
via University of Cambridge
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
Alpha Lee
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.”
Learn more: AI learns the language of chemistry to predict how to make medicines
The Latest on: Drug discovery
via Google News
The Latest on: Drug discovery
- Car stuck in snowbank leads to drug discovery in Sourison January 18, 2021 at 11:22 am
Two adults whose car was stuck in a snowbank in Souris, P.E.I., are now facing drug charges. In the mid-morning hours of Jan. 15, police responded to a report of a single-vehicle collision on Church ...
- Metrion Biosciences and LifeArc Further Extend Neuroscience-focused Ion Channel Drug Discovery Collaborationon January 18, 2021 at 6:00 am
Metrion Biosciences Limited (Metrion), the specialist ion channel CRO and drug discovery company, and LifeArc, a leading UK independent medical resear ...
- Global Computer-aided Drug Discovery (CADD) Market 2020 Comprehensive Industry and Vendor Landscape 2025on January 17, 2021 at 1:58 am
MarketsandResearch.biz is aimed at offering market research study on Global Computer-aided Drug Discovery (CADD) Market 2020 by Company, Type and Application, Forecast to 2025, provides an analysis of ...
- The Alzheimer's Drug Discovery Foundation Announces New Additions to Board of Governorson January 15, 2021 at 7:02 am
PRNewswire/ -- The Alzheimer's Drug Discovery Foundation (ADDF) announces two new members to its Board of Governors: Sharon T. Sager, CIMA, Managing ...
- ORION BIOTECHNOLOGY PROJECT AWARDED GRANT TO ADVANCE DRUG DISCOVERYon January 14, 2021 at 8:44 am
Orion Biotechnology Holding SA., a biotechnology company focused on precision engineering small protein therapeutics, today announced that its drug discovery project was awarded funding of CHF 0.9M ...
- 48Hour Discovery and Quantum Intelligence Corp Join Forces to Form Quantum Intelligence Discovery (QID) - An AI-Powered Drug Discovery Ventureon January 13, 2021 at 10:50 pm
Hour Discovery Inc. (48HD) and Quantum Intelligence Corp. (QIC) announced today the establishment of a joint venture called Qua ...
- Drug Discovery Services Market- Key Players Focus on Product Innovation to Consolidate Positionon January 13, 2021 at 6:09 am
Global Drug Discovery Services Market Overview The process of designing a new drug is called as drug discovery. Some of ...
- 2021 Could Be the Year of Quantum Drug Discoveryon January 11, 2021 at 12:09 pm
While this new year might not mark the moment when the first drugs are discovered via molecular dynamics simulations running on a full-scale quantum, ...
- AI Drug Discovery Startup Valo Raises $190 Million And Unveils Cancer Therapy Programson January 11, 2021 at 5:00 am
The Boston-based company aims to accelerate the drug discovery process for cancer therapies that are both more effective and less toxic.
- Relay Therapeutics Uses AWS to Accelerate Drug Discoveryon January 7, 2021 at 10:18 am
Relay Therapeutics is a precision medicine company transforming the drug discovery process by leveraging unparalleled insights into protein motion. Prior to testing promising compounds in the lab, ...
via Bing News