198 lines
6.8 KiB
Python
Executable file
198 lines
6.8 KiB
Python
Executable file
#!/usr/bin/env python3
|
|
# -*- coding: utf-8 -*-
|
|
'''
|
|
Created on Tue Aug 6 12:56:03 2019
|
|
|
|
@author: tanu
|
|
'''
|
|
#=============================================================================
|
|
# Task: Residue depth (rd) processing to generate a df with residue_depth(rd)
|
|
# values
|
|
|
|
# FIXME: source file is MANUALLY downloaded from the website
|
|
# Input: '.tsv' i.e residue depth txt file (output from .zip file manually
|
|
# downloaded from the website).
|
|
# This should be integrated into the pipeline
|
|
|
|
# Output: .csv with 3 cols i.e position, rd_values & 3-letter wt aa code(caps)
|
|
#=============================================================================
|
|
#%% load packages
|
|
import sys, os
|
|
import argparse
|
|
import pandas as pd
|
|
#=============================================================================
|
|
#%% 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
|
|
arg_parser = argparse.ArgumentParser()
|
|
arg_parser.add_argument('-d', '--drug', help='drug name', default = None)
|
|
arg_parser.add_argument('-g', '--gene', help='gene name (case sensitive)', 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('-rd','--rd_file', help = 'residue depth file. By default, it assmumes a file called <gene>_rd.tsv in output_dir')
|
|
|
|
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
|
|
gene_match = gene + '_p.'
|
|
|
|
datadir = args.datadir
|
|
indir = args.input_dir
|
|
outdir = args.output_dir
|
|
|
|
rd_filename = args.rd_file
|
|
|
|
DEBUG = args.debug
|
|
|
|
#============
|
|
# directories
|
|
#============
|
|
if not datadir:
|
|
datadir = homedir + '/' + 'git/Data'
|
|
|
|
if not indir:
|
|
indir = datadir + '/' + drug + '/' + 'input'
|
|
|
|
if not outdir:
|
|
outdir = datadir + '/' + drug + '/' + 'output'
|
|
|
|
#======
|
|
# input
|
|
#=======
|
|
if rd_filename:
|
|
in_filename_rd = rd_filename
|
|
else:
|
|
in_filename_rd = gene.lower() + '_rd.tsv'
|
|
|
|
infile_rd = outdir + '/' + in_filename_rd
|
|
print('Input file:', infile_rd
|
|
, '\n=============================================================')
|
|
|
|
#=======
|
|
# output
|
|
#=======
|
|
out_filename_rd = gene.lower() + '_rd.csv'
|
|
outfile_rd = outdir + '/' + out_filename_rd
|
|
print('Output file:', outfile_rd
|
|
, '\n=============================================================')
|
|
|
|
#%% end of variable assignment for input and output files
|
|
#=======================================================================
|
|
#%% rd values from <gene>_rd.tsv values
|
|
def rd_to_csv(inputtsv, outputrdcsv):
|
|
"""
|
|
formats residue depth values from input file
|
|
|
|
@param inputtsv: tsv file downloaded from {INSERT LINK}
|
|
@type inputtsv: string
|
|
|
|
@param outputrdsv: csv file with rd values
|
|
@type outfile_rd: string
|
|
|
|
@return: none, writes rd values df as csv
|
|
"""
|
|
#========================
|
|
# read downloaded tsv file
|
|
#========================
|
|
#%% Read input file
|
|
rd_data = pd.read_csv(inputtsv, sep = '\t')
|
|
print('Reading input file:', inputtsv
|
|
, '\nNo. of rows:', len(rd_data)
|
|
, '\nNo. of cols:', len(rd_data.columns))
|
|
|
|
print('Column names:', rd_data.columns
|
|
, '\n===========================================================')
|
|
#========================
|
|
# creating position col
|
|
#========================
|
|
# Extracting residue number from index and assigning
|
|
# the values to a column [position]. Then convert the position col to numeric.
|
|
rd_data['position'] = rd_data.index.str.extract('([0-9]+)').values
|
|
|
|
# converting position to numeric
|
|
rd_data['position'] = pd.to_numeric(rd_data['position'])
|
|
rd_data['position'].dtype
|
|
|
|
print('Extracted residue num from index and assigned as a column:'
|
|
, '\ncolumn name: position'
|
|
, '\ntotal no. of cols now:', len(rd_data.columns)
|
|
, '\n=========================================================')
|
|
|
|
#========================
|
|
# Renaming amino-acid
|
|
# and all-atom cols
|
|
#========================
|
|
print('Renaming columns:'
|
|
, '\ncolname==> # chain:residue: wt_3letter_caps'
|
|
, '\nYES... the column name *actually* contains a # ..!'
|
|
, '\ncolname==> all-atom: rd_values'
|
|
, '\n=========================================================')
|
|
|
|
rd_data.rename(columns = {'# chain:residue':'wt_3letter_caps', 'all-atom':'rd_values'}, inplace = True)
|
|
print('Column names:', rd_data.columns)
|
|
|
|
#========================
|
|
# extracting df with the
|
|
# desired columns
|
|
#========================
|
|
print('Extracting relevant columns for writing df as csv')
|
|
|
|
rd_df = rd_data[['position','rd_values','wt_3letter_caps']]
|
|
|
|
if len(rd_df) == len(rd_data):
|
|
print('PASS: extracted df has expected no. of rows'
|
|
,'\nExtracted df dim:'
|
|
,'\nNo. of rows:', len(rd_df)
|
|
,'\nNo. of cols:', len(rd_df.columns))
|
|
else:
|
|
print('FAIL: no. of rows mimatch'
|
|
, '\nExpected no. of rows:', len(rd_data)
|
|
, '\nGot no. of rows:', len(rd_df)
|
|
, '\n=====================================================')
|
|
|
|
# Ensuring lowercase column names for consistency
|
|
rd_df.columns = rd_df.columns.str.lower()
|
|
|
|
#===============
|
|
# writing file
|
|
#===============
|
|
print('Writing file:'
|
|
, '\nFilename:', outputrdcsv
|
|
# , '\nPath:', outdir
|
|
# , '\nExpected no. of rows:', len(rd_df)
|
|
# , '\nExpected no. of cols:', len(rd_df.columns)
|
|
, '\n=========================================================')
|
|
|
|
rd_df.to_csv(outputrdcsv, header = True, index = False)
|
|
|
|
#%% end of function
|
|
#=======================================================================
|
|
#%% call function
|
|
#rd_to_csv(infile_rd, outfile_rd)
|
|
#=======================================================================
|
|
def main():
|
|
print('residue depth using the following params'
|
|
, '\nInput residue depth file:', in_filename_rd
|
|
, '\nOutput:', out_filename_rd)
|
|
rd_to_csv(infile_rd, outfile_rd)
|
|
print('Finished Writing file:'
|
|
, '\nFilename:', outfile_rd
|
|
, '\n=============================================================')
|
|
|
|
if __name__ == '__main__':
|
|
main()
|
|
#%% end of script
|
|
#=======================================================================
|