
Photo courtesy: Gladstone Institutes
An artificial intelligence system is helping researchers track how hundreds of stem cells move and organize themselves.
The CIRM-funded study could reveal how cells work together to build organs and tissues. That knowledge may help scientists improve regenerative medicine approaches.
Tracking Cells in Motion
Following one person through a crowd can be difficult. Tracking hundreds of stem cells in a tiny dish presents an even greater challenge.
Researchers at the Gladstone Institutes in San Francisco developed a solution. In a CIRM-funded study, Todd McDevitt, Ph.D., and his team created an AI system that tracks stem cell movement.
The system also identifies patterns within a cell colony. For example, it can distinguish cells that appear to lead from those that follow.
Stem cells can move in coordinated ways when they encounter the right environment. These movements help them form organs and tissues.
Scientists still do not fully understand which conditions guide cells to build specific organs. Better tracking could help answer that question.
Neural Networks Track Cell Movements
Researchers typically attach fluorescent markers to cells. They then watch the cells under a microscope.
That process takes time and does not always produce accurate results.
McDevitt’s team used several neural networks to analyze cell movement. Neural networks are AI programs that detect patterns in data.
Together, the networks tracked about 95% of the cells. Human observers tracked up to 90%.
The AI system also worked much faster. It analyzed cell movement up to 500 times faster than people could.
Finding Leaders Among the Cells
The system revealed that stem cells move more often than researchers previously thought.
Cells moved for about 15 minutes before pausing for roughly 10 minutes. Some moved frequently in the same direction. Others shuffled within a limited area.
Certain cells appeared to act as “leaders.” Other cells seemed to follow their movements.
These patterns could help researchers understand how cells cooperate and arrange themselves in three-dimensional space.
“If I wanted to make a new human heart right now, I know what types of cells are needed,” McDevitt said. “But we really don’t know how to get those cells to come together to form something as complex as a heart.”
The team published its findings in Stem Cell Reports. McDevitt said the technique provides a more complete view of how cells behave and build complex organs.
With AI, “follow the leader” has become more than a children’s game. It is now a tool for studying how cells organize themselves.