From c96feefca6932ea266166c477fa8f9160281e884 Mon Sep 17 00:00:00 2001
From: Peter Ebert <pebert@mpi-inf.mpg.de>
Date: Fri, 15 Sep 2017 19:26:16 +0200
Subject: [PATCH] ENH: final version of CHPv5, validates against XSD and
 together with AMD of test sample

---
 docs/quantification/chip-seq/CHPv5.xml | 117 +++++++++++++------------
 1 file changed, 61 insertions(+), 56 deletions(-)

diff --git a/docs/quantification/chip-seq/CHPv5.xml b/docs/quantification/chip-seq/CHPv5.xml
index 8f92919..942f1a2 100644
--- a/docs/quantification/chip-seq/CHPv5.xml
+++ b/docs/quantification/chip-seq/CHPv5.xml
@@ -79,27 +79,29 @@
 			</comment>
 		</filetype>
         <filetype>
-			<identifier>QcSummary</identifier>
-			<format>JSON</format>
+			<identifier>GALvX_QCSummary</identifier>
+			<format>JSON / txt</format>
 			<quantity>collection</quantity>
 			<comment>
 				The median insert size (field: insertSizeMedian) is extracted from the QC summary file.
+				Note that for compatibility with previous alignment processes, the QC summary files
+				may also have the old tabular / text-based format (field: PE_insertsize (mapq&gt;0))
 			</comment>
 		</filetype>
 	</inputs>
 	<references>
-		<filetype>
-			<identifier>blacklist_regions</identifier>
-			<format>BED</format>
-			<quantity>single</quantity>
-			<comment>Blacklist region</comment>
-		</filetype>
 		<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>blacklist_regions</identifier>
+			<format>BED</format>
+			<quantity>single</quantity>
+			<comment>Blacklist region</comment>
+		</filetype>
 		<filetype>
 			<identifier>chromosome_sizes</identifier>
 			<format>TSV</format>
@@ -107,7 +109,7 @@
 			<comment>2-column, tab-separated table of chromosome sizes for reference genome</comment>
 		</filetype>
 		<filetype>
-			<identifier>autosomal_regions</identifier>
+			<identifier>autosome_regions</identifier>
 			<format>BED</format>
 			<quantity>single</quantity>
 			<comment>A file listing all autosomes as BED regions for filtering</comment>
@@ -115,13 +117,13 @@
 	</references>
 	<outputs>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.raw.bamcov</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.raw.bamcov</identifier>
 			<format>bigwig</format>
 			<quantity>collection</quantity>
 			<comment>Signal coverage track generated from raw BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.filt.bamcov</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.filt.bamcov</identifier>
 			<format>bigwig</format>
 			<quantity>collection</quantity>
 			<comment>
@@ -129,92 +131,91 @@
 			</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.ses-fc</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.ses.log2-Input</identifier>
 			<format>bigwig</format>
 			<quantity>collection</quantity>
-			<comment>SES normalized fold-change signal</comment>
+			<comment>SES normalized signal-over-Input track</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.cnt-fc</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.cnt.log2-Input</identifier>
 			<format>bigwig</format>
 			<quantity>collection</quantity>
-			<comment>Read-count normalized fold-change signal</comment>
+			<comment>Read-count normalized signal-over-Input track</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.gcfreq</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.gcbias</identifier>
 			<format>svg</format>
 			<quantity>collection</quantity>
 			<comment>GC bias plot based on raw BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.gcfreq</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.gcfreq</identifier>
 			<format>txt</format>
 			<quantity>collection</quantity>
 			<comment>Obs./exp. GC read frequencies based on raw BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.hhmm.emfit</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.hhmm.emfit</identifier>
 			<format>PDF</format>
 			<quantity>collection</quantity>
 			<comment>histoneHMM output visualizing the EM fit. Check this before using the histoneHMM output</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.hhmm.out</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.hhmm.out</identifier>
 			<format>zip</format>
 			<quantity>collection</quantity>
 			<comment>Zip archive containing other histoneHMM output files (raw data files not needed by most users)</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.macs.out</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.macs.out</identifier>
 			<format>zip</format>
 			<quantity>collection</quantity>
 			<comment>Zip archive containing other MACS output files (raw data files not needed by most users)</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.hhmm.broad</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.hhmm.broad</identifier>
 			<format>BED / broadPeak</format>
 			<quantity>collection</quantity>
 			<comment>Histone and Input enriched regions called by histoneHMM</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.macs.broad</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.macs.broad</identifier>
 			<format>BED / broadPeak</format>
 			<quantity>collection</quantity>
 			<comment>Histone enriched regions called by MACS</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.macs.narrow</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.macs.narrow</identifier>
 			<format>BED / narrowPeak</format>
 			<quantity>collection</quantity>
 			<comment>Histone enriched regions called by MACS</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.fgpr</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.fgpr</identifier>
 			<format>SVG</format>
 			<quantity>single</quantity>
 			<comment>Fingerprint plots based on raw BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.qm-fgpr</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.qm-fgpr</identifier>
 			<format>txt</format>
 			<quantity>single</quantity>
 			<comment>Fingerprint quality metrics based on raw BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.counts-fgpr</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.counts-fgpr</identifier>
 			<format>tsv</format>
 			<quantity>single</quantity>
 			<comment>Fingerprint raw counts based on raw BAM files</comment>
 		</filetype>
-
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.auto.counts-summ</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.auto.counts-summ</identifier>
 			<format>tsv</format>
 			<quantity>single</quantity>
 			<comment>multiBamSummary raw counts based on filtered and autosome-restricted BAM files</comment>
 		</filetype>
 		<filetype>
-			<identifier>DEEPID.PROC.DATE.auto.summ</identifier>
+			<identifier>DEEPID.PROC.DATE.ASSM.auto.summ</identifier>
 			<format>npz</format>
 			<quantity>single</quantity>
 			<comment>
@@ -222,16 +223,26 @@
 				The format is a numpy compatible binary file.
 			</comment>
 		</filetype>
-
+		<filetype>
+			<identifier>DEEPID.PROC.DATE.ASSM.bamcorr</identifier>
+			<format>SVG</format>
+			<quantity>collection</quantity>
+			<comment>Correlation heatmaps using Pearson and Spearman correlation measure</comment>
+		</filetype>
+		<filetype>
+			<identifier>DEEPID.PROC.DATE.ASSM.corrmat</identifier>
+			<format>tsv</format>
+			<quantity>collection</quantity>
+			<comment>Raw correlation matrices</comment>
+		</filetype>
 	</outputs>
 	<software>
-
 		<tool>
 			<name>bamCoverage</name>
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					bamCoverage -p {deeptools_parallel} --binSize 25 --bam {GALvX_*} --outFileName {DEEPID.PROC.DATE.bamcov}
+					bamCoverage -p {deeptools_parallel} --binSize 25 --bam {GALvX_*} --outFileName {DEEPID.PROC.DATE.ASSM.raw.bamcov}
 					--outFileFormat bigwig --normalizeTo1x {genomesize}
 				]]>
 			</command_line>
@@ -245,7 +256,7 @@
 				<![CDATA[
 					computeGCBias -p {deeptools_parallel} --bamfile {GALvX_*} --effectiveGenomeSize {genomesize}
 					--genome {reference_genome} --sampleSize 50000000 --fragmentLength {*_fraglen}
-					--GCbiasFrequenciesFile {DEEPID.PROC.DATE.gcfreq} --biasPlot {DEEPID.PROC.DATE.gcbias} --plotFileFormat svg
+					--GCbiasFrequenciesFile {DEEPID.PROC.DATE.ASSM.gcfreq} --biasPlot {DEEPID.PROC.DATE.ASSM.gcbias} --plotFileFormat svg
 				]]>
 			</command_line>
 			<loop>GALvX_Histone, GALvX_Input</loop>
@@ -257,7 +268,7 @@
 			<command_line>
 				<![CDATA[
 					bamCompare -p {deeptools_parallel} --bamfile1 {GALvX_Histone} --bamfile2 {GALvX_Input}
-					--outFileName {DEEPID.PROC.DATE.bamcomp} --outFileFormat bigwig --scaleFactorsMethod {*_scaling}
+					--outFileName {DEEPID.PROC.DATE.ASSM.*.log2-Input} --outFileFormat bigwig --scaleFactorsMethod {*_scaling}
 					--ratio log2 --binSize 25
 				]]>
 			</command_line>
@@ -272,10 +283,10 @@
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					plotFingerprint -p {deeptools_parallel} --bamfiles {GALvX_*} --plotFile {DEEPID.PROC.DATE.raw.fgpr}
+					plotFingerprint -p {deeptools_parallel} --bamfiles {GALvX_*} --plotFile {DEEPID.PROC.DATE.ASSM.fgpr}
 					--labels {plot_labels} --plotTitle {plot_title} --numberOfSamples 500000 --plotFileFormat svg
-					--outQualityMetrics {DEEPID.PROC.DATE.raw.qm-fgpr} --JSDsample {GALvX_Input}
-					--outRawCounts {DEEPID.PROC.DATE.raw.counts-fgpr}
+					--outQualityMetrics {DEEPID.PROC.DATE.ASSM.qm-fgpr} --JSDsample {GALvX_Input}
+					--outRawCounts {DEEPID.PROC.DATE.ASSM.counts-fgpr}
 				]]>
 			</command_line>
 			<loop>no looping</loop>
@@ -321,7 +332,7 @@
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					bamCoverage -p {deeptools_parallel} --binSize 25 --bam DEEPID.tmp.filt.bam --outFileName {DEEPID.PROC.DATE.filt.bamcov}
+					bamCoverage -p {deeptools_parallel} --binSize 25 --bam DEEPID.tmp.filt.bam --outFileName {DEEPID.PROC.DATE.ASSM.filt.bamcov}
 					--outFileFormat bigwig --normalizeTo1x {genomesize} --blackListFileName {blacklist_regions} --ignoreForNorm chrX chrY chrM X Y M MT
 				]]>
 			</command_line>
@@ -338,10 +349,10 @@
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					plotFingerprint -p {deeptools_parallel} --bamfiles DEEPID.tmp.filt.bam --plotFile DEEPID.PROC.DATE.filt.fgpr.tmp
+					plotFingerprint -p {deeptools_parallel} --bamfiles DEEPID.tmp.filt.bam --plotFile DEEPID.PROC.DATE.tmp.filt.fgpr
 					--labels {plot_labels} --plotTitle {plot_title} --numberOfSamples 500000 --plotFileFormat svg
-					--outQualityMetrics DEEPID.PROC.DATE.filt.qm-fgpr.tmp --JSDsample DEEPID_Input.tmp.filt.bam
-					--outRawCounts DEEPID.PROC.DATE.filt.counts-fgpr
+					--outQualityMetrics DEEPID.tmp.filt.qm-fgpr.tmp --JSDsample DEEPID_Input.tmp.filt.bam
+					--outRawCounts DEEPID.tmp.filt.counts-fgpr
 				]]>
 			</command_line>
 			<loop>no looping</loop>
@@ -370,7 +381,7 @@
 			<version>3.0</version>
 			<command_line>
 				<![CDATA[
-					zip -9 -X -j -q -D {DEEPID.PROC.DATE.macs.out} DEEPID_macs*
+					zip -9 -X -j -q -D {DEEPID.PROC.DATE.ASSM.macs.out} DEEPID_macs*
 				]]>
 			</command_line>
 			<loop>GALvX_Histone</loop>
@@ -398,7 +409,7 @@
 			<command_line>
 				<![CDATA[
 					cut -f 1,4,5,9 DEEPID-regions.gff | sort -V -k1,2 > DEEPID.hmm.bed &&
-					mv DEEPID-zinba-emfit.pdf {DEEPID.PROC.DATE.hhmm.emfit}
+					mv DEEPID-zinba-emfit.pdf {DEEPID.PROC.DATE.ASSM.hhmm.emfit}
 				]]>
 			</command_line>
 			<loop>DEEPID-regions.gff</loop>
@@ -409,7 +420,7 @@
 			<version>3.0</version>
 			<command_line>
 				<![CDATA[
-					zip -9 -X -j -q -D {DEEPID.PROC.DATE.hhmm.out} DEEPID_hhmm*
+					zip -9 -X -j -q -D {DEEPID.PROC.DATE.ASSM.hhmm.out} DEEPID_hhmm*
 				]]>
 			</command_line>
 			<loop>GALvX_Histone</loop>
@@ -418,8 +429,6 @@
 				-zinba-params-em.txt, .txt
 			</comment>
 		</tool>
-
-
 		<tool>
 			<name>sambamba</name>
 			<version>0.6.6</version>
@@ -432,7 +441,6 @@
 			<loop>DEEPID.tmp.filt.bam</loop>
 			<comment>Count number of reads overlapping peak regions, later used for FRiP score</comment>
 		</tool>
-
 		<tool>
 			<name>bedtools</name>
 			<version>2.26.0</version>
@@ -444,7 +452,6 @@
 			<loop>peak_file</loop>
 			<comment>Intersect all peak files with blacklist regions for flagging</comment>
 		</tool>
-
 		<tool>
 			<name>bedtools</name>
 			<version>2.26.0</version>
@@ -456,14 +463,13 @@
 			<loop>histoneHMM_peak_file</loop>
 			<comment>Intersect all histoneHMM peak files with Input peaks for flagging</comment>
 		</tool>
-
 		<tool>
 			<name>Python</name>
 			<version>2.7.13</version>
 			<command_line>
 				<![CDATA[
 					pipeline-merge peak-file DEEPID.peak-ovl-bl DEEPID.peak-ovl-input
-					> {DEEPID.PROC.DATE.macs.narrow} {DEEPID.PROC.DATE.macs.broad} {DEEPID.PROC.DATE.hhmm.broad}
+					> {DEEPID.PROC.DATE.ASSM.macs.narrow} {DEEPID.PROC.DATE.ASSM.macs.broad} {DEEPID.PROC.DATE.ASSM.hhmm.broad}
 				]]>
 			</command_line>
 			<loop>peak-file</loop>
@@ -473,7 +479,6 @@
 				standard broadPeak/narrowPeak format specifications.
 			</comment>
 		</tool>
-
 		<tool>
 			<name>sambamba</name>
 			<version>0.6.6</version>
@@ -493,9 +498,9 @@
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					multiBamSummary bins -p 8 --bamfiles DEEPID.tmp.auto.bam --outFileName {DEEPID.PROC.DATE.auto.summ}
+					multiBamSummary bins -p 8 --bamfiles DEEPID.tmp.auto.bam --outFileName {DEEPID.PROC.DATE.ASSM.auto.summ}
 					--labels {plot_labels} --binSize 1000 --distanceBetweenBins 2000 --blackListFileName {blacklist_regions}
-					--outRawCounts {DEEPID.PROC.DATE.auto.counts-summ}
+					--outRawCounts {DEEPID.PROC.DATE.ASSM.auto.counts-summ}
 				]]>
 			</command_line>
 			<loop>no looping</loop>
@@ -506,10 +511,10 @@
 			<version>2.5.3</version>
 			<command_line>
 				<![CDATA[
-					plotCorrelation bins --corData SAMPLEID.npz --plotFile {DEEPID.PROC.DATE.bamcorr} --whatToPlot heatmap
-					--plotTitle {plot_title} --plotFileFormat svg --corMethod {cor_method}
+					plotCorrelation bins --corData SAMPLEID.npz --plotFile {DEEPID.PROC.DATE.ASSM.bamcorr} --whatToPlot heatmap
+					--plotTitle {plot_title} --plotFileFormat svg --corMethod corr_method
 					--plotNumbers --zMin -1 --zMax 1 --colorMap coolwarm
-					--outFileCorMatrix {DEEPID.PROC.DATE.corrmat}
+					--outFileCorMatrix {DEEPID.PROC.DATE.ASSM.corrmat}
 				]]>
 			</command_line>
 			<loop>no looping</loop>