#!/bin/bash

#=======================================================================
#https://www.biostars.org/p/336891/
#python Mutate.py -v -o /path/to/output.fasta mutation_map_file.csv input.fasta
#=======================================================================


# make sure there is no new line at the end of the mutation file (snps.csv)
#python3 Mutate.py -v -o /home/tanu/git/Data/pyrazinamide/input/output.fasta mut_map.csv 3pl1.fasta.txt
python3 mutate.py -v -o /home/tanu/git/Data/pyrazinamide/output/pnca_msa.txt /home/tanu/git/Data/pyrazinamide/output/pnca_all_muts_msa.csv /home/tanu/git/Data/pyrazinamide/input/3pl1.fasta.txt

# remove fasta style header lines in the output i.e
# lines beginning with '>' so the file is just the mutated seqs
sed -i '/^>.*$/d' /home/tanu/git/Data/pyrazinamide/output/pnca_msa.txt
printf 'No. of lines after cleaning: '
cat /home/tanu/git/Data/pyrazinamide/output/pnca_msa.txt | wc -l

#%%
# Date: 13/01/22
# pre processing
sed 's/"//g' gene_msa_snp.csv > gid_mut_map.csv

# mut prefix for mutation map file MUST match fasta file header 
python3 mutate.py -v -o /home/tanu/git/LSHTM_analysis/scripts/plotting/scratch_plots/TEST2.csv /home/tanu/git/LSHTM_analysis/scripts/plotting/scratch_plots/gid_mut_map.csv /home/tanu/git/Data/streptomycin/input/gid2.fasta

wc -l TEST2.csv

# post processing
sed -E 's/>.*//g' TEST2.csv | sed '/^$/d' > TEST3.csv
wc -l TEST3.csv

# doubles the no as it adds the mut info
python3 mutate.py -v -o /home/tanu/git/LSHTM_analysis/scripts/plotting/scratch_plots/TEST.csv /home/tanu/git/LSHTM_analysis/scripts/plotting/scratch_plots/pnca_mut_map.csv /home/tanu/git/Data/pyrazinamide/input/pnca.fasta