AI Lets Scientists See Through Cell Membranes

We’ve been spying on our body’s cells for centuries using microscopes, but peering inside them has been more of a challenge. But now, artificial intelligence is helping researchers visualize the inner workings of living cells.

Scientists created the model by programming a computer to study thousands upon thousands of images from living cells. The computer eventually figured out the internal organization of a cell based on simple images.

The Institute’s 3D cell model

The 3D model overcomes the limitations of existing technologies such as microscopes by allowing scientists to observe all of the components of a cell at the same time, offering an unprecedented opportunity to study their interactions. The model also offers advantages over techniques that use dyes, intense light, or genetic modifications, since these methods damage the cells under observation.

Here’s Jon Hamilton, reporting for NPR:

Until now, there haven’t been good alternatives, says Graham Johnson, a computational biologist and medical illustrator at the Allen Institute.

He recalls the frustration when he was in high school and college of trying to study cells with a conventional microscope.

“You’d see a black-and-white clear object and it had lots of smaller objects inside of it that were moving around and changing shape and doing all sorts of mysterious things,” Graham Johnson says. But there was no good way to identify those shapes or understand what they were doing.

What’s more, this model is freely available. Where current techniques for studying cells require costly, specialized equipment, the new model can use inexpensive, commonly available hardware.

Roger Brent, a researcher from the Fred Hutchinson Cancer Research Center in Seattle who didn’t participate in the project, has already used the technology in his own research on yeast cells and managed to successfully run the model using off-the-shelf computer parts.

Researchers are optimistic that the model will help scientists better understand diseases, facilitating comparisons of healthy and unhealthy cells. The hope is that even labs with little equipment could use the model to see inside cancer cells and analyze the effectiveness of different treatments.

Read the original article.