Virtual cells built from 4D AI models and 'digital twins' could speed up drug discovery

Researchers at UC San Diego developed two 'virtual cell' platforms using 4D lattice light-sheet microscopy: a deep-learning model named MitoSpace and a physics-based digital twin of organelle dynamics. Trained on single-cell 4D movies, MitoSpace learned to predict cellular energetic states and drug mechanisms directly from mitochondrial morphology with 75% accuracy, significantly outperforming traditional 2D screening. These approaches validate that dynamic mitochondrial architecture reflects cellular health, offering computational frameworks to speed drug discovery across conditions like cancer, diabetes, and neurodegenerative disorders.

Summary written by AI Business Lens with an AI model from the article at phys.org. It is not the article, and the publisher has not reviewed it. For publishers.

Read the original at phys.org   Generate teaching or study materials

Instructors get discussion guides, assignments, and mini-cases. Students and readers get a plain summary, points to raise, an exercise, and a self-check. All built from the full article. A free account saves stories and gives you three generations. Stories stay on the brief for 14 days. After that this page keeps the link to the original.