# Nutmeg and SPICE: Models and Data for Biomolecular Machine Learning

arXiv: https://arxiv.org/abs/2406.13112 · HTML: https://mlsanity.com/paper/2406.13112/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 39 references that are in the map.
- First posted on arXiv 18 Jun 2024.

## Builds on (most cited first, 5 of 5)

- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Learning Local Equivariant Representations for Large-Scale Atomistic Dynamics](https://mlsanity.com/paper/2204.05249/) (2022)
- [SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects](https://mlsanity.com/paper/2105.00304/) (2021)
- [SPICE, A Dataset of Drug-like Molecules and Peptides for Training Machine Learning Potentials](https://mlsanity.com/paper/2209.10702/) (2022)
- [TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials](https://mlsanity.com/paper/2306.06482/) (2023)

## Built on by (most cited first, 7 of 7)

- [Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction](https://mlsanity.com/paper/2502.12147/) (2025)
- [High-performance training and inference for deep equivariant interatomic potentials](https://mlsanity.com/paper/2504.16068/) (2025)
- [On the design space between molecular mechanics and machine learning force fields](https://mlsanity.com/paper/2409.01931/) (2024)
- [Training Dynamics of Learning 3D-Rotational Equivariance](https://mlsanity.com/paper/2512.02303/) (2025)
- [Faster Molecular Dynamics with Neural Network Potentials via Distilled Multiple Time-Stepping and Non-Conservative Forces](https://mlsanity.com/paper/2602.14975/) (2026)
- [Performance of universal machine-learned potentials with explicit long-range interactions in biomolecular simulations](https://mlsanity.com/paper/2508.10841/) (2025)
- [Transferable Implicit Solvent Machine Learning Potential for Drugs and Proteins Approaching Ab Initio Accuracy](https://mlsanity.com/paper/2607.10887/) (2026)

## Abstract (arXiv)

We describe version 2 of the SPICE dataset, a collection of quantum chemistry calculations for training machine learning potentials. It expands on the original dataset by adding much more sampling of chemical space and more data on non-covalent 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 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.