Department of Chemical Engineering , University of Washington , Seattle , Washington 98105 , Unitd States.
J Chem Inf Model. 2019 Jun 24;59(6):2617-2625. doi: 10.1021/acs.jcim.9b00087. Epub 2019 Apr 19.
We present a computational adaptive learning and design strategy for ionic liquids. In this approach we show that (1) multiple cycles of chemical search via genetic algorithm (GA), property calculation with molecular dynamics, and property modeling with physiochemical descriptors and neural networks (QSPR/NN) lead to overall lower property prediction error rates compared to the original QSPR/NN models; (2) chemical similarity and kernel density estimation are a proxy for QSPR/NN error; and (3) single QSPR/NN models projected onto two-dimensional property space recreate the experimentally observed Pareto optimum frontier and, combined with the GA, lead to new structures with properties beyond the frontier.
我们提出了一种用于离子液体的计算自适应学习和设计策略。在这种方法中，我们表明：（1）通过遗传算法（GA）进行多次化学搜索循环，用分子动力学进行性质计算，以及用物理化学描述符和神经网络（QSPR/NN）进行性质建模，与原始的 QSPR/NN 模型相比，总体上降低了性质预测误差率；（2）化学相似性和核密度估计是 QSPR/NN 误差的代理；（3）二维性质空间上的单个 QSPR/NN 模型可以再现实验观测到的帕累托最优前沿，并且与 GA 结合，可以得到具有超越前沿的性质的新结构。
