Home · Business · Sep 20 archive
UC San Diego Researchers Build Virtual Cells to Speed Drug Discovery
Confirmed
In Short: UC San Diego researchers have developed virtual cells using AI models and 'digital twins' to predict how mitochondria in human cells will respond to drug treatments, potentially speeding up drug discovery.
UC San Diego researchers have developed virtual cells using artificial intelligence (AI) models and 'digital twins' to predict how mitochondria in human cells will respond to drug treatments, potentially speeding up drug discovery for diseases like cancer, diabetes, and Alzheimer’s.
The researchers used an advanced imaging technique to create high-fidelity 4D movies of drug-treated cells, allowing them to predict cellular health from mitochondrial shape alone.
One approach involved training a deep-learning AI model on 40,000 4D movies of drug-treated cells, while the other built a physics-based model of a living cell from a 4D movie.
The AI model was able to predict how mitochondria would respond when microtubules were partially broken down by a drug called nocodazole, without needing to know which drug was used on each cell.
The results showed that the way virtual mitochondrial networks responded to drugs closely matched real cells, reducing the need for time-consuming lab experiments.
The researchers treated cancer cells with 25 different compounds known to perturb mitochondria through different mechanisms, producing 40,000 single-cell 4D movies.
These studies, published in Cell, could accelerate drug discovery for a variety of diseases, including cancer, diabetes, Alzheimer’s, and pediatric mitochondrial disorders.
Background
UC San Diego researchers have developed virtual cells using artificial intelligence (AI) models and 'digital twins' to predict how mitochondria in human cells will respond to drug treatments, potentially speeding up drug discovery for diseases like cancer, diabetes, and Alzheimer’s.
The Food and Drug Administration (FDA) has opened applications for a pilot program aimed at reducing the time it takes for drugmakers to begin human testing, as part of efforts to compete with global biotech industries.
What's confirmed
- They found that the way virtual mitochondrial networks responded to drugs closely matched real cells.
- Together, these studies, both published in Cell, could reduce dependence on time-consuming lab experiments and accelerate drug discovery for a variety of diseases including cancer, diabetes, Alzheimer’s, and pediatric mitochondrial disorders.
- Unlike most AI models that require humans to manually label images, MitoSpace found patterns on its own, learning what makes the mitochondria of one cell distinct from that of another.
- The results were striking: without knowing which drug was used on each cell, the model produced an organized map that grouped cells that respond in similar ways together.
- “We have built a physics‑based virtual cell and can compare it side‑by‑side to the actual 3D microscopy movie, something that has never been possible before,” said Schöneberg.
- To test the model, the team asked it to predict how mitochondria would respond when microtubules were partially broken down by a drug called nocodazole.
- Using an advanced imaging technique to create high-fidelity 4D movies, UC San Diego researchers can now predict how mitochondria within human cells will respond to drug treatment.
- Now, researchers at University of California San Diego have employed two different approaches to quantify these morphological changes by creating “virtual cells” — digital models that mimic the dynamic biological processes of real cells.
- One approach trained a deep-learning artificial intelligence (AI) model on 40,000 4D movies of drug-treated cells to predict cellular health from mitochondrial shape alone.
- The other built a “digital twin” of a living cell from a 4D movie by defining a set of rules about how its organelles (tiny internal structures) behave and implementing those rules in a physics-based model.
- The researchers treated cancer cells with 25 different compounds known to perturb mitochondria through different mechanisms, producing 40,000 single-cell 4D movies.
What's still developing
- Recognising this, the UAE is expanding its transport networks and scaling smart cities, while investing in clean energy, utilities and digital infrastructure.
- The focus therefore needs to shift from building stronger infrastructure to building smarter, more predictive infrastructure, leveraging advanced technologies such as AI and digital twins to prepare cities for crises even before they occur.