DHSv3.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>3</version>
	<author>
		<name>Karl Nordström, Peter Ebert</name>
		<email>karl.nordstroem@uni-saarland.de, pebert@mpi-inf.mpg.de</email>
	</author>
    <description>
        Process DHSv3 has been created after software updates and to correct the command line call for the MACS peak caller. 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 DNase signal in a
        few selected control regions (for details, contact Nina Gasparoni, UdS Walter). Note that this plot is by no means suited to interpret the data or judge the genome-wide
        quality of the dataset - the plot of the control regions just shows regions with expected high or low signal. The scaling of the data values is done for layout reasons.
    </description>
	<inputs>
		<filetype>
			<identifier>GALvX_DNase</identifier>
			<format>BAM</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
		<filetype>
			<identifier>GALvX_Index</identifier>
			<format>BAI</format>
			<quantity>single</quantity>
			<comment></comment>
		</filetype>
        <filetype>
			<identifier>GALvX_QcSummary</identifier>
			<format>TXT</format>
			<quantity>single</quantity>
			<comment>This file contains QC information collected during the mapping. The median fragment length of the library is extracted from that file.</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>control_regions</identifier>
			<format>BED</format>
			<quantity>single</quantity>
			<comment>Control regions, i.e. regions expected to be open or closed</comment>
		</filetype>
	</references>
	<outputs>
		<filetype>
			<identifier>DEEPID.PROC.DATE.gcbias</identifier>
			<format>SVG</format>
			<quantity>single</quantity>
			<comment>deepTools graphics output</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.gcfreq</identifier>
			<format>tab-separated text file</format>
			<quantity>single</quantity>
			<comment>Required output file, currently not used for any downstream analysis</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.peaks</identifier>
			<format>XLS table</format>
			<quantity>single</quantity>
			<comment>Standard MACS2 output XLS table for broad and narrow marks</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.broadPeak</identifier>
			<format>broadPeak</format>
			<quantity>single</quantity>
			<comment>Standard MACS2 output in ENCODE's broadPeak format for broad marks, this file is usually used for subsequent analyses</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.gappedPeak</identifier>
			<format>gappedPeak</format>
			<quantity>single</quantity>
			<comment>Standard MACS2 output in ENCODE's gappedPeak format for broad marks</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.bamcov</identifier>
			<format>bigwig</format>
			<quantity>single</quantity>
			<comment>Sequencing-depth normalized signal coverage tracks</comment>
		</filetype>
		<filetype>
			<identifier>DEEPID.PROC.DATE.control</identifier>
			<format>SVG</format>
			<quantity>single</quantity>
			<comment>Plot of signal value in a set of control regions</comment>
		</filetype>
	</outputs>
	<software>
		<tool>
			<name>computeGCBias</name>
			<version>1.5.9.1</version>
			<command_line><![CDATA[ computeGCBias -p {deeptools_parallel} --bamfile {GALvX_DNase} --effectiveGenomeSize {genomesize} --genome {reference_genome} --fragmentLength {DNase_fraglen} --sampleSize 50000000 --GCbiasFrequenciesFile {DEEPID.PROC.DATE.gcfreq} --biasPlot {DEEPID.PROC.DATE.gcbias} --plotFileFormat svg ]]></command_line>
			<loop>no looping</loop>
			<comment></comment>
		</tool>
		<tool>
			<name>MACS2</name>
			<version>2.1.0.20140616</version>
			<command_line><![CDATA[ macs2 callpeak -t {GALvX_DNase} -f BAM --gsize {genomesize} --keep-dup all --name {DNase_name_prefix} --nomodel --shift -100 --extsize 200 --qvalue 0.05 ]]></command_line>
			<loop>no looping</loop>
			<comment></comment>
		</tool>
		<tool>
			<name>bamCoverage</name>
			<version>1.5.9.1</version>
			<command_line><![CDATA[ bamCoverage -p {deeptools_parallel} --bam {GALvX_DNase} --outFileName {DEEPID.PROC.DATE.bamcov} --outFileFormat bigwig --normalizeTo1x {genomesize} --fragmentLength {DNase_fraglen} ]]></command_line>
			<loop>no looping</loop>
			<comment>report read coverage normalized to 1x sequencing depth</comment>
		</tool>
		<tool>
			<name>potty_plotty.py</name>
			<version>0.2</version>
			<command_line><![CDATA[ potty_plotty.py --fg-label {DNase_label} --fg-color {DNase_color} --fg-values {DEEPID.PROC.DATE.bamcov} --plot-regions {control_regions} --binsize 50 --title DEEPID --outfile {DEEPID.PROC.DATE.control} ]]></command_line>
			<loop>no looping</loop>
			<comment>the binsize is selected according to the default value for deepTools (ie 50bp)</comment>
		</tool>
	</software>
</process>