From 7368a1da206660a5c65da344c83f45b383e0ace3 Mon Sep 17 00:00:00 2001
From: Yuuki Galaxy <galaxy001@gmail.com>
Date: Fri, 11 Oct 2024 09:45:49 +0800
Subject: [PATCH] 	new file:   extract_bam_tag.sh

---
 etc/salus/extract_bam_tag.sh | 15 +++++++++++++++
 1 file changed, 15 insertions(+)
 create mode 100755 etc/salus/extract_bam_tag.sh

diff --git a/etc/salus/extract_bam_tag.sh b/etc/salus/extract_bam_tag.sh
new file mode 100755
index 000000000..a9ae33be1
--- /dev/null
+++ b/etc/salus/extract_bam_tag.sh
@@ -0,0 +1,15 @@
+#!/usr/bin/env bash
+
+# https://gist.github.com/Shians/a95c49bda68481fb0adc83600d9eb6b8
+# called by
+# sh extract_bam_tag.sh input.bam BC
+# to print read_id and BC tag value
+
+# two arguments, a bam file and the tag to extract
+BAM=$1
+TAG=$2
+
+# write a tsv with columns read_id and tag value
+echo -e "read_id\t$TAG"
+samtools view "$BAM" | grep "$TAG:." | perl -pe 's/(^.+?)\t.*'$TAG':.:(.+?)\t.*/$1\t$2/g'
+# regular expression substutes pattern (read_id)*(tag_value)* for (read_id)\t(tag_value)
-- 
2.11.4.GIT