Research data supporting "MACE-OFF23"
Repository URI
Repository DOI
No Thumbnail Available
Type
Dataset
Change log
Authors
Moore, Harry https://orcid.org/0000-0001-5116-3027
Kovacs, David Peter
Browning, Nicholas J
Batatia, Ilyes
Horton, Joshua T
Description
This repository contains train and test datasets for MACE-OFF23 forcefields.
The core of the training set is the SPICE dataset. 95% of the data were used for training and validation, and 5% for testing. The MACE-OFF23 model is trained to reproduce the energies and forces computed at the ωB97M-D3(BJ)/def2-TZVPPD level of quantum mechanics, as implemented in the PSI4 software [56]. We have used a subset of SPICE that contains the ten chemical elements H, C, N, O, F, P, S, Cl, Br, and I, and has a neutral formal charge. We have also removed the ion pairs subset. Overall, we used about 85% of the full SPICE dataset.
Files are provided in extended xyz format and contain energies and force data in units of eV and eV/Angstrom
Version
Software / Usage instructions
Usage should follow documentation https://mace-docs.readthedocs.io/en/latest/
MACE code is available at https://github.com/ACEsuit/mace
Keywords
DFT, forcefield, machine learning
Publisher
Rights
MIT