From af04c69d661a201b8811438bc6681a24b57fadb7 Mon Sep 17 00:00:00 2001
From: Tanushree Tunstall <tanu@tunstall.in>
Date: Sun, 16 Jan 2022 18:34:49 +0000
Subject: [PATCH] A MAAAADDD MAAADDD DAYYYYY,messy embb numbering agrrrhhhhh

---
 scripts/gene_targets_names.txt |  7 ++++
 scripts/run_mutate2.sh         | 65 ++++++++++++++++++++++++++++++++++
 2 files changed, 72 insertions(+)
 create mode 100644 scripts/gene_targets_names.txt
 create mode 100755 scripts/run_mutate2.sh

diff --git a/scripts/gene_targets_names.txt b/scripts/gene_targets_names.txt
new file mode 100644
index 0000000..9b9a970
--- /dev/null
+++ b/scripts/gene_targets_names.txt
@@ -0,0 +1,7 @@
+embb ethambutol
+rpob rifampicin
+alr cycloserine
+katg isoniazid
+pnca pyrazinamide
+gid streptomycin
+
diff --git a/scripts/run_mutate2.sh b/scripts/run_mutate2.sh
new file mode 100755
index 0000000..5dd5c60
--- /dev/null
+++ b/scripts/run_mutate2.sh
@@ -0,0 +1,65 @@
+#!/bin/bash
+set -e
+
+# Metadata files edited:
+# rpob: remove positions above 1151
+# embb: remove positions above 1054
+#=======================================================================
+#https://www.biostars.org/p/336891/
+#python Mutate.py -v -o /path/to/output.fasta mutation_map_file.csv input.fasta
+#=======================================================================
+DATA_DIR="/home/tanu/git/Data"
+
+echo "Processing Mutation Files"
+echo "-------------------------"
+echo
+
+while read -r gene drug; do
+  echo "vvvvvvvvvvvvvvvvvvvvv"
+  echo "gene: $gene drug: $drug"; 
+  echo "Source File: ${DATA_DIR}/${drug}/output/${gene}_metadata.csv"
+  MSA_MAP=${DATA_DIR}/${drug}/output/${gene}_msa_map.csv
+  wc -l ${DATA_DIR}/${drug}/output/${gene}_metadata.csv
+  cat  ${DATA_DIR}/${drug}/output/${gene}_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | uniq -c  > ${DATA_DIR}/${drug}/output/${gene}_metadata_mut_count.csv
+  cat  ${DATA_DIR}/${drug}/output/${gene}_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | sed -e 's/"//g' > $MSA_MAP
+  echo "Output to: $MSA_MAP"
+  sed -i "s/^/${gene},/" $MSA_MAP
+  wc -l $MSA_MAP
+  echo "^^^^^^^^^^^^^^^^^^^^^"
+  echo
+  echo "Running mutate.py on data file $MSA_MAP"
+  python3 mutate.py -v -o ${DATA_DIR}/${drug}/output/${gene}_msa_interim.csv $MSA_MAP $DATA_DIR/${drug}/input/${gene}_f2.fasta
+  echo "mutate.py completed"
+  echo
+
+done < gene_targets_names.txt
+
+# Stop here so we don't run the examples below :)
+exit
+
+# make sure there is no new line at the end of the mutation file (snps.csv)
+# check
+cat  output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | head
+
+cat  output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort | uniq -c  > output/gid_metadata_mut_count.csv
+
+
+cat  output/gid_metadata.csv | rev| cut -d, -f1 |rev | tail -n +2 |sort > gid_msa_snp.csv
+sed -i 's/^/gid,/' gid_msa_snp.csv 
+
+#cp gid_msa_snp.csv gid_mut_map.csv
+#%%
+# Date: 16/01/22
+# pre processing
+sed 's/"//g' gene_msa_snp.csv > gid_mut_map.csv
+
+# mut prefix for mutation map file MUST match fasta file header 
+python3 mutate.py -v -o /home/tanu/git/Data/streptomycin/output/TEST2.csv /home/tanu/git/Data/streptomycin/output/gid_mut_map.csv /home/tanu/git/Data/streptomycin/input/gid2.fasta
+
+wc -l TEST2.csv
+
+# post processing
+sed -E 's/>.*//g' TEST2.csv | sed '/^$/d' > TEST3.csv
+wc -l TEST3.csv
+
+#==============================================