Merge branch 'embb_dev'

This commit is contained in:
Tanushree Tunstall 2021-11-19 08:05:46 +00:00
commit 4f52627740
10 changed files with 51 additions and 21 deletions

0
mcsm_na/examples.py Normal file → Executable file
View file

0
mcsm_na/format_results_mcsm_na.py Normal file → Executable file
View file

0
mcsm_na/get_results_mcsm_na.py Normal file → Executable file
View file

9
mcsm_na/run_format_results_mcsm_na.py Normal file → Executable file
View file

@ -52,15 +52,16 @@ if not outdir:
outdir_na = outdir + 'mcsm_na_results/'
# Input file
infile_mcsm_na = outdir_na + gene + '_output_combined_clean.tsv'
infile_mcsm_na = outdir_na + gene.lower() + '_output_combined_clean.tsv'
# Formatted output file
outfile_mcsm_na_f = outdir_na + gene + '_complex_mcsm_na_norm.csv'
outfile_mcsm_na_f = outdir_na + gene.lower() + '_complex_mcsm_na_norm.csv'
#==========================
#===========================================
# CALL: format_results_mcsm_na()
# Data: gid+streptomycin
#==========================
# Data: rpob+rifampicin, date: 18/11/2021
#===========================================
print('Formatting results for:', infile_mcsm_na)
mcsm_na_df_f = format_mcsm_na_output(mcsm_na_output_tsv = infile_mcsm_na)

View file

@ -18,14 +18,14 @@ print(my_prediction_url)
# TODO: add cmd line args
#gene = 'gid'
drug = 'streptomycin'
datadir = homedir + '/git/Data'
indir = datadir + '/' + drug + '/input'
outdir = datadir + '/' + drug + '/output'
outdir_mcsm_na = outdir + 'mcsm_na_results'
drug = ''
datadir = homedir + '/git/Data/'
indir = datadir + drug + 'input/'
outdir = datadir + drug + 'output/'
outdir_mcsm_na = outdir + 'mcsm_na_results/'
my_nuc_type = 'RNA'
my_pdb_file = indir + '/gid_complex.pdb'
my_pdb_file = indir + gene.lower() + '_complex.pdb'
#=============================================================================
# batch 26: 25.txt # RAN: 16 Feb:

27
mcsm_na/split_csv.sh Executable file
View file

@ -0,0 +1,27 @@
#!/bin/bash
# FIXME: This is written for expediency to kickstart running dynamut and mcsm-NA
# Usage: ~/git/LSHTM_analysis/dynamut/split_csv.sh <input file> <output dir> <chunk size in lines>
# copy your snp file to split into the mcsm_na dir
INFILE=$1
OUTDIR=$2
CHUNK=$3
mkdir -p ${OUTDIR}/${CHUNK}
cd ${OUTDIR}/${CHUNK}
split ../../${INFILE} -l ${CHUNK} -d snp_batch_
# use case
#~/git/LSHTM_analysis/mcsm_na/split_csv.sh gid_mcsm_formatted_snps.csv snp_batches 50
#~/git/LSHTM_analysis/mcsm_na/split_csv.sh embb_mcsm_formatted_snps.csv snp_batches 50
#~/git/LSHTM_analysis/mcsm_na/split_csv.sh rpob_mcsm_formatted_snps_chain.csv snp_batches 20 # date: 17/11/2021
#acccidently replaced file original rpob batches
#~/git/LSHTM_analysis/mcsm_na/split_csv.sh 5uhc_mcsm_formatted_snps_chain.csv snp_batches_5uhc 20 # date: 17/11/2021

0
mcsm_na/submit_mcsm_na.py Normal file → Executable file
View file