Bayesian reaction optimization as a tool for chemical synthesis
Bayesian reaction optimization as a tool for chemical synthesis
复制标题
DOI：
10.1038/s41586-021-03213-y
复制
发表时间：
2021-02-04
期刊：
影响因子：
64.8
通讯作者：
Doyle, Abigail G.
中科院分区：
文献类型：
--
作者：
Shields, Benjamin J.;Stevens, Jason;Doyle, Abigail G.
反应优化对合成化学至关重要，从优化工业流程的产率到选择制备药物候选物的条件都是如此（1）。同样，参数优化在人工智能中无处不在，从调整虚拟个人助手到训练社交媒体和产品推荐系统（2）。由于进行实验成本高昂，这两个领域的科学家都通过仅评估可能配置的一小部分来设定众多（超）参数值。贝叶斯优化是一种基于迭代响应面的全局优化算法，在机器学习模型的调优方面表现出卓越的性能（3）。贝叶斯优化最近也应用于化学领域（4 - 9）；然而，其在合成化学中反应优化的应用和评估尚未得到研究。在此我们报道了一个贝叶斯反应优化框架的开发以及一个开源软件工具，该工具使化学家能够轻松地将最先进的优化算法融入他们日常的实验室实践中。我们收集了一个用于钯催化的直接芳基化反应的大型基准数据集，对贝叶斯优化与反应优化中的人类决策进行了系统研究，并将贝叶斯优化应用于两个实际的优化工作（光延反应和脱氧氟化反应）。通过一个在线游戏完成基准测试，该游戏将专家化学家及工程师所做的决策与实验室中进行的实际实验相联系。我们的研究结果表明，贝叶斯优化在平均优化效率（实验次数）和一致性（结果相对于初始可用数据的方差）方面均优于人类决策。总体而言，我们的研究表明，在日常实验室实践中采用贝叶斯优化方法可以通过做出更明智的、数据驱动的关于进行哪些实验的决策，促进功能性化学品的更高效合成。
Reaction optimization is fundamental to synthetic chemistry, from optimizing the yield of industrial processes to selecting conditions for the preparation of medicinal candidates(1). Likewise, parameter optimization is omnipresent in artificial intelligence, from tuning virtual personal assistants to training social media and product recommendation systems(2). Owing to the high cost associated with carrying out experiments, scientists in both areas set numerous (hyper)parameter values by evaluating only a small subset of the possible configurations. Bayesian optimization, an iterative response surface-based global optimization algorithm, has demonstrated exceptional performance in the tuning of machine learning models(3). Bayesian optimization has also been recently applied in chemistry(4-9); however, its application and assessment for reaction optimization in synthetic chemistry has not been investigated. Here we report the development of a framework for Bayesian reaction optimization and an open-source software tool that allows chemists to easily integrate state-of-the-art optimization algorithms into their everyday laboratory practices. We collect a large benchmark dataset for a palladium-catalysed direct arylation reaction, perform a systematic study of Bayesian optimization compared to human decision-making in reaction optimization, and apply Bayesian optimization to two real-world optimization efforts (Mitsunobu and deoxyfluorination reactions). Benchmarking is accomplished via an online game that links the decisions made by expert chemists and engineers to real experiments run in the laboratory. Our findings demonstrate that Bayesian optimization outperforms human decisionmaking in both average optimization efficiency (number of experiments) and consistency (variance of outcome against initially available data). Overall, our studies suggest that adopting Bayesian optimization methods into everyday laboratory practices could facilitate more efficient synthesis of functional chemicals by enabling better-informed, data-driven decisions about which experiments to run.