
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
[google_news title=”” keyword=”drug discovery” num_posts=”10″ blurb_length=”0″ show_thumb=”left”]
via Google News
The Latest on: Drug discovery
- Psilera Eyes Non-Hallucinogenic Drug Candidates for First-in-Human Studieson March 30, 2023 at 7:49 am
Psilera is proud to achieve a landmark preclinical milestone with 100% success. Its first cohort of drug candidates designed and synthesized in-house have all proven to lack hallucinations in animals.
- Pfizer’s COVID-19 drug Paxlovid is less effective against viral infectionon March 30, 2023 at 5:43 am
Scientists showed that drug-resistant variants have appeared multiple times independently in different parts of the world, with regional clusters providing evidence for person-to-person transmission.
- A scientist who created Ozempic explains what the drug actually does to your brain — and why it makes people satisfied while eating lesson March 30, 2023 at 2:45 am
Knape, who oversees drug discovery at Ozempic manufacturer Novo Nordisk, on why this drug is a radical breakthrough for weight-loss.
- Computational Medicine and Drug Discovery Software Market Growth By 2031on March 29, 2023 at 9:23 pm
The "Computational Medicine and Drug Discovery Software Market" study describes how the technology industry is evolving ...
- A $50M preclinical drug discovery lab is coming to Midtownon March 29, 2023 at 7:10 am
A 6,000 square-foot, $50 million preclinical drug discovery lab will be coming to Deerfield’s Cure innovation campus in Midtown, Gov. Kathy Hochul announced today. The project will be supported by a ...
- Global Cell Based Assays Market Report to 2028: Increasing Number of Drug Discovery Activities Will Fuel Growthon March 28, 2023 at 5:30 pm
The "Cell Based Assays Market - Global Industry Size, Share, Trends, Opportunity, and Forecast, 2018-2028F Segmented By Products & Services (Reagents, Assay Kits, ...
- Advancing drug discovery through multitask learning techniqueson March 28, 2023 at 11:50 am
Following our recommendations, researchers in drug discovery will enhance the predictive accuracy of their models and accelerate the identification of novel drug candidates." More information: ...
- 2023 to 2030 Drug Discovery Software Market Upcoming Trendson March 28, 2023 at 11:21 am
The Global Drug Discovery Software market is expected to progress at a substantial rate during the forecast period, between 2023 and 2028. In 2023, the market is rising at a stable rate and with the ...
- ARTIFICIAL INTELLIGENCE FOR NEW DRUG DISCOVERYon March 27, 2023 at 5:00 pm
And the reason is simple. Artificial intelligence is helping to make pharmaceutical research and new drug discovery less expensive and definitely more productive. Researchers realize that in the ...
- Screening, diagnosis to drug discovery: ICMR lays down guidelines for AI in healthcareon March 27, 2023 at 4:13 am
The Indian Council of Medical Research (ICMR)'s Artificial Intelligence cell and the Department of Health Research released the first Ethical Guidelines for Application for Artificial Intelligence in ...
via Bing News