Alphabet's DeepMind unveils AlphaFold, an AI program creating 3D protein models

Steven Loeb · December 4, 2018 · Short URL:

AlphaFold recently won the the Critical Assessment of Structure Prediction contest


Health has long been a key component of Google's business, whether that be trying out a smart contact lens to measure glucose levels in the wearer’s tears to the founding of Calico in 2013 with the aim of taking on the aging process. The company has no shortage of health initiatives it has tried out over the years.

Now DeepMind, a division of Alphabet focused on AI research, has unveiled yet another health program called AlphaFold. It's an artificial intelligence platform that the company has used  to build out 3D models of protein structures.

AlphaFold is "DeepMind’s first significant milestone in demonstrating how artificial intelligence research can drive and accelerate new scientific discoveries," the company wrote in a blog post

"With a strongly interdisciplinary approach to our work, DeepMind has brought together experts from the fields of structural biology, physics, and machine learning to apply cutting-edge techniques to predict the 3D structure of a protein based solely on its genetic sequence."

Proteins are organic compounds that consist of large molecules composed of long chains of amino acids and they act as structural components of body tissues such as muscle, hair, collagen, enzymes and antibodies. AlphaFold has spent two years working on creating a 3D shape of a protein, something that the company "scientists have found challenging for decades," but which has now finally been cracked.

So why is all of this important? Because proteins are also critical for diagnosing diseases, such as Alzheimer’s, Parkinson’s, Huntington’s and cystic fibrosis. And being able to see the proteins in 3D will help see how proteins are folded, which can lead to more accurate diagnosis. 

"We are especially excited about how it might improve our understanding of the body and how it works, enabling scientists to design new, effective cures for diseases more efficiently. As we acquire more knowledge about the shapes of proteins and how they operate through simulations and models, it opens up new potential within drug discovery while also reducing the costs associated with experimentation. That could ultimately improve the quality of life for millions of patients around the world," the company wrote. 

"An understanding of protein folding will also assist in protein design, which could unlock a tremendous number of benefits. For example, advances in biodegradable enzymes—which can be enabled by protein design—could help manage pollutants like plastic and oil, helping us break down waste in ways that are more friendly to our environment. In fact, researchers have already begun engineering bacteria to secrete proteins that will make waste biodegradable, and easier to process."

The technology has already begun to be recognized: over the weekend, AlphaFold won the Critical Assessment of Structure Prediction (CASP) competition in Cancun.

Going forward, the company plans to use the AlphaFold artificial intelligence platform to solve more complex health problems.

"Even though there’s a lot more work to do before we’re able to have a quantifiable impact on treating diseases, managing the environment, and more, we know the potential is enormous. With a dedicated team focused on delving into how machine learning can advance the world of science, we’re looking forward to seeing the many ways our technology can make a difference," the company wrote.

This post has been updated to more accurately explain DeepMind's focus and place within the Alphabet group

(Image source:

Related News