Supporting Datasets for: Prediction of Charged Small Molecule Conformations in Solution using a Balanced ML/MM Potential

For each dataset, structures were generated by sampling every 1 ps from 20 ns molecular dynamics simulations in the aqueous phase using GAFF. For each structure, gas phase energies and Cartesian atomic forces were evaluated at the B3LYP-D3/6-31+G level of theory and unscaled partial atomic charges determined using the CM5 approach.
For each dataset, energies in energies.txt are given in units of kcal/mol, Cartesian atomic forces in forces.txt are given in units of kcal/mol/ångstrom, coordinates in coords.txt are given in units of ångstrom and partial charges in charges.txt are given in units of elementary charge. Nuclear charges, which define the atom ordering, are provided in nuclear_charges.txt.
In addition to the "ml_data" folder format used for PairFEQ-Net, datasets are also provided using comma separated values (CSV) format in the ml_data.csv file.