Nutmeg and SPICE: Models and Data for Biomolecular Machine Learning
Top Cited Papers
- 25 September 2024
- journal article
- research article
- Published by American Chemical Society (ACS) in Journal of Chemical Theory and Computation
- Vol. 20 (19) , 8583-8593
Abstract
We describe version 2 of the SPICE data set, a collection of quantum chemistry calculations for training machine learning potentials. It expands on the original data set by adding much more sampling of chemical space and more data on noncovalent interactions. We train a set of potential energy functions called Nutmeg on it. They are based on the TensorNet architecture. They use a novel mechanism to improve performance on charged and polar molecules, injecting precomputed partial charges into the model to provide a reference for the large-scale charge distribution. Evaluation of the new models shows that they do an excellent job of reproducing energy differences between conformations even on highly charged molecules or ones that are significantly larger than the molecules in the training set. They also produce stable molecular dynamics trajectories and are fast enough to be useful for routine simulation of small molecules.Keywords
All Related Versions
Funding Information
- Division of Chemistry (CHE-2136142)
- National Cancer Institute (P30 CA008748)
- Memorial Sloan-Kettering Cancer Center
- National Institute of General Medical Sciences (R01 GM140090, R35 GM152017)
This publication has 36 references indexed in Scilit:
- OpenMM 8: Molecular Dynamics Simulation with Machine Learning PotentialsThe Journal of Physical Chemistry B, 2023
- TorsionNet: A Deep Neural Network to Rapidly Predict Small-Molecule Torsional Energy Profiles with the Accuracy of Quantum MechanicsJournal of Chemical Information and Modeling, 2022
- The MolSSI QCArchive project: An open‐source platform to compute, organize, and share quantum chemistry dataWIREs Computational Molecular Science, 2020
- Robust Atomistic Modeling of Materials, Organometallic, and Biochemical SystemsAngewandte Chemie International Edition, 2020
- Polarisable force fields: what do they add in biomolecular simulations?Current Opinion in Structural Biology, 2020
- The Nonlocal Kernel in van der Waals Density Functionals as an Additive Correction: An Extensive Analysis with Special Emphasis on the B97M-V and ωB97M-V ApproachesJournal of Chemical Theory and Computation, 2018
- ff14SB: Improving the Accuracy of Protein Side Chain and Backbone Parameters from ff99SBJournal of Chemical Theory and Computation, 2015
- A polarizable model of water for molecular dynamics simulations of biomoleculesChemical Physics Letters, 2006
- The Stopping and Range of Ions in Solids1982
- Iterative partial equalization of orbital electronegativity—a rapid access to atomic chargesTetrahedron, 1980