University of California San Diego researchers develop virtual cells to track mitochondria

Researchers at the University of California San Diego have developed two new methods to create ‘virtual cells’ to better understand mitochondrial dynamics and accelerate drug discovery. While mitochondria are often depicted as static objects, they actually form a highly dynamic, interconnected network that changes shape based on cellular health.

Using 4D lattice light-sheet microscopy to capture three-dimensional movement over time, the researchers employed two distinct digital approaches. The first involved training a deep-learning AI model, named MitoSpace, on 40,000 4D movies of drug-treated cells to predict cellular health based on mitochondrial shape. The second approach created a ‘digital twin’ of a living cell by applying physics-based rules to the behavior of organelles.

Both studies, published in the journal Cell, demonstrated that virtual mitochondrial networks respond to drugs in a manner closely matching real cells. These advancements could reduce reliance on traditional laboratory experiments and speed up the development of treatments for diseases such as cancer, diabetes, Alzheimer’s, and pediatric mitochondrial disorders.