SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials

Eastman, PeterBehara, Pavan KumarDotson, David L.Galvelis, RaimondasHerr, John E.Horton, Josh T.Mao, YuezhiChodera, John D.Pritchard, Benjamin P.Wang, YuanqingDe Fabritiis, GianniMarkland, Thomas E.2023-04-042023-04-042023-01-0411http://hdl.handle.net/10919/114246Machine 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.application/pdfenCreative Commons Attribution 4.0 InternationalProtein-ligand bindingaccuracydatabaseSPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning PotentialsArticle - RefereedScientific Datahttps://doi.org/10.1038/s41597-022-01882-6101365998732052-4463