Machine learning potentials are an important tool for molecular simulation, but their development is held back by a shortage of high quality datasets to train them on. We describe the SPICE dataset, a new quantum chemistry dataset for training potentials relevant to simulating drug-like small molecules interacting with proteins. It contains over 1.1 million conformations for a diverse set of small molecules, dimers, dipeptides, and solvated amino acids. It includes 15 elements, charged and uncharged molecules, and a wide range of covalent and non-covalent interactions. It provides both forces and energies calculated at the {\omega}B97M-D3(BJ)/def2-TZVPPD level of theory, along with other useful quantities such as multipole moments and bond orders. We train a set of machine learning potentials on it and demonstrate that they can achieve chemical accuracy across a broad region of chemical space. It can serve as a valuable resource for the creation of transferable, ready to use potential functions for use in molecular simulations.
@article{arxiv.2209.10702,
title = {SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials},
author = {Peter Eastman and Pavan Kumar Behara and David L. Dotson and Raimondas Galvelis and John E. Herr and Josh T. Horton and Yuezhi Mao and John D. Chodera and Benjamin P. Pritchard and Yuanqing Wang and Gianni De Fabritiis and Thomas E. Markland},
journal= {arXiv preprint arXiv:2209.10702},
year = {2022}
}