LSHTM_analysis/dynamut/split_csv_chain.sh

41 lines
1.6 KiB
Bash
Executable file

#!/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 ${CHUNK} -d snp_batch_
########################################################################
# use cases
# Date: 20/09/2021
# sed -e 's/^/A /g' katg_mcsm_formatted_snps.csv > katg_mcsm_formatted_snps_chain.csv
#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh katg_mcsm_formatted_snps_chain.csv snp_batches 50
# Date: 01/10/2021
# sed -e 's/^/A /g' rpob_mcsm_formatted_snps.csv > rpob_mcsm_formatted_snps_chain.csv
#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh rpob_mcsm_formatted_snps_chain.csv snp_batches 50
# Date: 02/10/2021
# sed -e 's/^/A /g' alr_mcsm_formatted_snps.csv > alr_mcsm_formatted_snps_chain.csv
#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh alr_mcsm_formatted_snps_chain.csv snp_batches 50
# Date: 05/10/2021
#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh alr_mcsm_formatted_snps_chain.csv snp_batches 20
# Date: 30/11/2021
#~/git/LSHTM_analysis/dynamut/split_csv_chain.sh katg_mcsm_formatted_snps_chain.csv snp_batches 20
for i in {00..40}; do mv snp_batch_${i} snp_batch_${i}.txt; done
# add .txt to the files
########################################################################