Add ODAC deformation runner/reducer and benchmark dataset #1461
Conversation
|
Hi @lbrabson! Thank you for your pull request. We require contributors to sign our Contributor License Agreement, and yours needs attention. You currently have a record in our system, but the CLA is no longer valid, and will need to be resubmitted. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at [email protected]. Thanks! |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
|
This PR has been marked as stale because it has been open for 30 days with no activity. |
zulissimeta
left a comment
zulissimeta
left a comment
There was a problem hiding this comment.
Thanks @lbrabson !
Can you add some tests for this runner to make sure everything works and it doesn't break in the future?
| from ase.optimize import Optimizer | ||
|
|
||
|
|
||
| def relax_atoms_w_maxstep( |
There was a problem hiding this comment.
Is this function any different than the relax function here? If they are very similar we should combine implementation to avoid a lot of repeated code.
There was a problem hiding this comment.
@lbluque yes, this function is different in that it accepts an argument maxstep that limits the max displacement of an atom during relaxation. This is necessary to exactly replicate the results we published in ODAC25. Otherwise, the functions are identical. If we add this functionality to the main relax_atoms function, I can remove my version.
| from pymatgen.io.ase import MSONAtoms | ||
| from tqdm import tqdm | ||
|
|
||
| from adjust_adsorbate import get_large_adsorbate, shift_adsorbate |
There was a problem hiding this comment.
Is this from a missing file? Can you add all calculation utility files to fairchem/core/components/calculate/recipes?
There was a problem hiding this comment.
@lbluque yes, thank you for pointing this out. I will add this file to recipes
3 participants
Added dataset of 59 MOFs from https://arxiv.org/abs/2506.09256 with deformation runner and reducer classes. Benchmarking of ODAC25 ML potentials have been added to that work using these tools.