Chemical Research and Development, Pfizer Worldwide Research and Development, Groton Laboratories, Eastern Point Road, Groton, Connecticut 06340, United States
Auto-generated profile, based on publicly available information
Chase Anthony Salazar
Chemical Research and Development, Pfizer Worldwide Research and Development, Groton Laboratories, Eastern Point Road, Groton, Connecticut 06340, United States
A subtle balancing act for quinones: Palladium catalysis is widely used in drug synthesis to form carbon-carbon bonds, but typically both carbon centers need to be activated ahead of time. Although introducing oxygen as an oxidant diminishes the need for preactivation, the catalysis then tends to be less efficient, especially in the case of arene coupling. Salazar et al. pinpointed the role of quinone co-catalysts in these processes and determined that after accelerating carbon-carbon bond formation, the quinone slows down catalyst reoxidation by oxygen. Appending bulky substituents to the quinone struck a better balance and substantially enhanced catalytic efficiency. Science , this issue p. 1454
18 December 2024 in Angewandte Chemie International Edition
Electrochemical C−H oxidation reactions offer a sustainable route to functionalize hydrocarbons, yet identifying suitable substrates and optimizing synthesis remain challenging. Here, we report an integrated approach combining machine learning and large language models to streamline the exploration of electrochemical C−H oxidation reactions. Utilizing a batch rapid screening electrochemical platform, we evaluated a wide range of reactions, initially classifying substrates by their reactivity, while LLMs text‐mined literature data to augment the training set. The resulting ML models for reactivity prediction achieved high accuracy (>90 %) and enabled virtual screening of a large set of commercially available molecules. To optimize reaction conditions for selected substrates, LLMs were prompted to generate code that iteratively improved yields. This human‐AI collaboration proved effective, efficiently identifying high‐yield conditions for 8 drug‐like substances or intermediates. Notably, we benchmarked the accuracy and reliability of 12 different LLMs–including LLaMA series, Claude series, OpenAI o1, and GPT‐4‐on code generation and function calling related to ML based on natural language prompts given by chemists to showcase potentials for accelerating research across four diverse tasks. In addition, we collected an experimental benchmark dataset comprising 1071 reaction conditions and yields for electrochemical C−H oxidation reactions.
20 March 2020 in Angewandte Chemie International Edition