From 1ddac80fe3bbb98365d0f58158cfe2e25722c8db Mon Sep 17 00:00:00 2001
From: Laura Cook <l.cook2@student.unimelb.edu.au>
Date: Wed, 23 Sep 2020 20:00:01 +1000
Subject: [PATCH] first commit - subsample BAM files to the desired read number

---
 mouse/scripts/subsample.sh | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
 create mode 100644 mouse/scripts/subsample.sh

diff --git a/mouse/scripts/subsample.sh b/mouse/scripts/subsample.sh
new file mode 100644
index 0000000..da0efba
--- /dev/null
+++ b/mouse/scripts/subsample.sh
@@ -0,0 +1,17 @@
+
+
+TRA=($(for file in *_q30.sorted.dedup.bam; do echo $file |cut -d "_" -f 1-3;done))
+
+echo ${TRA[@]}
+
+for tr in ${TRA[@]};
+
+do
+
+echo ${tr}
+
+frac=$( samtools idxstats ${tr}_q30.sorted.dedup.bam | cut -f3 | awk 'BEGIN {total=0} {total += $1} END {frac=10000000/total; if (frac > 1) {print 1} else {print frac}}' )
+
+samtools view -bs $frac ${tr}_q30.sorted.dedup.bam > ../../results_10M/bwa/${tr}_q30.sorted.dedup.bam
+
+done
-- 
GitLab