24/7 BIOPHARMA - issue 1 / October 2024

LONZA

While the concept of retrosynthetic analysis has been routinely used by synthetic chemists for decades now, the application of computer techniques to the task has accelerated in recent times. Corey realised early on that applying computers to the task might help and more recent advances such as computer-aided synthesis planning (CASP) tools have greatly sped up the process. However skilled and however much literature knowledge a process chemist has, there are simply too many options for them to be certain they have identified the most likely synthetic route for making the molecule on a commercial scale. CASP tools can take information from large, curated reaction databases and use them to calculate possible routes back to simple starting materials. However, limitations remain. Significantly, while the tools may be able to search catalogues of research chemicals for potential starting materials, these catalogues do not give an insight into what is actually available in commercial quantities. What the CASP tool might think looks like a great synthetic route because it minimises steps and has a high yield could well be completely impractical at scale. Yes, the materials could be sourced, but if it’s not available from stock and there is a long lead time, the only options are to wait or to add further steps to make it in house. Even if an intermediate is readily available, it might be prohibitively expensive at a kilogram scale. With inventory issues continuing to burden the chemical supply chain, this is not a trivial problem. Data-driven approaches that include real-world commercial supply chain insights offer the potential to improve synthetic route planning, creating feasible and cost-effective routes more quickly. To address these issues, Lonza’s Small Molecules Division has developed an AI-enabled Route Scouting service. This provides customers looking to make a new API with a rapid way to identify commercially-viable synthetic routes. It combines advanced computational tools for route design with data that give an insight into real-world supply chain availability. The aim is to find synthetic pathways that are optimised for commercial production at an early stage of the development process. It is this integration of supply chain data combined with the technical knowledge and experience of our subject matter experts that differentiates the Lonza service from commercially-available CASP A route to better routes

tools. The company’s unique advantage, in addition to its raw material sourcing analysis, is that it prioritises scalable synthetic routes – something often overlooked by AI tools. AI-based predictive chemo-informatics does a great job of proposing routes that may be synthetically possible. What these methods cannot do is triage them effectively from a commercial perspective. By constraining the system to use Lonza’s vast databases containing the cost and availability of thousands of chemical building blocks, intermediates and basic chemicals, the automated system is able to produce routes more viable at a commercial scale. With the input of skilled process chemists, it will pinpoint those that are most likely to be successful, both from a chemistry perspective and from the standpoint of commercial viability. Lonza’s decades of experience in manufacturing APIs is invaluable, not least because of the vast amounts of data it has accumulated over that time. It allows it to make informed predictions about future prices of different raw materials thanks to the insight the historical data provides into pricing trends over time. All of these data points are considered, along with the options proposed by the predictive retrosynthetic design tools to add a commercial perspective to the route selection process.

27

TWENTYFOURSEVENBIOPHARMA Issue 1 / October 2024