Bases: BaseDataset
Transition1x dataset contains structures from 10k organic reaction pathways of various types. It contains energy
and force labels for 9.6 mio. conformers calculated at the wB97x/6-31-G(d) level of theory. The geometries and
the transition states are generated by running Nudged Elastic Band (NEB) with DFT.
Usage:
from openqdc.datasets import Transition1X
dataset = Transition1X()
References:
- https://www.nature.com/articles/s41597-022-01870-w
Source code in openqdc/datasets/potential/transition1x.py
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 | class Transition1X(BaseDataset):
"""
Transition1x dataset contains structures from 10k organic reaction pathways of various types. It contains energy
and force labels for 9.6 mio. conformers calculated at the wB97x/6-31-G(d) level of theory. The geometries and
the transition states are generated by running Nudged Elastic Band (NEB) with DFT.
Usage:
```python
from openqdc.datasets import Transition1X
dataset = Transition1X()
```
References:
- https://www.nature.com/articles/s41597-022-01870-w\n
- https://gitlab.com/matschreiner/Transition1x\n
"""
__name__ = "transition1x"
__energy_methods__ = [
PotentialMethod.WB97X_6_31G_D
# "wb97x/6-31G(d)",
]
energy_target_names = [
"wB97x_6-31G(d).energy",
]
__force_mask__ = [True]
force_target_names = [
"wB97x_6-31G(d).forces",
]
__energy_unit__ = "ev"
__distance_unit__ = "ang"
__forces_unit__ = "ev/ang"
__links__ = {"Transition1x.h5": "https://figshare.com/ndownloader/files/36035789"}
def read_raw_entries(self):
raw_path = p_join(self.root, "Transition1x.h5")
f = load_hdf5_file(raw_path)["data"]
res = sum([read_record(f[g], group=g) for g in tqdm(f)], []) # don't use parallelized here
return res
|