bring in embb stuff which was in the wrong branch

scripts/deepddg_format.py

@@ -0,0 +1,149 @@
+#!/usr/bin/env python3
+# -*- coding: utf-8 -*-
+'''
+Created on Tue Aug  6 12:56:03 2019
+
+@author: tanu
+'''
+#=======================================================================
+# Task: format deep ddg df to allow easy merging
+
+# Input:  2 dfs
+#1) <gene>.lower()'_mcsm_formatted_snps.csv'
+#2) <gene>.lower()_complex_ddg_results.csv'
+#=======================================================================
+#%% load packages
+import sys, os
+import pandas as pd
+from pandas import DataFrame
+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()
+#=======================================================================#%% command line args: case sensitive
+arg_parser = argparse.ArgumentParser()
+arg_parser.add_argument('-d', '--drug', help = 'drug name', default = '')
+arg_parser.add_argument('-g', '--gene', help = 'gene name', default = '') 
+
+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')
+
+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_mcsm_snps = gene.lower() + '_mcsm_formatted_snps.csv'
+infile_mcsm_snps = outdir + in_filename_mcsm_snps
+
+in_filename_deepddg = gene.lower() + '_complex_ddg_results.csv' 
+infile_deepddg = outdir + 'deep_ddg/' + in_filename_deepddg
+
+print('\nInput path:', indir
+      , '\nOutput path:', outdir, '\n'
+      , '\nInput filename mcsm snps', infile_mcsm_snps , '\n'
+      , '\nInput filename deepddg', infile_deepddg , '\n'
+      , '\n============================================================')
+
+#=======
+# output 
+#=======
+#out_filename_deepddg = gene.lower() + '_ni_deepddg.txt'
+out_filename_deepddg = gene.lower() + '_ni_deepddg.csv'
+outfile_deepddg_f =  outdir + out_filename_deepddg
+
+print('Output filename:', outfile_deepddg_f
+        , '\n===================================================================')
+# end of variable assignment for input and output files
+#%%============================================================================  
+print('==================================='
+      , '\nmcsm muts'
+      , '\n===================================')
+
+mcsm_muts_df =  pd.read_csv(infile_mcsm_snps , header = None, sep = ',', names = ['mutationinformation'])
+mcsm_muts_df.columns
+
+#%%============================================================================  
+print('==================================='
+      , '\nDeep ddg'
+      , '\n===================================')
+
+deepddg_df =  pd.read_csv(infile_deepddg, sep = ',')
+deepddg_df.columns
+
+deepddg_df.rename(columns = {'#chain'  : 'chain_id'
+                             , 'WT'    : 'wild_type_deepddg'
+                             , 'ResID' : 'position'
+                             , 'Mut'   : 'mutant_type_deepddg'}
+                             , inplace = True)
+deepddg_df.columns
+deepddg_df['mutationinformation'] = deepddg_df['wild_type_deepddg'] + deepddg_df['position'].map(str) + deepddg_df['mutant_type_deepddg']
+deepddg_df.columns
+
+# add deepddg outcome column: <0--> Destabilising, >0 --> Stabilising
+deepddg_df['deepddg_outcome'] = np.where(deepddg_df['deepddg'] < 0, 'Destabilising', 'Stabilising')
+deepddg_df['deepddg_outcome'].value_counts()
+
+# should be identical in count ot Destabilising and stabilising respectively
+len(deepddg_df.loc[deepddg_df['deepddg'] < 0])
+len(deepddg_df.loc[deepddg_df['deepddg'] >= 0])
+               
+#----------------------------------------------
+# drop extra columns to allow clean merging
+#----------------------------------------------
+#deepddg_short_df = deepddg_df.drop(['chain_id', 'wild_type_deepddg', 'position', 'mutant_type_deepddg'], axis = 1)
+
+#----------------------------------------------
+# embb (where gene-target has > 1 chain)
+# include chain else the numbering will be messed up!
+#----------------------------------------------
+deepddg_short_df = deepddg_df.drop(['wild_type_deepddg', 'position', 'mutant_type_deepddg'], axis = 1)
+
+# rearrange columns
+deepddg_short_df.columns
+deepddg_short_df = deepddg_short_df[["chain_id", "mutationinformation", "deepddg", "deepddg_outcome"]]
+
+#%% combine with mcsm snps 
+deepddg_mcsm_muts_dfs = pd.merge(deepddg_short_df
+                                 , mcsm_muts_df
+                                 , on = 'mutationinformation'
+                                 , how = 'right')
+deepddg_mcsm_muts_dfs ['deepddg_outcome'].value_counts()
+
+#%%============================================================================
+# write csv
+print('Writing file: formatted deepddg and only mcsm muts')
+deepddg_mcsm_muts_dfs.to_csv(outfile_deepddg_f, index = False)
+print('\nFinished writing file:'
+      , '\nNo. of rows:', deepddg_mcsm_muts_dfs.shape[0]
+      , '\nNo. of cols:', deepddg_mcsm_muts_dfs.shape[1])
+#%% end of script