Artificial intelligence aids in the development of new active ingredients
Researchers at HIPS are developing building blocks for active ingredient production
Nature offers a virtually limitless variety of chemical substances. Although these have been optimized over millions of years of evolution for their respective purposes, they have not been optimized for use as active ingredients in humans. For decades, researchers have therefore been attempting to genetically reprogram microbial producers of active ingredients so that they produce variants of their natural compounds with improved pharmaceutical properties. A major challenge in this endeavor is that the protein structures responsible for the production of natural products are extremely complex. Many changes to the corresponding blueprints therefore simply result in non-functional proteins. A team led by HIPS Junior Research Group Leader Dr. Kenan Bozhüyük has now addressed this problem with a new approach based on artificial intelligence. The idea is that if an AI can understand what makes production systems work, it may even be able to develop new building blocks for such systems that do not occur in nature—thereby further expanding chemical diversity for drug discovery. HIPS is a site of the Helmholtz Centre for Infection Research in collaboration with Saarland University.
The study focused on so-called non-ribosomal peptide synthetases, or NRPS for short. These large enzyme complexes function like molecular assembly lines. They produce a wide variety of biologically active natural compounds in microorganisms, including substances that have served as the basis for the development of numerous antibiotics, immunosuppressants, and cancer drugs. The problem is that a product can only be formed if the individual components interact precisely at the right moment. This is why NRPS are particularly difficult to modify in a targeted manner.
The researchers combined several pre-trained AI models with experimental test series to develop new so-called thiolation domains (T-domains). These building blocks act like movable transport arms within the NRPS: they pick up molecular intermediates and pass them on to the next processing station. In total, the team used AI to design 76 new T-domains, produced hundreds of different NRPS variants, and tested them in living cells.
The results showed that several of the AI-designed building blocks were functional. Some even enabled the formation of products in artificially combined enzyme systems and increased the yield up to three times compared to natural variants. In addition, at least one of the designed proteins proved to be more soluble and thermally more stable than the natural counterpart. Higher yields are not only important for future production. They also make it easier, even in the early stages of research, to obtain new natural compounds in sufficient quantities to determine their structure and investigate their effects more closely. A key factor was that the AI did not design the new building blocks in isolation, but rather tailored them to their immediate surroundings within the respective enzyme system. This is because whether such a building block functions depends heavily on its ability to interact with its neighboring regions.
“Our results show that artificial intelligence can be used not only to design individual proteins, but also to specifically redesign key building blocks of complex biological production systems,” says Bozhüyük. “AI does not replace experiments, but it helps us select promising candidates more quickly from among many possible variants.”
“The study shows that AI can significantly advance the development of new active compounds based on natural products,” says Prof. Rolf Müller, Scientific Director of HIPS and head of the department “Microbial Natural Products”. “If we can adapt such biosynthetic systems in a more targeted manner in the future, this will open up new possibilities for developing urgently needed drugs more efficiently and thus making them available for clinical applications more quickly.”
Helmholtz Centre for Infection Research:
Scientists at the Helmholtz Centre for Infection Research (HZI) in Braunschweig and its other sites in Germany are engaged in the study of bacterial and viral infections and the body’s defense mechanisms. They have a profound expertise in natural compound research and its exploitation as a valuable source for novel anti-infectives. As member of the Helmholtz Association and the German Center for Infection Research (DZIF) the HZI performs translational research laying the ground for the development of new treatments and vaccines against infectious diseases. https://www.helmholtz-hzi.de/en
Helmholtz Institute for Pharmaceutical Research Saarland:
The Helmholtz Institute for Pharmaceutical Research Saarland (HIPS) in Saarbrücken is a branch of the Helmholtz Centre for Infection Research (HZI) in Braunschweig and was established by the HZI and Saarland University in 2009. Its researchers are searching mainly for new agents against infectious diseases, optimise these agents for application in humans and research ways how these agents can be transported best through the body to the site of action. https://www.helmholtz-hips.de/en/
Journal
Nature Communications
Method of Research
Experimental study
Subject of Research
Cells
Article Title
Generative AI designs functional thiolation domains for reprogramming non-ribosomal peptide synthetases
New materials library could help AI design better sodium-ion batteries
University of Surrey
The start of a new battery materials library could pave the way for future AI models to help scientists design sodium-ion batteries that charge faster, last longer and store more energy, according to new research from the University of Surrey.
Sodium-ion batteries are being developed as a promising alternative to conventional lithium-ion batteries, as sodium is much more abundant and widely available. However, improving the amount of energy they can hold and how well they perform over repeated charging is a major barrier to their wider use.
In a new study published in the Journal of Materials Chemistry A, researchers investigated how changing the chemical makeup of sodium manganese oxide could improve its performance as a cathode – a key battery component that helps determine how much energy a battery can store and how well it performs.
The team created a library of 28 different compositions, substituting some of the manganese with varying amounts of iron, titanium and vanadium, before comparing how each performed when tested in sodium-ion batteries.
The results showed that iron was linked to higher energy-storage capacity, vanadium improved stability over repeated charging and discharging, and small amounts of titanium improved performance at higher rates. Some titanium-containing compositions also retained more than 90 per cent of their capacity after 100 cycles.
An automated approach was developed to analyse the large amounts of data generated by the experiments, with the resulting dataset used to train a machine-learning model. While the current library is too small for reliable predictions, expanding it could eventually allow AI to identify new battery compositions before they are made and tested in the lab.
Dr Daniel Commandeur, Lecturer at the School of Chemistry and Chemical Engineering and corresponding author of the study, said:
“We rely heavily on lithium-ion batteries, but lithium resources are relatively scarce and unevenly distributed around the world. Sodium is far more abundant, making sodium-ion batteries an important technology to develop.
“The challenge is finding materials that deliver the performance we need. This work is a first step towards building the larger datasets needed for machine learning to guide that search – helping us identify promising materials faster and accelerate the development of better sodium-ion batteries.”
Expanding the approach to a much wider range of cathode materials could create the larger, high-quality datasets needed for machine learning to help speed up the discovery of new battery materials.
Eden Marks, PhD Student in Space Engineering and co-lead author of the study, said:
“What stood out most was how relatively small changes in composition could shift the balance between how much energy a material can store, how it performs at higher rates and how well it lasts. Mapping those relationships gives us a much clearer picture of where to look next.”
In future, expanding the materials composition library could help scientists tailor sodium-ion cathodes to different performance needs – whether the priority is storing more energy, charging faster or lasting through more charge cycles.
[ENDS]
Notes to editors
Dr Daniel Commandeur is available for interview; please contact mediarelations@surrey.ac.uk to arrange.
The full paper can be found here: https://doi.org/10.1039/d6ta04588j
Journal
Journal of Materials Chemistry A
Article Title
Probing the composition space of V, Fe, and Ti substituted sodium manganese oxides for next-generation sodium-ion cathodes
No comments:
Post a Comment