MLPotential Keywords¶
Engine MLPotential¶
Backend- Type:
Multiple Choice
- Options:
[FAIRChem, M3GNet, MACE, NequIP, TorchANI]
- Description:
The machine learning potential backend.
Device- Type:
Multiple Choice
- Default value:
- Options:
[, cpu, cuda:0, cuda:1]
- Description:
Device on which to run the calculation (e.g. cpu, cuda:0).
If empty, the device can be controlled using environment variables for TensorFlow or PyTorch.
FAIRChem- Type:
Block
- Recurring:
False
- Description:
Options for the FAIRChem machine learning potential backend.
ModelTask- Type:
Multiple Choice
- Default value:
None
- Options:
[None, OC20, OMat, OMol, ODAC, OMC]
- Description:
Model task to use if a custom UMA/eSEN model is supplied via a parameter file. Ignored if a specific FAIRChem model is selected.
MACE- Type:
Block
- Recurring:
False
- Description:
Options for the MACE machine learning potential backend.
DataType- Type:
Multiple Choice
- Default value:
float32
- Options:
[float32, float64]
- Description:
Using
float32is faster but less accurate, and generally recommended for MD. Conversely usingfloat64is slower but more accurate, and recommended for geometry optimization.
EnableCuEquivariance- Type:
Bool
- Default value:
Yes
- Description:
Enable CUDA-accelerated cuEquivariance library for equivariant neural networks, if CUDA available.
MLDistanceUnit- Type:
Multiple Choice
- Default value:
Auto
- Options:
[Auto, angstrom, bohr]
- GUI name:
Internal distance unit
- Description:
Unit of distances expected by the ML backend (not the ASE calculator). The ASE calculator may require this information.
MLEnergyUnit- Type:
Multiple Choice
- Default value:
Auto
- Options:
[Auto, Hartree, eV, kcal/mol, kJ/mol]
- GUI name:
Internal energy unit
- Description:
Unit of energy output by the ML backend (not the unit output by the ASE calculator). The ASE calculator may require this information.
Model- Type:
Multiple Choice
- Default value:
ANI-2x
- Options:
[Custom, AIMNet2-B973c, AIMNet2-wB97MD3, ANI-1ccx, ANI-1x, ANI-2x, eSEN-S-Con-OMol, M3GNet-UP-2022, MACE-MP-0-Large, MACE-MP-0-Medium, MACE-MP-0-Small, MACE-MPA-0, UMA-S-1.1-OC20, UMA-S-1.1-ODAC, UMA-S-1.1-OMat, UMA-S-1.1-OMC, UMA-S-1.1-OMol]
- Description:
Select a particular parameterization.
AIMNet2 is based on ωB97m-D3 or B97-3c data, AIMNet2 has been parametrized to give good geometries and reaction energies for gasphase molecules and ions containing H, B, C, N, O, F, Si, P, S, Cl, As, Se, Br, I.
ANI-1x and ANI-2x are based on DFT (wB97X). ANI-1cxx is based on DLPNO-CCSD(T)/CBS whilst ANI-1x and ANI-1ccx have been parameterized to give good geometries, vibrational frequencies, and reaction energies for gasphase organic molecules containing H, C, O, and N. ANI-2x can also handle the atoms F, S, and Cl.
eSEN-S-Con-OMol is a pre-trained model based on DFT (ωB97M-V/def2-TZVPD) data from the OMol25 dataset, which contains data from diverse chemistry disciplines including biochemistry, electrochemistry, and organic and inorganic chemistry with all of the first 83 elements represented.
MACE-MP-0 is a pre-trained foundation model for materials chemistry, parameterized for 89 chemical elements. It is available in three sizes (small/medium/large) which balance accuracy vs. compute.
MACE-MPA-0 is a trained on a larger dataset with additional crystal structures, and improves accuracy compared to MACE-MP-0.
M3GNet-UP-2022 is a universal potential (UP) for the entire periodic table and has been primarily trained to crystal data (energies, forces, stresses) from the Materials Project.
UMA-S-1.1-OC20 is a pre-trained model based on DFT (RPBE) data, with training data comprising >100 million calculations of small molecules adsorbed on catalyst surfaces formed from materials in the Materials Project
UMA-S-1.1-ODAC is a pre-trained model based on DFT (PBE+D3) data, with training data comprising >10 million calculations of CO2/H2O molecules adsorbed in Metal Organic Frameworks sampled from various open databases like CoreMOF.
UMA-S-1.1-OMat is a pre-trained model based on DFT (PBE/PBE+U) data, with training data comprising >100 million calculations or inorganic materials collected from many open databases like Materials Project and Alexandria, and randomly sampled far from equilibria.
UMA-S-1.1-OMC is a pre-trained model based on DFT (PBE+D3) data, with training data comprising ~25 million calculations of organic molecular crystals from random packing of OE62 structures into various 3D unit cells.
UMA-S-1.1-OMol is a pre-trained model based on DFT (wB97M-V/def2-TZVPD) data, with training data comprising over 100 million calculations covering small molecules, biomolecules, metal complexes, and electrolytes.
Set to Custom to specify the backend and parameter files yourself.
NumThreads- Type:
String
- Default value:
- GUI name:
Number of threads
- Description:
Number of threads.
If not empty, OMP_NUM_THREADS will be set to this number; for PyTorch-engines, torch.set_num_threads() will be called.
ParameterDir- Type:
String
- Default value:
- GUI name:
Parameter directory
- Description:
Path to a set of parameters for the backend, if it expects to read from a directory.
ParameterFile- Type:
String
- Default value:
- Description:
Path to a set of parameters for the backend, if it expects to read from a file.
UnpairedElectrons- Type:
Integer
- Default value:
0
- Value Range:
value >= 0
- GUI name:
Spin polarization
- Description:
The number of unpaired electrons in the system for a spin unrestricted calculation. The spin multiplicity is taken as this value plus one.
Unrestricted- Type:
Bool
- Default value:
No
- Description:
Enables spin unrestricted calculations, passing spin information to the machine learning model. Only applicable to ‘UMA-S-1.1-OMol’ and custom FAIRChem models.