̽��ֱ�� of Cambridge - chemical reaction

Accelerating how new drugs are made with machine learning

sc604 — Mon, 15 Jan 2024 10:05:29 +0000

Predicting how molecules will react is vital for the discovery and manufacture of new pharmaceuticals, but historically this has been a trial-and-error process, and the reactions often fail. To predict how molecules will react, chemists usually simulate electrons and atoms in simplified models, a process that is computationally expensive and often inaccurate.

Now, researchers from the ̽��ֱ�� of Cambridge have developed a data-driven approach, inspired by genomics, where automated experiments are combined with machine learning to understand chemical reactivity, greatly speeding up the process. They’ve called their approach, which was validated on a dataset of more than 39,000 pharmaceutically relevant reactions, the chemical ‘reactome’.

Their results, reported in the journal Nature Chemistry, are the product of a collaboration between Cambridge and Pfizer.

“ ̽��ֱ��reactome could change the way we think about organic chemistry,” said Dr Emma King-Smith from Cambridge’s Cavendish Laboratory, the paper’s first author. “A deeper understanding of the chemistry could enable us to make pharmaceuticals and so many other useful products much faster. But more fundamentally, the understanding we hope to generate will be beneficial to anyone who works with molecules.”

̽��ֱ��reactome approach picks out relevant correlations between reactants, reagents, and performance of the reaction from the data, and points out gaps in the data itself. ̽��ֱ��data is generated from very fast, or high throughput, automated experiments.

“High throughput chemistry has been a game-changer, but we believed there was a way to uncover a deeper understanding of chemical reactions than what can be observed from the initial results of a high throughput experiment,” said King-Smith.

“Our approach uncovers the hidden relationships between reaction components and outcomes,” said Dr Alpha Lee, who led the research. “ ̽��ֱ��dataset we trained the model on is massive – it will help bring the process of chemical discovery from trial-and-error to the age of big data.”

In a related paper, published in Nature Communications, the team developed a machine learning approach that enables chemists to introduce precise transformations to pre-specified regions of a molecule, enabling faster drug design.

̽��ֱ��approach allows chemists to tweak complex molecules – like a last-minute design change – without having to make them from scratch. Making a molecule in the lab is typically a multi-step process, like building a house. If chemists want to vary the core of a molecule, the conventional way is to rebuild the molecule, like knocking the house down and rebuilding from scratch. However, core variations are important to medicine design.

A class of reactions, known as late-stage functionalisation reactions, attempts to directly introduce chemical transformations to the core, avoiding the need to start from scratch. However, it is challenging to make late-stage functionalisation selective and controlled – there are typically many regions of the molecules that can react, and it is difficult to predict the outcome.

“Late-stage functionalisations can yield unpredictable results and current methods of modelling, including our own expert intuition, isn't perfect,” said King-Smith. “A more predictive model would give us the opportunity for better screening.”

̽��ֱ��researchers developed a machine learning model that predicts where a molecule would react, and how the site of reaction vary as a function of different reaction conditions. This enables chemists to find ways to precisely tweak the core of a molecule.

“We trained the model on a large body of spectroscopic data – effectively teaching the model general chemistry – before fine-tuning it to predict these intricate transformations,” said King-Smith. This approach allowed the team to overcome the limitation of low data: there are relatively few late-stage functionalisation reactions reported in the scientific literature. ̽��ֱ��team experimentally validated the model on a diverse set of drug-like molecules and was able to accurately predict the sites of reactivity under different conditions.

“ ̽��ֱ��application of machine learning to chemistry is often throttled by the problem that the amount of data is small compared to the vastness of chemical space,” said Lee. “Our approach – designing models that learn from large datasets that are similar but not the same as the problem we are trying to solve – resolves this fundamental low-data challenge and could unlock advances beyond late-stage functionalisation.”

̽��ֱ��research was supported in part by Pfizer and the Royal Society.

References:
Emma King-Smith et al. ‘Predictive Minisci Late Stage Functionalization with Transfer Learning.’ Nature Communications (2023). DOI: 10.1038/s41467-023-42145-1

Emma King-Smith et al. ‘Probing the Chemical "Reactome" with High Throughput Experimentation Data.’ Nature Chemistry (2023). DOI: 10.1038/s41557-023-01393-w

Researchers have developed a platform that combines automated experiments with AI to predict how chemicals will react with one another, which could accelerate the design process for new drugs.

A deeper understanding of the chemistry could enable us to make pharmaceuticals and so many other useful products much faster.

Emma King-Smith

BlackJack3D via Getty Images

Digital Molecular Structure Concept

̽��ֱ��text in this work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Researchers unravel the complex reaction pathways in zero-carbon fuel synthesis

Anonymous — Fri, 20 Jan 2023 11:54:46 +0000

When the eCO2EP: A chemical energy storage technology project started in 2018, the objective was to develop ways of converting carbon dioxide emitted as part of industrial processes into useful compounds, a process known as electrochemical CO2 reduction (eCO2R)

While eCO2R is not a new technique, the challenge has always been the inability to control the end products. Now, researchers from the ̽��ֱ�� of Cambridge have outlined how carbon isotopes can be used to trace intermediates during the process, which will allow scientists to create more selective catalysts, control product selectivity, and promote eCO2R as a more promising production method for chemicals and fuels in the low-carbon economy. Their results are reported in the journal Nature Catalysis.

̽��ֱ��project was led by Professor Alexei Lapkin, from Cambridge’s Centre for Advanced Research and Education in Singapore (CARES Ltd) and Professor Joel Ager, from the Berkeley Education Alliance for Research in Singapore (BEARS Ltd). Both organisations are part of the Campus for Research Excellence and Technological Enterprise (CREATE) funded by Singapore’s National Research Foundation.

In the 1950s, Berkeley’s Melvin Calvin identified the elementary steps used in nature to fix carbon dioxide in photosynthesis. Calvin and his colleagues used a radioactive form of carbon as a tracer to learn the order in which intermediates appeared in the cycle now named after him, work which won him the Nobel Prize in Chemistry in 1961.

̽��ֱ��eCO2EP team found that with a sensitive enough mass spectrometer, they could use the small differences in reaction rates associated with the two stable isotopes of carbon, carbon-12 and carbon-13, to perform similar types of analyses.

First, a mixture of products such as methanol and ethylene were generated by a prototype reactor that was built to operate under industrial conditions. To detect both major and minor products in real time as the operating conditions were changed, high-sensitivity mass spectrometry was used.

Since high-sensitivity mass spectrometry is more commonly used in biological and atmospheric sciences, co-authors Dr Mikhail Kovalev and Dr Hangjuan Ren adapted the technique to their prototype system. They developed a method to directly sample the reaction environment with high sensitivity and time response.

̽��ֱ��researchers used the difference in reaction rates of carbon-12 and carbon-13 to group a product such as ethanol and its major intermediates sharing the same pathway, to deduce key relationships in the chemical network.

̽��ֱ��researchers found that there are substantial differences in the mechanisms at work in smaller reactors versus larger reactors, a finding which will enable them to better control product selectivity.

̽��ֱ��team also discovered that the reaction used less of the heavier carbon-13 isotope than carbon-12. This difference in usage was found to be five times greater than that observed in natural photosynthesis, where carbon-13 is fixed at a slower rate than carbon-12. This is inspiring efforts in Professor Ager’s lab to better understand fundamental physics and the chemical origins of this large and unanticipated effect. An international patent application has also been filed.

“ ̽��ֱ��set-up of the project within CREATE Campus allowed Joel and I to create an environment of creativity and ambition, to enable the researchers to excel and to target the really complex and interesting problems,” said Lapkin. “ ̽��ֱ��monitoring of multiple species in such a complex reaction is, by itself, a significant breakthrough by the team, but the ability to further dig into the mechanism by exploring the isotope enrichment effect has made all the difference.”

“This work required an interdisciplinary approach drawing on expertise from both Cambridge and Berkeley,” said Ager. “CREATE campus provided an ideal environment to realise this collaborative research with a skilled and motivated team.”

̽��ֱ��eCO2EP project was funded by the National Research Foundation, Prime Minister’s Office, Singapore under its Campus for Research Excellence and Technological Enterprise (CREATE) programme.

Reference:
Hangjuan Ren et al. ‘Operando proton-transfer-reaction time-of-flight mass spectrometry of carbon dioxide reduction electrocatalysis.’ Nature Catalysis (2022). DOI: 10.1038/s41929-022-00891-3.

Adapted from a story posted on the CARES website.

Researchers have used isotopes of carbon to trace how carbon dioxide emissions could be converted into low-carbon fuels and chemicals. ̽��ֱ��result could help the chemical industry, which is the third largest subsector in terms of direct CO2 emissions, recycle its own waste using current manufacturing processes.

yorkfoto via Getty Images

Chemical plant drone view

̽��ֱ��text in this work is licensed under a Creative Commons Attribution 4.0 International License. Images, including our videos, are Copyright © ̽��ֱ�� of Cambridge and licensors/contributors as identified. All rights reserved. We make our image and video content available in a number of ways – as here, on our main website under its Terms and conditions, and on a range of channels including social media that permit your use and sharing of our content under their respective Terms.

Yes

Miniature grinding mill closes in on the details of ‘green’ chemical reactions

cmm201 — Tue, 30 Nov 2021 11:14:29 +0000

̽��ֱ��study, published in Nature Communications and led by Cambridge Earth Sciences’ Dr Giulio Lampronti, observed reactions as materials were pulverised inside a miniaturised grinding mill — providing new detail on the structure and formation of crystals.

Knowledge of the structure of these newly-formed materials, which have been subjected to considerable pressures, helps scientists unravel the kinetics involved in mechanochemistry. But they are rarely able to observe it at the level of detail seen in this new work.

̽��ֱ��study also involved Dr Ana Belenguer and Professor Jeremy Sanders from Cambridge’s Yusuf Hamied Department of Chemistry.

Mechanochemistry is touted as a ‘green’ tool because it can make new materials without using bulk solvents that are harmful to the environment. Despite decades of research, the process behind these reactions remains poorly understood.

To learn more about mechanochemical reactions, scientists usually observe chemical transformations in real time, as ingredients are churned and ground in a mill — like mixing a cake — to create complex chemical components and materials.

Once milling has stopped, however, the material can keep morphing into something completely different, so scientists need to record the reaction with as little disturbance as possible — using an imaging technique called time-resolved in-situ analysis to essentially capture a movie of the reactions. But, until now, this method has only offered a grainy picture of the unfolding reactions.

By shrinking the mills and taking the sample size down from several hundred milligrams to less than ten milligrams, Lampronti and the team were able to more accurately capture the size and microscopic structure of crystals using a technique called X-ray diffraction.

̽��ֱ��down-scaled analysis could also allow scientists to study smaller, safer, quantities of toxic or expensive materials. “We realised that this miniaturised setup had several other important advantages, aside from better structural analysis,” said Lampronti. “ ̽��ֱ��smaller sample size also means that more challenging analyses of scarce and toxic materials becomes possible, and it’s also exciting because it opens up the study of mechanochemistry to all areas of chemistry and materials science.”

“ ̽��ֱ��combination of new miniature jars designed by Ana, and the experimental and analytical techniques introduced by Giulio, promise to transform our ability to follow and understand solid-state reactions as they happen,” said Sanders.

̽��ֱ��team observed a range of reactions with their new miniaturised setup, covering organic and inorganic materials as well as metal-organic materials — proving their technique could be applied to a wide range of industry problems. One of the materials they studied, ZIF-8, could be used for carbon capture and storage, because of its ability to capture large amounts of CO2. ̽��ֱ��new view on these materials meant they were able to uncover previously undetected structural details, including distortion of the crystal lattice in the ZIF-8 framework.

Lampronti says their new developments could not only become routine practice for the study of mechanochemistry, but also offer up completely new directions for research in this influential field, “Our method allows for much faster kinetics, and will open up doors for previously inaccessible reactions — this could really change the playing field of mechanochemistry as we know it.”

Reference:
Giulio I. Lampronti et al. ‘Changing the game of time resolved X-ray diffraction on the mechanochemistry playground by downsizing.’ Nature Communications (2021). DOI: 10.1038/s41467-021-26264-1

Scientists at the ̽��ֱ�� of Cambridge have developed a new approach for observing mechanochemical reactions — where simple ingredients are ground up to make new chemical compounds and materials that can be used in anything from the pharmaceutical to the metallurgical, cement and mineral industries.

It's exciting because it opens up the study of mechanochemistry to all areas of chemistry and materials science

Giulio Lampronti

Photo by Chokniti Khongchum from Pexels

Person in laboratory holding a flask

Yes