MLIP-Compatible Recipes¶
Several popular datasets used to train machine-learned interatomic potentials (MLIPs) were built from large collections of DFT calculations run with a specific, fixed set of computational settings. To let users generate additional data that is consistent with one of these datasets (e.g. to extend a dataset or build an internally-consistent benchmark without introducing methodological drift), quacc ships a set of recipes that reproduce those settings.
Note
While these recipes aim to reproduce the settings of each dataset, you should still manually confirm that the resulting calculator settings are consistent with the source dataset for good measure.
Supported Datasets¶
| Dataset | Recipe | Extra Dependencies |
|---|---|---|
| OC20 | quacc.recipes.vasp.fairchem.oc20_static_job | quacc[fairchem] |
| OC22 | quacc.recipes.vasp.fairchem.oc22_static_job | none |
| OC25 | quacc.recipes.vasp.fairchem.oc25_static_job | quacc[fairchem] |
| OMat24 | quacc.recipes.vasp.fairchem.omat_static_job | quacc[fairchem] |
| OMC25 | quacc.recipes.vasp.fairchem.omc_static_job | quacc[atomate2] |
| OMol25 | quacc.recipes.orca.fairchem.omol_static_job | quacc[fairchem] |
| ODAC23 | quacc.recipes.vasp.fairchem.odac23_static_job | none |
| ODAC25 | quacc.recipes.vasp.fairchem.odac25_static_job | none |
| AQCat25 | quacc.recipes.vasp.aqcat.aqcat25_static_job | none |
| MPtrj / WBM / sAlex / MatterSim | quacc.recipes.vasp.mp_legacy.mp_relax_set_job | none |
| MatPES | quacc.recipes.vasp.matpes.matpes_static_job | quacc[atomate2] |
| MP-ALOE | quacc.recipes.vasp.mp_aloe.mp_aloe_static_job | none |
A Representative Example¶
from ase.build import bulk
from quacc.recipes.vasp.fairchem import omat_static_job
# Make an Atoms object of a bulk Cu structure
atoms = bulk("Cu")
# Run a static calculation with OMat24-compatible VASP settings
result = omat_static_job(atoms)
print(result)
As with all quacc recipes, you can override any of the default calculator settings by passing additional keyword arguments: