A novel AI model called BINND has been developed to predict which DNA molecules bind to each other. The model achieved an accuracy of 83.5% in predicting DNA pairs that would bind, surpassing the state-of-the-art model by at least 10%. This improvement has significant utility for biomedical diagnostic tools and DNA computing applications.
SourceNorth Carolina State University·JournalNature Communications·TypeExperimental study·DateJul 14, 2026
Scientists at OIST successfully engineered a protein to bind a methylating agent instead of its natural coenzyme. The study uses insertions and deletions to modify the protein's structure, offering insights into coenzyme-protein interactions and potential applications in artificial enzyme design.
SourceOkinawa Institute of Science and Technology (OIST) Graduate University·JournalProceedings of the National Academy of Sciences·TypeExperimental study·DateNov 23, 2022