From aab07b4e2f3b69df8961ffe7e1afced83fe940c5 Mon Sep 17 00:00:00 2001
From: Donald Buczek <buczek@molgen.mpg.de>
Date: Tue, 13 Sep 2022 12:35:40 +0200
Subject: [PATCH] Add QC stuff

---
 Adapting_new_script_for_computing_cluster.sh | 20 +++++++++++++++++---
 1 file changed, 17 insertions(+), 3 deletions(-)

diff --git a/Adapting_new_script_for_computing_cluster.sh b/Adapting_new_script_for_computing_cluster.sh
index 824e41b..ed687bd 100755
--- a/Adapting_new_script_for_computing_cluster.sh
+++ b/Adapting_new_script_for_computing_cluster.sh
@@ -142,22 +142,36 @@ execute() {
 		--normalizeUsing CPM -ignore chrX chrY \
 		--numberOfProcessors $THREADS \
 
-	# Here I have no idea how to transfer this
-
 	: Generating QC files for the data
+
+	fragments=$(grep -Po -m 1 'Total reads processed.*' $id.trimmingStats.txt | grep -Po '[0-9,]*' | tr -d ,)
+	map=$(grep -Po '[0-9, /.]*% overall alignment rate' $id.mappingStats.txt | grep -Po '[0-9,/.]*')
+	mapFrac=$(printf "%.4f" $(echo $map / 100 | bc -l))
+	dedup=$(printf "%.4f" $(grep -Po 'Unknown Library.*' dedup/${id}_dedupMetric.txt | awk '{print $10}'))
+	filtered=$(expr $(samtools view -c dedup/${id}_dedup.bam) / 2)
+	ripReads=$(expr $(bedtools intersect -a dedup/${id}_dedup.bam -b dedup_peaks/${id}_dedup_peaks.narrowPeak -u -ubam | samtools view -c) / 2)
+	FRiP=$(printf "%.4f" $(echo $fripReads / $filtered | bc -l))
+	peaks=$(expr $(wc -l <"dedup_peaks/${id}_dedup_peaks.narrowPeak") - 1)
+	echo -e "$id\t$fragments\t$filtered\t$mapFrac\t$dedup\t$FRiP\t$peaks" >> cnt_gata_qc_metrics.txt
+
+	# Here I have no idea how to transfer this
 	: Generating pearson correlation between the samples
 
 
 	####################################
 
 	work_dir="$work_dir" flock $LOCK_FILE bash -c '
-mkdir -p $work_dir/peaks $work_dir/bigwig $work_dir/final_bam $work_dir/fastqc $work_dir/dedup $work_dir/dedup_peaks
+mkdir -p $work_dir/peaks $work_dir/bigwig $work_dir/final_bam $work_dir/fastqc $work_dir/dedup $work_dir/dedup_peaks \
+    $work_dir/qc
 cp final_bam/* $work_dir/final_bam
 cp peaks/* $work_dir/peaks/
 cp bigwig/* $work_dir/bigwig/
 cp fastqc/* $work_dir/fastqc
 cp dedup/* $work_dir/dedup
 cp dedup_peaks/* $work_dir/dedup_peaks
+test -e $work_dir/qc/cnt_gata_qc_metrics.txt \
+    || echo -e "Sample\tTotal\tFiltered\tMapped\tDuplicate\tFRiP\tPeaks"> $work_dir/qc/cnt_gata_qc_metrics.txt
+cat cnt_gata_qc_metrics.txt >> $work_dir/qc/cnt_gata_qc_metrics.txt
 '
 
 	ls -lR