Lifeboat Foundation

ChemCrow, an AI developed by researchers at EPFL, integrates multiple expert tools to perform chemical research tasks with unprecedented efficiency.

Chemistry, with its intricate processes and vast potential for innovation, has always been a challenge for automation. Traditional computational tools, despite their advanced capabilities, often remain underutilized due to their complexity and the specialized knowledge required to operate them.

AI Revolution in Chemistry.

A team led by Prof Frank Glorius from the Institute of Organic Chemistry at the University of Münster has developed an evolutionary algorithm that identifies the structures in a molecule that are particularly relevant for a respective question and uses them to encode the properties of the molecules for various machine-learning models.

A pressure of 3,000 bar is applied to the cold shock protein B of Bacillus subtilis in a small tube in the NMR spectroscopy laboratory at the University of Konstanz. This is roughly three times the water pressure at the deepest point of the ocean. The pressure is so intense that the highly dynamic protein shows structural features that would not be sufficiently visible under normal pressure. But why do scientists apply such high pressure, which does not occur anywhere else on our planet under natural conditions? The answer is: To study processes and properties that are too volatile to be observed under normal conditions.

“This high pressure allows us to make states visible that actually do exist at 1 bar, but which we can only observe directly at 3,000 bar”, explains Frederic Berner, University of Konstanz. Literally “under high pressure”, the doctoral researcher investigates the properties of a protein determined by its structure, and how changes in the structure in turn influence its properties. In the research group Physical Chemistry and Nuclear Magnetic Resonance at the University of Konstanz, led by Michael Kovermann, he recently implemented a new method for analyzing the structural properties of proteins at 3,000 bar with as little influence as possible from surrounding effects. The two researchers now present their new methodological approach in the journal Angewandte Chemie International Edition.

Year 2016 face_with_colon_three

Scientific Reports — Chemistry supports the identification of gender-specific reproductive tissue in Tyrannosaurus rex. Sci. Rep. 6, 23099; doi: 10.1038/srep23099 (2016).

Perovskites are among the most researched topics in materials science. Recently, a research team led by Prof. LOH Kian Ping, Chair Professor of Materials Physics and Chemistry and Global STEM Professor of the Department of Applied Physics of The Hong Kong Polytechnic University (PolyU), Dr Kathy LENG, Assistant Professor of the same department, together with Dr Hwa Seob CHOI, Postdoctoral Research Fellow and the first author of the research paper, has solved an age-old challenge to synthesise all-organic two-dimensional perovskites, extending the field into the exciting realm of materials. This breakthrough opens up a new field of 2D all-organic perovskites, which holds promise for both fundamental science and potential applications.

This research was published in the journal Science (“Molecularly thin, two-dimensional all-organic perovskites”).

Perovskites are named after their structural resemblance to the mineral calcium titanate perovskite, and are well known for their fascinating properties that can be applied in wide-ranging fields such as solar cells, lighting and catalysis. With a fundamental chemical formula of ABX 3, perovskites possess the ability to be finely tuned by adjusting the A and B cations as well as the X anion, paving the way for the development of high-performance materials.

A study from the Hackett group at EMBL Rome led to the development of a powerful epigenetic editing technology, which unlocks the ability to precisely program chromatin modifications.

Understanding how genes are regulated at the molecular level is a central challenge in modern biology. This complex mechanism is mainly driven by the interaction between proteins called transcription factors, DNA regulatory regions, and epigenetic modifications – chemical alterations that change chromatin structure. The set of epigenetic modifications of a cell’s genome is referred to as the epigenome.

Advancements in Epigenome Editing.

How can studying an exoplanet’s ozone help astronomers better understand its habitability potential? This is what a recent study published in the Monthly Notices of the Royal Astronomical Society hopes to address as a team of international researchers investigated how an ozone on the nearest exoplanet to Earth, Proxima Centauri b, could influence its own climate over time. This study holds the potential to help astronomers better understand how an exoplanet’s ozone could influence its formation, evolution, and potential habitability, and could have implications on how astronomers study Earth-like exoplanets throughout the cosmos.

“Imagine a world where ozone affects temperature and wind speed and holds the key to a planet’s very habitability,” said Dr. Assaf Hochman, who is a senior lecturer in the Institute of Earth Sciences at the Hebrew University of Jerusalem and a co-author on the study. “Our study unveils this intricate connection and underscores the importance of considering interactive ozone and other photochemical species in our quest to understand Earth-like exoplanets.”

For the study, the researchers used a series of computer simulations to ascertain how an active ozone on Proxima Centauri b could influence the exoplanet’s climate and potential habitability. In the end, the researchers discovered that an ozone layer on Proxima Centauri b could greatly influence the temperature and wind circulation patterns throughout its atmosphere. Additionally, they also found altitude also played a high role in the atmospheric temperature and temperature variances, as well. The researchers emphasized how these findings could help future researchers better understand the potential habitability of an exoplanet, noting how a potential ozone layer on Proxima Centauri b could greatly influence its climate.

Google DeepMind’s newly launched AlphaFold Server is the most accurate tool in the world for predicting how proteins interact with other molecules throughout the cell. It is a free platform that scientists around the world can use for non-commercial research. With just a few clicks, biologists can harness the power of AlphaFold 3 to model structures composed of proteins, DNA, RNA and a selection of ligands, ions and chemical modifications.

AlphaFold Server will help scientists make novel hypotheses to test in the lab, speeding up workflows and enabling further innovation. Our platform gives researchers an accessible way to generate predictions, regardless of their access to computational resources or their expertise in machine learning.

Continue reading “AlphaFold Server Demo — Google DeepMind” »

Chemistry, with its intricate processes and vast potential for innovation, has always been a challenge for automation. Traditional computational tools, despite their advanced capabilities, often remain underutilized due to their complexity and the specialized knowledge required to operate them.

Now, researchers with the group of Philippe Schwaller at EPFL have developed ChemCrow, an AI that integrates 18 expertly designed tools, enabling it to navigate and perform tasks within chemical research with unprecedented efficiency. Their research is published in Nature Machine Intelligence.

“You might wonder why a crow?” asks Schwaller. “Because crows are known to use tools well.”