Artificial intelligence and machine learning have demonstrated their potential role in predictive chemistry and synthetic planning of small molecules; there are at least a few reports of companies employing in silico synthetic planning into their overall approach to accessing target molecules. A data-driven synthesis planning program is one component being developed and evaluated by the Machine Learning for Pharmaceutical Discovery and Synthesis (MLPDS) consortium, comprising MIT and 13 chemical and pharmaceutical company members. Together, we wrote this perspective to share how we think predictive models can be integrated into medicinal chemistry synthesis workflows, how they are currently used within MLPDS member companies, and the outlook for this field.
25 September 2023 in Organic Process Research & Development
Flow chemistry was initially used for speed to early phase material delivery in the development laboratories, scaling up chemical transformations that we would not or could not scale up batch for safety reasons. Some early examples included a Newman Kwart Rearrangement, Claisen rearrangement, hydroformylation, and thermal imidazole cyclization. Next, flow chemistry was used to enable safe scale up of hazardous chemistries to manufacturing plants. Examples included high pressure hydrogenation, aerobic oxidation, and Grignard formation reactions. More recently, flow chemistry was used in Small Volume Continuous (SVC) processes, where highly potent oncolytic molecules were produced by fully continuous processes at about 10 kg/day including reaction, extraction, distillation, and crystallization, using disposable equipment contained in fume hoods.