Development of Range-Corrected Deep Learning Potentials for Fast, Accurate Quantum Mechanical/Molecular Mechanical Simulations of Chemical Reactions in Solution.
Development of Range-Corrected Deep Learning Potentials for Fast, Accurate Quantum Mechanical/Molecular Mechanical Simulations of Chemical Reactions in Solution.
复制标题
开发范围校正的深度学习潜力，用于快速，准确的量子力学/分子力学模拟溶液中的化学反应。
DOI：
10.1021/acs.jctc.1c00201
复制
发表时间：
2021-11-09
影响因子：
5.5
通讯作者：
York DM
中科院分区：
文献类型：
--
作者：
Zeng J;Giese TJ;Ekesan Ş;York DM
我们开发了一种新的深势程修正(DPRc)机器学习势，用于凝聚相化学反应的量子力学/分子力学(QM/MM)模拟。新的量程校正使短距离的QM/MM交互作用能够进行调整，以获得更高的精度，并且校正在指定的截止范围内平滑地消失。我们进一步开发了一种用于稳健神经网络训练的主动学习过程。我们测试了DPRc模型和训练程序针对一系列6个非酶的溶液中的磷酰转移反应，这些反应在RNA裂解酶的机理研究中很重要。具体地说，我们将DPRc修正应用于基本的QM模型，并测试其再现从目标QM模型产生的自由能分布的能力。我们使用MNDO/d和DFTB2半经验模型进行这些比较，因为它们处理轨道正交化和静电学的方式不同，并产生彼此显著不同的自由能分布，从而为DPRc模型和训练过程提供了严格的压力测试。比较表明，要准确地再现自由能分布，需要将QM/MM相互作用修正到6？我们进一步发现，模型的初始训练得益于从温度副本交换模拟中生成数据，并将高温组态纳入拟合过程，因此所得到的模型被训练以适当地避开高能区。一个DPRc模型被训练来再现4个不同的反应，并与目标QM/MM模拟得到的自由能分布很好地吻合。DPRc模型被进一步证明可以转移到训练中没有明确考虑的2D自由能表面和1D自由能分布。对DPRc模型的计算性能的检查表明，它在CPU上运行时相当慢，但在使用NVIDIA V100 GPU时速度几乎快100倍，导致几乎可以忽略不计的开销。新的DPRc模型和训练程序为创造下一代QM/MM潜力提供了一个潜在的强大新工具，适用于从药物发现到酶设计的广泛自由能应用。
We develop a new Deep Potential - Range Correction (DPRc) machine learning potential for combined quantum mechanical/molecular mechanical (QM/MM) simulations of chemical reactions in the condensed phase. The new range correction enables short-ranged QM/MM interactions to be tuned for higher accuracy, and the correction smoothly vanishes within a specified cutoff. We further develop an active learning procedure for robust neural network training. We test the DPRc model and training procedure against a series of 6 non-enzymatic phosphoryl transfer reactions in solution that are important in mechanistic studies of RNA-cleaving enzymes. Specifically, we apply DPRc corrections to a base QM model and test its ability to reproduce free energy profiles generated from a target QM model. We perform these comparisons using the MNDO/d and DFTB2 semiempirical models because they differ in the way they treat orbital orthogonalization and electrostatics, and produce free energy profiles which differ significantly from each other, thereby providing us a rigorous stress test for the DPRc model and training procedure. The comparisons show that accurate reproduction of the free energy profiles requires correction of the QM/MM interactions out to 6 Å. We further find that the model’s initial training benefits from generating data from temperature replica exchange simulations and including high-temperature configurations into the fitting procedure so the resulting models are trained to properly avoid high-energy regions. A single DPRc model was trained to reproduce 4 different reactions and yielded good agreement with the free energy profiles made from the target QM/MM simulations. The DPRc model was further demonstrated to be transferable to 2D free energy surfaces and 1D free energy profiles that were not explicitly considered in the training. Examination of the computational performance of the DPRc model showed that it was fairly slow when run on CPUs, but was sped up almost 100-fold when using an NVIDIA V100 GPUs, resulting in almost negligible overhead. The new DPRc model and training procedure provide a potentially powerful new tool for the creation of next-generation QM/MM potentials for a wide spectrum of free energy applications ranging from drug discovery to enzyme design.
登录
查看更多内容
影响因子：
5.5
作者：
Giese, Timothy J.;Panteva, Maria T.;Chen, Haoyuan;York, Darrin M.
通讯作者：
York, Darrin M.
影响因子：
5.5
作者：
Giese TJ;York DM
通讯作者：
York DM
影响因子：
5.5
作者：
Boeselt, Lennard;Thuerlemann, Moritz;Riniker, Sereina
通讯作者：
Riniker, Sereina
影响因子：
5.5
作者：
Giese, Timothy J.;York, Darrin M.
通讯作者：
York, Darrin M.
影响因子：
8.6
作者：
Behler, Joerg;Parrinello, Michele
通讯作者：
Parrinello, Michele