From 0881181f4b4aca34eee13d2d1983958e67246cc3 Mon Sep 17 00:00:00 2001 From: Tanushree Tunstall Date: Mon, 14 Jun 2021 13:24:00 +0100 Subject: [PATCH] added aa_prop.py and add_aa_prop.py to add aa properties for wt and mutant in a given file containing one letter code wt and mut cols as csv --- scripts/aa_prop.py | 113 ++++++++++++++++++++++++ scripts/add_aa_prop.py | 191 +++++++++++++++++++++++++++++++++++++++++ 2 files changed, 304 insertions(+) create mode 100644 scripts/aa_prop.py create mode 100644 scripts/add_aa_prop.py diff --git a/scripts/aa_prop.py b/scripts/aa_prop.py new file mode 100644 index 0000000..6ed9222 --- /dev/null +++ b/scripts/aa_prop.py @@ -0,0 +1,113 @@ +#!/usr/bin/env python3 +# -*- coding: utf-8 -*- +''' +Created on Mon June 14 2021 + +@author: tanu +''' +# FIXME: import dirs.py to get the basic dir paths available +#======================================================================= +# TASK + +# Input: + +# Output: +#======================================================================= +#%% load libraries +import os, sys +import pandas as pd +#import numpy as np +#from varname import nameof +import argparse + +DEBUG = False +#======================================================================= +#%% 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 +#======================================================================= +#%% +def get_aa_prop(df, col1 = 'aap1', col2 = 'aap2', col3 = 'aap_taylor', col4 = 'aap_kd', col5 = 'aap_polarity', col6 = 'aap_calcprop'): + + """Add amino acid properties for wt and mutant residues + + @df: df containing one letter aa code for wt and mutant respectively + @type: pandas df + + @col1: column adding 7 aa categories (no overlap; acidic, basic, amidic, hydrophobic, hydroxylic, aromatic, sulphur) + @type: str + + @col2: column adding 9 aa categories (overlap; acidic, basic, polar, hydrophobic, hydrophilic, small, aromatic, aliphatic, special) + @type: str + + @col3: column adding 8 aa categories (overlap; acidic, basic, polar, hydrophobic, small, aromatic, aliphatic, special) + @type: str + + @col4: column adding 3 aa categories (no overlap, hydrophobic, neutral and hydrophilic according to KD scale) + @type: str + + @col5: column adding 4 aa categories (no overlap, acidic, basic, neutral, non-polar) + @type: str + + @col6: column adding 4 aa categories (neg, pos, polar, non-polar) + @type: str + + returns df: with 6 added columns. If column names clash, the function column + name will override original column + @rtype: pandas df + """ + + lookup_dict_p1 = dict() + lookup_dict_p2 = dict() + + lookup_dict_taylor = dict() + lookup_dict_kd = dict() + + lookup_dict_polarity = dict() + lookup_dict_calcprop = dict() + + for k, v in oneletter_aa_dict.items(): + + lookup_dict_p1[k] = v['aa_prop1'] + + lookup_dict_p2[k] = v['aa_prop2'] + + lookup_dict_taylor[k] = v['aa_taylor'] + + lookup_dict_kd[k] = v['aa_prop_water'] + + lookup_dict_polarity[k] = v['aa_prop_polarity'] + + lookup_dict_calcprop[k] = v['aa_calcprop'] + + #if DEBUG: + # print('Key:', k, 'value:', v + # , '\n============================================================' + # , '\nlook up dict:\n') + + df['wt_aap1'] = df['wild_type'].map(lookup_dict_p1) + df['mut_aap1'] = df['mutant_type'].map(lookup_dict_p1) + + df['wt_aap2'] = df['wild_type'].map(lookup_dict_p2) + df['mut_aap2'] = df['mutant_type'].map(lookup_dict_p2) + + df['wt_aap_taylor'] = df['wild_type'].map(lookup_dict_taylor) + df['mut_aap_taylor'] = df['mutant_type'].map(lookup_dict_taylor) + + df['wt_aap_kd'] = df['wild_type'].map(lookup_dict_kd) + df['mut_aap_kd'] = df['mutant_type'].map(lookup_dict_kd) + + df['wt_aap_polarity'] = df['wild_type'].map(lookup_dict_polarity) + df['mut_aap_polarity'] = df['mutant_type'].map(lookup_dict_polarity) + + df['wt_aa_calcprop'] = df['wild_type'].map(lookup_dict_calcprop) + df['mut_aa_calcprop'] = df['mutant_type'].map(lookup_dict_calcprop) + + return df +#======================================== \ No newline at end of file diff --git a/scripts/add_aa_prop.py b/scripts/add_aa_prop.py new file mode 100644 index 0000000..ed2466d --- /dev/null +++ b/scripts/add_aa_prop.py @@ -0,0 +1,191 @@ +#!/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: +# + +# Input: + +# Output: +#======================================================================= +#%% 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 aa_prop import get_aa_prop +#======================================================================= +#%% 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 + + input') +arg_parser.add_argument('-o', '--output_dir', help = 'Output dir for results. By default, it assmes homedir + + 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_mcsm = gene.lower() + '_complex_mcsm_norm_SRY.csv' # gid +infile_mcsm = outdir + '/' + in_filename_mcsm +print('Input file: ', infile_mcsm + , '\n============================================================') + +#======= +# output +#======= +out_filename_aaps = gene.lower() + '_mcsm_aaps.txt' +outfile_aaps = outdir + '/' + out_filename_aaps +print('Output file: ', outfile_aaps + , '\n============================================================') + +#%% end of variable assignment for input and output files +#======================================================================= +#%% Read input files +print('Reading input file (merged file):', infile_mcsm) + +comb_df = pd.read_csv(infile_mcsm, sep = ',') + +print('Input filename: ', in_filename_mcsm + , '\nPath :', outdir + , '\nNo. of rows: ', len(comb_df) + , '\nNo. of cols: ', len(comb_df.columns) + , '\n============================================================') + +# column names +list(comb_df.columns) + +#%% sanity check +nrows_df = len(comb_df) +ncols_add = 12 +expected_cols = len(comb_df.columns) + ncols_add +print('\nAdding aa properties for wt and mutant: ', ncols_add, ' columns in total' + , '\n===============================================================') + +#%% call get_aa_prop(): +get_aa_prop(df = comb_df) + +#%% check dim of df +if len(comb_df) == nrows_df and len(comb_df.columns) == expected_cols: + print('Checking dim of df: ' + , '\nPASS: df dim match' + , '\nno.of rows: ', len(comb_df) + , '\nno. of cols: ', len(comb_df.columns)) +else: + print('\FAIL: dim mismatch' + , 'Expected rows: ', nrows_df + , '\Got: ', len(comb_df) + , '\nExpected cols: ', expected_cols + , '\nGot: ', len(comb_df.columns)) + sys.exit('Aborting') +#%% summary output +sys.stdout = open(outfile_aaps, 'w') + +print('################################################' + , '\n aa properties: ', gene + , '\n################################################') + +print('\n-------------------' + , '\nWild-type: aap 1' + , '\n-------------------\n' + , comb_df['wt_aap1'].value_counts() + , '\n-------------------' + , '\nmutant-type: aap 1' + , '\n-------------------\n' + , comb_df['mut_aap1'].value_counts() + , '\n===================================================') + +print('\n-------------------' + , '\nWild-type: aap 2' + , '\n-------------------\n' + , comb_df['wt_aap2'].value_counts() + , '\n-------------------' + , '\nmutant-type: aap 2' + , '\n-------------------\n' + , comb_df['mut_aap2'].value_counts() + , '\n===================================================') + +print('\n-------------------' + , '\nWild-type: aap taylor' + , '\n-------------------\n' + , comb_df['wt_aap_taylor'].value_counts() + , '\n-------------------' + , '\nmutant-type: taylor' + , '\n-------------------\n' + , comb_df['mut_aap_taylor'].value_counts() + , '\n===================================================') + +print('\n-------------------' + , '\nWild-type: aap water/kd' + , '\n-------------------\n' + , comb_df['wt_aap_kd'].value_counts() + , '\n-------------------' + , '\nmutant-type: water/kd' + , '\n-------------------\n' + , comb_df['mut_aap_kd'].value_counts() + , '\n===================================================') + +print('\n-------------------' + , '\nWild-type: aap polarity' + , '\n-------------------\n' + , comb_df['wt_aap_polarity'].value_counts() + , '\n-------------------' + , '\nmutant-type: polarity' + , '\n-------------------\n' + , comb_df['mut_aap_polarity'].value_counts() + , '\n===================================================') + +print('\n-------------------' + , '\nWild-type: aa calcprop' + , '\n-------------------\n' + , comb_df['wt_aa_calcprop'].value_counts() + , '\n-------------------' + , '\nmutant-type: aa calcprop' + , '\n-------------------\n' + , comb_df['mut_aa_calcprop'].value_counts() + , '\n===================================================') + +#%% end of script +#=======================================================================