Add BrightSurf on Google Email

Engineering molecular interactions with machine learning

Researchers at EPFL have computationally designed novel protein binders that attach seamlessly to key targets, including the SARS-CoV-2 spike protein, using deep learning-generated 'fingerprints' to characterize millions of protein fragments. This method demonstrates therapeutic potential for rapidly designing protein-based therapeutics.

SourceEcole Polytechnique Fédérale de Lausanne·JournalNature·TypeComputational simulation/modeling·DateMay 4, 2023

‘Fishing’ for biomarkers

A team of researchers from Syracuse University has developed a tiny, nano-sized sensor that can detect protein biomarkers in a sample at single-molecule precision. The sensor is capable of identifying and quantifying specific proteins associated with various hematological malignancies and solid tumors.

SourceSyracuse University·JournalNature Communications·DateMar 20, 2023

Artificial intelligence conjures proteins that speed up chemical reactions

Researchers used machine-learning algorithms to design new light-emitting enzymes called luciferases that can efficiently recognize specific chemicals and emit light. This breakthrough could lead to custom enzymes for a wide range of applications in biotechnology, medicine, environmental remediation, and manufacturing.

SourceUniversity of Washington School of Medicine/UW Medicine·JournalNature·TypeComputational simulation/modeling·DateFeb 22, 2023

Building better enzymes – by breaking them down

Researchers developed an algorithm that uses physics-based protein design calculations and machine learning to generate thousands of active enzymes, achieving a tenfold increase in success rate over traditional methods. The new method, CADENZ, has the potential to transform industries by providing green alternatives for processes such ...

SourceWeizmann Institute of Science·JournalScience·DateFeb 21, 2023

New AI tool makes speedy gene-editing possible

Researchers at NYU Langone Health and the University of Toronto have developed a new AI tool called ZFDesign, which enables customizable protein editing for treating genetic diseases. The tool promises to accelerate gene therapy development on a large scale, offering a potentially safer alternative to CRISPR.

SourceNYU Langone Health / NYU Grossman School of Medicine·JournalNature Biotechnology·TypeComputational simulation/modeling·DateJan 26, 2023

X-ray light reveals how virus responsible for COVID-19 covers its tracks, eluding the immune system

A new study uses serial femtosecond X-ray crystallography to reveal the structure of NendoU protein at room temperature. The resulting high-resolution image shows that the protein's flexibility plays a crucial role in its functional mechanism, which is essential for designing antiviral drugs against SARS-CoV-2.

SourceArizona State University·JournalStructure·TypeExperimental study·DateJan 10, 2023

Urine could play key part in future biotech systems

Researchers have developed a method that uses urea from urine to trigger the production of proteins in bacteria, replacing costly 'inducer' molecules. The new system produces similar quantities of protein as standard methods while being cheaper and easier to use, opening up new avenues for biotech industries.

SourceUniversity of Birmingham·JournalNew Biotechnology·TypeExperimental study·DateOct 26, 2022

Beyond AlphaFold: A.I. excels at creating new proteins

Researchers developed a new software tool called ProteinMPNN to create protein molecules more accurately and quickly than before. The team used machine learning algorithms, including AlphaFold, to generate new protein shapes and sequences, paving the way for novel vaccines, treatments, and sustainable biomaterials.

SourceUniversity of Washington School of Medicine/UW Medicine·JournalScience·TypeComputational simulation/modeling·DateSep 15, 2022

Proteins and natural language: Artificial intelligence enables the design of novel proteins

A research team led by Prof. Dr. Birte Höcker applied a computer-based natural language processing model to protein research, creating new proteins capable of stable folding and defined functions. The ProtGPT2 model generates proteins with differentiated structures, eliminating the need for functionalization processes.

SourceUniversität Bayreuth·JournalNature Communications·TypeNews article·DateAug 4, 2022

To cell surface and beyond: Tracing subcellular glycoprotein transport using modified cholera toxin

Scientists at Okayama University designed and tested a modified cholera toxin to study glycosylation in eukaryotic cells. They tracked the toxin's movement through organelles using bioluminescence, gaining insights into protein modification. This method may lead to new treatments for diseases caused by enzyme deficiencies.

SourceOkayama University·JournalChemistry - A European Journal·TypeExperimental study·DateJul 25, 2022

How a virus packages its genetic material

A UC Riverside-led team developed a theory and performed simulations to understand how viruses package their genetic material. The research reveals that capsid proteins are inclined to form shells around viral RNAs due to lower stress distribution, which can aid in designing nanocontainers for drug delivery.

SourceUniversity of California - Riverside·JournalACS Nano·TypeComputational simulation/modeling·DateMar 9, 2022

Live wire: new research on nanoelectronics

A study by Arizona State University shows that certain proteins can act as efficient electrical conductors, outperforming DNA-based nanowires in conductance. The protein nanowires display better performance over long distances, enabling potential applications for medical sensing and diagnostics.

SourceArizona State University·JournalACS Nano·TypeExperimental study·DateFeb 24, 2022

Stanford researchers take “protein circuits” a step closer to cell-to-cell communication

Stanford researchers have made a breakthrough in developing protein circuits that can enable cell-to-cell communication, mimicking the natural process of cells interacting with neighboring cells. The new platform, RELEASE, allows proteins to be secreted and displayed on the cell surface, enabling cells to respond to these signals.

SourceStanford University·JournalNature Communications·DateFeb 17, 2022

Illinois musicians, chemists use sound to better understand science

Researchers at the University of Illinois used sonification to analyze data and teach protein folding, leading to a new discovery about protein folding mechanisms. Musicians collaborated with chemists to create audio-mapped visualizations that complemented traditional views, increasing intuition for experts.

SourceUniversity of Illinois at Urbana-Champaign, News Bureau·JournalJournal of Chemical Education·TypeObservational study·DateFeb 17, 2022

Deep learning dreams up new protein structures

A team of researchers, including those from Rensselaer Polytechnic Institute and the University of Washington, have developed a neural network that can predict protein shapes with high accuracy. The network was trained on random protein sequences and generated 2,000 new proteins, many of which were successfully produced in the lab.

SourceRensselaer Polytechnic Institute·JournalNature·TypeComputational simulation/modeling·DateDec 1, 2021

More effective treatment of Alzheimer’s

Researchers at Uppsala University have designed new antibodies that bind to both large and small aggregates of the amyloid-beta protein, potentially providing a more effective treatment for Alzheimer's disease. The new antibody format is stronger in binding to clumps and can also target smaller aggregates.

SourceUppsala University·JournalTranslational Neurodegeneration·TypeExperimental study·DateSep 30, 2021

What to call seafood made from fish cells

A new Rutgers study suggests that food companies use the terms "cell-based" or "cell-cultured" when labeling seafood products made from fish cells. The study found that both terms meet FDA regulations and help consumers understand the production process, while also recognizing potential allergens.

SourceRutgers University·JournalJournal of Food Science·DateAug 9, 2021