/
qm7_datasets.py
297 lines (252 loc) · 11.3 KB
/
qm7_datasets.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
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
"""
qm7 dataset loader.
"""
import os
import numpy as np
import deepchem
import scipy.io
import logging
logger = logging.getLogger(__name__)
DEFAULT_DIR = deepchem.utils.get_data_dir()
QM7_MAT_URL = 'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.mat'
QM7_CSV_URL = 'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7.csv'
QM7B_MAT_URL = 'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/qm7b.mat'
GDB7_URL = 'http://deepchem.io.s3-website-us-west-1.amazonaws.com/datasets/gdb7.tar.gz'
def load_qm7_from_mat(featurizer='CoulombMatrix',
split='stratified',
reload=True,
move_mean=True,
data_dir=None,
save_dir=None,
**kwargs):
qm7_tasks = ["u0_atom"]
if data_dir is None:
data_dir = DEFAULT_DIR
if save_dir is None:
save_dir = DEFAULT_DIR
if reload:
save_folder = os.path.join(save_dir, "qm7-featurized")
if not move_mean:
save_folder = os.path.join(save_folder, str(featurizer) + "_mean_unmoved")
else:
save_folder = os.path.join(save_folder, str(featurizer))
if featurizer == "smiles2img":
img_spec = kwargs.get("img_spec", "std")
save_folder = os.path.join(save_folder, img_spec)
save_folder = os.path.join(save_folder, str(split))
loaded, all_dataset, transformers = deepchem.utils.save.load_dataset_from_disk(
save_folder)
if loaded:
return qm7_tasks, all_dataset, transformers
if featurizer == 'CoulombMatrix':
dataset_file = os.path.join(data_dir, "qm7.mat")
if not os.path.exists(dataset_file):
deepchem.utils.download_url(url=QM7_MAT_URL, dest_dir=data_dir)
dataset = scipy.io.loadmat(dataset_file)
X = dataset['X']
y = dataset['T'].T
w = np.ones_like(y)
dataset = deepchem.data.DiskDataset.from_numpy(X, y, w, ids=None)
elif featurizer == 'BPSymmetryFunctionInput':
dataset_file = os.path.join(data_dir, "qm7.mat")
if not os.path.exists(dataset_file):
deepchem.utils.download_url(url=QM7_MAT_URL, dest_dir=data_dir)
dataset = scipy.io.loadmat(dataset_file)
X = np.concatenate([np.expand_dims(dataset['Z'], 2), dataset['R']], axis=2)
y = dataset['T'].reshape(-1, 1) # scipy.io.loadmat puts samples on axis 1
w = np.ones_like(y)
dataset = deepchem.data.DiskDataset.from_numpy(X, y, w, ids=None)
else:
dataset_file = os.path.join(data_dir, "qm7.csv")
if not os.path.exists(dataset_file):
deepchem.utils.download_url(url=QM7_CSV_URL, dest_dir=data_dir)
if featurizer == 'ECFP':
featurizer = deepchem.feat.CircularFingerprint(size=1024)
elif featurizer == 'GraphConv':
featurizer = deepchem.feat.ConvMolFeaturizer()
elif featurizer == 'Weave':
featurizer = deepchem.feat.WeaveFeaturizer()
elif featurizer == 'Raw':
featurizer = deepchem.feat.RawFeaturizer()
elif featurizer == "smiles2img":
img_spec = kwargs.get("img_spec", "std")
img_size = kwargs.get("img_size", 80)
featurizer = deepchem.feat.SmilesToImage(
img_size=img_size, img_spec=img_spec)
loader = deepchem.data.CSVLoader(
tasks=qm7_tasks, smiles_field="smiles", featurizer=featurizer)
dataset = loader.featurize(dataset_file)
if split == None:
raise ValueError()
else:
splitters = {
'index': deepchem.splits.IndexSplitter(),
'random': deepchem.splits.RandomSplitter(),
'stratified':
deepchem.splits.SingletaskStratifiedSplitter(task_number=0)
}
splitter = splitters[split]
frac_train = kwargs.get("frac_train", 0.8)
frac_valid = kwargs.get('frac_valid', 0.1)
frac_test = kwargs.get('frac_test', 0.1)
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
dataset,
frac_train=frac_train,
frac_valid=frac_valid,
frac_test=frac_test)
transformers = [
deepchem.trans.NormalizationTransformer(
transform_y=True, dataset=train_dataset, move_mean=move_mean)
]
for transformer in transformers:
train_dataset = transformer.transform(train_dataset)
valid_dataset = transformer.transform(valid_dataset)
test_dataset = transformer.transform(test_dataset)
if reload:
deepchem.utils.save.save_dataset_to_disk(
save_folder, train_dataset, valid_dataset, test_dataset, transformers)
return qm7_tasks, (train_dataset, valid_dataset, test_dataset), transformers
def load_qm7b_from_mat(featurizer='CoulombMatrix',
split='stratified',
reload=True,
move_mean=True,
data_dir=None,
save_dir=None,
**kwargs):
"""Load QM7B dataset
QM7b is an extension for the QM7 dataset with additional properties predicted at different levels (ZINDO, SCS, PBE0, GW). In total 14 tasks are included for 7211 molecules with up to 7 heavy atoms.
The dataset in .mat format(for python users, we recommend using `scipy.io.loadmat`) includes two arrays:
"X" - (7211 x 23 x 23), Coulomb matrices
"T" - (7211 x 14), properties
Atomization energies E (PBE0, unit: kcal/mol)
Excitation of maximal optimal absorption E_max (ZINDO, unit: eV)
Absorption Intensity at maximal absorption I_max (ZINDO)
Highest occupied molecular orbital HOMO (ZINDO, unit: eV)
Lowest unoccupied molecular orbital LUMO (ZINDO, unit: eV)
First excitation energy E_1st (ZINDO, unit: eV)
Ionization potential IP (ZINDO, unit: eV)
Electron affinity EA (ZINDO, unit: eV)
Highest occupied molecular orbital HOMO (PBE0, unit: eV)
Lowest unoccupied molecular orbital LUMO (PBE0, unit: eV)
Highest occupied molecular orbital HOMO (GW, unit: eV)
Lowest unoccupied molecular orbital LUMO (GW, unit: eV)
Polarizabilities α (PBE0, unit: Å^3)
Polarizabilities α (SCS, unit: Å^3)
Reference:
Blum, Lorenz C., and Jean-Louis Reymond. "970 million druglike small molecules for virtual screening in the chemical universe database GDB-13." Journal of the American Chemical Society 131.25 (2009): 8732-8733.
Montavon, Grégoire, et al. "Machine learning of molecular electronic properties in chemical compound space." New Journal of Physics 15.9 (2013): 095003.
"""
if data_dir is None:
data_dir = DEFAULT_DIR
if save_dir is None:
save_dir = DEFAULT_DIR
dataset_file = os.path.join(data_dir, "qm7b.mat")
if not os.path.exists(dataset_file):
deepchem.utils.download_url(url=QM7B_MAT_URL, dest_dir=data_dir)
dataset = scipy.io.loadmat(dataset_file)
X = dataset['X']
y = dataset['T']
w = np.ones_like(y)
dataset = deepchem.data.DiskDataset.from_numpy(X, y, w, ids=None)
if split == None:
raise ValueError()
else:
splitters = {
'index': deepchem.splits.IndexSplitter(),
'random': deepchem.splits.RandomSplitter(),
'stratified':
deepchem.splits.SingletaskStratifiedSplitter(task_number=0)
}
splitter = splitters[split]
frac_train = kwargs.get("frac_train", 0.8)
frac_valid = kwargs.get('frac_valid', 0.1)
frac_test = kwargs.get('frac_test', 0.1)
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
dataset,
frac_train=frac_train,
frac_valid=frac_valid,
frac_test=frac_test)
transformers = [
deepchem.trans.NormalizationTransformer(
transform_y=True, dataset=train_dataset, move_mean=move_mean)
]
for transformer in transformers:
train_dataset = transformer.transform(train_dataset)
valid_dataset = transformer.transform(valid_dataset)
test_dataset = transformer.transform(test_dataset)
qm7_tasks = np.arange(y.shape[1])
return qm7_tasks, (train_dataset, valid_dataset, test_dataset), transformers
def load_qm7(featurizer='CoulombMatrix',
split='random',
reload=True,
move_mean=True,
data_dir=None,
save_dir=None,
**kwargs):
"""Load qm7 datasets.
QM7 is a subset of GDB-13 (a database of nearly 1 billion
stable and synthetically accessible organic molecules)
containing up to 7 heavy atoms C, N, O, and S. The 3D
Cartesian coordinates of the most stable conformations and
their atomization energies were determined using ab-initio
density functional theory (PBE0/tier2 basis set).This dataset
also provided Coulomb matrices as calculated in [Rupp et al.
PRL, 2012]:
C_ii = 0.5 * Z^2.4
C_ij = Z_i * Z_j/abs(R_i − R_j)
Z_i - nuclear charge of atom i
R_i - cartesian coordinates of atom i
The data file (.mat format, we recommend using `scipy.io.loadmat` for python users to load this original data) contains five arrays:
"X" - (7165 x 23 x 23), Coulomb matrices
"T" - (7165), atomization energies (unit: kcal/mol)
"P" - (5 x 1433), cross-validation splits as used in [Montavon et al. NIPS, 2012]
"Z" - (7165 x 23), atomic charges
"R" - (7165 x 23 x 3), cartesian coordinate (unit: Bohr) of each atom in the molecules
Reference:
Rupp, Matthias, et al. "Fast and accurate modeling of molecular atomization energies with machine learning." Physical review letters 108.5 (2012): 058301.
Montavon, Grégoire, et al. "Learning invariant representations of molecules for atomization energy prediction." Advances in Neural Information Processing Systems. 2012.
"""
# Featurize qm7 dataset
logger.info("About to featurize qm7 dataset.")
if data_dir is None:
data_dir = DEFAULT_DIR
if save_dir is None:
save_dir = DEFAULT_DIR
dataset_file = os.path.join(data_dir, "gdb7.sdf")
if not os.path.exists(dataset_file):
deepchem.utils.download_url(url=GDB7_URL, dest_dir=data_dir)
deepchem.utils.untargz_file(os.path.join(data_dir, 'gdb7.tar.gz'), data_dir)
qm7_tasks = ["u0_atom"]
if featurizer == 'CoulombMatrix':
featurizer = deepchem.feat.CoulombMatrixEig(23)
loader = deepchem.data.SDFLoader(
tasks=qm7_tasks,
smiles_field="smiles",
mol_field="mol",
featurizer=featurizer)
dataset = loader.featurize(dataset_file)
if split == None:
raise ValueError()
splitters = {
'index': deepchem.splits.IndexSplitter(),
'random': deepchem.splits.RandomSplitter(),
'stratified': deepchem.splits.SingletaskStratifiedSplitter(task_number=0)
}
splitter = splitters[split]
frac_train = kwargs.get("frac_train", 0.8)
frac_valid = kwargs.get('frac_valid', 0.1)
frac_test = kwargs.get('frac_test', 0.1)
train_dataset, valid_dataset, test_dataset = splitter.train_valid_test_split(
dataset,
frac_train=frac_train,
frac_valid=frac_valid,
frac_test=frac_test)
transformers = [
deepchem.trans.NormalizationTransformer(
transform_y=True, dataset=train_dataset, move_mean=move_mean)
]
for transformer in transformers:
train_dataset = transformer.transform(train_dataset)
valid_dataset = transformer.transform(valid_dataset)
test_dataset = transformer.transform(test_dataset)
return qm7_tasks, (train_dataset, valid_dataset, test_dataset), transformers