Researchers have designed a machine learning algorithm that predicts the outcome of chemical reactions with much higher accuracy than trained chemists and suggests ways to make complex molecules, removing a significant hurdle in drug discovery.
Our platform is like a GPS for chemistry
University of Cambridge researchers have shown that an algorithm can predict the outcomes of complex chemical reactions with over 90% accuracy, outperforming trained chemists. The algorithm also shows chemists how to make target compounds, providing the chemical ‘map’ to the desired destination. The results are reported in two studies in the journals ACS Central Science and Chemical Communications.
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, who led the studies. “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.”
The algorithm developed by Lee and his group uses tools in pattern recognition to recognise how chemical groups in molecules react, by training the model on millions of reactions published in patents.
The researchers 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. The model then uses the patterns in the text to learn how to ‘translate’ between the two languages.
Using this approach, the model achieves 90% accuracy in predicting the correct product of unseen chemical reactions, whereas the accuracy of trained human chemists is around 80%. The researchers say that the model is accurate enough to detect errors in the data and correctly predict a plethora of difficult reactions.
The model also knows what it doesn’t know. It produces an uncertainty score, which eliminates incorrect predictions with 89% accuracy. As experiments are time-consuming, accurate prediction is crucial to avoid pursuing expensive experimental pathways that eventually end in failure.
In the second study, Lee and his group, collaborating with the biopharmaceutical company Pfizer, demonstrated 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,” said Lee, who is also a Research Fellow at St Catharine’s College. “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 Cambridge 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 Peter Bolgar, a PhD student in synthetic organic chemistry involved in both studies. “The model and human chemists together would become extremely powerful in designing experiments, more than each would be without the other.”
The Latest on: Drug discovery
via Google News
The Latest on: Drug discovery
- Report: Speed up drug development with artificial intelligenceon January 22, 2020 at 2:04 pm
“In drug discovery, researchers are using [machine learning] to identify new drug targets, screen known compounds for new therapeutic applications, and design new drug candidates, among other ...
- Surprise discovery shakes up our understanding of gene expressionon January 22, 2020 at 1:53 pm
The discovery has significant implications for our understanding of human disease and drug design. "It appears to be a fundamental pathway we didn't know about. Anytime that happens, it holds promise ...
- Cancer: Faster drug discovery to hit 'undruggable' targetson January 22, 2020 at 1:26 pm
The main challenge is getting the peptides into cells, which is a problem that Thurber's team is currently pursuing. University of Michigan. "Cancer: Faster drug discovery to hit 'undruggable' targets ...
- Melting reveals drug targets in a living organismon January 22, 2020 at 12:48 pm
In their results, the scientists mapped protein-drug interactions in rat organs and blood. Their research opens pathways in drug discovery, fundamental biology, and personalized medicine. Developing ...
- Drug Discovery Informatics Market Size, Growth Forecast to Witness Robust Expansion Throughout the Forecast Period 2019 – 2026on January 22, 2020 at 5:45 am
Market Study Report Provides A Detailed Overview Of Drug Discovery Informatics Market With Respect To The Pivotal Drivers Influencing The Revenue Graph Of This Business Sphere. The Current Trends Of ...
- Faster drug discovery to hit 'undruggable' targetson January 21, 2020 at 9:13 am
But a new technique, developed at the University of Michigan, could change that. It can harness bacteria to produce billions of different drug candidates that won't fall apart quickly inside the body.
- PhoreMost Enters Multi-Project Drug Discovery Collaboration With Otsuka Pharmaceuticalon January 21, 2020 at 12:25 am
PhoreMost's next-generation phenotypic screening platform, SITESEEKER, to identify novel targets for Otsuka's therapeutics discovery programmes Programmes to initially focus on gene therapy ...
- Drug Discovery Technologies Market Share Growing Rapidly with Recent Trends, Revenue and Forecast to 2025on January 20, 2020 at 9:35 am
New York, January 20, 2020: The global Drug Discovery Technologies market is expected to exceed more than US$ 79 Billion by 2024, at a CAGR of 8.9% in the given forecast period. Browse Full Report: ...
- Uncovering novel protein biomarkers in drug discovery and development: Targeting disease diagnosis and drug response monitoringon January 17, 2020 at 2:19 pm
Consequently, some pharmaceutical companies are including protein biomarker programs in their drug discovery and development processes, to identify early diagnostic markers of disease that may also ...
- Methods for generating and screening libraries of genetically encoded cyclic peptides in drug discoveryon January 17, 2020 at 1:23 am
Drug discovery has traditionally focused on using libraries of small molecules to identify therapeutic drugs, but new modalities, especially libraries of genetically encoded cyclic peptides, are ...
via Bing News