Design of Experimental Conditions with Machine Learning for Collaborative Organic Synthesis Reactions Using Transition-Metal Catalysts

Abstract

To improve product yields in synthetic reactions, it is important to use appropriate catalysts. In this study, we used machine learning to design catalysts for a reaction system in which both Buchwald−Hartwig-type and Suzuki−Miyaura-type cross-coupling reactions proceed simultaneously. First, using an existing dataset, yield prediction models were constructed with machine learning between experimental conditions, including the substrate and catalyst and the yields of the two products. Seven methods for calculating both the substrate and catalyst descriptors were proposed, and the predictive ability of the yield prediction models was discussed in terms of the descriptors and machine learning methods. Then, the constructed models were used to predict the compound yields for new combinations of substrates and catalysts, and the predictions were experimentally validated with high reproducibility, confirming that machine learning can predict yields from experimental conditions with high accuracy. In addition, to design catalysts that will improve the yields in our dataset, we added datasets collected from scientific papers and designed catalyst ligands. The proposed catalyst candidates were tested in actual synthetic experiments, and the experimental results exceeded the existing yields.

Molecular Machine Learning for Chemical Catalysis: Prospects and Challenges

“…The vast amount of chemical data generated during wet-lab experiments is often underutilized. The application of data-driven approaches for reaction discovery, optimization, and prediction can make a significant impact on efficient exploration of the multidimensional chemical space . In recent years, the increase in computing power ably complemented by improved data availability has led to notable progress in the use of machine learning (ML) in many areas of chemistry, ranging from retrosynthetic planning to property or reaction outcome predictions …”

Catalyst Design and Feature Engineering to Improve Selectivity and Reactivity in Two Simultaneous Cross-Coupling Reactions

“…Studies on selectivity 10 and machine learning investigations of the selectivity in multiple coupling reactions have been reported. 11 Although the maximum yield of BHCC reaction products was less than 10% when aryl chlorides were used in the reaction system where BHCC and SMCC reactions occurred simultaneously, a catalyst with a 33% yield of BHCC products was successfully developed. 11 The objective of this study was to develop catalyst−ligand combinations, including the development of new variables (x) under all experimental conditions, an estimation of the reaction mechanism, and new reaction developments.…”

“…Although the detailed reaction mechanism in the reaction system where BHCC and SMCC reactions occur simultaneously is not fully understood, the same reaction mechanism can be estimated up to oxidative addition in BHCC and SMCC cross-coupling reactions. Studies on selectivity and machine learning investigations of the selectivity in multiple coupling reactions have been reported . Although the maximum yield of BHCC reaction products was less than 10% when aryl chlorides were used in the reaction system where BHCC and SMCC reactions occurred simultaneously, a catalyst with a 33% yield of BHCC products was successfully developed …”

Prediction of the photoelectrochemical performance of hematite electrodes using analytical data

“…11,12 For example, a cross-coupling reaction was optimized in terms of concentrations and catalysts with a small number of synthetic data. 13 Recently, Tamura et al demonstrated the optimization of material properties using molecular descriptors and the experimentally obtained analytical data. 14 Also, the solubility data were also predicted with a combination of analytical data and molecular descriptors.…”