School of Information Science & Engineering, Lanzhou University, Lanzhou, China, 730000.
School of Cyberspace Security, Gansu University of Political Science and Law, Lanzhou, China, 730070.
J Chem Inf Model. 2022 Sep 12;62(17):4122-4133. doi: 10.1021/acs.jcim.2c00747. Epub 2022 Aug 29.
To develop a realistic electrostatic model that allows for the anisotropy of the atomic electron density, high-rank atomic multipole moments computed by quantum chemical calculations have been studied extensively. However, it is hard to process huge RNA systems only relying on quantum chemical calculations due to its highly computational cost. In this study, we employ five machine learning methods of Gaussian process regression with automatic relevance determination (ARDGPR), Kriging, radial basis function neural networks, Bagging, and generalized regression neural network to predict atomic multipole moments. Atom-atom electrostatic interaction energies are subsequently computed using the predicted atomic multipole moments in the pilot system pentose of RNA. Here, the performance of the five methods is compared in terms of both the multipole moment prediction errors and the electrostatic energy prediction errors. For the predicted high-rank multipole moments of the four elements (O, C, N, and H) in capped pentose, ARDGPR and Kriging consistently outperform the other three methods. Therefore, the multipole moments predicted by the two best methods of ARDGPR and Kriging are then used to predict electrostatic interaction energy of each pentose. Finally, the absolute average energy errors of ARDGPR and Kriging are 1.83 and 4.33 kJ mol, respectively. Compared to Kriging, the ARDGPR method achieves a 58% decrease in the absolute average energy error. These satisfactory results demonstrated that the ARDGPR method with the strong feature extraction ability can predict the electrostatic interaction energy of pentose in RNA correctly and reliably.
为了开发能够考虑原子电子密度各向异性的现实静电模型，人们广泛研究了通过量子化学计算得到的高阶原子多极矩。然而，由于其计算成本非常高，仅依靠量子化学计算很难处理庞大的 RNA 系统。在这项研究中，我们采用了高斯过程回归自动相关性确定（ARDGPR）、克里金、径向基函数神经网络、套袋和广义回归神经网络等五种机器学习方法来预测原子多极矩。随后，在 RNA 的戊糖先导系统中，使用预测的原子多极矩计算原子间静电相互作用能。在这里，我们比较了这五种方法在多极矩预测误差和静电能预测误差方面的性能。对于 capped pentose 中四个元素（O、C、N 和 H）的高阶多极矩预测，ARDGPR 和克里金始终优于其他三种方法。因此，我们使用 ARDGPR 和克里金这两种最佳方法预测的多极矩来预测每个戊糖的静电相互作用能。最后，ARDGPR 和克里金的绝对平均能量误差分别为 1.83 和 4.33 kJ/mol。与克里金相比，ARDGPR 方法的绝对平均能量误差降低了 58%。这些令人满意的结果表明，具有强大特征提取能力的 ARDGPR 方法可以正确可靠地预测 RNA 中戊糖的静电相互作用能。
