LSHTM_analysis/mcsm_na/run_format_results_mcsm_na.py

48 lines
1.4 KiB
Python

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Feb 12 12:15:26 2021
@author: tanu
"""
#%% load packages
import os
homedir = os.path.expanduser('~')
os.chdir (homedir + '/git/LSHTM_analysis/mcsm_na')
from format_results_mcsm_na import *
########################################################################
# variables
# TODO: add cmd line args
# Imagine we've done the work
gene = 'gid'
drug = 'streptomycin'
datadir = homedir + '/git/Data'
indir = datadir + '/' + drug + '/input'
outdir = datadir + '/' + drug + '/output'
outdir_na = outdir + '/mcsm_na_results/'
# Input file
infile_mcsm_na = outdir_na + gene + '_output_combined_clean.tsv'
# Formatted output file
outfile_mcsm_na_f = outdir_na + gene + '_complex_mcsm_na_norm.csv'
#==========================
# CALL: format_results_mcsm_na()
# Data: gid+streptomycin
#==========================
print('Formatting results for:', infile_mcsm_na)
mcsm_na_df_f = format_mcsm_na_output(mcsm_na_output_tsv = infile_mcsm_na)
# writing file
print('Writing formatted df to csv')
mcsm_na_df_f.to_csv(outfile_mcsm_na_f, index = False)
print('Finished writing file:'
, '\nFile:', outfile_mcsm_na_f
, '\nExpected no. of rows:', len(mcsm_na_df_f)
, '\nExpected no. of cols:', len(mcsm_na_df_f.columns)
, '\n=============================================================')
#%%#####################################################################