From 63ec8a1c374c4285ef17104a3661c9923f0a571e Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Fri, 29 Oct 2021 14:00:25 +0100
Subject: [PATCH] added split_csv_chain.sh for mCSM-NA analysis in scripts/

---
 mcsm_na/split_csv_chain.sh | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)
 create mode 100755 mcsm_na/split_csv_chain.sh

diff --git a/mcsm_na/split_csv_chain.sh b/mcsm_na/split_csv_chain.sh
new file mode 100755
index 0000000..263bbb6
--- /dev/null
+++ b/mcsm_na/split_csv_chain.sh
@@ -0,0 +1,27 @@
+#!/bin/bash
+
+# FIXME: This is written for expediency to kickstart running dynamut, mcsm-PPI2 (batch pf 50) and mCSM-NA (batch of 20)
+
+# Usage: ~/git/LSHTM_analysis/dynamut/split_csv.sh <input file> <output dir> <chunk size in lines>
+# copy your snp file to split into the dynamut dir
+# use sed to add chain ID to snp file and then split to avoid post processing
+
+INFILE=$1
+OUTDIR=$2
+CHUNK=$3
+
+mkdir -p ${OUTDIR}/${CHUNK}/chain_added
+cd ${OUTDIR}/${CHUNK}/chain_added
+
+# makes the 3 dirs, hence ../..
+split ../../../${INFILE} -l ${CHUNK} -d snp_batch_
+
+########################################################################
+# use cases
+
+# Date: 29/10/2021, 5UHC (for rifampicin)
+~/git/LSHTM_analysis/mcsm_na/split_csv_chain.sh rpob_mcsm_formatted_snps_chain.csv snp_batches 20    
+  
+# add .txt to the files
+for i in {00..56}; do mv snp_batch_${i} snp_batch_${i}_chain.txt; done
+########################################################################