A Fast, Low-Cost and Simple Method for Predicting Atomic/Inter-Atomic Properties by Combining a Low Dimensional Deep Learning Model with a Fragment Based Graph Convolutional Network
A Fast, Low-Cost and Simple Method for Predicting Atomic/Inter-Atomic Properties by Combining a Low Dimensional Deep Learning Model with a Fragment Based Graph Convolutional Network
复制标题
DOI：
10.3390/cryst12121740
复制
发表时间：
2022-12
期刊：
影响因子：
2.7
通讯作者：
Peng Gao;Zonghang Liu;Jie Zhang;Jia-ao Wang;G. Henkelman
中科院分区：
文献类型：
--
作者：
Peng Gao;Zonghang Liu;Jie Zhang;Jia-ao Wang;G. Henkelman
原子和原子间性质的高精度计算，如核磁共振（NMR）光谱和键离解能（BDE），对于药物分子结构分析、药物探索和筛选都很有价值。重要的是，这些计算应包括相对论效应，这是计算昂贵的治疗。非相对论计算是比较便宜，但其结果是不太准确。在这项研究中，我们提出了一个计算框架，用于预测原子和原子间的属性，通过使用机器学习在一个非相对论，但准确和计算成本低廉的框架。通过嵌入在基于片段的图卷积神经网络（F-GCN）中的低维深度神经网络（DNN）获得精确的原子和原子间性质。F-GCN充当原子指纹生成器，将原子局部环境转换为DNN的数据，这提高了学习能力，与实验相比，结果更准确。使用这个框架，奈韦拉平和苯酚O-H BDEs的13 C/1H NMR化学位移预测与实验测量结果吻合良好。
Calculations with high accuracy for atomic and inter-atomic properties, such as nuclear magnetic resonance (NMR) spectroscopy and bond dissociation energies (BDEs) are valuable for pharmaceutical molecule structural analysis, drug exploration, and screening. It is important that these calculations should include relativistic effects, which are computationally expensive to treat. Non-relativistic calculations are less expensive but their results are less accurate. In this study, we present a computational framework for predicting atomic and inter-atomic properties by using machine-learning in a non-relativistic but accurate and computationally inexpensive framework. The accurate atomic and inter-atomic properties are obtained with a low dimensional deep neural network (DNN) embedded in a fragment-based graph convolutional neural network (F-GCN). The F-GCN acts as an atomic fingerprint generator that converts the atomistic local environments into data for the DNN, which improves the learning ability, resulting in accurate results as compared to experiments. Using this framework, the 13C/1H NMR chemical shifts of Nevirapine and phenol O–H BDEs are predicted to be in good agreement with experimental measurement.