Researchers Use AI to Create the First Complete 3D Model of a Human Cell

Modern medicine has seen many great advances. We have scans, stains, and microscopes that allow us to see how the body is working. However, seeing inside the body can still be difficult because these technologies only offer limited information and can also damage or alter the cells that a doctor or researcher is trying to see in the first place.

For example, it’s especially tricky to see exactly what’s going on with individual cells as they fight disease, which in turn can make it hard to understand what a person needs to make them better.

Thus to help address this issue and get a more thorough view of what’s going on in individual cells, researchers at the Allen Institute turned to artificial intelligence to create the first complete, 3D model of a human cell that demonstrates how all the different parts and structures found within a cell fit and work together.

The model portrays what typical human induced pluripotent stem cells (hiPSCs) might look like (they chose hiPSCs because they were cloning them as they tagged different structures within them). To train the AI that produced it, the researchers took detailed scans of thousands of cells using their online tool, which is free and open to the public. It provides 3D views of 32,000 cells.

Using that information, the AI produced a model that predicts where each organelle, or internal component of a cell, is most likely to be found, and how it fits in with the rest of the cell. This model can predict where these organelles will be found in any new cell, as long as it’s given an image from a microscope.

The researchers also used AI to design a probable model that takes its best guess at where one might expect to find those same organelles if given a cell’s size and shape, in addition to the location of its nucleus.

These models are helpful for doctors and scientists since they offer a close-up look at the effects of cancer and other diseases on individual cells. By feeding the AI with data and images of cancer cells, they can get a more complete picture of how the cell, and its individual components, are affected. This, in turn, can indicate how doctors can help each patient with treatment customized to their disease.

The researchers at the Allen Institute hopes their tools can help democratize medical research, improving healthcare in underserved areas. Therefore, the researchers are working to enhance them by crafting more complete models, as reported by NPR.  The team hopes to expand the database making models of more cells available over the next few months.



Image Credit: Billion Photos / Shutterstock


Become a Citizen