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

Peter Eastman; Pavan Kumar Behara; David L Dotson; Raimondas Galvelis; John E Herr; Josh T Horton; Yuezhi Mao; John D Chodera; Benjamin P Pritchard; Yuanqing Wang; Gianni De Fabritiis; Thomas E Markland

doi:10.1038/s41597-022-01882-6

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

Sci Data. 2023 Jan 4;10(1):11. doi: 10.1038/s41597-022-01882-6.

Authors

Peter Eastman¹, Pavan Kumar Behara², David L Dotson³, Raimondas Galvelis⁴, John E Herr⁵, Josh T Horton⁶, Yuezhi Mao⁷, John D Chodera⁸, Benjamin P Pritchard⁹, Yuanqing Wang^{8

10}, Gianni De Fabritiis^{4

11}, Thomas E Markland⁷

Affiliations

¹ Department of Chemistry, Stanford University, Stanford, CA, 94305, USA. peastman@stanford.edu.
² Department of Pharmaceutical Sciences, University of California, Irvine, CA, 92697, USA.
³ The Open Force Field Initiative, Open Molecular Software Foundation, Davis, CA, 95616, USA.
⁴ Acellera Labs, Doctor Trueta 183, 08005, Barcelona, Spain.
⁵ Department of Chemistry and Biochemistry, University of Notre Dame, Notre Dame, IN, 46556, USA.
⁶ School of Natural and Environmental Sciences, Newcastle University, Newcastle upon Tyne, NE1 7RU, United Kingdom.
⁷ Department of Chemistry, Stanford University, Stanford, CA, 94305, USA.
⁸ Computational and Systems Biology Program, Sloan Kettering Institute, Memorial Sloan Kettering Cancer Center, New York, NY, 10065, USA.
⁹ Molecular Sciences Software Institute, Virginia Polytechnic Institute and State University, Blacksburg, VA, 24060, USA.
¹⁰ Graduate Program in Physiology, Biophysics, and Systems Biology, Weill Cornell Graduate School of Medical Sciences, New York, NY, 10065, USA.
¹¹ Computational Science Laboratory, Universitat Pompeu Fabra, Barcelona Biomedical Research Park (PRBB), Carrer Dr. Aiguader 88, 08003, Barcelona, Spain and ICREA, Passeig Lluis Companys 23, 08010, Barcelona, Spain.

Abstract

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 ωB97M-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.

Publication types

Dataset

Abstract

Publication types

Grants and funding