Daeyaert Frits, Ye Fengdan, Deem Michael W
Department of Bioengineering, Rice University, Houston, TX 77005.
Department of Physics & Astronomy, Rice University, Houston, TX 77005.
Proc Natl Acad Sci U S A. 2019 Feb 26;116(9):3413-3418. doi: 10.1073/pnas.1818763116. Epub 2019 Feb 7.
We report a machine-learning strategy for design of organic structure directing agents (OSDAs) for zeolite beta. We use machine learning to replace a computationally expensive molecular dynamics evaluation of the stabilization energy of the OSDA inside zeolite beta with a neural network prediction. We train the neural network on 4,781 candidate OSDAs, spanning a range of stabilization energies. We find that the stabilization energies predicted by the neural network are highly correlated with the molecular dynamics computations. We further find that the evolutionary design algorithm samples the space of chemically feasible OSDAs thoroughly. In total, we find 469 OSDAs with verified stabilization energies below -17 kJ/(mol Si), comparable to or better than known OSDAs for zeolite beta, and greatly expanding our previous list of 152 such predicted OSDAs. We expect that these OSDAs will lead to syntheses of zeolite beta.
我们报告了一种用于设计β沸石有机结构导向剂（OSDA）的机器学习策略。我们利用机器学习，通过神经网络预测取代对β沸石内部OSDA稳定能进行的计算成本高昂的分子动力学评估。我们在4781个候选OSDA上训练神经网络，这些候选OSDA涵盖了一系列稳定能。我们发现神经网络预测的稳定能与分子动力学计算高度相关。我们进一步发现，进化设计算法彻底地对化学上可行的OSDA空间进行了采样。总共，我们发现了469种经证实稳定能低于-17 kJ/（mol Si）的OSDA，与已知的β沸石OSDA相当或更好，大大扩充了我们之前列出的152种此类预测的OSDA。我们预计这些OSDA将有助于β沸石合成。
