110 lines
3.4 KiB
Python
Executable file
110 lines
3.4 KiB
Python
Executable file
#!/home/tanu/anaconda3/envs/ContactMap/bin/python3
|
|
# -*- coding: utf-8 -*-
|
|
"""
|
|
Created on Tue Feb 18 10:10:12 2020
|
|
|
|
@author: tanu
|
|
"""
|
|
#=======================================================================
|
|
# Task: Read a DSSP file into a data frame and output to a csv file
|
|
|
|
# Input: '.dssp' i.e gene associated.dssp file (output from run_dssp.sh)
|
|
|
|
# Output: '.csv' file containing DSSP output as a df ith ASA, RSA, etc.
|
|
|
|
# useful links:
|
|
#https://jbloomlab.github.io/dms_tools2/dms_tools2.dssp.html
|
|
#https://jbloomlab.github.io/dms_tools2/dms_tools2.dssp.html
|
|
#=======================================================================
|
|
#%% load packages
|
|
import sys, os
|
|
import re
|
|
import pandas as pd
|
|
from Bio.PDB import PDBParser
|
|
from Bio.PDB.DSSP import DSSP
|
|
import pandas as pd
|
|
import pprint as pp
|
|
#from Bio.PDB.PDBParser import PDBParser
|
|
import dms_tools2
|
|
import dms_tools2.dssp
|
|
#=======================================================================#
|
|
#%% specify homedir and curr dir
|
|
homedir = os.path.expanduser('~')
|
|
|
|
# set working dir
|
|
os.getcwd()
|
|
os.chdir(homedir + '/git/LSHTM_analysis/meta_data_analysis')
|
|
os.getcwd()
|
|
#=======================================================================
|
|
#%% variable assignment: input and output
|
|
drug = 'pyrazinamide'
|
|
gene = 'pncA'
|
|
#gene_match = gene + '_p.'
|
|
|
|
#==========
|
|
# data dir
|
|
#==========
|
|
#indir = 'git/Data/pyrazinamide/input/original'
|
|
datadir = homedir + '/' + 'git/Data'
|
|
|
|
#=======
|
|
# input from outdir
|
|
#=======
|
|
#indir = datadir + '/' + drug + '/' + 'output'
|
|
outdir = datadir + '/' + drug + '/' + 'output'
|
|
#in_filename = 'pnca.dssp'
|
|
in_filename = gene.lower() +'.dssp'
|
|
infile = indir + '/' + in_filename
|
|
print('Input filename:', in_filename
|
|
, '\nInput path:', indir
|
|
, '\n============================================================')
|
|
|
|
# specify PDB chain
|
|
my_chain = 'A'
|
|
|
|
#=======
|
|
# output
|
|
#=======
|
|
outdir = datadir + '/' + drug + '/' + 'output'
|
|
out_filename = gene.lower() + '_dssp.csv'
|
|
outfile = outdir + '/' + out_filename
|
|
print('Output filename:', out_filename
|
|
, '\nOutput path:', outdir
|
|
, '\nOutfile: ', outfile
|
|
, '\n=============================================================')
|
|
|
|
#%% end of variable assignment for input and output files
|
|
#=======================================================================
|
|
# Process dssp output and extract into df
|
|
dssp_file = infile
|
|
dssp_df = dms_tools2.dssp.processDSSP(dssp_file, chain = my_chain)
|
|
# returns df with ASA and RSA (base on Tien at al 2013 (theor.) values)
|
|
# Link: https://en.wikipedia.org/wiki/Relative_accessible_surface_area
|
|
pp.pprint(dssp_df)
|
|
|
|
#=====================
|
|
# Renaming amino-acid
|
|
# and site columns
|
|
#=====================
|
|
|
|
# Rename column (amino acid) as 'wild_type' and (site} as 'position'
|
|
# to be the same names as used in the file required for merging later.
|
|
dssp_df.columns
|
|
dssp_df.rename(columns = {'site':'position', 'amino_acid':'wild_type_dssp'}, inplace = True)
|
|
dssp_df.columns
|
|
|
|
#%% Write ouput csv file
|
|
print('Writing file:', outfile
|
|
, '\nFilename:', out_filename
|
|
, '\nPath:', outdir
|
|
, '\n=============================================================')
|
|
|
|
# write to csv
|
|
dssp_df.to_csv(outfile, header=True, index = False)
|
|
|
|
print('Finished writing:', out_filename
|
|
, '\nNo. of rows:', len(dssp_df)
|
|
, '\nNo. of cols:', len(dssp_df.columns)
|
|
, '\n==============================================================')
|
|
#%% end of script
|
|
#=======================================================================
|