Datasets of Formate on Cu, Li4P2)7 quench, and LiPS used in Batzner et al. "E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials}"

The data set is shared as an extended xyz file. To read the data into a list of ase.Atoms objects:

from ase.io import read atoms = read('lipsxyz', index=':', format='extxyz') positions = atoms[0].get_positions() cell = atoms[0].get_cell() species = atoms[0].get_chemical_symbols() energy = atoms[0].get_potential_energy() forces = atoms[0].get_forces()