moved scripts to /ind_scripts & added add col to formatting script
This commit is contained in:
parent
e94da61871
commit
a405aa17c3
6 changed files with 1129 additions and 62 deletions
340
mcsm/ind_scripts/format_results.py
Executable file
340
mcsm/ind_scripts/format_results.py
Executable file
|
|
@ -0,0 +1,340 @@
|
|||
#!/usr/bin/env python3
|
||||
#=======================================================================
|
||||
#TASK:
|
||||
#=======================================================================
|
||||
#%% load packages
|
||||
import os,sys
|
||||
import subprocess
|
||||
import argparse
|
||||
#import requests
|
||||
import re
|
||||
#import time
|
||||
import pandas as pd
|
||||
from pandas.api.types import is_string_dtype
|
||||
from pandas.api.types import is_numeric_dtype
|
||||
import numpy as np
|
||||
from mcsm import *
|
||||
|
||||
#=======================================================================
|
||||
#%% specify input and curr dir
|
||||
homedir = os.path.expanduser('~')
|
||||
# set working dir
|
||||
os.getcwd()
|
||||
os.chdir(homedir + '/git/LSHTM_analysis/mcsm')
|
||||
os.getcwd()
|
||||
#=======================================================================
|
||||
#%% variable assignment: input and output
|
||||
#drug = 'pyrazinamide'
|
||||
#gene = 'pncA'
|
||||
|
||||
drug = 'isoniazid'
|
||||
gene = 'KatG'
|
||||
|
||||
#drug = args.drug
|
||||
#gene = args.gene
|
||||
|
||||
gene_match = gene + '_p.'
|
||||
#==========
|
||||
# data dir
|
||||
#==========
|
||||
datadir = homedir + '/' + 'git/Data'
|
||||
|
||||
#=======
|
||||
# input:
|
||||
#=======
|
||||
# 1) result_urls (from outdir)
|
||||
outdir = datadir + '/' + drug + '/' + 'output'
|
||||
in_filename = gene.lower() + '_mcsm_output.csv' #(outfile, from mcsm_results.py)
|
||||
infile = outdir + '/' + in_filename
|
||||
print('Input filename:', in_filename
|
||||
, '\nInput path(from output dir):', outdir
|
||||
, '\n=============================================================')
|
||||
|
||||
#=======
|
||||
# output
|
||||
#=======
|
||||
outdir = datadir + '/' + drug + '/' + 'output'
|
||||
out_filename = gene.lower() + '_complex_mcsm_results.csv'
|
||||
outfile = outdir + '/' + out_filename
|
||||
print('Output filename:', out_filename
|
||||
, '\nOutput path:', outdir
|
||||
, '\n=============================================================')
|
||||
#%%=====================================================================
|
||||
def format_mcsm_output(mcsm_outputcsv):
|
||||
"""
|
||||
@param mcsm_outputcsv: file containing mcsm results for all muts
|
||||
which is the result of build_result_dict() being called for each
|
||||
mutation and then converting to a pandas df and output as csv.
|
||||
@type string
|
||||
|
||||
@return formatted mcsm output
|
||||
@type pandas df
|
||||
|
||||
"""
|
||||
#############
|
||||
# Read file
|
||||
#############
|
||||
mcsm_data = pd.read_csv(mcsm_outputcsv, sep = ',')
|
||||
dforig_shape = mcsm_data.shape
|
||||
print('dimensions of input file:', dforig_shape)
|
||||
|
||||
#############
|
||||
# rename cols
|
||||
#############
|
||||
# format colnames: all lowercase, remove spaces and use '_' to join
|
||||
print('Assigning meaningful colnames i.e without spaces and hyphen and reflecting units'
|
||||
, '\n===================================================================')
|
||||
my_colnames_dict = {'Predicted Affinity Change': 'PredAffLog' # relevant info from this col will be extracted and the column discarded
|
||||
, 'Mutation information': 'mutation_information' # {wild_type}<position>{mutant_type}
|
||||
, 'Wild-type': 'wild_type' # one letter amino acid code
|
||||
, 'Position': 'position' # number
|
||||
, 'Mutant-type': 'mutant_type' # one letter amino acid code
|
||||
, 'Chain': 'chain' # single letter (caps)
|
||||
, 'Ligand ID': 'ligand_id' # 3-letter code
|
||||
, 'Distance to ligand': 'ligand_distance' # angstroms
|
||||
, 'DUET stability change': 'duet_stability_change'} # in kcal/mol
|
||||
|
||||
mcsm_data.rename(columns = my_colnames_dict, inplace = True)
|
||||
#%%===========================================================================
|
||||
#################################
|
||||
# populate mutation_information
|
||||
# col which is currently blank
|
||||
#################################
|
||||
# populate mutation_information column:mcsm style muts {WT}<POS>{MUT}
|
||||
print('Populating column : mutation_information which is currently empty\n', mcsm_data['mutation_information'])
|
||||
mcsm_data['mutation_information'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str) + mcsm_data['mutant_type']
|
||||
print('checking after populating:\n', mcsm_data['mutation_information']
|
||||
, '\n===================================================================')
|
||||
|
||||
# Remove spaces b/w pasted columns
|
||||
print('removing white space within column: \mutation_information')
|
||||
mcsm_data['mutation_information'] = mcsm_data['mutation_information'].str.replace(' ', '')
|
||||
print('Correctly formatted column: mutation_information\n', mcsm_data['mutation_information']
|
||||
, '\n===================================================================')
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# sanity check: drop dupliate muts
|
||||
#############
|
||||
# shouldn't exist as this should be eliminated at the time of running mcsm
|
||||
print('Sanity check:'
|
||||
, '\nChecking duplicate mutations')
|
||||
if mcsm_data['mutation_information'].duplicated().sum() == 0:
|
||||
print('PASS: No duplicate mutations detected (as expected)'
|
||||
, '\nDim of data:', mcsm_data.shape
|
||||
, '\n===============================================================')
|
||||
else:
|
||||
print('FAIL (but not fatal): Duplicate mutations detected'
|
||||
, '\nDim of df with duplicates:', mcsm_data.shape
|
||||
, 'Removing duplicate entries')
|
||||
mcsm_data = mcsm_data.drop_duplicates(['mutation_information'])
|
||||
print('Dim of data after removing duplicate muts:', mcsm_data.shape
|
||||
, '\n===============================================================')
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# Create col: duet_outcome
|
||||
#############
|
||||
# classification based on DUET stability values
|
||||
print('Assigning col: duet_outcome based on DUET stability values')
|
||||
print('Sanity check:')
|
||||
# count positive values in the DUET column
|
||||
c = mcsm_data[mcsm_data['duet_stability_change']>=0].count()
|
||||
DUET_pos = c.get(key = 'duet_stability_change')
|
||||
# Assign category based on sign (+ve : Stabilising, -ve: Destabilising, Mind the spelling (British spelling))
|
||||
mcsm_data['duet_outcome'] = np.where(mcsm_data['duet_stability_change']>=0, 'Stabilising', 'Destabilising')
|
||||
mcsm_data['duet_outcome'].value_counts()
|
||||
if DUET_pos == mcsm_data['duet_outcome'].value_counts()['Stabilising']:
|
||||
print('PASS: DUET outcome assigned correctly')
|
||||
else:
|
||||
print('FAIL: DUET outcome assigned incorrectly'
|
||||
, '\nExpected no. of stabilising mutations:', DUET_pos
|
||||
, '\nGot no. of stabilising mutations', mcsm_data['duet_outcome'].value_counts()['Stabilising']
|
||||
, '\n===============================================================')
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# Extract numeric
|
||||
# part of ligand_distance col
|
||||
#############
|
||||
# Extract only the numeric part from col: ligand_distance
|
||||
# number: '-?\d+\.?\d*'
|
||||
mcsm_data['ligand_distance']
|
||||
print('extracting numeric part of col: ligand_distance')
|
||||
mcsm_data['ligand_distance'] = mcsm_data['ligand_distance'].str.extract('(\d+\.?\d*)')
|
||||
mcsm_data['ligand_distance']
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# Create 2 columns:
|
||||
# ligand_affinity_change and ligand_outcome
|
||||
#############
|
||||
# the numerical and categorical parts need to be extracted from column: PredAffLog
|
||||
# regex used
|
||||
# numerical part: '-?\d+\.?\d*'
|
||||
# categorocal part: '\b(\w+ing)\b'
|
||||
print('Extracting numerical and categorical parts from the col: PredAffLog')
|
||||
print('to create two columns: ligand_affinity_change and ligand_outcome'
|
||||
, '\n===================================================================')
|
||||
|
||||
# 1) Extracting the predicted affinity change (numerical part)
|
||||
mcsm_data['ligand_affinity_change'] = mcsm_data['PredAffLog'].str.extract('(-?\d+\.?\d*)', expand = True)
|
||||
print(mcsm_data['ligand_affinity_change'])
|
||||
|
||||
# 2) Extracting the categorical part (Destabillizing and Stabilizing) using word boundary ('ing')
|
||||
#aff_regex = re.compile(r'\b(\w+ing)\b')
|
||||
mcsm_data['ligand_outcome']= mcsm_data['PredAffLog'].str.extract(r'(\b\w+ing\b)', expand = True)
|
||||
print(mcsm_data['ligand_outcome'])
|
||||
print(mcsm_data['ligand_outcome'].value_counts())
|
||||
|
||||
#############
|
||||
# changing spelling: British
|
||||
#############
|
||||
# ensuring spellings are consistent
|
||||
american_spl = mcsm_data['ligand_outcome'].value_counts()
|
||||
print('Changing to Bristish spellings for col: ligand_outcome')
|
||||
mcsm_data['ligand_outcome'].replace({'Destabilizing': 'Destabilising', 'Stabilizing': 'Stabilising'}, inplace = True)
|
||||
print(mcsm_data['ligand_outcome'].value_counts())
|
||||
british_spl = mcsm_data['ligand_outcome'].value_counts()
|
||||
# compare series values since index will differ from spelling change
|
||||
check = american_spl.values == british_spl.values
|
||||
if check.all():
|
||||
print('PASS: spelling change successfull'
|
||||
, '\nNo. of predicted affinity changes:\n', british_spl
|
||||
, '\n===============================================================')
|
||||
else:
|
||||
print('FAIL: spelling change unsucessfull'
|
||||
, '\nExpected:\n', american_spl
|
||||
, '\nGot:\n', british_spl
|
||||
, '\n===============================================================')
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# ensuring corrrect dtype columns
|
||||
#############
|
||||
# check dtype in cols
|
||||
print('Checking dtypes in all columns:\n', mcsm_data.dtypes
|
||||
, '\n===================================================================')
|
||||
print('Converting the following cols to numeric:'
|
||||
, '\nligand_distance'
|
||||
, '\nduet_stability_change'
|
||||
, '\nligand_affinity_change'
|
||||
, '\n===================================================================')
|
||||
|
||||
# using apply method to change stabilty and affinity values to numeric
|
||||
numeric_cols = ['duet_stability_change', 'ligand_affinity_change', 'ligand_distance']
|
||||
mcsm_data[numeric_cols] = mcsm_data[numeric_cols].apply(pd.to_numeric)
|
||||
# check dtype in cols
|
||||
print('checking dtype after conversion')
|
||||
cols_check = mcsm_data.select_dtypes(include='float64').columns.isin(numeric_cols)
|
||||
if cols_check.all():
|
||||
print('PASS: dtypes for selected cols:', numeric_cols
|
||||
, '\nchanged to numeric'
|
||||
, '\n===============================================================')
|
||||
else:
|
||||
print('FAIL:dtype change to numeric for selected cols unsuccessful'
|
||||
, '\n===============================================================')
|
||||
print(mcsm_data.dtypes)
|
||||
#%%===========================================================================
|
||||
|
||||
#############
|
||||
# scale duet values
|
||||
#############
|
||||
# Rescale values in DUET_change col b/w -1 and 1 so negative numbers
|
||||
# stay neg and pos numbers stay positive
|
||||
duet_min = mcsm_data['duet_stability_change'].min()
|
||||
duet_max = mcsm_data['duet_stability_change'].max()
|
||||
|
||||
duet_scale = lambda x : x/abs(duet_min) if x < 0 else (x/duet_max if x >= 0 else 'failed')
|
||||
|
||||
mcsm_data['duet_scaled'] = mcsm_data['duet_stability_change'].apply(duet_scale)
|
||||
print('Raw duet scores:\n', mcsm_data['duet_stability_change']
|
||||
, '\n---------------------------------------------------------------'
|
||||
, '\nScaled duet scores:\n', mcsm_data['duet_scaled'])
|
||||
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# scale affinity values
|
||||
#############
|
||||
# rescale values in affinity change col b/w -1 and 1 so negative numbers
|
||||
# stay neg and pos numbers stay positive
|
||||
aff_min = mcsm_data['ligand_affinity_change'].min()
|
||||
aff_max = mcsm_data['ligand_affinity_change'].max()
|
||||
|
||||
aff_scale = lambda x : x/abs(aff_min) if x < 0 else (x/aff_max if x >= 0 else 'failed')
|
||||
|
||||
mcsm_data['affinity_scaled'] = mcsm_data['ligand_affinity_change'].apply(aff_scale)
|
||||
print('Raw affinity scores:\n', mcsm_data['ligand_affinity_change']
|
||||
, '\n---------------------------------------------------------------'
|
||||
, '\nScaled affinity scores:\n', mcsm_data['affinity_scaled'])
|
||||
#=============================================================================
|
||||
# Adding colname: wild_pos: sometimes useful for plotting and db
|
||||
print('Creating column: wild_position')
|
||||
mcsm_data['wild_position'] = mcsm_data['wild_type'] + mcsm_data['position'].astype(str)
|
||||
print(mcsm_data['wild_position'].head())
|
||||
# Remove spaces b/w pasted columns
|
||||
print('removing white space within column: wild_position')
|
||||
mcsm_data['wild_position'] = mcsm_data['wild_position'].str.replace(' ', '')
|
||||
print('Correctly formatted column: wild_position\n', mcsm_data['wild_position'].head()
|
||||
, '\n===================================================================')
|
||||
#=============================================================================
|
||||
#%% ensuring dtypes are string for the non-numeric cols
|
||||
#) char cols
|
||||
char_cols = ['PredAffLog', 'mutation_information', 'wild_type', 'mutant_type', 'chain'
|
||||
, 'ligand_id', 'duet_outcome', 'ligand_outcome', 'wild_position']
|
||||
|
||||
#mcsm_data[char_cols] = mcsm_data[char_cols].astype(str)
|
||||
cols_check_char = mcsm_data.select_dtypes(include='object').columns.isin(char_cols)
|
||||
|
||||
if cols_check_char.all():
|
||||
print('PASS: dtypes for char cols:', char_cols, 'are indeed string'
|
||||
, '\n===============================================================')
|
||||
else:
|
||||
print('FAIL:dtype change to numeric for selected cols unsuccessful'
|
||||
, '\n===============================================================')
|
||||
#mcsm_data['ligand_distance', 'ligand_affinity_change'].apply(is_numeric_dtype(mcsm_data['ligand_distance', 'ligand_affinity_change']))
|
||||
print(mcsm_data.dtypes)
|
||||
#=============================================================================
|
||||
# Removing PredAff log column as it is not needed?
|
||||
print('Removing col: PredAffLog since relevant info has been extracted from it')
|
||||
mcsm_dataf = mcsm_data.drop(columns = ['PredAffLog'])
|
||||
#%%===========================================================================
|
||||
#############
|
||||
# sanity check before writing file
|
||||
#############
|
||||
expected_ncols_toadd = 5 # beware of hardcoded numbers
|
||||
dforig_len = dforig_shape[1]
|
||||
expected_cols = dforig_len + expected_ncols_toadd
|
||||
if len(mcsm_dataf.columns) == expected_cols:
|
||||
print('PASS: formatting successful'
|
||||
, '\nformatted df has expected no. of cols:', expected_cols
|
||||
, '\ncolnames:', mcsm_dataf.columns
|
||||
, '\n----------------------------------------------------------------'
|
||||
, '\ndtypes in cols:', mcsm_dataf.dtypes
|
||||
, '\n----------------------------------------------------------------'
|
||||
, '\norig data shape:', dforig_shape
|
||||
, '\nformatted df shape:', mcsm_dataf.shape
|
||||
, '\n===============================================================')
|
||||
else:
|
||||
print('FAIL: something went wrong in formatting df'
|
||||
, '\nLen of orig df:', dforig_len
|
||||
, '\nExpected number of cols to add:', expected_ncols_toadd
|
||||
, '\nExpected no. of cols:', expected_cols, '(', dforig_len, '+', expected_ncols_toadd, ')'
|
||||
, '\nGot no. of cols:', len(mcsm_dataf.columns)
|
||||
, '\nCheck formatting:'
|
||||
, '\ncheck hardcoded value:', expected_ncols_toadd
|
||||
, '\nis', expected_ncols_toadd, 'the no. of expected cols to add?'
|
||||
, '\n===============================================================')
|
||||
|
||||
|
||||
return mcsm_dataf
|
||||
#=======================================================================
|
||||
# call function
|
||||
mcsm_df_formatted = format_mcsm_output(infile)
|
||||
|
||||
# writing file
|
||||
print('Writing formatted df to csv')
|
||||
mcsm_df_formatted.to_csv(outfile, index = False)
|
||||
|
||||
print('Finished writing file:'
|
||||
, '\nFile', outfile
|
||||
, '\nExpected no. of rows:', len(mcsm_df_formatted)
|
||||
, '\nExpected no. of cols:', len(mcsm_df_formatted)
|
||||
, '\n=============================================================')
|
||||
#%%
|
||||
#End of script
|
||||
Loading…
Add table
Add a link
Reference in a new issue