Google DeepMind uses AI tech to predict protein shapes

It's one of the most accurate and fastest ways of determining very complex 3D shapes

Brain, network, network intelligence, AI, computing, connected, artificial intelligence, machine learning

The latest scientific application of Google's DeepMind AI project is identifying and predicting the complexity of proteins via its AlphaFold discovery programme.

In doing so, the reasons some of the most widespread genetic illnesses exist could potentially be uncovered.

DeepMind has brought together some of the most advanced thinkers in structural biology, physics, and machine learning to predict 3D shapes in proteins, based on its genetic sequence.

AlphaFold has been running for more than two years and the team behind the project thinks it's the most accurate way of predicting the 3D shape of a protein yet. This means it could potentially uncover faults in DNA that causes conditions such as Alzheimer's, Parkinson's, Huntington's and cystic fibrosis.

Advertisement
Advertisement - Article continues below
Advertisement - Article continues below

"The challenge is that DNA only contains information about the sequence of a protein's building blocks called amino acid residues, which form long chains," the DeepMind Project team said in a blog post.

"Predicting how those chains will fold into the intricate 3D structure of a protein is what's known as the "protein folding problem. The bigger the protein, the more complicated and difficult it is to model because there are more interactions between amino acids to take into account."

According to researchers, it would take longer than the age of the universe to work out every possible configuration of proteins before working out the 3D structure. But AlphaMind's advanced intelligence and modelling system could get to the bottom of the complexities.

Using neural networks, the AlphaFold project has managed to determine the distances between pairs of amino acids and the angles between chemical bonds that connect those amino acids. These are then matched with structures that are already known. The next stage was training a neural network to invent new fragments, which could improve the accuracy of the model.

"The success of our first foray into protein folding is indicative of how machine learning systems can integrate diverse sources of information to help scientists come up with creative solutions to complex problems at speed,"

"Just as we've seen how AI can help people master complex games through systems like AlphaGo and AlphaZero, we similarly hope that one day, AI breakthroughs will help us master fundamental scientific problems, too."

Featured Resources

Digital Risk Report 2020

A global view into the impact of digital transformation on risk and security management

Download now

6 ways your business could suffer if you don’t backup Office 365

Office 365 makes it easy to lose valuable data regularly, unpredictably, unintentionally, and for good

Download now

Get the best out of your workforce

7 steps to unleashing their true potential with robotic process automation

Download now

8 digital best practices for IT professionals

Don't leave anything to chance when going digital

Download now
Advertisement

Most Popular

Visit/mobile/28299/how-to-use-chromecast-without-wi-fi
Mobile

How to use Chromecast without Wi-Fi

5 Feb 2020
Visit/operating-systems/27717/how-to-fix-a-stuck-windows-10-update
operating systems

How to fix a stuck Windows 10 update

12 Feb 2020
Visit/security/34616/the-top-ten-password-cracking-techniques-used-by-hackers
Security

The top ten password-cracking techniques used by hackers

10 Feb 2020
Visit/security/cyber-security/354827/mcafee-researchers-trick-tesla-autopilot-with-a-strip-of-tape
cyber security

McAfee researchers trick Tesla autopilot with a strip of tape

21 Feb 2020