Automation and computer-assisted planning for chemical synthesis

A reactivity model for oxidative addition to palladium enables quantitative predictions for catalytic cross-coupling reactions

“…Emerging approaches in reactivity prediction that combine high-throughput experimentation [8][9][10][11][12][13][14] with molecular descriptor sets [15][16][17][18][19][20][21][22][23][24] and multivariate statistical analysis including machine learning [25][26][27][28][29][30][31][32][33][34] can accelerate the screening/optimization process and increase success rates; however, predictions generated by these approaches are oen limited to the specic reaction under investigation. Developing and rening the next generation of organic chemistry tools, including computer-aided synthesis design, automated reaction optimization, and predictive algorithms, 35 requires the development of general and quantitative frameworks that rapidly link molecular structure to reactivity for many different reactants and catalysts.…”

A reactivity map for oxidative addition enables quantitative predictions for multiple catalytic reaction classes

“…Emerging approaches in reactivity prediction that combine highthroughput experimentation [5][6][7][8] with molecular descriptor sets [9][10][11] and multivariate statistical analysis including machine learning [12][13][14][15][16] can accelerate this process and increase success rates; however, the predictions generated by these approaches are often limited to the specific reaction under investigation (Figure 1A). Developing and refining the next generation of organic chemistry tools, including computer-aided synthesis design, automated reaction optimization, and predictive algorithms, 17 requires the development of general and quantitative frameworks linking molecular structure to reactivity for many different reactants and catalysts.…”

The Formal Cross‐Coupling of Amines and Carboxylic Acids to Form sp3–sp3 Carbon–Carbon Bonds

“…Reactions were documented in a machine-readable format to provide systematically captured reaction data for the machine learning community. [66] During reaction optimization, an additional metallophotoredox survey interrogated the possibility of replacing the triphenylpyridinium salt (3) with benzyltrimethylammonium chloride, but 3 uniformly outperformed trimethylammonium as a C À N bond-activating group (see Supporting Information). Follow up studies (see Supporting Information) revealed that reactions performed similarly in the absence of photocatalyst and blue light irradiation so further studies omitted photoredox technology.…”