It’s hard enough trying to follow the movements of individuals in a crowd of people but imagine how much harder it is to follow the movements of stem cells, crowded into a tiny petri dish. Well, researchers at the Gladstone Institutes in San Francisco have done just that.

In a CIRM-funded study ($5.85M) Dr. Todd McDevitt and his team created a super smart artificial intelligence way of tracking the movements of hundreds of stem cells growing together in a colony, and even identify “leaders” in the pack.

In our bodies groups of stem cells are able to move in specific ways to form different organs and tissues when exposed to the right environment. Unfortunately, we are still trying to learn what “the right environment” is for different organs.

In a news release, McDevitt, the senior author of the paper published in the journal Stem Cell Reports, says this method of observing cells may help us better understand that.

“If I wanted to make a new human heart right now, I know what types of cells are needed, and I know how to grow them independently in dishes. But we really don’t know how to get those cells to come together to form something as complex as a heart. To accomplish that, we need more insights into how cells work cooperatively to arrange themselves.”

Normally scientists watch cells by tagging them with a fluorescent marker so they can see them under a microscope. But this is slow, painstaking work and not particularly accurate. This new method used a series of what are called “neural networks”, which are artificial intelligence (AI) programs that can detect patterns in the movements of the cells. When combined together the networks proved to be able to track the movement of 95 percent of the cells. Humans by comparison can only manage up to 90 percent. But the nets were not only sharper, they were also faster, much faster, some 500 times faster.

This enhanced ability to watch the cells showed that instead of being static most of the time, as had previously been thought, they were actually on the move a lot of the time. They would move around for 15 minutes and then take a breather for ten minutes (time for the stem cell equivalent of a cup of tea perhaps).  

Some cells moved around a lot in one direction, while others just seemed to shuffle around in the same area. Some cells even seemed to act as “leaders” while other cells appeared to be “followers” and shuffle along behind them.

None of this would have been visible without the power of the AI networks and McDevitt says being able to tap into this could help researchers better understand how to use these complex movements.

“This technique gives us a much more comprehensive view of how cells behave, how they work cooperatively, and how they come together in physical space to form complex organs.

Follow the Leader is not just a kids’ game anymore. Now it’s a scientific undertaking.