Predictive Retrosynthesis: Empowering Chemists

Traditional Retrosynthesis, a chemical synthesis method of breaking down the target molecule into its simplest starting materials, essentially working back from the finished state to the initial state, is still a common method used by chemists all over the world. However, there exist limitations to that method: the time it can take, as well as the knowledge required for each material.

To make chemist's research more time-efficient, Reaxys has developed Reaxys Predictive Retrosynthesis, an AI-powered tool?aimed at boosting success rates in synthesis route design and prediction. Retrosynthetic analysis once relied solely on the chemist’s expertise as well as their time. The award-winning Reaxys Predictive Retrosynthesis, however, holds the expertise. It augments your knowledge with robustly predicted routes by applying AI to the world’s largest database of chemical reactions. This allows researchers to get answers for a broader range of molecules, saving time and resources for chemical researchers across a multitude of industries.

Carreira Research Group at ETH Zurich is one of the research groups that utilize Reaxys database and the Predictive Retrosynthesis tool. Moritz Classen, Ph.D. student at the Carreira Research Group, explained, in our Pharma blogpost, how the predictive retrosynthesis interface not only answered the questions they had but also created new questions by identifying certain factors of the materials that may not have been known to the chemist.

“I saw the information breakdown in three ways. The smallest proportion was the chemistry you already know works. Then came the chemistry you already know?doesn’t work?because you have tried it in the past. But the biggest proportion was the chemistry you didn’t know anything about – which can be super inspiring,” – Moritz Classen.

??Having the supporting literature as well as the commercial availability of the materials was a clear advantage for Classen. “Having this great access to all the literature is really beyond what even a very experienced chemist has”. If you are interested in learning more about how Reaxys Predictive Retrosynthesis was used by the research group, watch Moritz Classen demonstrating the reaction routes tested, and discover why Moritz calls the Predictive Retrosynthesis a user-friendly and a time saver tool.?

This tool is not meant to replace researchers but to empower them by working together, combining the knowledge of the researchers with the data of Reaxys. This synergy also comes through listening to the feedback from the researcher and adapting the tool to the needs and demands to improve the service. Improvements such as giving researchers more control over the AI to the researchers and improving editing synthesis plans.

Still curious about how the Reaxys Predictive Retrosynthesis tool can benefit you? Read Moritz Classen's journey on the Pharma blog as well as reading more about predictive retrosynthesis on the Reaxys Predictive Retrosynthesis page.