Towards an autonomous DataFactory for the small-batch cooling crystallisation of active pharmaceutical ingredients

As a method of forming and purifying the pharmaceutically relevant polymorph[1], crystallisation of an active pharmaceutical ingredient (API) is a key step in pharmaceutical manufacturing. Determining an industrial-relevant approach for API crystallisation can be resource-intensive as a candidate crystallisation process is constrained by and assessed against industrial relevant solubilities, downstream processing practicalities, and regulatordetermined Critical Quality Attributes (CQA) of the API[2-4].

The DataFactory at the CMAC aims to use high throughput smallbatch cooling crystallisation experiments coupled with machine learning to reduce the time and material costs associated with this process. Alongside the development of automated data collection, we are incorporating an autonomous decision-making system to optimize the small-batch cooling crystallisation of APIs and calculate relevant kinetic parameters to inform larger-scale experiments.

Here we present the steps we’re taking to integrate and automate different platforms via a cobot and a central control PC, in addition to the beginnings of the database that will be the foundation of a crystallisation classification system.