[论文解读] MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry

Ilyes Batatia, William J. Baldwin+11 more|arXiv (Cornell University)|Feb 23, 2026

Machine Learning in Materials Science被引用 0

一句话总结

引入 MACE-POLAR-1，一种极化的静电基础模型，通过长程感应和基于 Fukui 函数的电荷/自旋平衡来准确建模可变电荷/自旋状态与非局部相互作用，扩展了 MACE。

ABSTRACT

Accurate modelling of electrostatic interactions and charge transfer is fundamental to computational chemistry, yet most machine learning interatomic potentials (MLIPs) rely on local atomic descriptors that cannot capture long-range electrostatic effects. We present a new electrostatic foundation model for molecular chemistry that extends the MACE architecture with explicit treatment of long-range interactions and electrostatic induction. Our approach combines local many-body geometric features with a non-self-consistent field formalism that updates learnable charge and spin densities through polarisable iterations to model induction, followed by global charge equilibration via learnable Fukui functions to control total charge and total spin. This design enables an accurate and physical description of systems with varying charge and spin states while maintaining computational efficiency. Trained on the OMol25 dataset of 100 million hybrid DFT calculations, our models achieve chemical accuracy across diverse benchmarks, with accuracy competitive with hybrid DFT on thermochemistry, reaction barriers, conformational energies, and transition metal complexes. Notably, we demonstrate that the inclusion of long-range electrostatics leads to a large improvement in the description of non-covalent interactions and supramolecular complexes over non-electrostatic models, including sub-kcal/mol prediction of molecular crystal formation energy in the X23-DMC dataset and a fourfold improvement over short-ranged models on protein-ligand interactions. The model's ability to handle variable charge and spin states, respond to external fields, provide interpretable spin-resolved charge densities, and maintain accuracy from small molecules to protein-ligand complexes positions it as a versatile tool for computational molecular chemistry and drug discovery.

研究动机与目标

• 开发一个物理信息驱动的基础模型，能够准确捕捉分子体系中的长程静电和感应。
• 在可扩展的 MLIP 框架内实现可变电荷和自旋状态及对外场的响应。
• 在保持计算效率和训练可行性的同时，在多样化的化学领域获得高精度。

提出的方法

• 在 MACE 架构中扩展非自洽场（SCF）形式以实现长程感应。
• 引入可学习的自旋-电荷密度，作为长程相互作用的粗粒度代理。
• 通过全局卷积和局部更新迭代细化自旋-电荷多极矩，然后使用可学习的 Fukui 函数使总电荷和自旋达到平衡。
• 将自旋-电荷密度投影到原子中心高斯基底，获得非局部静电特征。
• 加入一个从局部几何和自旋-电荷/静电特征中学习的非局部能量项。
• 从经分布处理的多极矩计算静电能量，利用解析可处理的高斯基变换。

实验结果

研究问题

• RQ1 如何在保持效率的同时将长程静电和感应纳入基于 ML 的原子间势？
• RQ2 一个可学习的自旋分辨电荷密度和基于 Fukui 函数的平衡是否能准确处理可变电荷和自旋状态？
• RQ3 显式长程静电对如分子晶体和蛋白质-配体相互作用等挑战性基准的影响为何？
• RQ4 模型在带电种、过渡金属和溶液中的氧化还原化学方面的性能如何？

主要发现

• 显式长程静电显著改进了带电体系和非共价复合体的描述。
• 在如分子晶体晶格能和蛋白质–配体结合等挑战性基准上达到甚高的准确度。
• 加入长程相互作用相比非电性模型对超分子复合体和蛋白质–配体相互作用有较大提升。
• 模型能够处理可变电荷和自旋状态，并对外场做出响应，具备可解释的自旋分辨电荷密度。
• 性能覆盖从小分子到蛋白质–配体复合体，适用于药物发现和生物模拟应用。