File size: 3,671 Bytes
70b95b8 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 |
#!/usr/bin/python
# coding: utf-8
# Author: LE YUAN
# Date: 2020-07-23
# This python script is to obtain canonical SMILES just by chemical name using PubChem API
import json
import time
import requests
import multiprocessing as mp
from multiprocessing.dummy import Pool
from pubchempy import Compound, get_compounds
# Small example:
# results = get_compounds('aspirin', 'name')
# for compound in results :
# print(compound.canonical_smiles)
# have a try by running 100 case
# with open("../complementaryData/Kcat_sabio_clean_unisubstrate.tsv", "r", encoding='utf-8') as file :
# lines = file.readlines()[1:]
# substrates = [line.strip().split('\t')[2] for line in lines]
# print(len(substrates))
# print(substrates[:10])
# for substrate in substrates[:100] :
# print(substrate)
# results = get_compounds(substrate, 'name')
# print(len(results))
# if len(results) >0 :
# print(results[0].canonical_smiles)
# else :
# print('-------------------------------------------------')
name_smiles = dict()
# One method to obtain SMILES by PubChem API using the website
def get_smiles(name):
# smiles = redis_cli.get(name)
# if smiles is None:
try :
url = 'https://pubchem.ncbi.nlm.nih.gov/rest/pug/compound/name/%s/property/CanonicalSMILES/TXT' % name
req = requests.get(url)
if req.status_code != 200:
smiles = None
else:
smiles = req.content.splitlines()[0].decode()
print(smiles)
# redis_cli.set(name, smiles, ex=None)
# print smiles
except :
smiles = None
name_smiles[name] = smiles
# Another method to retrieve SMILES by Pubchempy
# def get_smiles(name):
# time.sleep(0.5)
# results = get_compounds(name, 'name')
# # print(len(results))
# if len(results) >0 :
# smiles = results[0].canonical_smiles
# print(smiles)
# else :
# smiles = None
# print(smiles)
# print('-------------------------------------------------')
# name_smiles[name] = smiles
# # To obtain SMILES for substrates using provided API by PubChem
# def main():
# # with open('./smiles_data.json') as f:
# # names = json.load(f)
# # print(len(names))
# with open("../complementaryData/Kcat_brenda_clean.tsv", "r", encoding='utf-8') as file :
# lines = file.readlines()[1:]
# substrates = [line.strip().split('\t')[2] for line in lines]
# print(len(substrates)) # 52390
# names = list(set(substrates))
# print(len(names)) # 14457
# # for substrate in substrates[:100] :
# # print(substrate)
# # thread_pool = mp.Pool(4)
# thread_pool = Pool(4)
# thread_pool.map(get_smiles, names)
# with open('../complementaryData/Kcat_brenda_smiles.json', 'w') as outfile:
# json.dump(name_smiles, outfile, indent=2)
# To test how many entries having SMILES for Sabio-RK database
def main():
with open('../../Data/database/Kcat_brenda_smiles.json', 'r') as infile:
name_smiles = json.load(infile)
with open("../../Data/database/Kcat_brenda_clean.tsv", "r", encoding='utf-8') as file :
lines = file.readlines()[1:]
substrates = [line.strip().split('\t')[2] for line in lines]
print(len(substrates)) # 52390
substrate_smiles = list()
for substrate in substrates :
# print(substrate)
smiles = name_smiles[substrate]
# print(smiles)
if smiles is not None :
# print(smiles)
substrate_smiles.append(smiles)
print(len(substrate_smiles)) # 34857 have SMILES
if __name__ == '__main__':
main() |