Datasets from "Electrostatic Embedding of Machine Learning Potentials"

Data required to reproduce results in "Electrostatic Embedding of Machine Learning Potentials" article. See https://github.com/emedio/embedding for details.

• QM7_B3LYP_cc-pVTZ.tgz - outputs of single point B3LYP/cc-pVTZ calculations of structures in QM7 dataset with ORCA 5. Include molecular dipolar polarizabilities.
• QM7_B3LYP_cc-pVTZ_horton.tgz - MBIS partitioning of the B3LYP/cc-pVTZ densities with Horton 2.1.0.
• mpro_xyz.tgz - coordinates of the ligand and surrounding point charges from 100 snapshots of SARS-CoV-2 Mpro complex with PF-00835231.
• mpro_*.tgz - DFT and semiempirical single point calculations with ORCA 5 for the coordinates from mpro_xyz.tgz, in vacuo and in presence of point charges.
• mlmm.mat - learned parameters and SOAP feature vectors of reference atomic environments