MACE-POLAR-1：一种可极化的静电基础模型用于分子化学
MACE-POLAR-1: A Polarisable Electrostatic Foundation Model for Molecular Chemistry
- Engineering Laboratory, University of Cambridge, Trumpington St, Cambridge, UK
- Yusuf Hamied Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, UK
- Cavendish Laboratory, University of Cambridge, J. J. Thomson Avenue, Cambridge, UK
- Scientific Computing Department, Science
- Technology Facilities Council, Daresbury Laboratory, Keckwick Lane, Daresbury WA4 4AD, UK
- Department of Physics
- Astronomy, University College London, 7-19 Gordon St, London WC1H 0AH, United Kingdom
- Initiative for Computational Catalysis, Flatiron Institute, 160 5th Avenue, New York, NY 10010
- School of Natural
- Environmental Sciences, Newcastle University, Newcastle upon Tyne, UK
- Max Planck Institute for Polymer Research, Ackermannweg 10, Mainz, Germany
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
MACE-POLAR-1通过引入长程静电学和极化迭代，提升了分子化学中非共价相互作用和超分子复合物的描述精度，适用于从小分子到蛋白质-配体复合物的多种计算场景。
AI中文摘要：
准确建模静电相互作用和电荷转移对计算化学至关重要，但大多数机器学习原子间势能（MLIPs）依赖于局部原子描述符，无法捕捉长程静电效应。我们提出了一种新的静电基础模型用于分子化学，该模型扩展了MACE架构，明确处理长程相互作用和静电诱导。我们的方法结合了局部多体几何特征和一种非自洽场形式，通过可学习的电荷和自旋密度进行极化迭代来建模诱导，随后通过可学习的Fukui函数进行全局电荷平衡，以控制总电荷和总自旋。这种设计使系统在不同电荷和自旋状态下能够获得准确且物理的描述，同时保持计算效率。在OMol25数据集（包含1亿次混合DFT计算）上训练的模型在各种基准测试中实现了化学精度，其在热力学、反应能垒、构象能和过渡金属复合物方面的准确性与混合DFT相当。值得注意的是，我们证明了长程静电学的引入在非共价相互作用和超分子复合物的描述上相比非静电模型有显著提升，包括在X23-DMC数据集中对分子晶体形成能的亚千卡/摩尔预测，以及在蛋白质-配体相互作用上比短程模型提高了四倍。该模型能够处理可变电荷和自旋状态、响应外部场、提供可解释的自旋解析电荷密度，并且在从小分子到蛋白质-配体复合物的准确性上保持一致，使其成为计算分子化学和药物发现的多功能工具。
英文摘要：
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.
