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
- New Drug Screening Tool for Cancer Research Comes to Marketon September 6, 2019 at 11:25 am
The discovery of Cancer Stem Cells in some blood and tumor cancer ... interested in using the Matrix for cancer or stem cell research purposes, High-Throughput Drug Testing or whatever other purposes ...
- Cleveland Clinic's Medical Innovation Summit to focus on AI, drug discovery and moreon September 6, 2019 at 11:09 am
Cleveland Clinic's 17th annual Medical Innovation Summit will tackle artificial intelligence, new drug discovery, nontraditional participants and personalization in health care, with a focus on the ...
- IICT’s Mol Bank to spread drug discovery cultureon September 6, 2019 at 11:00 am
When CSIR-Indian Institute of Chemical Technology (IICT) here signed a pact with Sun Pharma to ‘out-license’ a patent for a new chemical entity with a potential for developing life saving drugs for ...
- Insilico Medicine Brings GENTRL AI System to Open Source for Drug Discoveryon September 6, 2019 at 8:20 am
Insilico Medicine has developed GENTRL, a new artificial intelligence system for drug discovery that dramatically accelerates the process from years to days. In the industry’s first successful ...
- Drug Discovery Informatics Market Competitive Strategies, Regional Analysis Forecast 2024on September 6, 2019 at 7:51 am
Sep 06, 2019 (Heraldkeepers) -- New York, September 06, 2019: The report covers detailed competitive outlook including the market share and company profiles of the key participants operating in the ...
- Lexaria Bioscience Corp. (CSE: LXX) (OTCQX: LXRP) Featured in NetworkNewsAudio Publication Discussing Innovative Drug-Delivery Discoveryon September 6, 2019 at 5:30 am
NEW YORK, Sept. 06, 2019 (GLOBE NEWSWIRE) -- via NetworkNewsAudio – Lexaria Bioscience Corp. (CSE: LXX) (OTCQX: LXRP) announces the availability of a NetworkNewsAudio publication titled, “Innovative ...
- Fluorinated compounds present opportunities for drug discoveryon September 4, 2019 at 10:13 am
A practical method has been devised to synthesize compounds that have previously been almost impossible to make. The combination of fluorine atoms and amide groups in the compounds might be useful in ...
- NIH trial aims to improve drug discovery for ischemic strokeon September 4, 2019 at 8:50 am
The National Institutes of Health (NIH) has announced it will fund a nationwide preclinical trial platform called the Stroke Preclinical Assessment Network (SPAN) to ensure candidate new treatments ...
- Maruho and X-Chem Announce Drug Discovery Collaborationon September 4, 2019 at 5:54 am
X-Chem, Inc. (X-Chem), a privately held biotechnology company focused on applying its next-generation, industry-leading DNA-Encoded library (DEX TM ) drug discovery platform to the generation of novel ...
- AI-powered drug discovery in days, not yearson September 4, 2019 at 12:08 am
A new study has found that artificial intelligence can drastically speed up drug discovery, from years to just days. This has significant implications for the discovery of new medicines for the ...
via Bing News