LSHTM_analysis/scripts/reference_dict.py

237 lines
8.8 KiB
Python
Executable file

#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Tue Jun 18 11:32:28 2019
@author: tanushree
"""
#=======================================================================
# TASK: creating an aa dict to map aa 3-letter and 1-letter code to aa
# properties. Other mappings can also be created trivially by adpating
# the code
# Input: .csv file containing aa_code
# Output: sourced by other .py script to perform aa property mapping.
#=======================================================================
#%% load packages
import pandas as pd
import os
#=======================================================================
#%% specify homedir and curr dir
homedir = os.path.expanduser('~')
#=======================================================================
#%% variable assignment
#==========
# data dir
#==========
datadir = homedir + '/' + 'git/Data'
#=======
# input
#=======
in_filename = 'aa_codes.csv'
infile = datadir + '/' + in_filename
#print('Input filename:', in_filename
# , '\nInput path:', datadir
# , '\n============================================================')
#%% Read input file
aa_table = pd.read_csv(infile) #20, 6
#------------------------
#1) 3-letter (lower) code as key
#-------------------------
# assign the one_letter code as the row names so that it is easier to create
# a dict of dicts using index
#my_aa = pd.read_csv('aa_codes.csv', index_col = 0) #20, 6 #a way to it since it is the first column
my_aa = aa_table.set_index('three_letter_code_lower') #20, 5
my_aa.columns
my_aa.index
#==================
# convert file
# to dict of dicts
#====================
# convert each row into a dict of dicts so that there are 20 aa and 5 keys within
# with your choice of column name that you have assigned to index as the "primary key".
# using 'index' creates a dict of dicts
# using 'records' creates a list of dicts
#FIXME: remove this and replace with below as shown
my_aa_dict = my_aa.to_dict('index') #20, with 5 subkeys
#print('Printing my_aa_dict:', my_aa_dict.keys())
#FIXME : use the below in all code
low_3letter_dict = my_aa.to_dict('index') #20, with 5 subkeys
#print('Printing lower-case 3 letter aa dict:',low_3letter_dict.keys())
#------------------------
#2) 1-letter code as key
#-------------------------
aa_1let = aa_table.set_index('one_letter_code') #20, 5
aa_1let.columns
aa_1let.index
oneletter_aa_dict = aa_1let.to_dict('index') #20, with 5 subkeys
#print('Printing one letter aa dict:', oneletter_aa_dict.keys())
#------------------------
#3) amino acid name as key
#-------------------------
aa_name = aa_table.set_index('amino_acid_name') #20, 5
aa_name.columns
aa_name.index
aa_name_dict = aa_name.to_dict('index') #20, with 5 subkeys
#print('Printing amino acid names aa dict:', aa_name_dict.keys())
#------------------------
#3) 3 letter uppercase as key
#-------------------------
aa_up3let = aa_table.set_index('three_letter_code_upper') #20, 5
aa_up3let.columns
aa_up3let.index
up_3letter_aa_dict = aa_up3let.to_dict('index') #20, with 5 subkeys
#print('Printing upper case 3 letter aa dict:', up_3letter_aa_dict.keys())
#================================================
# dict of aa with their corresponding properties
#================================================
# 7 categories: no overlap
qualities1 = { ('R', 'H', 'K'): 'Basic'
, ('D', 'E'): 'Acidic'
, ('N', 'Q'): 'Amidic'
, ('G', 'A', 'V', 'L', 'I', 'P'): 'Hydrophobic'
, ('S', 'T'): 'Hydroxylic'
, ('F', 'W', 'Y'): 'Aromatic'
, ('C', 'M'): 'Sulphur'
}
# 9 categories: allowing for overlap
qualities2 = { ('R', 'H', 'K'): 'Basic'
, ('D', 'E'): 'Acidc'
, ('S', 'T', 'N', 'Q'): 'Polar'
, ('V', 'I', 'L', 'M', 'F', 'Y', 'W'): 'Hydrophobic'
, ('S', 'T', 'H', 'N', 'Q', 'E', 'D', 'K', 'R'): 'Hydrophilic'
, ('S', 'G', 'A', 'P'): 'Small'
, ('F', 'W', 'Y', 'H'): 'Aromatic'
, ('V', 'I', 'L', 'M'): 'Aliphatic'
, ('C', 'G', 'P'): 'Special'
}
# taylor classification: allowing for overlap
qualities_taylor = { ('R', 'H', 'K'): 'Basic'
, ('D', 'E'): 'Acidc'
, ('S', 'T', 'N', 'Q', 'C', 'Y', 'W', 'H', 'K', 'R', 'D', 'E'): 'Polar'
, ('V', 'I', 'L', 'M', 'F', 'Y', 'W', 'C', 'A', 'G', 'T', 'H'): 'Hydrophobic'
#, ('S', 'T', 'H', 'N', 'Q', 'E', 'D', 'K', 'R'): 'Hydrophilic', #C, W, y MISSING FROM POLAR!
, ('S', 'G', 'A', 'P', 'C', 'T', 'N', 'D', 'V'): 'Small'
, ('F', 'W', 'Y', 'H'): 'Aromatic'
, ('V', 'I', 'L', 'M'): 'Aliphatic' #although M is not strictly in the circle!
, ('C', 'G', 'P'): 'Special'
}
# ternary classification: hydrophobic --> neutral --> hydrophilic (KD scale)
#http://www.imgt.org/IMGTeducation/Aide-memoire/_UK/aminoacids/IMGTclasses.html
qualities_water = { ('I','V','L','F','C','M','A','W'): 'hydrophobic'
, ('G','T','S','Y','P','H'): 'neutral'
, ('N','D','Q','E','K','R'): 'hydrophilic'
}
# polarity: no overlap
qualities_polarity = { ('D', 'E'): 'acidic'
, ('H', 'K', 'R'): 'basic'
, ('C', 'G', 'N', 'Q', 'S', 'T', 'Y'): 'neutral'
, ('A', 'F', 'I', 'L', 'M', 'P', 'V', 'W'): 'non-polar'
}
# almost same as the one above but as pos, neg, polar and non-polar
aa_calcprop = { ('D', 'E'): 'neg'
, ('H', 'K', 'R'): 'pos'
, ('N', 'Q', 'S', 'T', 'Y'): 'polar'
, ('C', 'G', 'A', 'F', 'I', 'L', 'M', 'P', 'V', 'W'): 'non-polar'
}
#==============================================================================
#%% Adding amino acid properties to my dict of dicts
#---------------------------------------------
# building dict: my_aa_dict
# FIXME: my_aa_dict.items:
# should be changed to 'low_3letter_dict'
#---------------------------------------------
for k, v in my_aa_dict.items():
#print (k,v)
v['aa_prop1'] = str() #initialise keys
v['aa_prop2'] = list() #initialise keys (allows for overalpping properties)
v['aa_taylor'] = list() #initialise keys (allows for overalpping properties)
v['aa_prop_water'] = str() #initialise keys
v['aa_prop_polarity'] = str() #initialise keys
v['aa_calcprop'] = str() #initialise keys
for group in qualities1:
if v['one_letter_code'] in group:
v['aa_prop1']+= qualities1[group] # += for str concat
for group in qualities2:
if v['one_letter_code'] in group:
v['aa_prop2'].append(qualities2[group]) # append to list
for group in qualities_taylor:
if v['one_letter_code'] in group:
v['aa_taylor'].append(qualities_taylor[group]) # append to list
for group in qualities_water:
if v['one_letter_code'] in group:
v['aa_prop_water']+= qualities_water[group] # += for str concat
for group in qualities_polarity:
if v['one_letter_code'] in group:
v['aa_prop_polarity']+= qualities_polarity[group] # += for str concat
for group in aa_calcprop:
if v['one_letter_code'] in group:
v['aa_calcprop']+= aa_calcprop[group] # += for str concat
#%%
#-----------------------------------
# building dict: oneletter_aa_dict
#-----------------------------------
for k, v in oneletter_aa_dict.items():
#print (k,v)
v['aa_prop1'] = str() #initialise keys
v['aa_prop2'] = list() #initialise keys (allows for overalpping properties)
v['aa_taylor'] = list() #initialise keys (allows for overalpping properties)
v['aa_prop_water'] = str() #initialise keys
v['aa_prop_polarity'] = str() #initialise keys
v['aa_calcprop'] = str() #initialise keys
for group in qualities1:
if k in group:
v['aa_prop1']+= qualities1[group] # += for str concat
for group in qualities2:
if k in group:
v['aa_prop2'].append(qualities2[group]) # append to list
for group in qualities_taylor:
if k in group:
v['aa_taylor'].append(qualities_taylor[group]) # append to list
for group in qualities_water:
if k in group:
v['aa_prop_water']+= qualities_water[group] # += for str concat
for group in qualities_polarity:
if k in group:
v['aa_prop_polarity']+= qualities_polarity[group] # += for str concat
for group in aa_calcprop:
if k in group:
v['aa_calcprop']+= aa_calcprop[group] # += for str concat
#%%
# COMMENT:VOILA! two different keytypes set for dicts containinga all
# associated aa properties
#==============================================================================
#%% end of script