop>
			<comment></comment>
		</tool>
	</software>
</process>