tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

added split_csv_chain.sh for mCSM-NA analysis in scripts/

Browse source
This commit is contained in:
Tanushree Tunstall 2021-10-29 14:00:25 +01:00
parent e2bc1cdde1
commit 63ec8a1c37
1 changed files with 27 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

27
mcsm_na/split_csv_chain.sh Executable file
View file

@ -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
########################################################################