Open Catalyst 2020 Nudged Elastic Band (OC20NEB)#
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:]
--2025-12-23 21:42:34-- 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)...
52.84.217.5, 52.84.217.128, 52.84.217.55, ...
Connecting to dl.fbaipublicfiles.com (dl.fbaipublicfiles.com)|52.84.217.5|: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 15%[==> ] 1.46M 6.66MB/s
desorption_id_83_24 100%[===================>] 9.61M 30.7MB/s in 0.3s
2025-12-23 21:42:35 (30.7 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 |
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'.
Step Time Energy fmax
BFGS: 0 21:42:50 -305.763014 5.169705
BFGS: 1 21:42:51 -305.691690 11.366597
BFGS: 2 21:42:52 -305.916311 1.889963
BFGS: 3 21:42:53 -305.932501 2.616028
BFGS: 4 21:42:54 -306.010363 2.264344
BFGS: 5 21:42:55 -306.003677 6.892221
BFGS: 6 21:42:56 -306.254761 9.617142
BFGS: 7 21:42:57 -306.224762 3.370867
BFGS: 8 21:42:58 -306.290787 4.666003
BFGS: 9 21:42:59 -306.315119 0.727082
BFGS: 10 21:43:00 -306.329416 0.654044
BFGS: 11 21:43:01 -306.357723 1.619526
BFGS: 12 21:43:03 -306.412176 1.940742
BFGS: 13 21:43:04 -306.441267 0.604959
BFGS: 14 21:43:05 -306.471001 0.559471
BFGS: 15 21:43:06 -306.495159 2.155568
BFGS: 16 21:43:07 -306.497845 0.480775
BFGS: 17 21:43:08 -306.504566 0.518926
BFGS: 18 21:43:09 -306.511310 0.714050
BFGS: 19 21:43:10 -306.508516 0.832510
BFGS: 20 21:43:11 -306.477873 1.208988
BFGS: 21 21:43:12 -306.508839 0.552523
BFGS: 22 21:43:13 -306.509933 0.379559
BFGS: 23 21:43:14 -306.396639 3.011676
BFGS: 24 21:43:15 -306.426273 1.008951
BFGS: 25 21:43:16 -306.390575 0.993510
BFGS: 26 21:43:17 -306.185505 0.925041
BFGS: 27 21:43:18 -306.127514 0.638757
BFGS: 28 21:43:19 -306.158028 0.669404
BFGS: 29 21:43:20 -306.240238 0.423369
BFGS: 30 21:43:21 -306.258076 0.527813
BFGS: 31 21:43:22 -306.257641 0.610025
BFGS: 32 21:43:23 -306.250221 0.648697
BFGS: 33 21:43:24 -306.257538 0.536956
BFGS: 34 21:43:25 -306.273964 0.436475
BFGS: 35 21:43:26 -306.311193 0.513248
BFGS: 36 21:43:27 -306.361092 0.543804
BFGS: 37 21:43:28 -306.432796 0.515683
BFGS: 38 21:43:29 -306.503700 0.485924
BFGS: 39 21:43:29 -306.530908 0.795098
BFGS: 40 21:43:30 -306.458948 1.429151
BFGS: 41 21:43:31 -306.300835 1.016157
BFGS: 42 21:43:32 -306.236401 0.796859
BFGS: 43 21:43:33 -306.260273 0.390382
BFGS: 44 21:43:34 -306.288555 0.345175
BFGS: 45 21:43:34 -306.316677 0.403329
BFGS: 46 21:43:35 -306.326887 0.518405
BFGS: 47 21:43:36 -306.308002 0.552446
BFGS: 48 21:43:37 -306.283466 0.417554
BFGS: 49 21:43:38 -306.273874 0.486212
BFGS: 50 21:43:39 -306.273495 0.296720
BFGS: 51 21:43:40 -306.276230 0.364837
BFGS: 52 21:43:41 -306.291931 0.296960
BFGS: 53 21:43:42 -306.317383 0.355936
BFGS: 54 21:43:42 -306.317064 0.359512
BFGS: 55 21:43:43 -306.309568 0.310920
BFGS: 56 21:43:44 -306.313925 0.269742
BFGS: 57 21:43:45 -306.321632 0.284377
BFGS: 58 21:43:46 -306.325144 0.252475
BFGS: 59 21:43:47 -306.331365 0.285908
BFGS: 60 21:43:48 -306.335789 0.244770
BFGS: 61 21:43:49 -306.332867 0.274321
BFGS: 62 21:43:50 -306.335716 0.217616
BFGS: 63 21:43:51 -306.344705 0.201684
BFGS: 64 21:43:52 -306.352756 0.209932
BFGS: 65 21:43:53 -306.349832 0.262015
BFGS: 66 21:43:54 -306.346144 0.266027
BFGS: 67 21:43:55 -306.365097 0.223561
BFGS: 68 21:43:56 -306.370190 0.382092
BFGS: 69 21:43:56 -306.327362 0.406294
BFGS: 70 21:43:57 -306.342176 0.208020
BFGS: 71 21:43:58 -306.350353 0.241796
BFGS: 72 21:43:59 -306.352682 0.127880
BFGS: 73 21:44:00 -306.351660 0.091098
BFGS: 74 21:44:01 -306.351990 0.074124
BFGS: 75 21:44:02 -306.355099 0.207719
BFGS: 76 21:44:03 -306.351688 0.235298
BFGS: 77 21:44:04 -306.349195 0.183163
BFGS: 78 21:44:04 -306.351738 0.172485
BFGS: 79 21:44:05 -306.356153 0.190859
BFGS: 80 21:44:06 -306.356924 0.124700
BFGS: 81 21:44:07 -306.349928 0.191069
BFGS: 82 21:44:08 -306.335524 0.277620
BFGS: 83 21:44:09 -306.248386 0.520793
BFGS: 84 21:44:10 -306.255560 0.482899
BFGS: 85 21:44:11 -306.317415 0.533368
BFGS: 86 21:44:12 -306.337398 0.722898
BFGS: 87 21:44:13 -306.342962 0.528065
BFGS: 88 21:44:14 -306.345962 0.339795
BFGS: 89 21:44:15 -306.345669 0.128839
BFGS: 90 21:44:16 -306.341663 0.165354
BFGS: 91 21:44:17 -306.340023 0.245824
BFGS: 92 21:44:18 -306.348480 0.341181
BFGS: 93 21:44:19 -306.359266 0.316924
BFGS: 94 21:44:20 -306.355087 0.234602
BFGS: 95 21:44:21 -306.345188 0.213146
BFGS: 96 21:44:22 -306.340412 0.176998
BFGS: 97 21:44:23 -306.325180 0.390251
BFGS: 98 21:44:24 -306.321546 0.404556
BFGS: 99 21:44:25 -306.347170 0.369873
BFGS: 100 21:44:26 -306.365696 0.375770
BFGS: 101 21:44:27 -306.368448 0.262075
BFGS: 102 21:44:28 -306.366629 0.274718
BFGS: 103 21:44:29 -306.359739 0.249257
BFGS: 104 21:44:30 -306.360655 0.136701
BFGS: 105 21:44:31 -306.355627 0.224843
BFGS: 106 21:44:32 -306.354639 0.252765
BFGS: 107 21:44:33 -306.352846 0.209089
BFGS: 108 21:44:34 -306.359110 0.185192
BFGS: 109 21:44:35 -306.360464 0.118802
BFGS: 110 21:44:36 -306.360580 0.135978
BFGS: 111 21:44:37 -306.357159 0.154989
BFGS: 112 21:44:38 -306.358721 0.137018
BFGS: 113 21:44:38 -306.357166 0.135403
BFGS: 114 21:44:39 -306.348875 0.228825
BFGS: 115 21:44:40 -306.334053 0.363359
BFGS: 116 21:44:41 -306.297026 0.538728
BFGS: 117 21:44:42 -306.289436 0.546414
BFGS: 118 21:44:43 -306.337982 0.416674
BFGS: 119 21:44:44 -306.357647 0.600634
BFGS: 120 21:44:45 -306.353899 0.205752
BFGS: 121 21:44:46 -306.365894 0.337602
BFGS: 122 21:44:47 -306.355513 0.226244
BFGS: 123 21:44:48 -306.359566 0.118230
BFGS: 124 21:44:49 -306.361311 0.162960
BFGS: 125 21:44:50 -306.361362 0.065746
BFGS: 126 21:44:51 -306.362484 0.136808
BFGS: 127 21:44:51 -306.362183 0.073019
BFGS: 128 21:44:52 -306.362183 0.128290
BFGS: 129 21:44:53 -306.362183 0.051831
BFGS: 130 21:44:53 -306.362183 0.050717
BFGS: 131 21:44:54 -306.362183 0.476923
BFGS: 132 21:44:54 -306.362183 0.171536
BFGS: 133 21:44:55 -306.362183 0.283749
BFGS: 134 21:44:55 -306.362183 0.263087
BFGS: 135 21:44:56 -306.362183 0.142148
BFGS: 136 21:44:56 -306.362183 0.117537
BFGS: 137 21:44:57 -306.362183 0.720018
BFGS: 138 21:44:58 -306.362183 0.436413
BFGS: 139 21:44:58 -306.362183 0.339500
BFGS: 140 21:44:59 -306.362183 0.160624
BFGS: 141 21:44:59 -306.362183 0.085518
BFGS: 142 21:45:00 -306.362183 0.177152
BFGS: 143 21:45:00 -306.362183 0.124666
BFGS: 144 21:45:01 -306.362183 0.118213
BFGS: 145 21:45:01 -306.362183 0.074450
BFGS: 146 21:45:02 -306.362183 0.194829
BFGS: 147 21:45:02 -306.362183 0.481882
BFGS: 148 21:45:03 -306.362183 1.196119
BFGS: 149 21:45:04 -306.362183 0.622913
BFGS: 150 21:45:05 -306.362183 0.678975
BFGS: 151 21:45:06 -306.362183 0.306593
BFGS: 152 21:45:06 -306.362183 0.273331
BFGS: 153 21:45:07 -306.362183 0.412972
BFGS: 154 21:45:08 -306.362183 0.638374
BFGS: 155 21:45:09 -306.362183 0.324265
BFGS: 156 21:45:10 -306.362183 0.264524
BFGS: 157 21:45:11 -306.362183 0.205086
BFGS: 158 21:45:12 -306.362183 0.199725
BFGS: 159 21:45:13 -306.362183 0.090013
BFGS: 160 21:45:14 -306.362183 0.118822
BFGS: 161 21:45:14 -306.362183 0.205041
BFGS: 162 21:45:15 -306.362183 0.246975
BFGS: 163 21:45:16 -306.362183 0.331774
BFGS: 164 21:45:16 -306.362183 0.215043
BFGS: 165 21:45:17 -306.362183 0.215259
BFGS: 166 21:45:18 -306.362183 0.230183
BFGS: 167 21:45:18 -306.362183 0.208553
BFGS: 168 21:45:19 -306.362183 0.431626
BFGS: 169 21:45:20 -306.362183 0.133996
BFGS: 170 21:45:20 -306.362183 0.105486
BFGS: 171 21:45:21 -306.362183 0.480994
BFGS: 172 21:45:22 -306.362183 0.300610
BFGS: 173 21:45:22 -306.362183 0.205220
BFGS: 174 21:45:23 -306.362183 0.188655
BFGS: 175 21:45:24 -306.362183 0.304838
BFGS: 176 21:45:24 -306.362183 0.263159
BFGS: 177 21:45:25 -306.362183 0.147536
BFGS: 178 21:45:26 -306.362183 0.128801
BFGS: 179 21:45:26 -306.362183 0.369622
BFGS: 180 21:45:27 -306.362183 0.206404
BFGS: 181 21:45:28 -306.362183 0.078798
BFGS: 182 21:45:28 -306.362183 0.056927
BFGS: 183 21:45:29 -306.362183 0.048082