UC San Diego reports 4D virtual-cell models for drug studies

UC San Diego researchers reported two virtual-cell approaches using 4D lattice light-sheet microscopy. In one Cell study, a model trained on 40,000 movies of drug-treated cells grouped drugs by mechanism with 75% accuracy, versus 56% for 2D images. A second study built a physics-based digital twin whose simulated mitochondrial response to a drug matched real treated cells. The work remains laboratory research in cancer cells and organoids.