tanu/LSHTM_analysis
1
0
Fork 0
Code Issues Pull requests Releases Wiki Activity

added dynamut results formatting scripts, althouh needs to be rerun once b7 completes

Browse source
This commit is contained in:
Tanushree Tunstall 2021-08-13 13:24:22 +01:00
parent 64669eb05f
commit 5529fbf63d
2 changed files with 214 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

161
dynamut/format_results_dynamut.py Normal file
View file

@ -0,0 +1,161 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Wed Aug 19 14:33:51 2020
@author: tanu
"""
#%% load packages
import os,sys
import subprocess
import argparse
import requests
import re
import time
from bs4 import BeautifulSoup
import pandas as pd
import numpy as np
from pandas.api.types import is_string_dtype
from pandas.api.types import is_numeric_dtype
#%%#####################################################################
def format_dynamut_output(dynamut_output_csv):
"""
@param dynamut_output_csv: file containing dynamut results for all muts
which is the result of combining all dynamut_output batch results, and using
bash scripts to combine all the batch results into one file.
This is post run_get_results_dynamut.py
Formatting df to a pandas df and output as csv.
@type string
@return (not true) formatted csv for dynamut output
@type pandas df
"""
#############
# Read file
#############
dynamut_data_raw = pd.read_csv(dynamut_output_csv, sep = ',')
# strip white space from both ends in all columns
dynamut_data = dynamut_data_raw.apply(lambda x: x.str.strip() if x.dtype == 'object' else x)
dforig_shape = dynamut_data.shape
print('dimensions of input file:', dforig_shape)
#%%============================================================================
#####################################
# create binary cols for each param
# >=0: Stabilising
######################################
outcome_cols = ['ddg_dynamut', 'ddg_encom', 'ddg_mcsm','ddg_sdm', 'ddg_duet']
# col test: ddg_dynamut
#len(dynamut_data[dynamut_data['ddg_dynamut'] >= 0])
#dynamut_data['ddg_dynamut_outcome'] = dynamut_data['ddg_dynamut'].apply(lambda x: 'Stabilising' if x >= 0 else 'Destabilising')
#len(dynamut_data[dynamut_data['ddg_dynamut_outcome'] == 'Stabilising'])
print('\nCreating classification cols for', len(outcome_cols), 'columns'
, '\nThese are:')
for cols in outcome_cols:
print(cols)
tot_muts = dynamut_data[cols].count()
print('\nTotal entries:', tot_muts)
outcome_colname = cols + '_outcome'
print(cols, ':', outcome_colname)
c1 = len(dynamut_data[dynamut_data[cols] >= 0])
dynamut_data[outcome_colname] = dynamut_data[cols].apply(lambda x: 'Stabilising' if x >= 0 else 'Destabilising')
c2 = len(dynamut_data[dynamut_data[outcome_colname] == 'Stabilising'])
if c1 == c2:
print('\nPASS: outcome classification column created successfully'
, '\nColumn created:', outcome_colname
#, '\nNo. of stabilising muts: ', c1
#, '\nNo. of DEstabilising muts: ', tot_muts-c1
, '\n\nCateg counts:\n', dynamut_data[outcome_colname].value_counts() )
else:
print('\nFAIL: outcome classification numbers MISmatch'
, '\nexpected length:', c1
, '\nGot:', c2)
# Rename categ for: dds_encom
len(dynamut_data[dynamut_data['dds_encom'] >= 0])
dynamut_data['dds_encom_outcome'] = dynamut_data['dds_encom'].apply(lambda x: 'Increased_flexibility' if x >= 0 else 'Decreased_flexibility')
dynamut_data['dds_encom_outcome'].value_counts()
#%%=====================================================================
################################
# scale all ddg param values
#################################
# Rescale values in all ddg cols col b/w -1 and 1 so negative numbers
# stay neg and pos numbers stay positive
outcome_cols = ['ddg_dynamut', 'ddg_encom', 'ddg_mcsm','ddg_sdm', 'ddg_duet', 'dds_encom']
for cols in outcome_cols:
#print(cols)
col_max = dynamut_data[cols].max()
col_min = dynamut_data[cols].min()
print( '\n===================='
, '\nColname:', cols
, '\n===================='
, '\nMax: ', col_max
, '\nMin: ', col_min)
scaled_colname = cols + '_scaled'
print('\nCreated scaled colname for', cols, ':', scaled_colname)
col_scale = lambda x : x/abs(col_min) if x < 0 else (x/col_max if x >= 0 else 'failed')
dynamut_data[scaled_colname] = dynamut_data[cols].apply(col_scale)
col_scaled_max = dynamut_data[scaled_colname].max()
col_scaled_min = dynamut_data[scaled_colname].min()
print( '\n===================='
, '\nColname:', scaled_colname
, '\n===================='
, '\nMax: ', col_scaled_max
, '\nMin: ', col_scaled_min)
#%%=====================================================================
#############
# reorder columns
#############
dynamut_data.columns
dynamut_dataf = dynamut_data[['mutationinformation'
, 'ddg_dynamut'
, 'ddg_dynamut_scaled'
, 'ddg_dynamut_outcome'
, 'ddg_encom'
, 'ddg_encom_scaled'
, 'ddg_encom_outcome'
, 'ddg_mcsm'
, 'ddg_mcsm_scaled'
, 'ddg_mcsm_outcome'
, 'ddg_sdm'
, 'ddg_sdm_scaled'
, 'ddg_sdm_outcome'
, 'ddg_duet'
, 'ddg_duet_scaled'
, 'ddg_duet_outcome'
, 'dds_encom'
, 'dds_encom_scaled'
, 'dds_encom_outcome']]
if len(dynamut_data.columns) == len(dynamut_dataf):
print('\nPASS: outcome_classification, scaling and column reordering completed')
else:
print('\nFAIL: Something went wrong...'
, '\nExpected length: ', len(dynamut_data.columns)
, '\nGot: ', len(dynamut_dataf))
return(dynamut_dataf)
#%%#####################################################################

53
dynamut/run_format_results_dynamut.py Normal file
View file

@ -0,0 +1,53 @@
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Feb 12 12:15:26 2021
@author: tanu
"""
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
# FIXME
# RE RUN when B07 completes!!!! as norm gets affected!
#!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!!
#%% load packages
import os
homedir = os.path.expanduser('~')
os.chdir (homedir + '/git/LSHTM_analysis/dynamut')
from format_results_dynamut import *
########################################################################
# variables
# TODO: add cmd line args
gene = 'gid'
drug = 'streptomycin'
datadir = homedir + '/git/Data'
indir = datadir + '/' + drug + '/input'
outdir = datadir + '/' + drug + '/output'
outdir_dynamut = outdir + '/dynamut_results/'
# Input file
infile_dynamut = outdir_dynamut + gene + '_dynamut_all_output_clean.csv'
# Formatted output filename
outfile_dynamut_f = outdir_dynamut + gene + '_complex_dynamut_norm.csv'
#==========================
# CALL: format_results_mcsm_na()
# Data: gid+streptomycin
#==========================
print('Formatting results for:', infile_dynamut)
dynamut_df_f = format_dynamut_output(dynamut_output_csv = infile_dynamut)
# writing file
print('Writing formatted dynamut df to csv')
dynamut_df_f.to_csv(outfile_dynamut_f, index = False)
print('Finished writing file:'
, '\nFile:', outfile_dynamut_f
, '\nExpected no. of rows:', len(dynamut_df_f)
, '\nExpected no. of cols:', len(dynamut_df_f.columns)
, '\n=============================================================')
#%%#####################################################################