The combination of neural network potential (NNP) with molecular simulations plays an important role in an efficient and thorough understanding of a molecular system's potential energy surface (PES). However, grasping the interplay between input features and their local contribution to NNP is growingly evasive due to heavy featurization. In this work, we suggest an end-to-end model which directly predicts per-atom energy from the coordinates of particles, avoiding expert-guided featurization of the network input. Employing self-attention as the main workhorse, our model is intrinsically equivariant under the permutation operation, resulting in the invariance of the total potential energy. We tested our model against several challenges in molecular simulation problems, including periodic boundary condition (PBC), $n$-body interaction, and binary composition. Our model yielded stable predictions in all tested systems with errors significantly smaller than the potential energy fluctuation acquired from molecular dynamics simulations. Thus, our work provides a minimal baseline model that encodes complex interactions in a condensed phase system to facilitate the data-driven analysis of physicochemical systems.
翻译:神经网络潜力(NNP)与分子模拟相结合,在高效和透彻地了解分子系统潜在能源表面(PES)方面发挥着重要作用。然而,掌握输入特征之间的相互作用及其对NNP的当地贡献,由于重产化,正在日益蒸发。在这项工作中,我们建议采用一个端到端模型,直接从粒子坐标中预测每原子能量,避免由专家引导的网络输入成形。将自我注意作为主要工作马,我们的模型在变异操作中具有内在的变异性,导致总的潜在能量的变异性。我们测试了我们的模型,以应对分子模拟问题中的若干挑战,包括定期边界状况(PBC)、美元-体相互作用和二元构成。我们模型对所有测试的系统进行了稳定预测,其误差大大小于分子动态模拟获得的潜在能源波动。因此,我们的工作提供了一种最起码的基线模型,在压缩的阶段系统中编码复杂的相互作用,以便利对物理化学系统进行数据驱动分析。