Contact UsInvestorsCareersMediaScienceContact Us
HomeScienceOpen InnovationCollaboration with Cambridge University on an AI model to help predict chemical reaction outcomes

Collaboration with Cambridge University on an AI model to help predict chemical reaction outcomes

In 2019, we began a partnership with the University of Cambridge on an AI (artificial intelligence) driven project to help predict how certain chemicals will react with each other. The long-term ambition is to help revolutionise medicine design by accurately predicting the outcomes of chemical reactions, thereby streamlining the medicine development process.

Digital illustration of molecules. Scientists are using AI and machine learning to understand the chemical reactions between molecules.

Currently scientists apply fundamental principles of chemical reactivity, learnings from previous/published experiments, and trial and error processes to predict how molecules will react. These reactions are an essential part of the manufacturing process of pharmaceuticals, but the trial-and-error process is often time consuming and expensive. However, through Pfizer's collaboration with the University of Cambridge, the adoption of AI and machine learning is seeking to rapidly improve and speed up this process.

The researchers at the University of Cambridge used a technique called transfer learning, where the AI programme was trained on a different task before being used to help predict chemical reactions.1 Researchers trained the AI programme using a large spectroscopic dataset (Carbon-13 Nuclear Magnetic Resonance), which identifies different chemical environments in a given molecule.1 Having trained the programme on this data alongside Pfizer’s internal chemical reaction data, it was then given the task of trying to predict chemical reaction outcomes.  

The results generated by the AI programme were a significant step forward in the development of a predictive tool. 

"The critical breakthrough was realising that we could leverage chemical knowledge from other sources, not just Pfizer's internal data, to guide our AI's learning. In the same way that we often learn more thoroughly through a variety of information sources, so to do these machine learning models. We hope to apply this technique of transfer learning towards a 'foundational model' - an AI tool that can be readily deployed towards a plethora of chemical reactivity-based tasks." said Dr Emma King-Smith, lead author of the publication.

During the research project, it was found that including negative data (data about reactions that didn’t work) was important for improving the performance of the AI tool.1

"Our machine learning advance is made possible by the volume and quality of data generated from Pfizer’s late stage functionalisation platform, including negative data which is commonly unreported in chemistry literature. This underpins the importance of academic-industry collaborations in advancing AI for chemical sciences"

Dr Alpha Lee
Faculty member at the University of Cambridge who led the researchIn another aspect of the collaboration, thousands of Pfizer’s chemical high-throughput experimentation datapoints were shared with the scientific community alongside a computational framework to uncover hidden chemical insights within large datasets.2

So, how will this lead to pharmaceutical advancement? These findings could fundamentally improve the accuracy and cost of medicine development, by potentially speeding up the drug design process through predictive modelling.

This research is a significant advancement for medicine design, however, there is still a need for further exploration. Researchers are hoping this breakthrough will inspire more research into the area. Pfizer is committed to working with researchers to optimise medicine design and to harness the potential power of AI.

OUR SCIENCE

Pfizer's collaboration with CMAC

We've been a Tier 1 partner of the centre for Continuous Manufacturing and Advanced Crystallisation (CMAC), at the University of Strathclyde, since 2017.

OUR SCIENCE

 Partnership with Regeneron for UK Biobank exome sequencing

We were part of a collaboration that aimed to speed up the exome sequencing of 500,000 UK participants.

References

  1. Nature Communications. ​​​​​​Predictive Minisci late stage functionalization with transfer learning. Published January 2024. Accessed Nov 2024.
  2. Nature Chemistry. Probing the Chemical "Reactome" with High Throughput Experimentation Data. Published January 2024. Accessed Nov 2024.
    PP-UNP-GBR-10856 / November 2024
    Science Products Responsibility PartnershipsCareers Privacy Statement Terms of Use Contact UsSitemap Copyright © 2017-2024 Pfizer Limited. PP-UNP-GBR-8108 / January 2024. All rights reserved. Registered in England and Wales No. 526209. Registered office: Ramsgate Road, Sandwich, Kent CT13 9NJ. VAT No. GB201048427. This website is intended for the general public in the UK.