LSHTM_analysis/scripts/mut_electrostatic_changes.py

220 lines
8 KiB
Python
Executable file

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
'''
Created on Tue Aug 6 12:56:03 2019
@author: tanu
'''
# FIXME: import dirs.py to get the basic dir paths available
#=======================================================================
# TASK: calculate how many mutations result in
# electrostatic changes wrt wt
# Input: mCSM-normalised file or any file containing one-letter aa code
# of wt and mut
# Note: this can be easily modified into 3-letter code
# TODO: turn to a function
# Output: mut_elec_changes_results.txt
#=======================================================================
#%% load libraries
import os, sys
import pandas as pd
#import numpy as np
#from varname import nameof
import argparse
#=======================================================================
#%% specify input and curr dir
homedir = os.path.expanduser('~')
# set working dir
os.getcwd()
os.chdir(homedir + '/git/LSHTM_analysis/scripts')
os.getcwd()
from reference_dict import oneletter_aa_dict
#=======================================================================
#%% command line args
arg_parser = argparse.ArgumentParser()
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
arg_parser.add_argument('-g', '--gene', help='gene name', default = None)
arg_parser.add_argument('--datadir', help = 'Data Directory. By default, it assmumes homedir + git/Data')
arg_parser.add_argument('-i', '--input_dir', help = 'Input dir containing pdb files. By default, it assmumes homedir + <drug> + input')
arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + <drug> + output')
arg_parser.add_argument('--debug', action ='store_true', help = 'Debug Mode') # not used atm
args = arg_parser.parse_args()
#%% variable assignment: input and output
drug = args.drug
gene = args.gene
datadir = args.datadir
indir = args.input_dir
outdir = args.output_dir
#%%=======================================================================
#==============
# directories
#==============
if not datadir:
datadir = homedir + '/' + 'git/Data'
if not indir:
indir = datadir + '/' + drug + '/input'
if not outdir:
outdir = datadir + '/' + drug + '/output'
#=======
# input
#=======
#in_filename = 'merged_df3.csv'
in_filename = gene.lower() + '_complex_mcsm_norm.csv'
#in_filename = gene.lower() + '_complex_mcsm_norm_SRY.csv' # gid
infile_merged_df3 = outdir + '/' + in_filename
print('Input file: ', infile_merged_df3
, '\n============================================================')
#=======
# output
#=======
out_filename = gene.lower() + '_mut_elec_changes.txt'
outfile_elec_changes = outdir + '/' + out_filename
print('Output file: ', outfile_elec_changes
, '\n============================================================')
#%% end of variable assignment for input and output files
#=======================================================================
#%% Read input files
print('Reading input file (merged file):', infile_merged_df3)
comb_df = pd.read_csv(infile_merged_df3, sep = ',')
print('Input filename: ', in_filename
, '\nPath :', outdir
, '\nNo. of rows: ', len(comb_df)
, '\nNo. of cols: ', len(comb_df.columns)
, '\n============================================================')
# column names
list(comb_df.columns)
# clear variables
del(in_filename, infile_merged_df3)
#%%
#----------------------------------------------------------------
# add aa properties considering df has columns:
# 'wild_type', 'mutant_type' separately as single letter aa code
#----------------------------------------------------------------
lookup_dict = dict()
for k, v in oneletter_aa_dict.items():
lookup_dict[k] = v['aa_calcprop']
#print(lookup_dict)
comb_df['wt_calcprop'] = comb_df['wild_type'].map(lookup_dict)
comb_df['mut_calcprop'] = comb_df['mutant_type'].map(lookup_dict)
#%% subset unique mutations
df = comb_df.drop_duplicates(['mutationinformation'], keep = 'first')
total_muts = df['mutationinformation'].nunique()
#df.Mutationinformation.count()
print('Total mutations associated with structure: ', total_muts
, '\n===============================================================')
#%% combine aa_calcprop cols so that you can count the changes as value_counts
# check if all muts have been categorised
print('Checking if all muts have been categorised: ')
if df['wt_calcprop'].isna().sum() == 0 & df['mut_calcprop'].isna().sum():
print('PASS: No. NA detected. All muts have aa prop associated'
, '\n===============================================================')
else:
print('FAIL: NAs detected. Some muts remain unclassified'
, '\n===============================================================')
sys.exit()
df['wt_calcprop'].head()
df['mut_calcprop'].head()
print('Combining wt_calcprop and mut_calcprop...')
#df['aa_calcprop_combined'] = df['wt_calcprop']+ '->' + df['mut_calcprop']
df['aa_calcprop_combined'] = df.wt_calcprop.str.cat(df.mut_calcprop, sep = '->')
df['aa_calcprop_combined'].head()
mut_categ = df["aa_calcprop_combined"].unique()
print('Total no. of aa_calc properties: ', len(mut_categ))
print('Categories are: ', mut_categ)
# Counting no. of muts in each mut categ
# way1: count values within each combinaton
df.groupby('aa_calcprop_combined').size()
#df.groupby('aa_calcprop_combined').count()
# way2: count values within each combinaton
df['aa_calcprop_combined'].value_counts()
# comment: the two ways should be identical
# groupby result order is similar to pivot table order,
# I prefer the value_counts look
# assign to variable: count values within each combinaton
all_prop = df['aa_calcprop_combined'].value_counts()
# convert to a df from Series
ap_df = pd.DataFrame({'aa_calcprop': all_prop.index, 'mut_count': all_prop.values})
# subset df to contain only the changes in prop
all_prop_change = ap_df[ap_df['aa_calcprop'].isin(['neg->neg','non-polar->non-polar','polar->polar', 'pos->pos']) == False]
elec_count = all_prop_change.mut_count.sum()
print('Total no.of muts with elec changes: ', elec_count)
# calculate percentage of electrostatic changes
elec_changes = (elec_count/total_muts) * 100
print('\n==============================================================='
, '\nResults for electrostatic changes from nsSNPs for', gene,':'
, '\n\nTotal no. of mutations:', total_muts
, '\nMutations with electrostatic changes:', elec_count
, '\nPercentage(%) of electrostatic changes:', elec_changes
, '\n===============================================================')
# check no change muts
no_change_muts = ap_df[ap_df['aa_calcprop'].isin(['neg->neg','non-polar->non-polar','polar->polar', 'pos->pos']) == True]
no_change_muts.mut_count.sum()
if no_change_muts.mut_count.sum() + elec_count == total_muts:
print('\nPASS: numbers cross checked'
, '\nWriting output file:', outfile_elec_changes)
else:
print('\nFAIL: numbers mismatch')
sys.exit()
#%% output from console
#sys.stdout = open(file, 'w')
sys.stdout = open(outfile_elec_changes, 'w')
print('################################################'
, '\nResults for gene:', gene
, '\n################################################'
, '\n\n======================'
, '\nUnchanged muts:'
, '\n=====================\n'
, no_change_muts
, '\n=============================\n'
, 'Muts with changed properties:'
, '\n============================\n'
, all_prop_change
, '\n=====================================================')
print('Total no. of mutations: ', total_muts
, '\nTotal no. of mutions with electrostatic changes:', elec_count
, '\nCorresponding (%):', elec_changes
, '\nTotal no. of changed muts: ', all_prop_change.mut_count.sum()
, '\nTotal no. of unchanged muts: ', no_change_muts.mut_count.sum()
, '\n=======================================================')
#%% end of script
#=======================================================================