Algorithm can predict outcomes of chemical reactions

Researchers from the University of Cambridge have designed a machine learning algorithm that can predict the outcomes of complex chemical reactions with over 90% accuracy, outperforming trained chemists. The algorithm also suggests ways to make complex molecules, removing a significant hurdle in drug discovery.

A central challenge in drug discovery and materials science is finding ways to make complicated organic molecules by chemically joining together simpler building blocks. The problem is that those building blocks often react in unexpected ways.

“Making molecules is often described as an art realised with trial-and-error experimentation because our understanding of chemical reactivity is far from complete,” said Dr Alpha Lee from Cambridge’s Cavendish Laboratory. “Machine learning algorithms can have a better understanding of chemistry because they distil patterns of reactivity from millions of published chemical reactions — something that a chemist cannot do.”

Dr Lee and his group looked at chemical reaction prediction as a machine translation problem. The reacting molecules are considered as one ‘language’, while the product is considered as a different language. Following pattern recognition training to recognise how chemical groups in molecules react, the team’s algorithm uses the patterns in the text to learn how to ‘translate’ between the two languages.

Writing in the journal ACS Central Science, the researchers revealed that their model achieves 90% accuracy in predicting the correct product of unseen chemical reactions, whereas the accuracy of trained human chemists is around 80%. The model also knows what it doesn’t know — it produces an uncertainty score, which eliminates incorrect predictions with 89% accuracy.

In a second study, published in the journal Chemical Communications, Dr Lee and his group collaborated with biopharma company Pfizer to demonstrate the practical potential of the method in drug discovery. The researchers showed that when trained on published chemistry research, the model can make accurate predictions of reactions based on lab notebooks, showing that the model has learned the rules of chemistry and can apply it to drug discovery settings.

The team also showed that the model can predict sequences of reactions that would lead to a desired product. They applied this methodology to diverse drug-like molecules, showing that the steps that it predicts are chemically reasonable. This technology can significantly reduce the time of preclinical drug discovery because it provides medicinal chemists with a blueprint of where to begin.

“Our platform is like a GPS for chemistry,” Dr Lee said. “It informs chemists whether a reaction is a go or a no-go, and how to navigate reaction routes to make a new molecule.”

The researchers are currently using this reaction prediction technology to develop a complete platform that bridges the design-make-test cycle in drug discovery and materials discovery: predicting promising bioactive molecules, ways to make those complex organic molecules and selecting the experiments that are the most informative. The researchers are now working on extracting chemical insights from the model, attempting to understand what it has learned that humans have not.

“We can potentially make a lot of progress in chemistry if we learn what kinds of patterns the model is looking at to make a prediction,” said Cambridge PhD student Peter Bolgar. “The model and human chemists together would become extremely powerful in designing experiments — more than each would be without the other.”

This story is a modified version of a news item published by the University of Cambridge under CC BY 4.0.

Image credit: ©Shawn Hempel/Dollar Photo Club

Please follow us and share on Twitter and Facebook. You can also subscribe for FREE to our weekly newsletters and bimonthly magazine.

Originally published here.