Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
Machine Learning in QM/MM Molecular Dynamics Simulations of Condensed-Phase Systems
复制标题
DOI：
10.1021/acs.jctc.0c01112
复制
发表时间：
2021-04-05
影响因子：
5.5
通讯作者：
Riniker, Sereina
中科院分区：
文献类型：
--
作者：
Boeselt, Lennard;Thuerlemann, Moritz;Riniker, Sereina
量子力学/分子力学（QM/MM）分子动力学（MD）模拟已被开发用于模拟分子系统，在这些系统中，电子结构变化的明确描述是必要的。然而，与完全经典的模拟相比，QM/MM MD模拟在计算上是昂贵的，因为所有价电子都被明确处理，并且需要自洽场（SCF）过程。最近，有人提出用机器学习（ML）模型取代QM描述的方法。然而，由于长程相互作用，凝聚相系统对这些方法构成了挑战。在这里，我们建立了一个工作流程，它将MM环境作为一种元素类型纳入高维神经网络势（HDNNP）中。拟合的HDNNP用静电嵌入方案描述QM粒子的势能面。因此，MM粒子感受到来自极化的QM粒子的力。为了达到化学精度，我们发现即使是简单的系统也需要具有强梯度正则化、大量数据点和大量参数的模型。为了解决这个问题，我们将我们的方法扩展到一种Δ -学习方案，其中ML模型学习参考方法（密度泛函理论（DFT））和一种更便宜的半经验方法（密度泛函紧束缚（DFTB））之间的差异。我们表明，这种方案达到了DFT参考方法的精度，同时所需参数显著减少。此外，Δ -学习方案能够在1.4纳米的截断范围内正确纳入长程相互作用。通过对水中视黄酸以及水中S -腺苷甲硫氨酸和胞嘧啶之间的相互作用进行MD模拟对其进行了验证。所呈现的结果表明，Δ -学习是凝聚相系统（QM）ML/MM MD模拟的一种有前途的方法。
Quantum mechanics/molecular mechanics (QM/MM) molecular dynamics (MD) simulations have been developed to simulate molecular systems, where an explicit description of changes in the electronic structure is necessary. However, QM/MM MD simulations are computationally expensive compared to fully classical simulations as all valence electrons are treated explicitly and a self-consistent field (SCF) procedure is required. Recently, approaches have been proposed to replace the QM description with machine-learned (ML) models. However, condensed-phase systems pose a challenge for these approaches due to long-range interactions. Here, we establish a workflow, which incorporates the MM environment as an element type in a high-dimensional neural network potential (HDNNP). The fitted HDNNP describes the potential-energy surface of the QM particles with an electrostatic embedding scheme. Thus, the MM particles feel a force from the polarized QM particles. To achieve chemical accuracy, we find that even simple systems require models with a strong gradient regularization, a large number of data points, and a substantial number of parameters. To address this issue, we extend our approach to a.-learning scheme, where the ML model learns the difference between a reference method (density functional theory (DFT)) and a cheaper semiempirical method (density functional tight binding (DFTB)). We show that such a scheme reaches the accuracy of the DFT reference method while requiring significantly less parameters. Furthermore, the.-learning scheme is capable of correctly incorporating long-range interactions within a cutoff of 1.4 nm. It is validated by performing MD simulations of retinoic acid in water and the interaction between S-adenoslymethioniat and cytosine in water. The presented results indicate that.-learning is a promising approach for (QM)ML/MM MD simulations of condensed-phase systems.