讲座题目：Accelerating Chemical Discovery and Development with Continuous Flow, Automation, and AI
主讲人：Klavs F. Jensen 院士
主持人：钱旭红 院士
开始时间：2025-04-11 16:00
讲座地址：闵行校区光学大楼三楼报告厅
主办单位：药学院
报告人简介：
Klavs F. Jensen is Warren K. Lewis Professor in Chemical Engineering and Materials Science and Engineering at the Massachusetts Institute of Technology. He is a co-director of MIT’s consortium, Machine Learning for Pharmaceutical Discovery and Synthesis, which aims to bring machine learning technology into pharmaceutical discovery and development. From 2007 to July 2015, he was the Head of the Department of Chemical Engineering. Prof. Jensen’s research integrates chemical engineering, organic chemistry, and computer science to accelerate the discovery and development of new materials and synthetic routes while reducing costs and improving safety. His multidisciplinary work has contributed to microfluidic devices for chemical synthesis; fundamental technologies for continuous synthesis of fine chemicals and pharmaceuticals, “flow chemistry;” development of automation methods for pharmaceutical development and automated chemical synthesis; combining machine learning techniques, chemical synthesis, and engineering to develop new tools for the design of synthetic pathways for target molecules; development of automated robotic platforms that use machine learning to plan and execute synthetic routes to meet specific goals. Prof. Jensen is the co-author of more than 500 refereed journal publications and the inventor of ~65 US patents. His work has been cited over 80,000 times. He was the inaugural Editor-in-Chief of the Royal Society of Chemistry Journal Reaction Chemistry and Engineering from 2015 to 2024. He has received several awards, including the W.H. Walker and Founders Awards of the American Institute of Chemical Engineers and the inaugural IUPAC-ThalesNano Prize in Flow Chemistry. Professor Jensen is a member of the US National Academy of Sciences, the US National Academy of Engineering, and the American Academy of Arts and Science. He is the National Academy of Inventors, the American Institute of Chemical Engineers, and the Royal Society of Chemistry.
报告内容：
Continuous flow, automation, robotics, and artificial intelligence (AI) tools promise to accelerate chemical synthesis processes underlying the discovery and development of molecules. Case studies illustrate strategies for the development and optimization of multistep continuous organic synthesis (flow chemistry) enabled by the integration of computer computer-aided synthesis planning (CASP), automation, robotics, machine learning (ML), and process analytic tools. Elements of CASP are briefly reviewed, along with the design characteristics of a modular, robotic flow synthesis platform and its application in the synthesis of pharmaceutical intermediates. Optimization of a CASP-proposed and human-refined multistep synthesis of an exemplary small molecule, sonidegib. The platform’s modularity, robotic reconfigurability, and flexibility for convergent synthesis play a critical role in the multi-objective Bayesian optimization of categorical and continuous process variables in the multistep route. Solids handling in flow is illustrated with optimization of photo-redox catalysis in an automated cascade of miniaturized continuous stirred tank reactors (CSTRs). A final case study integrates ML algorithms for multi-property prediction, molecular generation, CASP, and automated analytical quantification with an automated 96-well-plate platform encompassing liquid handling, multistep chemical synthesis, isolation, and optical and chemical characterization. The discovery of new organic dye molecules and histone deacetylase inhibitors exemplifies the transformational potential of such an autonomous molecular discovery platform. Overall, the presented case studies aim to show that automation, continuous flow, modularity, and robotics integrated with AI/ML techniques enhance our ability to perform multistep synthesis through idea generation, experimental design, execution, optimization, and autonomy.
