| Property | Value |
|---|---|
| Size | 932 NEB relaxation trajectories |
| Reaction Types | Desorptions, Dissociations, Transfers |
| Purpose | Transition state energy calculations |
| Paper | CatTSunami (arXiv) |
| License | CC-BY-4.0 |
Overview¶
This is a validation dataset which was used to assess model performance in CatTSunami: Accelerating Transition State Energy Calculations with Pre-trained Graph Neural Networks. It is comprised of 932 NEB relaxation trajectories. There are three different types of reactions represented: desorptions, dissociations, and transfers. NEB calculations allow us to find transition states. The rate of reaction is determined by the transition state energy, so access to transition states is very important for catalysis research. For more information, check out the paper.
File Structure and Contents¶
The tar file contains 3 subdirectories: dissociations, desorptions, and transfers. As the names imply, these directories contain the converged DFT trajectories for each of the reaction classes. Within these directories, the trajectories are named to identify the contents of the file. Here is an example and the anatomy of the name:
desorption_id_83_2409_9_111-4_neb1.0.traj
desorptionindicates the reaction type (dissociation and transfer are the other possibilities)ididentifies that the material belongs to the validation in domain split (ood - out of domain is th e other possibility)83is the task id. This does not provide relavent information2409is the bulk index of the bulk used in the ocdata bulk pickle file9is the reaction index. for each reaction type there is a reaction pickle file in the repository. In this case it is the 9th entry to that pickle file111-4the first 3 numbers are the miller indices (i.e. the (1,1,1) surface), and the last number cooresponds to the shift value. In this case the 4th shift enumerated was the one used.neb1.0the number here indicates the k value used. For the full dataset, 1.0 was used so this does not distiguish any of the trajectories from one another.
The content of these trajectory files is the repeating frame sets. Despite the initial and final frames not being optimized during the NEB, the initial and final frames are saved for every iteration in the trajectory. For the dataset, 10 frames were used - 8 which were optimized over the neb. So the length of the trajectory is the number of iterations (N) * 10. If you wanted to look at the frame set prior to optimization and the optimized frame set, you could get them like this:
from __future__ import annotations
!wget https://dl.fbaipublicfiles.com/opencatalystproject/data/large_files/desorption_id_83_2409_9_111-4_neb1.0.traj
from ase.io import read
traj = read("desorption_id_83_2409_9_111-4_neb1.0.traj", ":")
unrelaxed_frames = traj[0:10]
relaxed_frames = traj[-10:]--2026-02-20 22:38:37-- https://dl.fbaipublicfiles.com/opencatalystproject/data/large_files/desorption_id_83_2409_9_111-4_neb1.0.traj
Resolving dl.fbaipublicfiles.com (dl.fbaipublicfiles.com)... 52.84.217.124, 52.84.217.128, 52.84.217.55, ...
Connecting to dl.fbaipublicfiles.com (dl.fbaipublicfiles.com)|52.84.217.124|:443... connected.
HTTP request sent, awaiting response... 200 OK
Length: 10074935 (9.6M) [binary/octet-stream]
Saving to: ‘desorption_id_83_2409_9_111-4_neb1.0.traj’
desorptio 0%[ ] 0 --.-KB/s desorption 6%[> ] 657.71K 3.21MB/s desorption_id_83_24 100%[===================>] 9.61M 22.4MB/s in 0.4s
2026-02-20 22:38:38 (22.4 MB/s) - ‘desorption_id_83_2409_9_111-4_neb1.0.traj’ saved [10074935/10074935]
Download¶
| Splits | Size of compressed version (in bytes) | Size of uncompressed version (in bytes) | MD5 checksum (download link) |
|---|---|---|---|
| ASE Trajectories | 1.5G | 6.3G | 52af34a93758c82fae951e52af445089 |
Use¶
One more note: We have not prepared an lmdb for this dataset. This is because it is NEB calculations are not supported directly in ocp. You must use the ase native OCP class along with ase infrastructure to run NEB calculations. Here is an example of a use:
import os
from ase.io import read
from ase.mep import DyNEB
from ase.optimize import BFGS
from fairchem.core import FAIRChemCalculator, pretrained_mlip
traj = read("desorption_id_83_2409_9_111-4_neb1.0.traj", ":")
images = traj[0:10]
predictor = pretrained_mlip.get_predict_unit("uma-s-1p1")
neb = DyNEB(images, k=1)
for image in images:
image.calc = FAIRChemCalculator(predictor, task_name="oc20")
optimizer = BFGS(
neb,
trajectory="neb.traj",
)
# Use a small number of steps here to keep the docs fast during CI, but otherwise do quite reasonable settings.
fast_docs = os.environ.get("FAST_DOCS", "false").lower() == "true"
if fast_docs:
optimization_steps = 20
else:
optimization_steps = 300
conv = optimizer.run(fmax=0.45, steps=optimization_steps)
if conv:
neb.climb = True
conv = optimizer.run(fmax=0.05, steps=optimization_steps)WARNING:root:device was not explicitly set, using device='cuda'.
WARNING:root:If 'dataset_list' is provided in the config, the code assumes that each dataset maps to itself. Please use 'dataset_mapping' as 'dataset_list' is deprecated and will be removed in the future.
Step Time Energy fmax
BFGS: 0 22:39:00 -305.763014 5.169706
BFGS: 1 22:39:04 -305.691696 11.366599
BFGS: 2 22:39:08 -305.916305 1.889963
BFGS: 3 22:39:11 -305.932505 2.616029
BFGS: 4 22:39:15 -306.010364 2.264345
BFGS: 5 22:39:19 -306.003685 6.892203
BFGS: 6 22:39:22 -306.254764 9.617142
BFGS: 7 22:39:27 -306.224768 3.370852
BFGS: 8 22:39:31 -306.290781 4.665969
BFGS: 9 22:39:34 -306.315126 0.727080
BFGS: 10 22:39:45 -306.329416 0.653949
BFGS: 11 22:39:55 -306.357733 1.619413
BFGS: 12 22:39:58 -306.412187 1.941402
BFGS: 13 22:40:02 -306.441265 0.604919
BFGS: 14 22:40:06 -306.471025 0.560355
BFGS: 15 22:40:14 -306.495159 2.151691
BFGS: 16 22:40:18 -306.497852 0.480684
BFGS: 17 22:40:23 -306.504515 0.517828
BFGS: 18 22:40:28 -306.511330 0.711001
BFGS: 19 22:40:32 -306.508497 0.824330
BFGS: 20 22:40:37 -306.477810 1.211299
BFGS: 21 22:40:41 -306.508875 0.552318
BFGS: 22 22:40:44 -306.509811 0.379495
BFGS: 23 22:40:48 -306.396065 3.025528
BFGS: 24 22:40:54 -306.426214 1.008434
BFGS: 25 22:41:02 -306.390575 0.993413
BFGS: 26 22:41:07 -306.185148 0.918144
BFGS: 27 22:41:11 -306.127603 0.639502
BFGS: 28 22:41:19 -306.158256 0.668857
BFGS: 29 22:41:26 -306.240353 0.423182
BFGS: 30 22:41:33 -306.258219 0.528999
BFGS: 31 22:41:39 -306.257784 0.609786
BFGS: 32 22:41:45 -306.250343 0.648430
BFGS: 33 22:41:52 -306.257646 0.537434
BFGS: 34 22:41:57 -306.274040 0.436378
BFGS: 35 22:42:04 -306.311235 0.513360
BFGS: 36 22:42:09 -306.361029 0.543442
BFGS: 37 22:42:14 -306.432625 0.515129
BFGS: 38 22:42:18 -306.503437 0.485138
BFGS: 39 22:42:22 -306.530634 0.796621
BFGS: 40 22:42:25 -306.458790 1.427465
BFGS: 41 22:42:29 -306.300939 1.014027
BFGS: 42 22:42:33 -306.236318 0.795739
BFGS: 43 22:42:37 -306.260094 0.389664
BFGS: 44 22:42:43 -306.288412 0.344554
BFGS: 45 22:42:47 -306.316362 0.402540
BFGS: 46 22:42:51 -306.326822 0.518370
BFGS: 47 22:42:55 -306.308317 0.552247
BFGS: 48 22:42:59 -306.283693 0.421232
BFGS: 49 22:43:03 -306.274086 0.484083
BFGS: 50 22:43:07 -306.273703 0.296283
BFGS: 51 22:43:15 -306.276337 0.363976
BFGS: 52 22:43:19 -306.292019 0.296653
BFGS: 53 22:43:23 -306.317373 0.355296
BFGS: 54 22:43:27 -306.317230 0.359721
BFGS: 55 22:43:33 -306.309839 0.309600
BFGS: 56 22:43:37 -306.314127 0.268204
BFGS: 57 22:43:43 -306.321852 0.282956
BFGS: 58 22:43:48 -306.325226 0.256294
BFGS: 59 22:43:52 -306.331180 0.287803
BFGS: 60 22:43:56 -306.335894 0.243479
BFGS: 61 22:44:00 -306.333073 0.274525
BFGS: 62 22:44:04 -306.335808 0.222215
BFGS: 63 22:44:08 -306.344576 0.200859
BFGS: 64 22:44:12 -306.352861 0.207824
BFGS: 65 22:44:19 -306.350017 0.262066
BFGS: 66 22:44:23 -306.346147 0.262728
BFGS: 67 22:44:29 -306.364551 0.220545
BFGS: 68 22:44:33 -306.370249 0.379456
BFGS: 69 22:44:37 -306.328752 0.414200
BFGS: 70 22:44:41 -306.342241 0.198225
BFGS: 71 22:44:45 -306.351110 0.244703
BFGS: 72 22:44:49 -306.352571 0.134011
BFGS: 73 22:44:54 -306.351244 0.132978
BFGS: 74 22:44:58 -306.351917 0.088923
BFGS: 75 22:45:02 -306.355671 0.152395
BFGS: 76 22:45:09 -306.355839 0.176664
BFGS: 77 22:45:13 -306.344551 0.225784
BFGS: 78 22:45:17 -306.342525 0.201806
BFGS: 79 22:45:21 -306.371477 0.568085
BFGS: 80 22:45:25 -306.355537 0.298258
BFGS: 81 22:45:29 -306.356462 0.097104
BFGS: 82 22:45:36 -306.357145 0.093860
BFGS: 83 22:45:41 -306.348631 0.576579
BFGS: 84 22:45:48 -306.348434 0.479055
BFGS: 85 22:45:52 -306.337868 0.190295
BFGS: 86 22:45:59 -306.344789 0.368532
BFGS: 87 22:46:05 -306.347586 0.241326
BFGS: 88 22:46:10 -306.348923 0.405564
BFGS: 89 22:46:15 -306.342962 0.399021
BFGS: 90 22:46:20 -306.338335 0.456940
BFGS: 91 22:46:25 -306.346128 0.273018
BFGS: 92 22:46:31 -306.345592 0.509563
BFGS: 93 22:46:36 -306.347456 0.277569
BFGS: 94 22:46:40 -306.347305 0.267305
BFGS: 95 22:46:46 -306.346920 0.211357
BFGS: 96 22:46:50 -306.346071 0.236754
BFGS: 97 22:46:58 -306.360214 0.683618
BFGS: 98 22:47:03 -306.372147 0.421920
BFGS: 99 22:47:08 -306.347092 0.982559
BFGS: 100 22:47:14 -306.367971 0.229007
BFGS: 101 22:47:18 -306.362823 0.139783
BFGS: 102 22:47:22 -306.360273 0.141253
BFGS: 103 22:47:28 -306.356436 0.298560
BFGS: 104 22:47:32 -306.365919 0.595697
BFGS: 105 22:47:37 -306.350840 1.319173
BFGS: 106 22:47:45 -306.356558 0.253267
BFGS: 107 22:47:51 -306.358679 0.318441
BFGS: 108 22:47:57 -306.352394 0.908227
BFGS: 109 22:48:01 -306.350338 1.162744
BFGS: 110 22:48:06 -306.337665 0.971851
BFGS: 111 22:48:11 -306.330784 0.394322
BFGS: 112 22:48:17 -306.337706 0.662680
BFGS: 113 22:48:22 -306.350706 0.857419
BFGS: 114 22:48:27 -306.355842 0.406655
BFGS: 115 22:48:31 -306.361919 0.197629
BFGS: 116 22:48:37 -306.362169 0.152837
BFGS: 117 22:48:41 -306.359846 0.231848
BFGS: 118 22:48:48 -306.359419 0.116586
BFGS: 119 22:48:53 -306.359520 0.193793
BFGS: 120 22:48:57 -306.357023 0.778863
BFGS: 121 22:49:03 -306.331217 2.452282
BFGS: 122 22:49:08 -306.348791 1.660100
BFGS: 123 22:49:14 -306.349182 0.662135
BFGS: 124 22:49:18 -306.342863 0.412437
BFGS: 125 22:49:22 -306.318762 0.580041
BFGS: 126 22:49:27 -306.310263 0.792768
BFGS: 127 22:49:31 -306.305109 0.949832
BFGS: 128 22:49:38 -306.342852 0.701320
BFGS: 129 22:49:42 -306.386055 0.357853
BFGS: 130 22:49:46 -306.371223 0.252744
BFGS: 131 22:49:51 -306.327663 0.469085
BFGS: 132 22:49:58 -306.338770 0.364624
BFGS: 133 22:50:03 -306.294458 1.390134
BFGS: 134 22:50:08 -306.340376 0.360732
BFGS: 135 22:50:14 -306.352661 0.339716
BFGS: 136 22:50:20 -306.348888 0.316250
BFGS: 137 22:50:24 -306.344129 0.411114
BFGS: 138 22:50:28 -306.349789 0.231063
BFGS: 139 22:50:33 -306.353668 0.129973
BFGS: 140 22:50:39 -306.356665 0.207153
BFGS: 141 22:50:45 -306.357864 0.154266
BFGS: 142 22:50:50 -306.356205 0.097168
BFGS: 143 22:50:54 -306.354816 0.153041
BFGS: 144 22:50:57 -306.355125 0.086987
BFGS: 145 22:51:01 -306.354896 0.109054
BFGS: 146 22:51:04 -306.355574 0.135614
BFGS: 147 22:51:08 -306.358393 0.105965
BFGS: 148 22:51:10 -306.360235 0.101621
BFGS: 149 22:51:14 -306.359989 0.157062
BFGS: 150 22:51:19 -306.359201 0.078602
BFGS: 151 22:51:24 -306.359951 0.043418