Coupling the industry’s push to accelerate drug development with the increasing complexity in small molecule drug candidates has resulted in a significant need to quickly adopt new technologies and predictive tools. Our group has created a Rapid Kinetics Workflow (RKW) which enables a predictive, agile approach to traditional drug substance process development and enables early troubleshooting of scale-up issues prior to initial clinical manufacturing campaigns. We will describe our High-throughput Kinetics (HTK) platform which expands traditional High-throughput Experimentation (HTE) to incorporate graphical analysis and mechanistic insight. The HTK platform allows significant acceleration of projects, as the timeline to go from initial screening of a variety of reaction conditions to creation of a predictive model for virtual optimization only takes one week to complete. This workflow will be demonstrated for an aza-Michael transformation. Our current focus is on linking machine learning to the HTK platform for even greater predictability and virtual optimization of chemical transformations, as well as a variety of unit operation steps.

Rapid kinetics workflow: Incorporating high-throughput experimentation, machine learning, graphical analysis, and fit-for-purpose modeling into accessible tools for accelerated drug development

ACS Spring 2022

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.