There’s the use of AI to help tighten organizational finances, and there’s the use of AI to help organize growing caches of unstructured data.  And then there’s the use of AI that, every once in a while, sends our understanding of the biology of life hurtling forward.

It’s that use on display in a recent piece at SingularityHub that describes the efforts of scientists to solve the mysteries of protein folding, one of the fundamental building blocks of biological life.

As the writer explains, “Proteins are the minions of life. They form our bodies, fuel our metabolism, and are the target of most of today’s medicine. They start out as a simple ribbon, translated from DNA, and subsequently fold into intricate three-dimensional architectures. Similar to Transformers, many protein units further assemble into massive, moving complexes that change their structure depending on their functional needs at the moment.”

The problem is that “misfolded” proteins can have devastating effects in the form of diseases ranging from cancer to Alzheimer’s. Given those effects, “One of biology’s grandest challenges for the past 50 years has been deciphering how a simple one-dimensional ribbon-like structure turns into 3D shapes, equipped with canyons, ridges, valleys, and caves. It’s as if an alien is reading the coordinates of hundreds of locations on a map of the Grand Canyon on a notebook, and reconstructing it into a 3D hologram of the actual thing—without ever laying eyes on it or knowing what it should look like.”

Until now.

In two new papers, scientists at DeepMind, the British AI subsidiary of Google parent company Alphabet, and the University of Washington, “deep learning-based methods to solve protein folding—the last step of executing the programming in our DNA.”

In simple terms, the goal for decades is to develop methods to “computationally predict a protein’s 3D structure. The problem is time and power: like trying to hack a password with hundreds of characters suspended in 3D space, the potential solutions are astronomical.”

Enter, first, DeepMind, followed by the University of Washington. In fact, when DeepMind unveiled their AI algorithms, called AlphaFold, that used deep learning to predict a protein’s three-dimensional (3D) shape, that inspired Dr. Minkyung Baek at the University of Washington to develop her own approach.

With the two studies, says the writer, “we’re entering a new world of predicting—and subsequently engineering or changing—the building blocks of life.”

Indeed, said Dr. Andrei Lupas, an evolutionary biologist at the Max Planck Institute for Developmental Biology, “This will change medicine. It will change research.  It will change bioengineering. It will change everything.”

Photo by wildpixel/Getty Images