-
Notifications
You must be signed in to change notification settings - Fork 5
/
processing_canonical.py
executable file
·122 lines (105 loc) · 3.18 KB
/
processing_canonical.py
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
import rdkit
from rdkit import Chem
import numpy as np
import pandas as pd
from functools import partial
from multiprocessing import Pool
import pandas as pd
from tqdm.auto import tqdm
import pathlib
import argparse
def get_parser():
parser = argparse.ArgumentParser()
parser.add_argument(
'--model', '-m',
type=str, default='aae',
help='model name : aae vae latentgan reinvent organ char_rnn'
)
parser.add_argument(
'--epoch', '-e',
type=int, default=100,
help='epoch that SMILES was sampled'
)
parser.add_argument(
'--n_jobs', type=int, default=40,
help='number of processes to use'
)
parser.add_argument(
'--path', type=str,
default='./',
help='path to sampled files'
)
parser.add_argument(
'--output', '-o', type=str,
default='./SampledDatasetCano.csv',
help='path to save files'
)
parser.add_argument(
'--sample_id', '-si', type=int,
default='0',
help='Index of sampling'
)
return parser
def file_collection(model, epoch):
file_set = []
for i in range(8):
file_set.append('%s_model_s_%d_%d.csv' % (model, epoch, i))
return file_set
def open_file(file_set, path):
dataset = []
file_path = pathlib.Path(path, file_set)
with open(file_path, 'r') as f: # gzip.open(path) as smi:
next(f)
lines = f.readlines()
for line in lines:
line = line.split()
dataset.append(line[0])
return dataset
def smile_canonical(smi):
try:
mol = Chem.MolFromSmiles(smi)
smi_cano = Chem.MolToSmiles(mol, isomericSmiles=False)
return smi_cano
except:
print(smi + "was not valid SMILES\n")
return None
def set_canonical(n_jobs, output, file_set):
global dataset
with Pool(n_jobs) as pool:
smile_canonical_p = partial(smile_canonical)
dataset_cano = [x for x in tqdm(
pool.imap_unordered(smile_canonical_p, dataset),
total=len(dataset),
miniters=1000
)
if x is not None
]
dataset = []
dataset_cano = pd.DataFrame(dataset_cano, columns=['SMILES'])
dataset_cano.to_csv(file_set+'_nofilter.cano', index=None)
dataset_cano = dataset_cano.drop_duplicates('SMILES')
dataset_cano.to_csv(file_set+'.cano', index=None)
def main(config):
#model = config.model
#epoch = config.epoch
sample_id = config.sample_id
n_jobs = config.n_jobs
path = config.path
output = config.output
global dataset
# file_set = file_collection(model, epoch)
for sample_id in range(0,1,1):
file_set = 'ChEMBL_training_set.csv'
dataset = open_file(file_set, path)
# dataset = ['C12C3C4C5C4C4C(C4C13)C25',
# 'C1C2C1C1C3C4CC4C2C13',
# 'C1C2C1C1C3C4CC4C1C23',
# 'C1C2C1C1C3C4CC(C24)C13',
# 'C1C2C1C1C3CC4C2C4C31',
# 'C1C2']
set_canonical(n_jobs, output, file_set)
if __name__ == '__main__':
parser = get_parser()
config, unknown = parser.parse_known_args()
dataset = []
main(config)