On the design space between molecular mechanics and machine learning force fields

A force field as accurate as quantum mechanics (QMs) and as fast as molecular mechanics (MMs), with which one can simulate a biomolecular system efficiently enough and meaningfully enough to get quantitative insights, is among the most ardent dreams of biophysicists—a dream, nevertheless, not to be fulfilled any time soon. Machine learning force fields (MLFFs) represent a meaningful endeavor in this direction, where differentiable neural functions are parametrized to fit ab initio energies and forces through automatic differentiation. We argue that, as of now, the utility of the MLFF models is no longer bottlenecked by accuracy but primarily by their speed, as well as stability and generalizability—many recent variants, on limited chemical spaces, have long surpassed the chemical accuracy of 1 kcal/mol—the empirical threshold beyond which realistic chemical predictions are possible—though still magnitudes slower than MM. Hoping to kindle exploration and design of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the technical design space (the speed-accuracy trade-off) between MM and ML force fields. After a brief review of the building blocks (from a machine learning-centric point of view) of force fields of either kind, we discuss the desired properties and challenges now faced by the force field development community, survey the efforts to make MM force fields more accurate and ML force fields faster, and envision what the next generation of MLFF might look like.

Authors

Institutions

Publication Details

Journal
Applied Physics Reviews
Published
2025-04-02
DOI
https://doi.org/10.1063/5.0237876
Citations
23
Primary Topic
Machine Learning in Materials Science
Type
article
Field-Weighted Citation Impact
11.39
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

On the design space between molecular mechanics and machine learning force fields

Stefano Martiniani, Daniel J. Cole, Arnav Nagle, Joshua A. Rackers et al.
23 citations
Applied Physics Reviews
Machine Learning in Materials Science
11.39
article

On the design space between molecular mechanics and machine learning force fields

Stefano Martiniani, Daniel J. Cole, Arnav Nagle, Joshua A. Rackers, Tong Zhu, Michael S. Chen, Kuang Yu, John Z. H. Zhang, Joe G. Greener, Peter Eastman, Kenichiro Takaba, Mark E. Tuckerman, Marcus Wieder, Kyunghyun Cho, Yuanqing Wang, Xinyan Wang, Yuzhi Xu
article en
23 citations

Abstract

A force field as accurate as quantum mechanics (QMs) and as fast as molecular mechanics (MMs), with which one can simulate a biomolecular system efficiently enough and meaningfully enough to get quantitative insights, is among the most ardent dreams of biophysicists—a dream, nevertheless, not to be fulfilled any time soon. Machine learning force fields (MLFFs) represent a meaningful endeavor in this direction, where differentiable neural functions are parametrized to fit ab initio energies and forces through automatic differentiation. We argue that, as of now, the utility of the MLFF models is no longer bottlenecked by accuracy but primarily by their speed, as well as stability and generalizability—many recent variants, on limited chemical spaces, have long surpassed the chemical accuracy of 1 kcal/mol—the empirical threshold beyond which realistic chemical predictions are possible—though still magnitudes slower than MM. Hoping to kindle exploration and design of faster, albeit perhaps slightly less accurate MLFFs, in this review, we focus our attention on the technical design space (the speed-accuracy trade-off) between MM and ML force fields. After a brief review of the building blocks (from a machine learning-centric point of view) of force fields of either kind, we discuss the desired properties and challenges now faced by the force field development community, survey the efforts to make MM force fields more accurate and ML force fields faster, and envision what the next generation of MLFF might look like.

Applied Physics ReviewsVol. 12(2)
MRC Laboratory of Molecular Biology (GB), Shenzhen University (CN), University of Washington (US), New York University Shanghai (CN), Courant Institute of Mathematical Sciences (US), Open Geospatial Consortium (US), Asahi Kasei (Japan) (JP), SP Technology (South Korea) (KR), Shenzhen Technology University (CN), Open Molecular Software Foundation, New York University (US), Newcastle University (GB), Medical Research Council (GB), Stanford University (US), Tsinghua University (CN)
Openalex Percentile: Top 1%
Machine Learning in Materials Science
11.39
DOISourceOpenAlex
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.