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
- SLU Institute for Drug and Biotherapeutic Innovationon May 1, 2021 at 2:53 am
The Saint Louis University Institute for Drug and Biotherapeutic Innovation (SLU-IDBI) is a multidisciplinary association of researchers with a shared interest in drug and biotherapeutic discovery ...
- PsychLight: Genetically Encoded Sensor to Enable Discovery of New Psychiatric Drugson April 30, 2021 at 9:19 pm
A genetically encoded sensor to detect hallucinogenic compounds has been developed by researchers at the University of California, Davis. Named psychLight, the sensor could be used in discovering new ...
- AI in Drug Discovery Market Value Expected to Grow at CAGR of 42.2% from 2021-2027on April 30, 2021 at 5:15 am
Whipsmartmi com offers Global Artificial Intelligence in Drug Discovery Market from its research database The AI in drug discovery industry is expected to grow USD 342 16 million at CAGR of 42 2 from ...
- Top 6 AI-Powered Drug Discovery Tools In 2021on April 30, 2021 at 12:30 am
AI has a lot of potential to enhance and accelerate drug discovery — the process of identifying potential medicines. In January 2020, British start-up Exscientia and Japanese pharmaceutical firm ...
- Artificial Intelligence In Drug Discovery Market Growth To Be At A Rate Of 38% Through 2025on April 29, 2021 at 7:33 pm
Width='300' Height='151'/>Artificial Intelligence (AI) In Drug Discovery Global Market Report 2021: COVID-19 Growth And Change To 2030 The Business R ...
- Drug Discovery Informatics Market SWOT Analysis by Key Players: Charles River Laboratories, Collaborative Drug Discovery, Certaraon April 27, 2021 at 12:31 pm
Get a view on global Drug Discovery Informatics market sales by marketing channels. Target important market by region and tap important dynamics of this industry.
- Here’s a look at natural product drug discovery 2.0on April 26, 2021 at 2:33 pm
Plant-based drug discovery may be tens of thousands of years old, but in 2021, it feels exciting, rich, and full of potential. Companies are rapidly building scalable databases with hundreds of ...
- Drug-discovery collaboration finds potential new antimalarial drug candidateson April 22, 2021 at 7:49 pm
Potential new antimalarial drug candidates are being developed through an extended drug-discovery collaboration between Australian medical research institute WEHI and Janssen Pharmaceutica NV. The ...
- How COVID-19 Impacting AI for Drug Discovery Market? Top Key Players: Atomwise, Inc., Insilico Medicine, Numerateon April 22, 2021 at 12:09 am
A new market study report by The Insight Partners on the AI for Drug Discovery Market has been released with reliable information and accurate forecasts for a better understanding of the current and ...
- Growing Drug Discovery In Academia - the IRIC-IRICoR model in Quebecon April 20, 2021 at 8:45 am
The Biotechnology Innovation Organization is the world's largest biotech trade association. Learn about BIO, register for events and explore member services.
via Bing News