Get started¶
The quickest way to use MLatom is to run it online on the Aitomistic Hub or Aitomistic Lab@XMU — nothing to install. To run locally, just install MLatom — it pulls in the required dependencies automatically (including the PyTorch/TorchANI and geometry-optimization backends the AIQM2 example below uses). AIQM2 additionally needs the DFT-D4 program (via conda):
pip install -U mlatom
conda install -c conda-forge dftd4
export dftd4bin=$(which dftd4) # point MLatom at the dftd4 executable
See the installation guide for the full dependency list and other methods.
Quick start¶
Optimize the geometry of a water molecule with AIQM2 — an AI-enhanced quantum-mechanical method (native to MLatom, CHNO elements) that reaches beyond-DFT accuracy at semi-empirical cost.
Python API¶
import mlatom as ml
mol = ml.data.molecule.from_xyz_string('''3
O 0.00000 0.00000 0.11779
H 0.00000 0.75545 -0.47116
H 0.00000 -0.75545 -0.47116
''')
aiqm2 = ml.methods(method='AIQM2')
opt = ml.optimize_geometry(model=aiqm2, initial_molecule=mol).optimized_molecule
print(opt.energy) # optimized energy in hartree
To check your setup worked, the printed energy should be approximately:
-76.3838
Command line (input file)¶
The same calculation from the command line. Save the geometry as init.xyz:
3
O 0.00000 0.00000 0.11779
H 0.00000 0.75545 -0.47116
H 0.00000 -0.75545 -0.47116
and the input as geomopt.inp:
AIQM2 # method
geomopt # task: geometry optimization
xyzfile=init.xyz # input geometry
optxyz=opt.xyz # output geometry
then run:
mlatom geomopt.inp
The optimized geometry is written to opt.xyz, and the output reports the
optimized energy (≈ -76.3838 hartree). You can also
download geomopt.inp and
init.xyz.
Note
Prefer zero setup? Run these online on the Aitomistic Hub or Aitomistic Lab@XMU (both powered by Protomia) — no installation needed.