An AI tool has made a step forward in translating the language proteins use to dictate whether they form sticky clumps similar to those linked to Alzheimer’s Disease and around fifty other types of human disease. In a departure from typical “black-box” AI models, the new tool, CANYA, was designed to be able to explain its decisions, revealing the specific chemical patterns that drive or prevent harmful protein folding. The discovery, published today in the journal Science Advances, was possible thanks to the largest-ever dataset on protein aggregation created to date. The study gives new insights about the molecular mechanisms underpinning sticky proteins, which are linked to diseases affecting half a billion people worldwide. 

A new 3D "atlas" of the mouse brain, developed by Duke University School of Medicine and collaborators, promises to sharpen scientists' ability to measure brain changes and share findings across studies of diseases like Alzheimer's. The Duke Mouse Brain Atlas combines microscopic detail from multiple imaging techniques into a living, distortion-free map—offering a powerful new tool for research and discovery. The open-source atlas, reported April 30 in Science Advances, is already helping scientists track neurodegeneration in mouse models.

Researchers have developed a new protocol to transplant immune cells called microglia into the brain – and show the strategy can protect neurons and combat hallmarks of neurological disorders in mice. Their therapy stands out from traditional microglia replacement methods because it doesn’t rely on risky conditioning regimens, making it a safer and more practical approach for microglia replacement. Studies have established a firm link between some neurological disorders and defects in microglia, which are immune cells that maintain and clean up the central nervous system. Scientists theorize that correcting or replacing these dysfunctional microglia could help treat neurological conditions such as Alzheimer’s disease. However, traditional methods to replenish microglia rely on bone marrow transplantation, which is arduous and inefficient. Furthermore, these transplants require strict preconditioning regimens that use radiation or chemotherapy, which can damage the brain, and the microglia that result from the transplanted bone barrow aren’t faithful copies of the originals. To avoid the need for preconditioning, Dadian Chen and colleagues developed a new approach named tricyclic microglial depletion for transplantation (TCMDT). This strategy uses three cycles of an experimental compound that inhibits the CSF1R receptor, which microglia require to proliferate. The treatments deplete the native, dysfunctional microglia and provide an optimal window to transplant cultured, healthy microglia. Chen et al. found that TCMDT given before symptoms replaced defective microglia and slowed the degeneration of neurons in mouse models of Alzheimer’s disease and Sandhoff disease, an inherited neurodegenerative disorder. The team calls for further research into the mechanisms at play, and to test whether human induced pluripotent stem cells could be used as a more clinically relevant source for microglia.

An international research team led by Professor Kiavash Movahedi from the Brussels Center for Immunology at the Vrije Universiteit Brussel has published groundbreaking results today in the prestigious journal Immunity. Their study sheds new light on the possibility of effectively replacing defective microglia—the brain’s immune cells—marking a potential breakthrough in the treatment of neurodegenerative diseases such as Alzheimer’s and Parkinson’s.