analiza aiqbench
The paper proposes an extension to the TensorNet equivariant neural network that passes information about nearby classical atoms through its message-passing layers, while using electric-field features for more distant environments. The authors argue that field-only features can't distinguish some electrostatic environments, and that the hybrid approach beats either method alone. For ML readers, the useful point is that how a machine learning interatomic potential encodes its surroundings can limit accuracy in QM/MM simulations, a design choice that matters beyond this specific system.
A Hybrid Message-Passing and Electric-Field Representation for Electrostatic QM/MM Embedding with Machine Learning Interatomic Potentials
arXiv:2610.41523v1 Announce Type: cross Abstract: Within a hybrid quantum mechanics/molecular mechanics approach a small region of a large atomistic system is described quantum mechanically, while the rest of the system is represented by a classical force field. Despite this, the computational cost of the quantum calculation severely limits the accessible simulation and sampling time. Replacing the quantum calculation with a machine learning interatomic potential (MLIP) trained on quantum reference data can greatly increase the accessible simulation time. However, the accuracy and efficiency strongly depend on the specific way in which the MLIP incorporates information about the classical (electrostatic) environment. Here, we demonstrate that existing strategies based purely on features derived from an external electric field fail to distinguish certain environments, ultimately limiting their accuracy. As a solution, we propose an extension to the equivariant TensorNet architecture that mitigates this shortcoming by incorporating classical atoms close to the quantum region into the message-passing scheme, combined with features derived from the electric field for describing the environment farther away. We show that this combination achieves higher accuracy than either approach alone.
Abstract:Within a hybrid quantum mechanics/molecular mechanics approach a small region of a large atomistic system is described quantum mechanically, while the rest of the system is represented by a classical force field. Despite this, the computational cost of the quantum calculation severely limits the accessible simulation and sampling time. Replacing the quantum calculation with a machine learning interatomic potential (MLIP) trained on quantum reference data can greatly increase the accessible simulation time. However, the accuracy and efficiency strongly depend on the specific way in which the MLIP incorporates information about the classical (electrostatic) environment. Here, we demonstrate that existing strategies based purely on features derived from an external electric field fail to distinguish certain environments, ultimately limiting their accuracy. As a solution, we propose an extension to the equivariant TensorNet architecture that mitigates this shortcoming by incorporating classical atoms close to the quantum region into the message-passing scheme, combined with features derived from the electric field for describing the environment farther away. We show that this combination achieves higher accuracy than either approach alone.
Chemical Physics (physics.chem-ph); Biological Physics (physics.bio-ph); Computational Physics (physics.comp-ph); Quantum Physics (quant-ph)
arXiv:2610.41523 [physics.chem-ph]
(or arXiv:2610.41523v1 [physics.chem-ph] for this version)
https://doi.org/10.48550/arXiv.2610.41523 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 277 cuvinte